2024 International Conference on

Smart Technologies for Sustainable

Development Goals

th th
6 - 8 Nov 2024

ICSTSDG
PROCEEDINGS

S.A. ENGINEERING COLLEGE

(An Autonomous Institution, Affiliated to Anna University)
Accredited by NBA, NAAC with ‘A’ Grade & ISO 9001:2015 Certified Institution
POONAMALLEE – AVADI MAIN ROAD, THIRUVERKADU, CHENNAI – 600 077

Technically Co - Sponsored by
Title of Talks

1. Sustainability: Navigating Environmental, Economic, and Social Imperatives to Shape Future

Generations
Lijetha C Jaffrin, Maheshwaran T, Sivakumar S, Sassirekha S M, Sakthivel M and Nalini M . . . . . . . . 1

2. Academic Performance Evaluation Using Data Engineering and Multi-Model Machine Learning
System
P.J.Beslin Pajila, Gautham Anand, K Neela, Gowri M, Karthikeyan M and Nithyanandhan R . . . . . . . 1

3. Smart Helmet For Digcrafters Using IoT

Anita M, Maheshwaran T, Dhivya R, .Muthuram A, Dinesh M G and Dr. M. Jayakumar M . . . . . . . . 2

4. Infrasecure: Enhancing V2I Communication Using Data Integrity

G. Mariammal, S. Sridevi, D. Mangaiyarkarasi, M. Sai Venkata Adithya, G. Balaji and S. Venkateswaralu 2

5. Agritool -A Farm Log Rental Service Platform with Crop Management

Pathmanaban J, Sangeetha, Prabahar Godwin James T, Sibisurya S, Sakthi Arunachalam S and Abiram R 3

6. Optimizing Crop Yield And Profitability With An Fpga Enabled Smart Irrigation System For
Agriculture
Vivekanandan M, Saranya G, Kumaran K and Vidhyalakshmi M . . . . . . . . . . . . . . . . . . . . . . . 3

7. Air Quality Index Prediction using GCN + LSTM Model

R. Kingsy Grace, Karthik J and Pranav J . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

8. Integrated AI-Driven Agricultural Automation for Precision Farming: A Smart Approach to

Pest Management and Irrigation Control
Dharshini S, Preetha Lakshmi, Joshna B S, Jayachandiran Udayakumar and Muthamilselvan S . . . . . . 4

9. Side Channel Power attack Dataset Characterization for Secure Adiabatic Circuit level VLSI
Abstraction
V.Harynee, G.K.Bhuvanesh, Anjana Jyothi Banu and A.Prathiba . . . . . . . . . . . . . . . . . . . . . . . 5

10. Revamping Ola Bike Services with Advanced Demand Forecasting via Machine Learning
Jayadharshini P, Dinesh Subramani, S.Santhiya, Sudharshan.S, Sudheksha.K and Rithanya.M . . . . . . . 5

11. Efficient Document Image Classification Using Deep Learning Enhance with CNN Architectures
Jayadharshini P, P.Karunakaran, S.Santhiya, Harshini.M and Arunachalam.M . . . . . . . . . . . . . . . . 6

12. Medicinal Plant Identification Using CNN And Pytorch Lightning

Thilagam.T, Anees Fathima M, Varsha V, Janani P, Priyadarshini A and Sariga B . . . . . . . . . . . . . 6

13. DrowsiGuard: Machine Learning-Based Driver Drowsiness Detection System for Enhanced
Road Safety
S. Gunanandhini, T.Thilagam, G.Manisha, S.N.Ananthi and G. Belshia Jebamalar . . . . . . . . . . . . . 7

14. A Review on the effectiveness of Deep Learning Algorithms for pedestrian detection
Arumai Shiney.S, Thilagam.T, Manisha.G and Ananthi S N . . . . . . . . . . . . . . . . . . . . . . . . . . 7

15. Automated Vision-Based System for Comprehensive and Real-Time Detection and
Classification of Fruit Surface Damages
Dr. K Vijayalakshm, Nitin Darapareddy and D.Anish Chandra . . . . . . . . . . . . . . . . . . . . . . . . 8

16. Predicting Fit Sizes in E-Commerce using Machine Learning

Beulah N, Dr.D.Umanandhini Udhayakumar, Shyamaladevi M., Geetha Jenifel M and Jangili Supriya . . 8

iii
17. An Efficient AI Based Ensemble Model for Human Detection and Rescue During Disaster using
UAV
Konijeti Sai Kalyan, Maddu Rakesh, Nukala Rohith and B. Yamini . . . . . . . . . . . . . . . . . . . . . . 9

18. Maximizing Mango Yields: Disease Prediction, Grade Classification, and Production
Management through EfficientNet Models and PHP-MySQL Integration
B.Yamini, Dr.G.Premalatha, Konijeti Sai Kalyan, Maddu Rakesh, Nukala Rohith and Jino Paulraj . . . . 9

19. Machine Learning-based Classification for Sentimental Analysis of IMDb Reviews

Santhiya S, Lalitha Krishnasamy, Rakoth Kandan Sambandam, Jayadharshini P, Dharshan P P and
Haripreetha S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

20. Comprehensive Drowsiness Detection System Using OpenCV, Machine Learning, and Heart
Rate Monitoring
Shruthik Kalyana Venkatesh, Sharmishtha S.K, Gogul Ram S and Dr.B.Yamini . . . . . . . . . . . . . . . 10

21. Applications of Wireless Sensor Networks in the Healthcare Sector

L. A. Anto Gracious, Ganeshan R, T Periyasamy, R. Abirami, R. Kennady and A.Prabha . . . . . . . . . 11

22. Proactive Disease Detection : A Web-Based Application

Robert Emmanuel S, Ravivarman R, Gaurav Singh, Jaya Kumar Sa and Hemanand D . . . . . . . . . . . 11

23. Quantum Machine Learning Algorithms for Traffic Management in Big Cities
Dr. D. Hemanand, Dr.M.Anuradha, Lakshmipriya C and Revathi V . . . . . . . . . . . . . . . . . . . . . 12

24. Enhancing Online Payment Security: A Machine Learning Approach to Fraud Detection
. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12

25. Wireless Surveillance Robotic Car for Crop Disease Detection

Chettiyar Vani Vivekanand, Dr. Inbamalar T M, Harish R, Masthan Gowtham Kommuru and Ganesh Perim 13

26. Centralized Service Management Across Hybrid Environments: Harnessing Zookeeper with
Cloud Computing
P. Kumar, Duraimurugan N and Ananthajothi K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

27. Revolutionizing CPR Training: An Arduino-Powered Automated Resuscitation Model

Dr.T.S.Geetha, Nivethitha. M, Swetha. N, Eswar Prasad. G, Naveen Raj. A and Deepan. P . . . . . . . 14

28. Multimodal Anomaly Detection and Probabilistic Risk Prognostication for IT infrastructure:
A hyperparameter tuned Random Forest regressor a Probabilistic Regression Model
Mr.M.Balasubramanian, Abirami.J, Betsey Neela Raju and Harini.P . . . . . . . . . . . . . . . . . . . . . 14

29. Revised Kuhn-Munkres Algorithm for Dynamic Job Allocation using Dummy Decider Technique
Sridevi Sridhar and Thilagavathi Narayanamoorthy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

30. Infinite Environment to Sustainable Tamil NLP

Krishnan R and Murugan A . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

31. Prioritising Hospital Admission According to Emergency using Machine Learning

Pandiaraj A, Lakshmanaprakash S, Angayarkanni Veeraputhiran, Ramshankar N, Kamalakannan R and
Vinnie Sharma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16

32. Identification of Different Medicinal Plants Through Image Processing

Dr. J. Anvar Shathik, S. Hashini, A.Pandiaraj, N.Ramshankar, Naveen G and Amirthavarshini K B . . . 16

33. Enhancing Traceability and Transparency in Agriculture: Blockchain-Based Tagging of Farm

Produce
G Manisha, T.Thilagam, Ananthi.S.N and S.Gunanandhini . . . . . . . . . . . . . . . . . . . . . . . . . . 17

34. Enhancement of Hugging Face Transformers for Synthetic Media Verification

Vignesh H, Vignesh P, Nandhakumar K P and Dr.Anuradha M . . . . . . . . . . . . . . . . . . . . . . . . 17

35. Carbon Storage and Sequestration Potential of Aboveground Biomass of Neem Trees in
Southern Regions of Chennai
Mrs Arumai shiney, Ms. Keerthana S, Ms. Harini A and Mr. JONAH S . . . . . . . . . . . . . . . . . . . 18

iv
36. Machine Learning-Based Predictive Modeling for Cardiovascular Disease
Kiruthiga S, Kanishka A and Shri Vidhya K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18

37. Analysis of Hybrid Encryption

Dr.ChitraDevi .D, Chandrasekar.K.V, Karthikeyan.J and Sribalaji.E . . . . . . . . . . . . . . . . . . . . . 19

38. Recommendation System for NFT Platform

Dr. K A Varun Kumar, Gopika M Nair and M Pranita . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19

39. Smart Ports: Utilizing AI-Driven Predictive Analytics and Simulation for Operational Excellence
Balika J Chelliah, Sarghi Kaur Gahra, A.Senthilselvi and S.Senthil Pandi . . . . . . . . . . . . . . . . . . 20

40. Tranqsoul – A Mental Health Assistance App

Jayanthi.M, Arumai Shiney.S,Adaikkammai.A, Selvakumaran.S,Poonguzhali.C and Rajavinu.N . . . . . . 20

41. Advanced Underwater Object Detection: Integrating Enhanced SSD with Comprehensive
Image Enhancement Techniques
Ashok P, Indravahini B S, Niroshini B, Hamsasini B and Nirmaladevi G . . . . . . . . . . . . . . . . . . . 21

42. Exploring the Impact of Pharmaceutical Supply Chains on the Advancement of Sustainable
Development Goals: A Comparative Study Across Cases
Padma Prabha C, Poomagal A, Dinesh S, Balakrishnan S, Poornima A.S and Renuka Vidhyashankar . . . 21

43. Short Review on Classifying Normal and Diabetic Foot Infrared Images: Existing Machine
Learning and Deep Learning Techniques, Limitations and Future Trends
Mahalakshmi S and Lokesh S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22

44. Driving Social Impact And Inclusive Growth: Role Of Indian Social Stock Exchanges
Dr Poornima A S, Dr Poomagal A, Dr Padmaprabha C, Dinesh S and Balakrishnan S . . . . . . . . . . . 22

45. Hierarchical Bayesian Modeling for FVC Prediction in Pulmonary Fibrosis and Low-Cost
Spirometer Incorporating Internet of Things
Sumithra M, Sundari S, Deepa V, Nagaraj P, Dhiliphan Rajkumar Thambidurai and Magesh Kumar S . . 23

46. Reliable Communication in VANET Environment through Mobility aware clustering and Multi
Hop Routing
Jemima Havila Catherine A, Dr. A. Maria Christina Blessy, Dr. K. Danesh and Dr. V. Diana Earshia . . 23

47. Performance Analysis of Active-Quasi Z-Source Inverter fed Induction Motor using SVM
T. Muthamizhan, B. Naveen and P.P.Narenthira Sai Raam . . . . . . . . . . . . . . . . . . . . . . . . . . . 24

48. Exploring Students Perception and Behavioral Intentions in Online Learning

Dinesh S, Balakrishnan S, Poornima A.S, Padma Prabha C, Poomagal A and Renuka Vidhyashankar . . . 24

49. Autoencoder and Decoder for Efficient Network Intrusion Detection in Internet of Vehicles
Pranav S A, Sathya Priya S and Hariharan B . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25

50. Promoting Feline and Canine Hydration: Design and Evaluation of a Gravity-Fed Water
Dispenser with Automatic Lid
Harshitha Seetharaman, Jai Udhaya S and Raj Kumar K . . . . . . . . . . . . . . . . . . . . . . . . . . . 25

51. Crime Defender - A Proactive Measure For Community Security

S. Juliafaith, A.M Sermakani, T. Veena, D.Chithra and R.Devprasad . . . . . . . . . . . . . . . . . . . . . 26

52. Exam Preparation Assistance Chatbot using Retrieval Augmented Generation

Kumar P, Haresh M and Hayagreevan V . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26

53. Agricultural Product Price and Crop Prediction based on Data Science Technique
Kumar P, Vijayaraj A, Senthil Pandi. S and Venkatesh Prabhu Balakrishnan . . . . . . . . . . . . . . . . 27

54. IoT-Enhanced Wireless Sensor Network for Precision Agriculture: Advancing Environmental
Monitoring and Resource Optimization
R. Banu Prakash, Dr. V. DhilipKumar, Dr. K. Durairaj, Nuti Dhruv and C. Alamelu . . . . . . . . . . . 27

55. Unauthorized Access Detection System using Machine Learning with Honeypot Integration
Mrs.D.Thamizhselvi, Aswin Kumar K and Ajith Raj N . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28

v
56. Fake Manipulation Detection in Social Network (FACT-HIVE)
Avinaash Venkat B, Dhakshin Vikash V, Mrs.Thamizhselvi D, Suganthi P and Dr.Punitha A . . . . . . . 28

57. Machine Learning-Based Threat Detection in Crowded Environments

Cherin Yacoob Wattacheril, Dr. G. R. Hemalakshmi, Ashin Murugan, P.N.V. Abhiram, Harisankar G and
Ansu M George . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29

58. Enhanced Breast Cancer Prediction through Block Processing of Gene Data and Random Forest
Regression
J. Godly Gini and S.Padmakala . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29

59. Decentralized Real-Time Communication:WebRTC and WebSockets forPeer-to-PeerFile

Sharing
Nachiappan C, Navajeevan M, Sathish Kanna L and Ms R Dhivyabharathi . . . . . . . . . . . . . . . . . 30

60. Predicting Stock Market Web App using LSTM Model and Facebook Prophet
Sarvesh Susindran, Sanjay Nagarajan, Perinban Prabu and Ms.Dhivya Bharathi . . . . . . . . . . . . . . . 30

61. Exam Proctoring System using Machine Learning

Hariprasad V, Alister Francis Fernandez, Pragadeesh N and Dr.N.Thilgavathi . . . . . . . . . . . . . . . . 31

62. Enhancing Energy Efficiency in Hybrid Vehicles using Model Predictive Control with
Reinforcement Learning
Senthil Pandi S, Bala Subramanian C, Vaijayanthi.S and Chaithra I V . . . . . . . . . . . . . . . . . . . . 31

63. Uncovering Characteristics for Entrepreneurial Success and Intention; Focusing on Moderating
Effects of Entrepreneurial Orientation
Dr. S. Avinash, Dr. M. Thamizhselvi, Dr. Anugragha.S.S, Dr. I. Shanmugapriya and S. Murugan . . . . 32

64. Exploring The Attitude Towards Entrepreneurship, Choice Of Business, Attributes, And
Perception Of Entrepreneurs: A Road Map To Success
Dr. R. Meenambigai, Dr. N. Saranya Devi and Dr. Yogita Saurav Gupta . . . . . . . . . . . . . . . . . . 32

65. A Content Analysis of Education and Awareness Campaigns in Metaverse; Opportunities And
Ethical Standards
Dr. S. Sathyasundari, Dr. C. Velusamy, Dr. K. Arulini, E. R. Vadivel, S. Uma Maheswari and S. Murugan 33

66. Transforming Market Dynamics, E-Business and E-Commerce in Hospitality and Tourism
Dr R. Monisha, M.Jaiganesh, Dr. L. Sujatha and Dr. I. Shanmugapriya . . . . . . . . . . . . . . . . . . . 33

67. Exploring the Confronts Faced by Women Entrepreneurs -An Insight into Problems, Prospects
and Development; an Empirical Study
Dr R.Monisha, Dr. Veto Dey, Dr. N. Jayapriya and Dr. I. Shanmugapriya . . . . . . . . . . . . . . . . . . 34

68. Enhancing Voter Identity Verification Through Cloud Computing Enabled Biometric
Authentication-Modern Voting
Chitra Sabapathy Ranganathan, Kabaleeswaran S, Dr. P L Kishan Kumar Reddy, Dr. P. Selvarani, C.
Srinivasan and Rajarajan S J . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34

69. Intelligent Security System for e-Bikes using Smart Lock with Tamper Detection
Dr. L. Chitra, V. Rattan Kumar, K. Devabalaji, P.Veeramuneeswaran, A. Mohamed anas and S. Anbarasan 35

70. Data Mining Approach for Emotional Regulation and Social Adjustment among Adolescents
Saravanan.S and Tamizharasi.K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35

71. Study on Spatial Distance Optimization of Delivery of Mails from the Nearest Postal Location
T.A. Rajasekaran, Vijayalakshmi. P and Rajendran. V . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

72. Big Data Analytics for Pattern Recognition and Technological Decision-Making
Vidhya. N and Dr. C. Meenakshi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36

73. Review of AI-Driven Machine Learning Solutions for Modern Agriculture

K. Suganthavalli and Dr. C. Meenakshi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

74. Real-Time Emotion-Based Music Recommendation System Using YOLOv5 and Spotify API
J. Sujithra, Karthik Balaji B M and Yashwanth J . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37

vi
75. Smart Well Networks for Adaptive Groundwater Management Integrating Cloud Computing
and Wireless Sensor Technologies
V G Sivakumar, Dr. S. Vimaladevi, Dr. R. Thenmozhi, Dr. P. Epsiba, S. Sujatha and M. Nalini . . . . . 38

76. Efficient Sports Training Periodization through Cloud-Based Support Vector Machines
Dr. Barkathulla A, Mothiram Rajasekaran, Dr. P L Kishan Kumar Reddy, G. Manikandan, G.
Bhuvaneswari and R. Priyanka . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38

77. Smart Gloves for Hand Injury Prevention in Manufacturing Plants Using IoT Sensors and
One-Class SVM Integration
Dr. MD Ashfaqul Hasan, Gurumoorthi Gurulakshmanan, Rajeshkumar Sampathrajan, Bharat Tidke, C.
Srinivasan and R. Kamalakannan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39

78. Predictive Analytics for Sales Demand Forecasting using HML Model
Sujithra J, Nithya Shree S and Sathyabama R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39

79. IoT-Driven Green Building Materials and Life Cycle Assessment with Gradient Boosting
Machines
Chitra Sabapathy Ranganathan, A. Arokiaraj Jovith, Dr. P. Selvarani, S. Saravana Kumar, S. Sujatha and
Dr. K. A. Niranjan Kumar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40

80. Smart Home Security System with Integrated Motion Detection and Facial Recognition
Dr. V.R.Kanagavalli, Ms.Janani S and Ms.Madura S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40

81. Flight Simulation Trainer with LMS using Virtual Reality (VR)
Gomathy G, Kalaiselvi P, Aditya S, Nawin Viswajith B, Navaneetha Krishnan R and Mohamed Suhail Y 41

82. Real-Time Snoring Monitoring and Intervention with IoT and Long Short-Term Memory Network
Chitra Sabapathy Ranganathan, Kabaleeswaran S, M Vadivel, S Prabha, C Srinivasan and E Lavanya . . 41

83. Intelligent Robotics for Sorting Clothing and Textile Waste using Cloud-Integrated Recycling
Systems and CNN
Chitra Sabapathy Ranganathan, Kabaleeswaran S, S P Vimal, Dr. V. Kannagi, M. Muthulekshmi and Dr.
M. Meganathan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42

84. Cloud-Driven Autonomous Drones for Dynamic Emergency Medical Response Using
Convolutional Neural Networks
P. Karthikeyani, D. David Neels Ponkumar, S. Hemalatha, M. Tamilselvam, M. Muthulekshmi and C.
Dhanesh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42

85. Cloud-Enabled Electronic Waste Tracking and Traceability Solutions using Random Forest
Algorithm
Raveendra N Amarnath, V Vijaya Baskar, Dr. V. Kannagi, Dr. S. Kolangiammal, M. Muthulekshmi and
G. S. Gayathri . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 43

86. A comprehensive survey on Intrusion Detection Systems in IoT-Enabled Wireless Sensor

Networks: Techniques, Challenges and future directions
Poonguzhali C, Tapas bapu B R, Kalaivani K, Kaviya M, Madhubala S and Sharon Chrysolite C . . . . . 43

87. Real-Time Speed Detection in Sports Events Using Cloud-Sensor Fusion with Support Vector
Machines
E. N. Ganesh, Mothiram Rajasekaran, K. Sangeethalakshmi, S. Murugan, Dr. S. Karthikeyan and Senthil P 44

88. Optimizing Harvesting Operations with Cloud-Connected Robots for Fruit and Nut Crop Yield
Enhancement with CNN
Dr. M.Santhanalakshmi, Mothiram Rajasekaran, Dr. G. Kumar, C. Viswanathan, V. Amirthalingam and
Dhivya V . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44

89. AI-Driven Yoga Evolution for Advancing Mindfulness and Well-being through Cloud-connected
Practices
Chitra Sabapathy Ranganathan, Dr. T. Senthil Kumar, E. Sivanantham, Aarthy.S.T, S. Murugan and M.
Nalini . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45

90. Intelligent Defect Detection and Classification in Manufacturing Execution Systems with IoT
Chitra Sabapathy Ranganathan, Aarthy.S.T, Dr. S. Prabha, C. Srinivasan, M. Rajmohan and Malarvizhi S 45

vii
91. Interactive Simulation Tool for Cloud Resource Allocation Strategies and Performance Analysis
Devesh Kumar Bandla, Burri Deeleep Sanjay Reddy, Myla Greeshmanth Reddy and Dr. B, Yamini . . . . 46

92. Gender Equality and Women’s Empowerment as Essential to Food Systems and Economic Justice
Dr R. Monisha, Dr. S. Prabhu, Dr. Harish. M, Dr. RM. Sivagama Sundari, Dr. Indumathi. N and S.
Murugan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 46

93. Mapping the Mind of the Retail Investor: A Comprehensive Analysis of Behavioral Biases in
Individual Investment Decisions
Dr Subalya S, Dr. N. Jayanthi, Dr.R.Tamilmaran and Dr. T. Rekha Kiran Kumar . . . . . . . . . . . . . 47

94. A Deep Learning Approach to Sign Language Recognition for Speech-Impaired Individuals
Deepak T and K. Dinakaran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47

95. Predictive Analytics Techniques for Enhancing Peripheral Vascular Catheter Care Bundles
Ambiga C and Sasi V . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48

96. Evaluating Buzzy Technique’s Effect on Pain and Parental Satisfaction Using Wilcoxon Signed-
Rank Test
Parimaladevi. L and Dr. Tamizharasi. K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48

97. Influence of ICT on the Academic Achievement of Engineering Students and the Moderating
Role of Socio-Economic Status
Dr Krithika. M, Aarthi Suresh, Mr.T Koteswara Rao, S. Murugan and Sowmya R . . . . . . . . . . . . . 49

98. Impact of Gender and Technological Advancement on Employee Productivity in the Post-
Pandemic Era
Sarath Kumar. C, Dr Krithika. M, C. Srinivasan and Sunantha Sri B . . . . . . . . . . . . . . . . . . . . 49

99. Advanced Load Monitoring system for Energy Audits using Programmable Meters
Dakka.Obulesu, K. Shiva Kumar and A.S.S.Murugan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50

100. Artificial Intelligence and Machine Learning: Developing the Future of Text Analytics and
Natural Language Processing (NLP)
N.K.Senthil Kumar, Rajasekaran.A, K.Saraswathi, Srinadh Unnava, V.Samuthira Pandi and Shobana D . 50

101. IoT- Powered Smart Electric Automobile Ecosystems: Using Intelligent Infrastructure and
Connected Technologies for Innovative Mobility
S.Balaji, Shobana D, V.Samuthira Pandi, K.Makanyadevi, Lakshmi Priya J and C Muralidharan . . . . . 51

102. Precision Medicine with Deep Learning: Enhancing Biomedical Applications with Superior
Data Analysis and Customized Medical Solutions
Srinath Rajagopalan, S.Kavitha, V.Samuthira Pandi, Lakshmi Priya J, M.Shanmuganathan and N. V. S.
Natteshan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51

103.Wearable Technology and Cloud Computing Integration for Adaptive Cognitive Load Management
S P Vimal, Palaniraj Rajidurai Parvathy, John Benito Jesudasan Peter, Brinda P, S. Srinivasan and R Sankar 52

104. Predictive Modeling of Chronic Pain Flares with Cloud-Enabled Wearable Sensors and
Recurrent Neural Networks
M. Vadivel, Kabaleeswaran S, Rajeshkumar Sampathrajan, P. Sivalakshmi, S. Srinivasan and Anitha G . 52

105.IoT-Enabled Plant Root Monitoring for Improved Water and Nutrient Uptake with Long Short-
Term Memory
Chitra Sabapathy Ranganathan, Kabaleeswaran S, Dr. MD Ashfaqul Hasan, M. Vadivel, S. Srinivasan and
T. Annalakshmi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53

106. Gesture Recognition and Human-Computer Interaction for User Control Applications using
Embedded Sensors
Dr. Ramakrishnan Raman, Dr. R. Meenakshi, Ramya. R, Dr. Meenakshi Kaul, S. Srinivasan and A. Prabha 53

107. Integrating MQTT Protocol for Smart Greenhouse Management and Environmental Control
System
Dr. Nelson Kennedy Babu C, Dr. A. Deepa, Dr. S. Sankar, B. Prasad, T. Geetha and Dr. Praveenkumar S 54

viii
108. Cooperative Transmission and Analysing Packet Size For Optimal Routing in Wireless Network
Mothiram Rajasekaran, Chitra Sabapathy Ranganathan, A. Arokiaraj Jovith, Dr. S. Rajes Kannan, S.
Srinivasan and Dr. R. Radhika . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54

109.Wireless Sensor Networks for Environmental Management in IoT: Air and Water Quality Using
Decision Tree Algorithm
V. Nandagopal, S. Kalaichelvi, S. Saravana Kumar, K. Manikandaprabhu, S. Srinivasan and A. Karunakaran 55

110. Real-Time Monitoring in Healthcare: Addressing Technical and Ethical Issues with Digital
Twin Technology
V. T. Vithya and P. Valarmathie . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55

111.Patient-Centered Care in the Metaverse: Augmented Reality and Virtual Reality for Enhanced
Surgical Experiences
Aparna P and Valarmathie P . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56

112. Efficient Energy Monitoring in Home Appliances using IoT

Thangapalani L, Lieo Ambrouse E, Karthikeyan M C and Kavin Aarya A.R . . . . . . . . . . . . . . . . . 56

113. Improving The Quality Of User Experience In The Context Of An Online Car Rental System
Services With The Use Of Real Time Data Analytic
Mithun Kumar S.R and Ardly Melba Reena .B . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57

114. Dual-Module Blood Bank Web System: The Donor and the Receiver Integration
Baranibabu S and Nizmi shaik . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57

115. Enhancing Reading Comprehension for Mobile Users: A Flutter-Based Application with
ChatGPT API for Instant Word Meaning Retrieval
G. Abay Ragav and K. Dinakaran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58

116. Feast Finder - A Recipe Application

Mohammed Afeef Abdulla and Mangaleswaran M . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58

117. Intuitive Online Table Booking System for Restaurants

Chetan Annamalai M and Muthukumar G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59

118. Weather Application

Loganathan C and Muthukumar G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 59

119. Test Hub using PHP

Bhagya Sree S and Nizmi shaik . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

120. Trip Guidance with Recommendation and Shortest Route Using AI Algorithm
EZHILARASI A and SEVANTHI P . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 60

121.Impact Of Yogic Practices And Skill Development On Physiological And Psychological Metrics
In Kabaddi Players Using Advanced Technology
Dr. C. Kala, Dr. C. Selvaraj and Dr. P. Ramesh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61

122. MapMed: A study on Mapbox tools and API Integration for locating nearby Health Facilities
Aayushi Iyengar, Vertika Singh and Dr. S Saravanan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61

123. Resume Parsing Matching Talent Recruitment Platform

Mr. P. Senthil, E. Arun, B. Lingeswaran, M. Midun, L. NaveenNarayanan and V. Saravanan . . . . . . . 62

124. AI Powered Book Recommendation for Online Shopping

Mugilan N V and K Dinakaran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62

125. An Analysis of Awareness Regarding the Impact of the National Education Policy (NEP) 2020
Among Teachers and Students in Higher Education Institutions for Sustainable Growth
Arjita Jain, Sandeep Bhanot, Kiran Kakade, Kasturi Naik and Dhananjay Mankar . . . . . . . . . . . . . 63

126. Generation Z and the Sustainable Paradigm Shift: A Perceptual Study of Personal and
Organizational Values in Mumbai’s HEIs
DrSandeep Bhanot, Arjita Jain, Dhananjay Mankar, Kiran Kakade and Sushma Patil . . . . . . . . . . . . 63

ix
127. Sustainable Volunteering among Generation Z: An Attitudinal Survey
Sandeep Bhanot, Arjita Jain, Pankaj Natu, Kiran Kakade and Dhananjay Mankar . . . . . . . . . . . . . 64

128. Operational Strategies and Leadership in Industry 4.0: Impact on Customer Experience (CX)
and Sustainable Development
Dr. Jayant Brahmane, Dr. Kiran Kakade, Brig (Dr) Rajiv Divekar, Dr. Arjita Jain, Prof. Subhash Yadav
and Dr Shilpa Shinde . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 64

129. The Role of Education for Sustainable Development in India: Challenges and Effective
Implementation Strategies
Dr. Kiran Kakade, Dr Shilpa Shinde, Brig (Dr) Rajiv Divekar, Prof. Subhash Yadav, Dr. Arjita Jain and
Dr. Jayant Brahmane . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65

130. The Role of Emotional Intelligence and Transformational Leadership in Fostering Sustainable
Leadership in Higher Education
Dr. Kiran Kakade, Dr Shilpa Shinde, Dr. Pravin Kumar Bhoyar, Prof. Subhash Yadav, Dr. Jayant
Brahmane and Prof. Anjali M. Kulkarni . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65

131. Analyzing Different Strategies Launched For Solving Food Insecurity Problems in India And
Tamilnadu
A. Sindhuja and Dr. B. Venugopal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66

132. Demographic Influence On It Workers’ Work-Life Balance During Covid-19 Pandemic

Bharathi Kannamma. V and Dr Krithika. M . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66

133. Understanding the Dynamics of Job Satisfaction, Personal Factors, and Retention in Seafaring
Dr. I. Shanmugapriya, Aarthi Suresh, Dr. Krithika. M, Dr S Arul Kumar,S. Murugan and K. Revathik . 67

134. IMU Based Inference System for Vehicles

Vikram Adithya Anand, Dr R Lathamanju and Dr V Arulkumar . . . . . . . . . . . . . . . . . . . . . . . 67

135. Underwater Image Enhancement and Object Recognition Using CNN Algorithm
Vijayalakshmi. P, Seetharaman. M and Praveen. E . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68

136. Use Of 4 Enterprise Technologies In The Food Supply Chain To Enhance Visibility And
Streamline Operations
Santosh M, Ayshwarya R, Janane S and Revathy S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68

137. Real-Time Asset Tracking with IoT Core API and Lora Technology using Multiple Sensors
Dr.Lathamanju R, Kishore G, Venkatesh Prasath J and Krishnavel K . . . . . . . . . . . . . . . . . . . . 69

138. Secure E-Voting Technology System Using Blockchain And Authentication Via Face Recognition
M.P. Kumar, Dr.R.G.Kumar, R. G. Santhi, Sampathi Sai Vamsi, Chellu Mani Ratnam and K. Muhammad
Ashiq . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69

139. Harnessing AI for Robust Deep Fake Detection in Image

B. Pavan Kumar, Dr.R.Elankavi, K. Kesava, M. Krishna Dinesh, K. Susmitha and N Pallavi . . . . . . . . 70

140. Enhancing Dental X-Ray Segmentation using Deep Learning

B. Sarvesan, Dr.J.Sridhar, S Soumya, Vaddi Tejaswini, Gopi Yamini and Shasidhar Avula . . . . . . . . . 70

141. Accident Detection on Roads and Tunnels using Deep Learning Technique
N. Babu, R. Sandhya, N.G. Saikiran, Saravanan Meghana, V. Maheswara Reddy and P. Sarathkumar . . 71

142. IoT-Enhanced Deep Learning Model for Elderly Motor Function Assessment in Rehabilitation
Devices
Sakthisaravanan B, Mothiram Rajasekaran, Arul Prasath A, N Mohankumar, S Murugan and R Creesy . 71

143. IoT and AI-Enabled Smart Contact Lenses for Proactive Glaucoma Management
G Geethamahalakshmi, Mothiram Rajasekaran, Sivanesan T M, Pramod Pandey, S. Murugan and V Praveena 72

144. Apparel Production Paradigms through a Technological Tapestry of AI Driven Smart

Mannequin Automation and Image Processing Precision
C S Manigandaa, M Bindu Sudeeksha, Challapalli Manikantaa, M Jyothsna, V.D.Ambeth Kumar and
P.Sindhu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 72

x
145. Climatic Oracle: Unveiling Future Weather Trends with Data Science
Periasamy J K, Sree Nidhi S, Gunasundhari N and Sharlatha R . . . . . . . . . . . . . . . . . . . . . . . . 73

146. Augmented Reality Applications in Education: Challenges and Opportunities

M.Krishnamurthy, P. Kabilamani, B. Manimaran, T.Kavitha, P.Nagarajan and N.Ashokkumar . . . . . . 73

147. Drone Detection and Drone Type Classification Using Deep Learning Technique
Ashokkumar.N, Nagarajan.P, Kavitha.T, R. Bhairavi, Arulmary A and Balamanikandan.A . . . . . . . . 74

148. Particle Swarm Optimization Based Intelligent Smart City Parking Guidance System
Ashokkumar.N, Dr C Venkataramanan, Nagarajan.P, C. Kanmani Pappa, P. Kabilamani and K.P.Porkodi 74

149. Deep Learning: Techniques, Taxonomy, Applications, and Future Directions

Mohana Sundari V, Mabel Rose R A, Sassirekha S M, Nalini M, Girija P and Siva Subramanian R . . . . 75

150. IoT and Data Analytics in Healthcare

Sekar G, John T Mesia Dhas, Anandaraj B, Nalini M, Sathya V and Siva Subramanian R . . . . . . . . . 75

151. An Improved Artificial Intelligence Assisted Sign Language Recognition Methodology using
Modified Deep Learning Principle
B.Vasumathi, N Aparna, A V. Allin geo, R.Thiagarajan, Pravin Kulurkar and R.Krishnamoorthy . . . . . 76

152. ELNN: A Novel Approach to Identify Periodontal Disease from Panoramic Radiographs in
Earlier Stages using Enhanced Logical Neural Networks
Bhuvaneshwari Karthikeyan,V.Balaji Vijayan,Kotteeswaran R,M.K.Vidhyalakshmi.Krishnamoorthy R and
R.Thiagarajan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 76

153. A Logical Design of Superficial Learning Methodology to Identify Dental Diseases using
Predictive Classification Principle
Bhuvaneshwari Karthikeyan, Pooja Bhagwat, Kishor patil, Shraddha Walekar Ghaisas, R.Thiagarajan and
R.Krishnamoorthy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 77

154.Experimental Evaluation of a Secured Blockchain based Data Management Scheme for Patient-
Centric Applications in Healthcare Industry
A. Sevuga Pandian, G.Sundar, P.Patchaiammal, AMOL L. Mangrulkar, R.Thiagarajan and R.Krishnamoorthy 77

155. A Smart and Intelligent Robotic Design to Rescue Human from Disaster Conditions using
Artificial Intelligence Assistance
Reddi Khasim Shaik, V.Balaji vijayan, Kotteeswaran R, AMOL L. Mangrulkar, R.Krishnamoorthy and
R.Thiagarajan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78

156.A Smart and Secured Anomaly Detection Scheme for Internet of Things (IoT) Powered Devices
using Federated Learning Technology
G. Sundar, P.Patchaiammal, AMOL L. Mangrulkar, Sameer Sharma, R.Krishnamoorthy and R.Thiagarajan 78

157. IoT Powered Energy Optimization and Monitoring System for Smart Buildings using Learning
based Artificial Intelligence Association
C. Meenakshi,S. Meyyappan,M.Vijayakarthick,A.G. Ganesh Ram,B. Vinoth and Thiagarajan R . . . . . . 79

158. Enhancing Efficiency, Collaboration and Innovation Through Transparent Systems

Dr. Gnana Jeslin J, Glory Sangeetha. R, Dr Uma Maheswari G, Dr. Raja Suguna M, T.Anand and Mrs.E.
Lavanya . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79

159.Video Frame Transmission Using Semantic Frame Segmentation over Deep Series Network with
AWGN Channel
Ashok S, Alex Joseph K, Kessavan M, Susendhiran E, Prabhu.V and Venkat S . . . . . . . . . . . . . . . 80

160. Enhancing Prediction Accuracy through Random Forest in Classification and Regression
Ignatious K Pious, Rajalakshmi A, Prem Kumar R, Varun C M, Nalini M and Siva Subramanian R . . . 80

161. “Post-COVID-19 Adoption of Digital Financial Services: Analysing Usage Patterns and
Demographic Influences in Maharashtra State”
Kiran Kakade, Anjali Kulkarni, Ameya Patil, Pravin Bhoyar, Jayant Brahmane and Subhash Yadav . . . 81

xi
162. OPEN EYE: An Information Gathering Tool Using OSINT Framework
A. M.Sermakan, P.Sreejith, A.Leela Krishna. S.Lokesh, Kaushik Narayanan.C.VR and Jaya siva
subramaniam.N . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 81

163. Construction of Smart Automation System using Cisco Packet Tracer

Mrs. Maheswari A, Dr. Raja B, Mohamed Eghiya Kamal and Peer Arif P . . . . . . . . . . . . . . . . . . 82

164. Psychological Escalation of Gaandness State and Analysing the Triggering Subfactors
Contributing to Mental Outbreak
Vincent Gnanaraj T, Chenni Kumaran J, Bhavani R and Mohan A . . . . . . . . . . . . . . . . . . . . . . 82

165. Foreign Language Learning Portal with TTS

Dr G Adiline Macriga, Sri Shakthi K and Priyatharshini . . . . . . . . . . . . . . . . . . . . . . . . . . . . 83

166. Secure and Scalable Blockchain-Based Electronic Health Record System Enhancing Data
Interoperability and Patient Privacy
Shyamala Kumari, Prasanth J, Sanjeeviram C.M and Prashanth K . . . . . . . . . . . . . . . . . . . . . . 83

167. A Comprehensive Examination of the Advancements in Deep Learning Models for Enhanced
Disease Prediction
Sasirekha.K and Joe Prathap P.M . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84

168. Machinelearnpro: Redefining Predictive Maintenance through Data-Driven Approaches

Dr. Anand K, Dr. Ananthajothi K, Dr. Vinodkumar S and Dr.N. Duraimurugan . . . . . . . . . . . . . . 84

169. Deep Belief Networks for Brain Tumor Recurrence and Survival Rate Prediction
M. Sathish, M. Shafiya Banu, Kannan Shanmugam, P. Thenmozhi, C. Srinivasan and Sermakani A M . . 85

170. Advancing Telestroke Services Technology with Cloud and AI Solutions for Enhanced Care
Mothiram Rajasekaran, R. Meenakshi, Dr. P. K. Dhal, Dr. R. Aiyshwariya Devi, S. Sujatha and R.
Kamalakannan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85

171. Dynamic Traffic Flow Optimization with YOLO-Based Object Detection

Dr P Chitra, Divyesh S and Vibusha P . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 86

172. Water Quality Monitoring System Using Maps

Iyswariya A, Sai Sharan P, Valliappan PL, Sanjay S and Surya K . . . . . . . . . . . . . . . . . . . . . . . 86

173. Orphan Guard: A Website for Orphanage Management

Pathmanaban J, Vigneshwari M, Vivekanandan G, Ilamathi K B, Krithika S and Deepika S . . . . . . . . 87

174. Predicting the Results of Cricket Matches using Deep Learning Method
Kumar P, Senthil Pandi S, Karthikeyan N and Karthikeyan N . . . . . . . . . . . . . . . . . . . . . . . . . 87

175. Multimodal Fusion for Depression Detection and Severity Estimation Using Deep Learning
Senthil Pandi S, Kumar P, Salman Latheef T A and Varsha S P . . . . . . . . . . . . . . . . . . . . . . . . 88

176. Hybrid ACO-SA Algorithm for Bi-Objective Multi-Workflow Scheduling in Amazon Cloud
Environments
Senthil Pandi S, Kumar P, R.M.Suchindhar and Mithun Dineshkumar . . . . . . . . . . . . . . . . . . . . 88

177.Random Forest Bayesian Optimization Deep Transformer-Based Heterogeneous Spatiotemporal

Graph Neural Network for Identifying Parameters in QKD
Ilakkiaselvan Dhandapani, R.J.Kavitha, P.Ananadavalli, T.Thamizhmani, V.Balamurugan and
E.Elakkiyachelvan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 89

178. Morphological And Statistical Operations Based On Segmentation And Classification Of Skin
Cancer Images
S. Anantha Sivaprakasam, V.Saravana Kumar, N. Srinivasan and M.Kavitha . . . . . . . . . . . . . . . . . 89

179. Enhanced Clustering Method For Segmentation Of Hyperspectral Satellite Images

V.Saravana Kumar, Kavitha M, S. Anantha Sivaprakasam, Bavya, N. Srinivasan and Saravana Kumar . . 90

xii
180. Secure Data Exchange in Cloud Computing: Enhancing Confidentiality, Integrity, and
Availability Through Data Partitioning and Encryption
Mohammed Ali Shaik, Vupulluri Sudha Rani, Afshan Fatima, Masrath Parveen, Dr.Juhi Juwairiyyah and
Nikhat Fatima . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90

181. Smart Water Dispenser: Integrating VoiceCommands and Facial Gestures

Shanmuga Sundar, Dhanushkumar A, Shanmuga Vadivu Pandy S, Jeevanandam L and Dharunkumar A . 91

182. Smart Health Monitoring System Using IoT Sensors in Cloud Environment
Vigneswari J and B.Yamini . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 91

183. Understanding AI Model Collapse: Causes, Impacts and Solutions

S. Sheeba Rachel, Karthik Balaji B M and Saiganesh V . . . . . . . . . . . . . . . . . . . . . . . . . . . . 92

184. A Study On Menopausal Symptoms And Perceived Stress Among Middle – Aged Women In
An Urban Community
Bavanipriya V and Abirami M . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 92

185. Emotion-Based Frequency Recommendation and Healing System Using Speech Analysis
Vignesh Kumar M, Chintamakula Mehereesh, Busetty Praneeth, Boppudi Bhargav and Boyapati Kumar . 93

186. Solar Energy and Visible Light Communication for Eco-Friendly Communication Systems-An
Overview
P.Gandhimathi, A.Senthil Kumar, P Tharcis, Nirmala Baby and B. Anitha Vijayalakshmi . . . . . . . . . 93

187. Learning Plant Anatomy through Ar & Vr

Uma Mageswari, Rajasekar A, Dharunkumar A, Dinesh R, Jashwanth Sathish and Vasanth B . . . . . . . 94

188. Automatic Following Shopping Cart with Bluetooth Connectivity and Obstacle Avoidance
Suganeshwaran M, Kumaran K and Saranya G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 94

189. A Hybrid Machine Learning Approach for Accurate Railway Traffic Forecasting
P Vinayagam, Kanagamalliga S, M.V. Hariharan and S Niranjan . . . . . . . . . . . . . . . . . . . . . . . 95

190. A Novel Machine Learning approach for Real-Time Correction of Atmospheric Distortion in
Multispectral Satellite Images
Sivasakthi Thanigainathan, Anousouya Devi M, Keerthivasan K, Dharanyadevi P, Kalpana S and
Keerthivasan H . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 95

191. Optimizing Agricultural Yields using AI and Machine Learning

Vinayagam P, Kanagamalliga S, Hariharan M V and Niranjan S . . . . . . . . . . . . . . . . . . . . . . . . 96

192. House Authentication Using Finger Vein Based On Anatomical Features of Vein Patterns
D.Chithra, T. Veena, A.M Sermakani, S. Juliafaith and P. Senthil . . . . . . . . . . . . . . . . . . . . . . . 96

193. Design and Development of Virtual Reality Headset-Controlled Pick and Place Robot Arm
K Kaviya Sanjay, K Sreehari, G Shanmugasundar, Su Suganthi, R Preethi and J Kirthan . . . . . . . . . 97

194. ANTI-CONDOR (The Phishing Detector using Random Forest Algorithm)

Denish Manova M, Jeevanandam L, Shanmuga Vadivu Pandy S, Gopinathan S, Rajasekar A and Radhika
Rajaram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 97

195. AI Legal Documentation Assistant

Gopinathan S, Radhika Rajaram, Sivagar Mr, Jayapriya M, Samsthana K L and Jeyanthini E N . . . . . 98

196. Counterfeiting Detection System: A Solution to Combat Product Counterfeiting

Amit Kumar Gupta, Ruchi Rani Garg, Harsh Khatter and Mangal Sain . . . . . . . . . . . . . . . . . . . 98

197. Digital evidence extraction and analysis of Disk Image

Udhayakumar S, Sai Pavan Rangu S, Abhiram Patel U and Tata Seetha Rama Sai Vamshi Krishna . . . . 99

198. Hybrid Model For Email Spam Detection Using Multi-Modal Knn and Svm
I Vasudevan, Denis Amirtharaj, A.Jaisuriya, R.M.Dilip Charaan, S.Ashok Kumar and Leena Jenefa . . . 99

xiii
199. A Data Discovery on Prostat Cancer through Meta Hybrid Learning using Ensemble Deep
Autoencoder
K Nattar Kannan and E.Sathesh Abraham Leo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 100

200.Advanced Data Mining Techniques For Crop Yield Predictive Modeling: The Strategic Modified
Gradient Boosting Regression (Smgbr) Approach
Natvar Sardarbhai Patel, Dr. Bhavesh M Patel and Sirajbhai A Nagalpara . . . . . . . . . . . . . . . . . . 100

201. Timber Identification Based on the Grain Structure using Learning Algorithms
Kumar P, Senthil Pandi S, Jain Bai B and Sathish Kumar Kannaiah . . . . . . . . . . . . . . . . . . . . . 101

202. Text-to-Cadence: Synthesizing Rhythmic Voice Through Tacotron2 and Waveglow

Kumar P, Senthil Pandi S, Muqaddam Aaqil Sheriff and Sathish Kumar Kannaiah . . . . . . . . . . . . . 101

203. Analysis And Prediction Of Bitcoin Prices Utilizing The Data Science Methodology
Kumar P, Senthil Pandi S, Bala Subramanian C and Sathish Kumar Kannaiah . . . . . . . . . . . . . . . 102

204. Stock Market Portfolio Valuation using CPU based parallelism

Dr Kumaran K, Sarath Rajan Senthilkuma, P Kiranteja, Arun Karthik Anand Kumar and P K Desigan . 102

205. An Experimental Analysis On Optimizing Lithium Ion Battery Lifespan Predictions With
Xgboost And Bayesian Techniques
Keren Persis p, Dr. Saranya S, Dr.S.Sivasakthi and Swaroop Gannamani . . . . . . . . . . . . . . . . . . 103

206. Accuracy Enhancement in Detecting the Driver Drowsiness using CNN

Priyanka K, Senthil Pandi S, Srinivasan K S and Kumar P . . . . . . . . . . . . . . . . . . . . . . . . . . . 103

207. Exploring the Interplay between AI-Generated Art and Human-Created Art: A Comparative
Analysis
Shanu Khare, Navjot Singh, Sivakamy N, Veeramanickam M.R.M and Muthukumarasamy S . . . . . . . . 104

208. Optimizing DNA Cryptography: using HPC Leveraging GPU and Parallel Processing
Shreyank Saksena, Ishaan Kanade, Suyash Agrawal, Debesh Biswas and Kumaran K . . . . . . . . . . . . 104

209. Prevention Of Sql Injection

Sathya V, Anirutth SA and Mohamed Safresh H . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105

210. An Integrated Xgboost And Bilstm Model For Advanced Remaining Useful Life (Rul)
Predictions In Aircraft Maintenance
Sakthivel Janarthanan and A. Anthonisan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 105

211. Analyzing Global Development: A KMeans Clustering Approach to the 2023 Legatum
Prosperity Index
Ramya P, Subedha Varatharaj, C Amritha, S Hemalatha and Nithiyasree P . . . . . . . . . . . . . . . . . 106

212.IoT-Enabled Safety Helmet for Coal Miners: Real-Time Monitoring, Data Collection, and Analysis
Radhika Rajaram, Gopinathan S, Ranjith Kumar, Prajeeth Kumar, Harish V and Reddy Balaji Elumalai 106

213. Hand Gesture Recognition for Smart Control of Electrical Appliances using Computer Vision
Uday Kumar Rajanala, Naga Kanaka Bhavani Chinni, Gopika Sandaka and Raziya Shaik . . . . . . . . . 107

214. Mental Health Prediction of Students Using Machine Learning Method

Dr. B.R. Sathishkumar, M. Kavin Kumar, S.G. Paveen and S. Poorna Vignesh . . . . . . . . . . . . . . . 107

215. A Hybrid Approach for Diabetic Retinopathy Detection using Support Vector Machine
Senthil Pandi S, Shobana Lakshmi R and Jain Bai B . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108

216. Quantum Key Distribution-Based Security Framework for Wireless Sensor Networks:
Enhancing Resilience Against Classical and Quantum Cyber Threats
S. Senthilkumar, K.K. Shandhosh Shree, R. Rajaganapathy, P. Krishnamoorthy, L. Ramachandran and M.
Kavitha . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 108

217. Designing And Fabrication Of Panoramic Cooling System

B. Vijaya Ramnath, V. Ravi Raj, R M. Sanjay Kumar and S. Gananathji Naveen Kishore . . . . . . . . . 109

xiv
218. GenoCryptNet: The Future of Secure Communication through DNA
Shravya Munugala, Harsh Panchal, Suhani Goel and Padmanaban R . . . . . . . . . . . . . . . . . . . . . 109

219.An Implementation of Smart Agricultural Communication System using IoT and Bigdata Analytics
Dr. S. Raja, Dr. T. Guhan, Dr. M. Lalithambigai, Mr. P. Boopathi, Dr. S. S. Suganya and Dr. M.
Umamaheswari . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 110

220. Optimizing Crop Selection with Bigdata and IoT Sensor Technology in Modern Agriculture by
Univariate Feature Selection
R. Mahesh Kumar, G. Sujatha, B. Lavanya, Dr. R. Vijayabhanu, Dr. Sasikala Dhamodaran and D. Saranya 110

221. A Novel Approach for Waste Classification Using Active Deep Learning
Raja K, Anandaperumal E, Abhishek M B, Senthilselvi A, Senthil Pandi S and Kaavya R . . . . . . . . . 111

222. EDUHUB - An Integrated Learning Management System Using DJANGO

Devi Arumugam, Amirthasaravanan Arivunambi, K. Dhivya, Robinbritto V, P. Dharanyadevi and
H.Keerthivasan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 111

223. AGI With Human

Lithish M, Denish Manova M, Jashwanth Sathish, Kailash A, Sathyanarayanan P and Arwind Ragaw S.K 112

224.Hybrid Deep Learning Approaches for Predictive Modeling of Aluminium Gallium Nitride with
Rime Optimization Algorithm
M.Priscilla, Dr.A.Mohan Babu and Dr.Radhika . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 112

225. Multifaceted Feature Extraction and Machine Learning Approaches for Mortality Risk
Prediction in Pediatric Intensive Care Units
Shib Kumar Saraf and Solaimurugan Vellaipandiyan . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113

226. A Comparative Analysis of Corn Leaf Disease Classification Using Advanced CNN Architectures
Kappala Vikash and M. Kalyan Ram . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 113

227. MindGuard : Digital Aid for Smartphone Addiction

Hariharan M, Kavitha R, Monish Kiran S and Ezhumalai M . . . . . . . . . . . . . . . . . . . . . . . . . . 114

228. Voice-Activated Email System: Enhancing Accessibility with Speech-to-Text Integration

Srinivasan A, Meenakshi B and Swathiha R R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 114

229. IoT Enabled Smart Reminder System

Satya Jagu, Manju Bhargavi Pilli, Samuel Devanaboina and Rushikesh Dhornala . . . . . . . . . . . . . . 115

230.Enhanced Automatic Number Plate Recognition using Yolov7, Resnet, and Image Rectification
Techniques
Dr.M.Kathiravan, Dr.Vijay R, Mr.A.Irumporai, Dr.R.Buvanesvari, Mr.Vengatramana R and Dr. V. Kaliraj 115

231. Dynamic optimization of Traffic management using Gen AI

Mr. S. Jegadeesan, M.Harin Sowmiya, R.Ambika and S.Thanusha . . . . . . . . . . . . . . . . . . . . . . . 116

232. A Non-invasive Efficient Interpretation of Heart Beat Monitoring System

N Shivaanivarsha, Sai Santhiya G, Rajalakshmi K, Lokith Sharan R, Karthikeyan S and Pavita S . . . . . 116

233. Machine Learning in Healthcare: Opportunities and Challenges

Peer Mohamed Appa M.A.Y, Sudha K, Pooja E, Lekha D, Ezhilvendan M and Gayathri S . . . . . . . . . 117

234. Schemes Paaru! - A Multi-Platform Chatbot for Government Scheme Information in India
Dhanushprakash.V.C, Balaji.A, Malathi, Sripriya.T, Arthy .G. and Sinthia.P . . . . . . . . . . . . . . . . 117

235. Aqua Garbage Cleaning RO Boat

Kamalakkannan Sivaraman, Vinoth Kumar.Ls, Sathish Kumar.M, Sathish Kumar.M, Saravanan.A and
Sarath Kumar.D . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118

236. Systematic Review of Security for Health Records using Blockchain

Shivalingappa P and Nagaraja G S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 118

237. Adaptive Development of the StaySmart Booking System through Agile Methodology
Saraswathi P, Adeline Joanna V, Shanmuga Priya AR, Subhadharshini V and Prabha M . . . . . . . . . . 119

xv
238. Dual-Level Contrastive Learning with Reverse Translation for summarisation
Joanna Samuel, Nandithaa I N, Nithyanjali Maruboina and Dr. Deva Hema D . . . . . . . . . . . . . . . 119

239. Prediction of Loan Approval in Banks using Machine Learning Algorithm

Mathan Kumar Mounagurusamym, Dr. P A Manoharan, Dr. J. Anvar Shathik, A.Pandiaraj, N.
Ramshankar and Naveen G . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 120

240. K-Nearest Neighbors in Machine Learning: Theory, Practice, and Advances

Manjunathan N, Vijaya Prabhu R, Sudha K, Lekha D, Ezhilvendan M and Gayathri S . . . . . . . . . . . 120

241. Iterative Deepening Chess Engine with Alpha Beta Pruning

Dr. E. Kodhai, Dr. E. Bhuvaneswari, Dr. V. Anjana Devi and S.T. Preethi . . . . . . . . . . . . . . . . . 121

242.Assessing the Efficacy of ML Techniques for Forecasting Healthcare Consumer Readmission: A

Comparative Analysis of Risk Factors and Healthcare Interventions
Loganayagi S, S. Alagu Thangam, Dr. V.R.Vimal and Dr.T.Suresh Balakrishnan . . . . . . . . . . . . . . 121

243. Integrating Sustainability Development Goals into Business, Marketing, Finance and
Engineering for a Better World
Mr.S.Amarnaath and Ms.G.Deepana . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 122

244. Incorporating Sustainable Development Goals (SDGs) into Marketing Strategies: A Path to
Business Growth and Global Impact
Mr.S.Amarnaath and Ms.G.Deepana . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 122

245. Swarm-Based LSTM for Temperature Forecasting Using Big Data Analytics
Mathankumar Mounagurusamy,, Pandiaraj A, Ramshankar N, Naveen Gandhi Anbullam, Dhivya V and
Jeeva K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 123

246. Survey on Text Mining using Bert and Probabilistic Topic Modelling
Varshni S V, Kavitha D, Dharaniya D, Sangeetha J and Kaliraj V . . . . . . . . . . . . . . . . . . . . . . 123

247. Plant Leaf Disease Detection using CNN

Abirami A, Prabhu K, Kaliraj V, Mahesh Vaijainthymala Krishnamoorthy and Dharaniya.R . . . . . . . . 124

248. A survey on detection of oil-spill in satellite-based Synthetic aperture radar (sar) images using
neural Network
Saranya T V, Justindhas Y, Satish Srinivas S, Ahamed Ali S and V.Kaliraj . . . . . . . . . . . . . . . . . 124

249.Survey On the Facial Recognition Of Humans With Masks Post Covid using Artificial Intelligence
Satish Srinivas S, S. Ahamed Ali, Saranya TV, Justindhas Y and V.Kaliraj . . . . . . . . . . . . . . . . . 125

250. Face Authentication System using Face Recognition and Firebase

Muhemin Sheriff M, Bhuvaneswari S, Balakrishnan, C, Muralitharan G, Kaliraj V and Dharaniya R . . . 125

251. Decoding Mental Health through Social Media with Dual-Stream AI

Senthil Pandi S, Kumar P, Salman Latheef T A and Karupannan P . . . . . . . . . . . . . . . . . . . . . . 126

252. AgroFusion: Combining Multiple Deep Learning Techniques of Data to Improve Crop
Management and Forecast Yield
Senthil Pandi S, Kumar P, Salman Latheef T A and Karupannan P . . . . . . . . . . . . . . . . . . . . . . 126

253. Enhanced Software Deployment and Integration with an Integrated CI/CD Pipeline
Senthil Pandi S, Kumar P, R.M.Suchindhar and Karupannan P . . . . . . . . . . . . . . . . . . . . . . . . 127

254. Improving Wind Power Forecasting using Hybrid Ensemble Methods

Kumar P, Senthil Pandi S, Karthikeyan N and Karupannan P . . . . . . . . . . . . . . . . . . . . . . . . . 127

255. HydroNet-Monitoring Water Health: A Comprehensive Approach to Evaluation and

Forecasting Quality
Kumar P, Senthil Pandi S, Karthikeyan N and Karupannan P . . . . . . . . . . . . . . . . . . . . . . . . . 128

256. Deep Learning for Sign Language Interpretation With Conventional Neural Network
A. Senthilselvi, Ballela Avinash Reddy, Charan Deepesh Kristam, Rachaputi Yeswanth Vardhan and Senthil
Pandi S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 128

xvi
257. A Novel Approach to Improve Crop yield using Machine Learning
A.Senthil Selvi, Gollapally Abhiram Sai, Abhinand TV, Jayadev Nukala, Syed Juniad and Senthil Pandi S 129

258. Towards Safer Environments: CNN-LSTM Framework for Accurate Fire Detection
Saranya V and Senthil Pandi S . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 129

259. Digital Renaissance: Government Scheme Notification and Smart Fund Disbursement as
Catalysts for Empowerment in Social Reliability
Ms. Kavitha Arunachalam, Ms. Swetha S and Ms. Swetha T R . . . . . . . . . . . . . . . . . . . . . . . . 130

260. Blockchain-Based Voting System With Fingerprint Authentication and Zero Knowledge Proofs
R. Sudharsan, L. Giridharan, Anto Micheal Infant and Dr. Suresh Annamalai . . . . . . . . . . . . . . . . 130

261. Improving Cloud Burst Prediction with Meteorological Analysis Driven by Machine Learning
Jagadeeshwaran S, Srinivasan Rama Krishnan, Vignesh Kumar A and Raja Priya D . . . . . . . . . . . . 131

262. Advancing Emotion Detection In Sentiment Analysis With Concept-Level Computing And
Machine Learning
Dr.M.Kathiravan, Dr.R.Bhuvaneshwari, Ms.Ramya M, Dr. Kaaliraj S, Mr.A.Irumporai and
Mr.Vengatramana R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 131

263. PlantMed -An Automated App for Monitoring the tasks of Farmers
B.Sundarambal, S.Manju and R. Aarthi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 132

264. AI Enhanced Logbook Management for Classrooms

Saraswathi P, Keerthana.R, SobanaManikandan, Muthulakshmi.P, A.Sameeha and Sharmila Devi R . . . 132

265. Diabetic Retinopathy Classification using Hybrid Optimized U-Net and Improved ResNet-18
with MISH Activation
S.Nithyapriya, S.Yuvalatha, S.Prabhavathy, T.Arun, Dr S.K Muthusundar and Dr. Antonidoss A . . . . . 133

266. Capsule-Infused Vision Transformer: A Hybrid Deep Learning for Hierarchical Feature Learning
S.Yuvalatha, S.Nithyapriya, R.Tamizh Kuzhali, S.savitha, Dr S.K Muthusundar and Dr. Antonidoss A . . 133

267. Decoding Emotions: A Deep Learning Framework for Speech Emotion Recognition
Shreyank Saksena, Anirudh AVS and Dr. Parkavi K . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 134

268. Securing Library Assets: Leveraging Blockchain for Unbreakable Data Integrity and Privacy
Dr .J.V.Anchitaalgammai, Mrs.S.Kavitha, Mr.S.Murali, J.Matcha Rani, R.Shreevarshini and V.Agniselvi . 134

269. Machine Learning Algorithms Based Approach for Detecting the LeukemiaDisease
Senthil Pandi S, Bala Subramanian C, Mithul Dev D and Kumar P . . . . . . . . . . . . . . . . . . . . . . 135

270. Optimizing Feature Selection for Big Data and Machine Learning: Challenges and Future
Prospects
V.Sharmila Bhargavi, T.P. Anish, Anusha S, V.Nivakumar, Dr M.Nalini and Siva Subramanian R . . . . . 135

271. IOT Based Continuous Blood Glucose Monitoring System for Enhanced Diabetic Care
Megala J, Divyapriya C, Gayathri G, and Logeshwari S . . . . . . . . . . . . . . . . . . . . . . . . . . . . 136

272. AI-Driven Predictive Modeling for Early Detection and Progression Monitoring of Chronic
Kidney Disease Using Multimodal Data
L Lakshmi Prasanna Kumar, Vankadara Sampath Kumar, G. Ashok Kumar, Y.Nagendar, Nithya M and
A.Athiraja . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 136

273. Enhancing Software Debugging Processes Through Machine Learning-Driven Automated Bug
Detection
Venkata Madhu Bindu Nalluri, Parvathraj K M M, Y.Nagendar, Kalaivani E, Prabhu A E and Dr.Athiraja
Atheeswaran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 137

274. Real-Time Vehicle Density Detection for Adaptive Traffic Signal Control Using YOLOv5
M. Mariyammal, Rakesh S P, Ramana Ganthan S, R Poornima Lakshmi, Ayyappan S and R. Ponnusamy 137

275. Stego-Image Data Masking

Aswathy M P, Megiba Jasmine R, P.J.Beslin Pajila, Anish T.P., Dinesh M G and Nithyanandhan R . . . 138

xvii
276. Facial Emotion Classification Utilizing Efficientnet: A Comprehensive Deep Learning Method
Veeramalai S, Chorko C, Akshaya A and Rahul Ramamoorthy . . . . . . . . . . . . . . . . . . . . . . . . 138

277. AI-Based Mathematical Modelling for Sustainable Business and Inventory Management
Arvind Nain, Madhu Arora, Saurabh Sharma, Anup Shekhar Chamoli, Satyam Prakash Srivastava and
Vasim Ahmad . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 139

278. Optimization of Green Finance Using AI and Blockchain in Inventory Management

Arvind Nain, Preeti Tyagi, Mayank Pant, Devesh Chand, Satyam Prakash Srivastava and Vasim Ahmad . 139

279. Temperature Monitoring System for Portable Incubators for Neonatal Care
Muthyala Prem Kumar and Gorthi Balaji . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140

280. An Intelligent Agents-Based Smart Drip Irrigation System Design Using Paddy Crops
D. Lekha and P. Valarmathie . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 140

281. Innovative Gym Management Platform For Effective Member Engagement And Service
DineshKumar S and Naveenkumar P . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 141

282. Enerlink Guardian: Dynamic Vehicle- to-Vehicle Charging and Battery Oversight System for
EV Charging Stations
Magadevi Nirmalkumar, S. Bharathi, S. Janani and S. Lekha . . . . . . . . . . . . . . . . . . . . . . . . . 141

283. Scalable Transaction Management System: A Blockchain-Based Approach using Solidity and
Ethereum
Annie Silviya S H and Dinakaran Karunakaran . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142

284. Dronav: Deep Learning based Autonomous Drone Navigation System

T. Daniya, Aditya Darapureddy, Guravana Ashok Kumar, Boyina Rajesh, Dinesh Potnuru and Sai Amrutha
Vugiri . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 142

285.Tribological and Mechanical Properties of Polymer Composites Reinforced with Alkali Treated
Prosopis Juliflora, Egg Shell, and Scallop Shell
Pravinprabu T, Rajarajan S J, Mounika J and Jayakumar T . . . . . . . . . . . . . . . . . . . . . . . . . . 143

286. Streamlit Enabled Adaptive Movie Recommendation Systems using Content-Based Filtering
Techniques
Prem Kumar R and Anitha R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 143

287. Forecasting Crop Yields Using Machine Learning Techniques For Sustainable Farming
Dr ChitraDevi D M.E, Mahalakshmi G, Priyadharshini M and Reshena R . . . . . . . . . . . . . . . . . . 144

288. Advanced Recurrent Neural Networks for Nail Disease Detection: A Comparative Analysis
Shanthalakshmi Revathy J, Menaga R and Pradeesha C . . . . . . . . . . . . . . . . . . . . . . . . . . . . 144

289. A CNN-Based Framework for Alzheimer’s Disease Diagnosis and Prognosis from Multimodal
Imaging Data
Balasubramanian M, Vishnu Sriram T, Gautam Kumar G, Jeo Godson Samuel J and Kanishka M . . . . 145

290. A Survey For Population Evaluation Using Machine Learning Techniques

B.Yuvasri and Dr.K.Ramar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 145

291. Market Basket Insights for NIFTY 50: Identifying Financial Winners and Losers with Eclat
and Apriori Algorithms in 2023-24
S.Magesh, Dr.L.Jabasheela, T Sanjayaakash, M Rupesh Kumar and K Sanjay Balaji . . . . . . . . . . . . 146

292. Puzzle Progression Game Using Reinforcement Learning

Abhigyan Ghoshal, Mohammad Armaan Ali and Dr.Kumaran K . . . . . . . . . . . . . . . . . . . . . . . 146

Author Index 147

xviii
 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Sustainability: Navigating Environmental, Economic, and Social Imperatives to Shape

Future Generations
Lijetha C Jaffrin, Maheshwaran T, Sivakumar S, Sassirekha S M, Sakthivel M and Nalini M
Sustainability becomes a key idea for managing and overcoming global problems and for contributing to the
developments of the generations to come. The present survey paper aims to analyse the multiple and interrelated
aspects of sustainability as well as its potential consequences for generations to come. Beginning with a foundational
exploration of sustainability and its theoretical underpinnings, including the principles of intergenerational equity
and the Sustainable Development Goals (SDGs), the paper navigates through three primary dimensions:
Environmental, economic, and social aspects of sustainable development have to become priorities for any company.
It also assesses the effects of current practices on environmental deterioration, economic volatility, social welfare,
while highlighting how these factors are interdependent in determining the future state. Moreover, the paper
explores the success factors and tools for the implementation of sustainable development policies, technologies and
practices as well as educational programs to enhance sustainable practices in the world. It also discusses the
numerous factors that lesser progress and stop the progress of such solutions from taking place including financial,
social, and institutional factors. Last, the paper discusses the future research directions where new and promising
areas have been noted, as well as several critical research areas that need to be addressed and expanded in future
research. In this regard, this paper seeks to present current insight and provide anticipating ideas to the
stakeholders, policymakers, and researchers on the majors of SD to achieve the resilient and equitable future.
Keywords: Sustainability, Economic Sustainability, Green Economy, Social Sustainability.

Paper ID - 0013

Academic Performance Evaluation Using Data Engineering and Multi-Model Machine

Learning System
P.J.Beslin Pajila, Gautham Anand, K Neela, Gowri M, Karthikeyan M and Nithyanandhan R
This paper aims at identifying and employing data engineering and multi-model machine learning techniques for the
assessment of student’s academic performance with a strong focus on data analytics approach in education. It starts
with data collection and cleaning of various data types such as demographic, attendance, academic performance, and
co-curricular records. These are consolidated into a unified database for training. Next, the Machine Learning model
is developed and trained with the help of the chosen Random Forest. Random Forest is one of the strong ensembles
learning models that build a large number of decision trees at the time of training. Training of each decision tree is
carried out on the features and data samples that are part of the dataset but different from the others to improve on
the degree off repetition and thereby increase the level of robustness of the final prediction. After the model training,
several Python libraries are used to design a local website for collecting student details for performance prediction.
The system then cross checks the input details with the trained model and provides the predicted performance output.
This approach therefore ensures that the model is able to perform well across various datasets and improves its capacity
to predict accurately, making it resourceful in identifying and predicting academic performance in this study.
Keywords: Image Processing, Image Enhancement, Image Transformation, Image Restoration, Image Segmentation.

Paper ID - 0014

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 1

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Smart Helmet For Digcrafters Using IoT

Anita M, Maheshwaran T, Dhivya R, .Muthuram A, Dinesh M G and Dr. M. Jayakumar M
The “Smart Helmet for Dig Crafters using IoT” is a unique and technologically more advanced which aims to minimize
the health risk, improve work productivity and efficiency of workers in construction and excavation field mostly known
as “Dig Crafting.” Internet of things is integrated in to this smart helmet to provide real-time and proactive data
communication for safety and problem solving of these workers. The primary goal of this smart helmet is to connect
and introduce an intelligent working environment in which Dig Crafters, their safety is provided, and Production
efficiency is determined. Key features and functionalities of the smart helmet include Real-time Hazard Detection:
The smart helmet also features sensors that detect factors that may include lethal gases, temperature, humidity, the
quality of the air within the location the individual is situated at. The basic function of the smart garment is that
when hazardous conditions are ascertained, it alerts the wearer and the central control systems thus minimizing the
chances of an accident. Health and Biometric Monitoring: This helmet is fitted with biometric sensors will be used
to keep track on the welfare of the workers. Its check’s essential signs such as pulse, temperature, and fatigue level
to ensure early treatment if the creature is ill. Environmental Data Collection: The helmet provides information on
the condition of the worksite environment and this information is highly beneficial in enhancing safety and resource
management in the future. The “Smart Helmet for Dig Crafters using IoT” is not only used as productivity tool but
also helps to improve the construction and excavation works. IoT within Dig Crafters enables data collected decisions
that prevent hazards and ensure a better working conditions for the company while it can be lively observed via web
application.
Keywords: Smart Helmet, Dig Crafters, Internet of Things (IoT), Construction and Excavation, Safety Enhancement,
Productivity Improvement, Well-being, Real-time Data Communication, Health Monitoring.
Paper ID - 0015

Infrasecure: Enhancing V2I Communication Using Data Integrity

G. Mariammal, S. Sridevi, D. Mangaiyarkarasi, M. Sai Venkata Adithya, G. Balaji and S.
Venkateswaralu
V2I communication is essential to contemporary transport systems because it provides advantages like collision
avoidance and real-time traffic data. Ensuring the security of data transmitted between infrastructure and vehicles
poses a considerable difficulty, though. The goal of this project is to improve data integrity through the use of
cryptographic methods, specifically the MD5 hashing algorithm.MD5, a popular cryptographic hash algorithm,
creates fixed-length hexadecimal hash values from data. A unique MD5 hash value is produced for each modification
to the original data, guaranteeing that the data is unchanged throughout transmission. Our study focuses on
efficiency and scalability in the research and implementation of cryptographic protocols. When data is transferred,
MD5 hashing creates distinct digital signatures that enable early identification of unwanted changes. The
communication route is secured by key management procedures, and prospective assaults are mitigated by
countermeasures. These initiatives promote the integration of autonomous vehicles, enhance traffic control, and
make the vehicle-to-intellect ecosystem safer. This initiative emphasises how important cryptographic
techniques—more specifically, MD5 in particular—are to improving the data integrity of vehicle- to-vehicle (V2I)
communication and advancing contemporary transportation systems. To sum up, using cryptographic meth-
ods—particularly the MD5 hashing algorithm—is essential to im- proving data integrity in vehicle-to-vehicle (V2I)
communication. This project aims to solve the critical requirement for reliable and secure communication routes
between infrastructure elements and automobiles. The project’s ultimate goal is to improve traffic management and
road safety within the framework of contemporary transportation systems, all the while advancing the development
and deployment of autonomous vehicles.
Keywords: Connected Vehicles, Intelligent transportation, Privacy, Road Side Unit, Security, Vehicular Units, V2I.
Paper ID - 0017

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 2

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Agritool -A Farm Log Rental Service Platform with Crop Management

Pathmanaban J, Sangeetha, Prabahar Godwin James T, Sibisurya S, Sakthi Arunachalam S and
Abiram R
In recent times, a significant number of individuals have opted for a career in agriculture. However, newcomers often
face challenges due to their limited knowledge of key agricultural aspects such as farming practices, soil types, and
climate variations. To facilitate the exchange of information and knowledge between novice and experienced farmers,
the need for a platform becomes evident. Agritool, a mobile application, emerges as a comprehensive solution for crop
cultivation and management. It serves as a valuable resource, offering guidance on crop production, and the integration
of smart farming techniques. Furthermore, it provides various allied services. Beyond its role as an information hub,
Agritool also functions as an idle vehicle rental, online marketplace, uniting farmers, agricultural input suppliers,
retailers, and fulfillment services on a common digital platform.
Keywords: agriculture, crop guidance, vehicle rent, mobile application, information hub.
Paper ID - 0042

Optimizing Crop Yield And Profitability With An Fpga Enabled Smart Irrigation
System For Agriculture
Vivekanandan M, Saranya G, Kumaran K and Vidhyalakshmi M
This study employs embedded technology to improve the productivity and quality of multi-crop agriculture. The
system gradually constructs logic, connects nodes, iterates through feedback, and executes embedded processing
while integrating irrigation engineering. Real-time input and output devices known as filaments, along with FPGA
technology facilitating dynamic partial self-reconfiguration, play pivotal roles. Independent experiments are conducted
for each crop to determine optimal strategies for maximizing both quantity and quality of yield. Fuzzy logic algorithms
are utilized to address uncertainties inherent in agricultural systems. Additionally, the Random Forest algorithm
is employed to predict soil moisture levels, aiding in the optimal timing and amount of irrigation across different
field areas. An FPGA-based autonomous watering system, employing solenoid switches for water flow control, is
implemented. Furthermore, a real-time integrated multi-data processing system monitors soil moisture, temperature,
humidity, and water levels to enhance crop output. The benefits of this approach include increased multi-crop yield
per unit area and reduced operation and maintenance costs. The prototype system facilitates central management,
statistics, and monitoring, thereby fostering economic growth in rural areas. Future dissemination of field traits to
farmers through education and rural networks is envisioned, with potential scalability to district and state levels.
Keywords: Agriculture, Multi Crops, FPGA, RFTransmitter, Actuator, Sensor, Irrigation, Solenoid Valve, Fuzzy
Logic, Random Forest.
Paper ID - 0045

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 3

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Air Quality Index Prediction using GCN + LSTM Model

R. Kingsy Grace, Karthik J and Pranav J
Innovative solutions are needed to limit the pollution on ecosystems and the human health, since it continues to be a
key global concern. The creation of a sophisticated predictive analytics model for predicting air quality in urban
settings, especially in smart cities, is the main goal of this research. The intricate dynamics of urban air pollution
are difficult for traditional forecasting techniques to fully capture, underscoring the need for more advanced
techniques. This project addresses this challenge by proposing a system that uses Graph Convolutional Networks
(GCN) and Long Short-Term Memory (LSTM) models. The GCN component captures spatial relationships between
monitoring stations, leveraging the underlying graph structure of the urban environment. In parallel, the LSTM
model captures temporal dynamics in air pollution data, enabling accurate forecasting based on historical
observations. The proposed system architecture encompasses data collection, preprocessing, feature engineering, and
model training stages. It constructs a graph representation of the urban environment, incorporates spatial and
temporal dependencies, and optimizes model performance through hyperparameter tuning. Real-time prediction and
monitoring capabilities empower stakeholders to make informed decisions and implement timely interventions to
manage air pollution effectively. By combining cutting-edge techniques from data science, environmental science, and
urban planning, this project offers a comprehensive solution to the challenges of urban air pollution. Successful
implementation of this predictive analytics model has the potential to revolutionize environmental management
practices, improve public health outcomes.
Keywords: Air Pollution, Graph Convolution Network, Air Quality, Long-Short Term Memory, Pollutants.

Paper ID - 0048

Integrated AI-Driven Agricultural Automation for Precision Farming: A Smart

Approach to Pest Management and Irrigation Control
Dharshini S, Preetha Lakshmi, Joshna B S, Jayachandiran Udayakumar and Muthamilselvan S
Agriculture continues to be the backbone of the Indian economy but faces increasing challenges due to environmental
impacts and resource inefficiencies resulting from traditional practices. This paper presents an integrated,
intelligence-based agricultural automation system that aims to address these issues through precision farming and
provide smart solutions for pest control and water management. The system is equipped with an automatic sprayer,
image recognition system that can accurately detect weeds and pests, and an IoT-based smart irrigation system.
Leveraging advanced technologies such as robotics, machine learning, and IoT, the framework optimizes resource
utilization, increases crop yields, and minimizes ecological impact. Field trials have shown significant improvements
in pest control, water conservation, and yield increase, demonstrating the potential of our solutions to transform
permaculture in India. We also offer recommendations on distribution and strategies to solve adoption problems,
with the aim of providing farmers with tools to increase productivity and control the environment.
Keywords: Precision farming, Agricultural automation, AI in agriculture, Pest management, Smart irrigation,
IoT-based agriculture, Autonomous vehicles, Image recognition in farming, Sustainable agriculture, Crop yield
optimization, Environmental impact reduction, Machine learning in agriculture, Robotics in farming, Indian
agriculture, Resource-efficient farming.
Paper ID - 0054

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 4

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Side Channel Power attack Dataset Characterization for Secure Adiabatic Circuit
level VLSI Abstraction
V.Harynee, G.K.Bhuvanesh, Anjana Jyothi Banu and A.Prathiba
The primary objective of this paper is to compile a benchmark dataset of power traces to evaluate side channel power
attack analysis on Charge Balancing Symmetric Preresolve Adiabatic Logic (CBSPAL) named as, CBSPAL-Side
Channel Attack (CBSPAL-SCA). CBSPAL and its related secure adiabatic logic styles in literature has been popular
towards its resilience against the differential, correlation and other statistical attack approaches. This CBSPAL-SCA
dataset is collected through the circuit level VLSI implementation during the Round 1 execution of the PRESENT
Algorithm in CBSPAL. The inputs for the circuit-level design (plaintext and key) are generated using Python scripts,
producing fixed key and random plaintext pairs. We collected 20, 000 power traces for the fixed first key 1 and 30, 000
for the fixed second key 2, resulting in a total of 50, 000 power traces. The metadata information for different power
leakage modeling has been provided. The leakage power traces dataset will be highly useful for the research community
to perform side channel power attack analysis, the first one reportedly on the circuit level VLSI implementation.
Keywords: power traces, side-channel analysis, CBSPAL-SCA dataset, plaintext, key, circuit level

Paper ID - 0055

Revamping Ola Bike Services with Advanced Demand Forecasting via Machine
Learning
Jayadharshini P, Dinesh Subramani, S.Santhiya, Sudharshan.S, Sudheksha.K and Rithanya.M
The market share and importance of ride-hailing or transportation companies (TNCs) such as Uber, Lyft, and Ola
continue to grow in many transportation markets. Big data and algorithms should be used to analyze the large
amounts of data available to improve service reliability, measure the effectiveness of these systems, and help users
meet their desired needs. In this study, a new model has been developed using data from Ola, a ride-hailing service
based in Bengaluru, to predict the gap between passenger demand and driver demand for specific times and specific
areas. The data used in this study is the application form. This information will include the following items: trip
booking time, pickup location, and latitude and longitude of the departure point. A set of data points associated with
a ride request are the customer ID, get on the latitude bus, get on the longitude bus, get off the latitude bus and get
off the longitude bus. On the mobile-based Ola app, passengers ’request’ (request) a ride by entering their departure
and arrival points and clicking on the ’Request Pickup’ button. The driver responds to the request by placing an
order. Although the training system is small compared to the entire Ola ride-hailing industry, it is large enough to
find and expand the sample.
Keywords: Big Data, Ride-Hailing, K-means group, XG removal, Error Handling.
Paper ID - 0067

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 5

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Efficient Document Image Classification Using Deep Learning Enhance with CNN
Architectures
Jayadharshini P, P.Karunakaran, S.Santhiya, Harshini.M and Arunachalam.M
Document image classification has a significant difficulty for the retrieval of digital documents and systems management
in recent years. The main goal of this study is to investigate the classification of scanned document images into
distinct groups using deep learning techniques. The numerous quantity of information and unpredictability present
in the document images is too much for the traditional methods, which usually rely on the human feature extraction
and conventional machine learning algorithms. VGG16, GoogleNet, DenseNet, and other advanced networks use
convolutional neural networks (CNNs) to increase the accuracy and efficiency in document classification task. There
are many important uses for classifying document images in various domains. It looks after the document management
process by classifying a large amount of documents including emails, invoices, letters, and forms for efficient processing,
retrieval, and storage. The main task includes the challenges of training and validating datasets for the purpose of
classifying document images. Next, it is necessary to have a closer look at CNN design, with a particular emphasis
on CNNs’ ability to learn hierarchical feature representations. Furthermore, CNN have the better efficiency in the
feature extraction and transfer learning capabilities, and mostly pre-trained CNN models like VGG16, GoogleNet,
and DenseNet have been used very often in document image classification. Different visual data contains generalized
feature representations so that it could be advantageous for document classification models and also pre-trained models
that were trained on large-scale datasets such as ImageNet were utilized.
Keywords: Convolutional Neural Networks, VGG16, DenseNet, GoogleNet, Document Classification.

Paper ID - 0068

Medicinal Plant Identification Using CNN And Pytorch Lightning

Thilagam.T, Anees Fathima M, Varsha V, Janani P, Priyadarshini A and Sariga B
Medicinal plants have long been integral to healthcare, providing natural therapeutic compounds. With the growing
interest in alternative medicine, accurate identification of these plants is crucial. Traditional identification methods
depend on expert botanists and manual examination, which are time-consuming and prone to errors. This paper
aims to develop a robust system for identifying medicinal plants using Convolutional Neural Networks (CNNs) and
the PyTorch Lightning framework. Our approach leverages deep learning to automate plant identification, addressing
the increasing demand for herbal medicine authentication. Using a dataset of annotated medicinal plant images,
we design a CNN architecture to extract features and accurately classify species. Transfer learning fine-tunes pre-
trained models to improve classification performance, even when training data is limited. The system is evaluated
using performance metrics like precision, recall, and F1-score. The goal is to create a reliable tool for botanists,
pharmacists, and herbal medicine practitioners, aiding in the authentication and preservation of traditional medicinal
knowledge. This automated identification system promises to enhance the accuracy and efficiency of medicinal plant
classification, supporting sustainable use and conservation efforts.
Keywords: Deep Learning, Image Processing, CNN.

Paper ID - 0070

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 6

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

DrowsiGuard: Machine Learning-Based Driver Drowsiness Detection System for

Enhanced Road Safety
S. Gunanandhini, T.Thilagam, G.Manisha, S.N.Ananthi and G. Belshia Jebamalar
Drivers need to stay focused on the road to respond quickly to unexpected situations. Fatigue is a significant factor
in many traffic accidents. Therefore, it’s important to have measures that can identify and alert drivers to their
deteriorating mental and physical state, potentially reducing fatigue-related incidents. This issue is becoming more
prevalent in modern times, leading to an increase in accidents. Various facial expressions and physical signs, like tired
eyes and yawning, are acknowledged as indicators of driver fatigue and drowsiness. Using vision-based techniques is
one of the technical solutions for creating driver drowsiness detection systems. We introduced a classifier for detecting
driver drowsiness using Convolutional Neural Networks (CNN). We conducted experiments using four different CNN
architectures: RESNET-34, Kinetics 400, CSPDarknet 53, and DenseNet, and discussed the results. The experimental
findings of these models in a driver drowsiness detection classifier represent a comprehensive approach to improving
road safety. Among the models tested, ResNet-34 showed superior accuracy and AUC-ROC, offering effective solutions
for preventing accidents related to drowsiness.
Keywords: Drowsiness detection, CNN, optical flow feature fusion.
Paper ID - 0072

A Review on the effectiveness of Deep Learning Algorithms for pedestrian detection

Arumai Shiney.S, Thilagam.T, Manisha.G and Ananthi S N
Deep learning approaches have improved pedestrian identification by employing neural networks to routinely study and
excerpt features from complex visual data. The application of convolutional neural networks (CNNs) and recurrent
neural networks (RNNs) has shown promising results in improving the precision of pedestrian detection systems. These
developments improve traffic safety to make a substantial contribution to the creation of effective monitoring systems.
Pedestrian detection technology is a useful tool that smart city infrastructure can use to optimize pedestrian flow,
manage traffic, and increase public safety. Future pedestrian detection researchers will find great value in having a
thorough understanding of the methodologies used in earlier studies. Researchers can further develop and create deep
learning models by expanding upon the foundations set by previous studies. This work will help to further improve
autonomous vehicles, intelligent transportation systems, and the general growth of smart cities.
Keywords: CNN, RNN, pedestrian detection, Deep Learning.
Paper ID - 0073

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 7

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Automated Vision-Based System for Comprehensive and Real-Time Detection and

Classification of Fruit Surface Damages
Dr. K Vijayalakshm, Nitin Darapareddy and D.Anish Chandra
Food security and the support of the world’s expanding population depend heavily on the global agriculture sector.
Reducing food waste and raising crop productivity are crucial as the market for agricultural products rises. The
creation of effective techniques for evaluating fruit quality and identifying damage is essential in this situation. In
order to overcome these obstacles, this work investigates the creative application of the YOLO (You Only Look Once)
object identification technique. It helps by recognizing and separating spoiled or diseased product, it guarantees the
high quality of fruits being transported. In order to satisfy the demanding requirements of global markets, reduce
the possibility of rejections, and prevent expensive financial losses brought on by shipments of inferior quality, quality
assurance is essential. We take high-resolution pictures of fruit samples, both whole and with damage, as part of our
methodology. A YOLO-based deep neural network is then trained using those images labeled with bounding boxes.
Through transfer learning, the YOLO model is adjusted to fruit-specific damage detection. Growers and quality
controllers may act promptly and intelligently since the trained model can locate and identify fruit damage with
amazing accuracy. There are various benefits to this creative strategy. Fruit inspection by hand is a labor-intensive
operation that is greatly reduced by it, increasing efficiency and saving money. It helps to decrease food waste and raise
the general standard of agricultural produce by automating the identification of damaged fruits. Furthermore, YOLO’s
real-time feature guarantees. Fruits inspection for quality has traditionally been primarily done by hand, using human
inspectors to distinguish rotten or sick fruits from healthy ones. This process takes a long time, requires a lot of
labor, and is prone to human mistake. It is also impractical for large-scale operations. Through the implementation
of market-specific quality standards and regulatory compliance, YOLO technology facilitates exporters’ entry into
competitive markets and establishes a durable presence in the global export arena. The advantages are numerous and
include market distinctiveness, liability reduction, and improvement of brand reputation. This abstract emphasizes
how crucial YOLO-based fruit damage detection is to transforming the export sector, solving major issues with quality
control, and escalating global trade. Through the implementation of market-specific quality standards and regulatory
compliance, YOLO technology facilitates exporters’ entry into competitive markets and establishes a durable presence
in the global export arena. The advantages are numerous and include market distinctiveness, liability reduction, and
improvement of brand reputation. This abstract emphasizes how crucial YOLO-based fruit damage detection is to
transforming the export sector, solving major issues with quality control, and increasing global trade.
Keywords: Yolo(you only look at once), bounding boxes, transfer learning.
Paper ID - 0095

Predicting Fit Sizes in E-Commerce using Machine Learning

Beulah N, Dr.D.Umanandhini Udhayakumar, Shyamaladevi M., Geetha Jenifel M and Jangili
Supriya
Accurate size and fit recommendations are critical for E-commerce platform in Fashion Designing Industry. Most of
the customers are not satisfied with final stitched materials, most of the time, it is not matched with their expectations.
Meanwhile tailors also struggling to grasp customer requirements in correct manner. To satisfy customer needs, this
concept is analyzing personalized size and fit recommendations that deal with difficulties of any fashion e-commerce
platform. Customer preferences can be considered by using traditional collaborative filtering algorithms based on
previous orders. These above challenges can be controlled by using the Random Forest Model system based on
collaborative methodology for personalized size and fit recommendation. The methodology employs a Random Forest
model for training and testing, and provides the prediction of clothing fits based on user information. For Future
development we can utilize machine learning techniques, able to generate personalized clothing recommendations
which benefits user satisfaction and engagement. The integration of user measurements, sentiment analysis, and
predictive modeling shows an advanced system can deliver tailored recommendations, and increments the area of the
immersive fashion e-commerce environment. This paper explores the use of Machine Learning techniques, specifically
Random Forest models, to predict customer’s fit sizes and enhances shopping experience in the Fashion Industry. The
method uses user data, measurements, and purchase behavior to predict the best clothing sizes of particular clients.
The technology reduces return rates and increases customer satisfaction. The study emphasizes the importance of
sentiment analysis and user input for continuous improvement.
Keywords: Personalized Fashion E-Commerce, Traditional Collaborative filtering, Random Forest model, Clothing
Recommendation, Tailored Recommendations.
Paper ID - 0098

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 8

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

An Efficient AI Based Ensemble Model for Human Detection and Rescue During
Disaster using UAV
Konijeti Sai Kalyan, Maddu Rakesh, Nukala Rohith and B. Yamini
Disaster management is important for saving people’s lives. It helps to save lives and respond in crucial times during
disasters. This paper presents a UAV system for enhancing disaster search and rescue operations. Utilizing an
Ensembled HOG Human Detection System-based computer vision, the system detects humans in real-time video
streams and estimates their distance from the UAV. This approach improves situational awareness for rescue teams,
addressing challenges like varying lighting and occlusions. The system demonstrates high accuracy in complex
scenarios, potentially expediting victim localization and improving survival rates. Future work will focus on
performance enhancement in diverse environments and integration with other disaster response technologies.
Keywords: UAV, Computer Vision, Human Detection, Distance Estimation, Disaster Response.
Paper ID - 0110

Maximizing Mango Yields: Disease Prediction, Grade Classification, and Production

Management through EfficientNet Models and PHP-MySQL Integration
B.Yamini, Dr.G.Premalatha, Konijeti Sai Kalyan, Maddu Rakesh, Nukala Rohith and Jino Paulraj
Mangoes are crucial to the fruit industry, and their health is essential. This research introduces an advanced but
user-friendly system for identifying and categorizing mango leaf diseases. The system leverages image processing
and machine learning, using the powerful EfficientNet B0 algorithm. It accurately detects diseases and provides
tailored treatment recommendations and possible causes, enabling proactive disease management. Additionally, it
assists farmers with breed recognition, customer support, and inventory management, empowering them for improved
agricultural practices.
Keywords: Image Processing, Artificial Intelligence, Deep Learning, Agriculture, Sustainable solution, Efficient Net
B0, Efficient Net B2, Data Augmentation, Database Management System.
Paper ID - 0112

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 9

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Machine Learning-based Classification for Sentimental Analysis of IMDb Reviews

Santhiya S, Lalitha Krishnasamy, Rakoth Kandan Sambandam, Jayadharshini P, Dharshan P P
and Haripreetha S
Filmmakers and audiences both need to understand how the public feels about movies in the age of digital media,
which is ruled by sites like IMDb. Given the volume of information available on IMDb, research into how machine
learning algorithms can consistently classify movie reviews as positive or negative attitudes is required. This study
aims to measure the way various machine learning algorithms perform when sentiment analysis of IMDb movie reviews
is performed to gain knowledge about the preferences and responses of the audience. An IMDb movie review dataset
was subjected to a range of machine learning techniques, such as k-nearest neighbors (KNN), Naive Bayes, logistic
regression, random forest, and decision trees. The dataset was used to train and test each algorithm’s ability to
categorize views as positive or negative. Among the methods under study, logistic regression achieved the highest
accuracy at 88.5%, closely followed by Naive Bayes at 85%. Compared to random forests, which achieved an accuracy
of 85.2%, decision trees performed relatively well, with an accuracy of 74.5%. However, KNN only demonstrated
mediocre effectiveness, with an accuracy of roughly 75.5%. These results show how effectively sentiment analysis of
IMDb movie reviews using logistic regression performs. The findings demonstrate how important sentiment analysis
is to understanding user opinions about movies on websites such as IMDb. Filmmakers and industry observers can
employ machine learning techniques, particularly logistic regression, to gain insightful information about the emotions
and preferences of their audience.
Keywords: Sentimental analysis, Movie reviews, Classification, Algorithm evaluation, text mining, positive sentiment,
data preprocessing, Feature selection.

Paper ID - 0116

Comprehensive Drowsiness Detection System Using OpenCV, Machine Learning, and

Heart Rate Monitoring
Shruthik Kalyana Venkatesh, Sharmishtha S.K, Gogul Ram S and Dr.B.Yamini
The face, an essential part of the body, communicates a vast array of information. When a driver is fatigued, their
facial expressions, along with the frequency of blinking and yawning, change notably compared to a normal state. This
project focuses on creating a system that identifies a driver’s fatigue indicators—such as yawning, blinking, and eye
closure duration—using video footage, without relying on wearable devices. We introduce a computer vision-based
method to detect driver drowsiness from a camera-recorded video. Our technique involves identifying the face and
detecting the eyes in each video frame. We have developed a unique detection method for facial regions using 68 key
points. These facial regions help evaluate the driver’s state. By examining the characteristics of the eyes and mouth,
we can issue a fatigue alert to the driver via an alarm sound. Moreover, once the fatigue continues, the self-driving
mode will be activated, and the system will detect the lane to ensure that the car moves in the correct lane. Integrate
a heart rate sensor to continuously monitor the driver’s heart rate. If an irregular heart rate is detected, alerts will
be sent to nearby hospitals. This system has the potential to greatly decrease the risk of accidents caused by drowsy
driving, a leading factor in traffic incidents globally.
Keywords: Drowsiness Detection, Driver Fatigue, Computer Vision, Machine Learning, OpenCV, Facial Recognition,
Eye Tracking, Yawning Detection.
Paper ID - 0119

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 10

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Applications of Wireless Sensor Networks in the Healthcare Sector

L. A. Anto Gracious, Ganeshan R, T Periyasamy, R. Abirami, R. Kennady and A.Prabha
WSNs are technology with a high potential that has different application cases in healthcare. They are the
communication channels that allow sensor nodes to exchange data wirelessly in real-time while at the same time, as
a network, offering a lot of opportunities for remote monitoring, data collection and analysis in healthcare settings.
This paper hereby presents the full examination of the utilization of WSNs in the medical field, demonstrating how
the technology can quantitatively upgrade patient monitoring, disease management, and healthcare. The review is
designed to detail several categories of WSNs used in healthcare facilities, such as the Body Area Networks (BANs),
Ambient Assisted Living (AAL) system and the environmental monitoring network. We explain our focus areas
involving WSNs namely, remote patient monitoring, fall detection, chronic disease management, medication
adherence monitoring and healthcare facility management. Moreover, we provide details on the difficulties and
limitations facing WSNs in healthcare such as security challenges, interoperability difficulty, and power consumption
constraints. In the following part, the integration with Internet of Things platforms and the subsequent use of
machine learning and artificial intelligence techniques, and the development of miniature sensors and wearable
technology will be discussed in more detail as the key future directions of healthcare WSNs. Finally, we underline
the need for uniformity requirements as one of the leverage points to increase the interoperability and scalability of
healthcare WSN implementations. The integration of current literature on the topic and technological advances shall
herein offer perspectives on the WSNs applicability in remaking the healthcare delivery system and the prospects to
further these patient outcomes. The evidence advises that innovation keeping the collaborative efforts should be
viewed as a priority while exploiting WSNs with a motive of improving healthcare sector services delivery.
Keywords: Wireless Sensor Networks, Body Area Networks, Healthcare.
Paper ID - 0123

Proactive Disease Detection : A Web-Based Application

Robert Emmanuel S, Ravivarman R, Gaurav Singh, Jaya Kumar Sa and Hemanand D
Chronic diseases like diabetes, heart disease, and Parkinson’s disease pose significant healthcare burdens globally.
Early detection improves patient outcomes and allows for preventive measures. This paper proposes a user-friendly
web application that leverages machine learning algorithms to predict the risk of developing these three prevalent
conditions. The application employs various machine learning models trained on relevant datasets containing labeled
patient information (details on specific models and datasets provided later). Users can conveniently input their health
data through a secure interface. The system then predicts the likelihood of developing each disease, empowering
individuals to take a proactive approach to their health by seeking preventive measures or further medical evaluation.
Keywords: Machine learning, Multi-disease prediction, Early detection, Preventive healthcare, Diabetes prediction,
Heart disease prediction, Parkinson’s disease prediction, Web application
Paper ID - 0125

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 11

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Quantum Machine Learning Algorithms for Traffic Management in Big Cities

Dr. D. Hemanand, Dr.M.Anuradha, Lakshmipriya C and Revathi V
This research paper proposes a novel approach to traffic management optimization using a hybrid quantum-inspired
machine learning method. We introduce a Hybrid Quantum and Bayesian Algorithm to compute Eigen values,
facilitating the extraction of crucial traffic network characteristics. Through the utilization of AWS Hyperparameter
Tuning SageMaker models, our technique comprises the following steps: data preparation, feature engineering, model
training, evaluation, deployment, and monitoring. By integrating SigOpt with AWS, we enhance model hyper
parameter optimization, significantly improving efficiency and accuracy. We discuss the relevance of our work to
current traffic management challenges, including scalability, expertise, and integration complexities. Our research
demonstrates the potential of machine learning that is inspired by quantum mechanics to revolutionize traffic control
systems for huge cities. The integration of quantum computing in intelligent traffic management systems aims to
address congestion and pollution issues. Quantum algorithms offer efficient solutions for traffic optimization, signal
timing, and flow prediction. Challenges include specialized hardware and expertise requirements. Future research
focuses on developing more effective algorithms and addressing quantum error correction. The potential benefits
include reduced congestion, fuel consumption, and air pollution. The field shows promise but requires further
advancements to fully leverage quantum computing capabilities in traffic management.
Keywords: Intelligent traffic management, Air pollution, Quantum Computing.
Paper ID - 0128

Enhancing Online Payment Security: A Machine Learning Approach to Fraud

Detection

Kumar P, Vijayaraj A, Senthil Pandi. S and Venkatesh Prabhu Balakrishnan The rising gamble of monetary
extortion has attracted consideration a period where remote correspondences are fundamental for communicating
gigantic measures of information while giving impedance avoidance. The RXT model is a cutting-edge man-made
brainpower arrangement planned explicitly for the examination of ongoing monetary exchange information. The
Gated Repetitive Unit (GRU) in ResNeXt is implicit. The need to battle the developing danger of monetary
misrepresentation, which presents huge dangers to both monetary establishments and their clients, propels our
coordinated way to deal with man-made consciousness procedures. After we start our computer-based intelligence
information admission and pre-handling activity, we utilize the Destroyed procedure to resolve the issue of
information unevenness. We join auto-encoders and ResNet utilizing a group strategy known as Procure. This
approach distinguishes huge examples in the information through highlight extraction. By employing additional
feature engineering techniques, we also enhance the model’s discrimination capability. The RXT-J model that serves
as the foundation for our artificial intelligence classification challenge was refined using the Jaya method. Careful
examination on three genuine monetary exchange datasets exhibits that our computer-based intelligence model
regularly beats cutting edge calculations overwhelmingly of 10% to 18% across various appraisal measures while
keeping up with great computational proficiency. In the ongoing fight against financial crime, this groundbreaking
study on artificial intelligence is a significant advancement. It makes financial transactions more secure and efficient.
We make our artificial intelligence projects with further developed security, expanded information availability,
reliability, and steadiness as a main priority. The financial sector is less vulnerable to cyberwarfare as a result.
Keywords: Financial Fraud, Interference prevention, ResNeXt, ResNet, SMOTE.
Paper ID - 0136

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 12

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Wireless Surveillance Robotic Car for Crop Disease Detection

Chettiyar Vani Vivekanand, Dr. Inbamalar T M, Harish R, Masthan Gowtham Kommuru and
Ganesh Perim
This project addresses the challenges of manual crop disease monitoring by introducing a smart robot system. Using
advanced image processing and Convolution Neural Network (CNN), the system swiftly identifies diseases to aid
farmers in efficient management. The robot, designed for large fields, employs real-time data processing and path
finding algorithms for optimal coverage. Key technologies include precise GPS navigation and SLAM for virtual
mapping, guiding the robot strategically. Equipped with sensors for disease identification, the project emphasizes
user-friendly design, displaying affected areas on a digital map. Beyond disease detection, the initiative promotes
sustainability by reducing pesticide usage, optimizing crop man agement, and enhancing productivity. Through the
integration of robotics, AI, and data analytics, the project envisions advancing crop health and fostering sustainable
farming practices. The step-by-step process involves GPS field selection after creating a virtual map using the LIDAR-
SLAM algorithm, ensuring precise navigation, disease detection, mapping, and effective communication. Driven by
personal experience, technology, and a forward-looking vision, the project aims to create a resilient, productive, and
sustainable agricultural landscape, leveraging GPS and LIDAR-SLAM for efficient disease monitoring.
Keywords: Autonomous robot, Crop disease detection, Image processing, Convolution Neural Network (CNN),
Early disease detection, Mitigation strategies, Pathfinding algorithms, Global Positioning System (GPS), LIDAR-
SLAM algorithms, Precision agriculture, Agricultural technology, Real-time data acquisition, Sustainability, Pesticide
reduction, Crop management optimization, User-centric design, Digital map, Native language outputs, Remedies for
crop diseases, Resilient agriculture.

Paper ID - 0138

Centralized Service Management Across Hybrid Environments: Harnessing Zookeeper

with Cloud Computing
P. Kumar, Duraimurugan N and Ananthajothi K
Traditional service management approaches based on manual processes, ad-hoc tools, and human intervention are
plagued by inefficiencies, error-proneness, and system downtime. As businesses transition complex on-premises
applications with outdated codebases and monolithic architectures to the cloud, they face additional challenges,
including lack of centralized management, error-prone manual interventions, absence of real-time performance
insights, and extensive training requirements across diverse tools. The proposed ”Centralized Service Management
Across Hybrid Environments: Harnessing Zookeeper and Cloud Technology” solution offers a centralized,
user-friendly tool for seamless orchestration and monitoring of operations across on-premises and cloud
environments. By leveraging Apache Zookeeper for coordination, it ensures efficient execution of operations, with
preinstalled Agents handling tasks on individual nodes. This approach enhances administrative control, prioritizes
security through granular user permissions, and provides real-time tracking via detailed logs. Integrating cloud
technology simplifies managing and monitoring hybrid environments, leveraging scalability, flexibility, and enhanced
performance insights. The solution streamlines operations during cloud migration while supporting regulatory
compliance. Utilizing Zookeeper as a centralized coordination service ensures synchronized and consistent distributed
services across the network. By combining Zookeeper’s distributed architecture with cloud integration, the system
scales seamlessly, dynamically allocating resources based on demand and optimizing performance for geographically
dispersed services. This comprehensive solution mitigates the limitations of traditional approaches by combining the
benefits of Apache Zookeeper, cloud technology, and centralized management. It enables businesses to maximize
performance, efficiency, and regulatory compliance when managing hybrid and distributed services in dynamic
environments.
Keywords: Monitoring, Coordination, Apache Zookeeper, Cloud, Distributed Service.
Paper ID - 0140

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 13

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Revolutionizing CPR Training: An Arduino-Powered Automated Resuscitation Model

Dr.T.S.Geetha, Nivethitha. M, Swetha. N, Eswar Prasad. G, Naveen Raj. A and Deepan. P
This research article details the creation of an Arduino-based CPR model to deliver effective and timely CPR
therapy during medical crises. The developed automated CPR model monitors the patient39;s ventilation and pulse
while controlling the patient39;s breathing methods and chest compressions using an Arduino microcontroller board.
The design ideas and techniques of hardware configuration, Arduino code, integration, testing, safety issues, user
interface design, documentation, deployment, and maintenance are all included in the CPR model. By methodically
merging hardware, software, and sensors, the CPR model provides standard CPR techniques that are dependable,
versatile, and dependable. Because creating a safe environment for patients and users is crucial, the system is
designed with several safety mechanism components that guard against harm to both parties. Applications for
medical devices often adhere to specific guidelines and criteria. To engage the user and provide feedback, the CPR
training tool or simulation should also have an intuitive user interface. In training hospitals, medical facilities, and
educational institutions, the system offers a cost-effective and useful CPR solution. The automated CPR model that
administers conventional CPR therapy in emergency medical situations is a useful tool for teaching CPR trainees,
enhancing their emergency response skills and potentially saving many lives in life-threatening situations. More
research and development may be done on potential system enhancements such adaptive feedback, real-time data
streams, or interface with existing medical equipment.
Keywords: Arduino-based CPR model; Automated CPR; Medical emergencies; CPR training device; Chest
compressions; Breathing techniques; Patient pulse monitoring.

Paper ID - 0147

Multimodal Anomaly Detection and Probabilistic Risk Prognostication for IT

infrastructure: A hyperparameter tuned Random Forest regressor a Probabilistic
Regression Model
Mr.M.Balasubramanian, Abirami.J, Betsey Neela Raju and Harini.P
In this technological era, it has been a hurdle for organizations to maintain their assets and when it is called asset,
it ranges from physical to logical assets. Apart from assets, it is also an uphill climb to track the risk arising from
those assets. It has always been a milestone for IT organizations to maintain as well as predict risks associated with
their organization to be a proactive level of management. But it has been a discretion between asset management
and risk identification. The motive of this project is to incorporate both the tasks in a single shot and the main goal
of the project is to deliver an intelligent IT asset and risk management system that uses machine learning technology
to predict and assess risk associated with IT assets. The system incorporates a comprehensive neural network and
regression model, which has high precision rate to analyze the dataset while the traditional application uses linear and
classification model which analyses the data in inefficient way and it is prone to overfitting and underfitting. The main
elements of the system include the web interface for user’s asset data entry, data storage history and machine learning
models for asset management testing and further sustenance. Users can easily upload asset data in CSV or Excel
format, making integration with existing asset management systems easy. The significance of this project is that it
changes the entire IT asset management process by introducing risk. By identifying and addressing risks before they
escalate, organizations can reduce the impact of security incidents, improve resource allocation, and improve their
overall resilient IT infrastructure.
Keywords: Machine learning Neural network Regression model Risk management IT management.
Paper ID - 0151

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 14

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Revised Kuhn-Munkres Algorithm for Dynamic Job Allocation using Dummy Decider
Technique
Sridevi Sridhar and Thilagavathi Narayanamoorthy
Generally, static job arrivals are assigned to resources by using the classical Kuhn-Munkres (KM) algorithm. However,
in many real-world scenarios, job arrivals are dynamic, leading to changes in the number of nodes. This leads to
dynamic node numbers in the left partition of the bipartite graph over time. Consequently, for such unbalanced
dynamic workload-based problems, the initial assignment becomes invalid. This paper tackles the issue of dynamic
job arrivals and proposes a revised assignment algorithm. It models both partial and complete reassignments in
response to dynamic job arrivals. Numerical results demonstrate effective assignments for unbalanced problems with
dynamic workload arrivals.
Keywords: Assignment problem, Kuhn-Munkres algorithm, Hungarian algorithm, bi-partite graph matching.
Paper ID - 0152

Infinite Environment to Sustainable Tamil NLP

Krishnan R and Murugan A
The Tamil language, with its rich literary heritage and unique linguistic characteristics, presents extensive opportunities
for Natural Language Processing (NLP) research. However, the field of Tamil NLP remains largely non-standardized,
resulting in a fragmented landscape of models and techniques. This paper addresses these challenges by offering
a comprehensive analysis of the current Tamil NLP environment. It examines digital font variations, transcription
methods, and the distinctions between prose and poetry, as well as the morphological intricacies of Tamil grammar
and phonetics. By evaluating these aspects, the paper aims to identify suitable adaptations of NLP techniques to
enhance the efficacy and sustainability of Tamil NLP models. The goal is to propose a unified and coherent framework
that supports sustainable development in Tamil NLP, contributing to robust, interoperable, and sustainable models.
Keywords: Tamil NLP, non-standardized NLP, linguistic characteristics, computational linguistics, Tamil grammar,
phonetics, digital font variations, transcription methods, prose and poetry, NLP sustainability, interoperable models.

Paper ID - 0156

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 15

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Prioritising Hospital Admission According to Emergency using Machine Learning

Pandiaraj A, Lakshmanaprakash S, Angayarkanni Veeraputhiran, Ramshankar N, Kamalakannan
R and Vinnie Sharma
The use of artificial intelligence and machine learning in emergency medicine is expanding swiftly. This paper evaluates
studies in the domain, organizing them into three groups: disease prediction and detection, hospital admission,
discharge, and mortality prediction, and machine learning-driven triage systems. The first group includes studies
employing machine learning algorithms with techniques like Logistic Regression, Naive Bayes, Random Forest, MLP,
SVC, LSTM, and data from electronic health records and medical imaging. The second group aims to predict hospital
admission, discharge, and mortality through machine learning, utilizing datasets such as electronic health records, lab
data, and vital signs, with decision trees, random forests, and logistic regression as common algorithms. The third
group discusses creating machine learning-based triage systems in emergency departments, using datasets like vital
signs and medical history, and techniques including decision trees, neural networks, and fuzzy logic. The reviewed
studies highlight the promise of AI and machine learning in emergency medicine, noting that algorithmic accuracy and
efficacy hinge on data quality and volume. Continued research is essential to corroborate these results and enhance
algorithm performance in real-world settings.
Keywords: Logistic Regression, Naive Bias, Random Forest, MLP, SVC, LSTM.
Paper ID - 0169

Identification of Different Medicinal Plants Through Image Processing

Dr. J. Anvar Shathik, S. Hashini, A.Pandiaraj, N.Ramshankar, Naveen G and Amirthavarshini K B
Identification of medicinal plants and raw materials is crucial for various applications including pharmaceuticals,
herbal remedies, and conservation efforts. Conventional methods of recognition often rely on expert intelligence and
instructions investigation which container be time-timewasting and lying to oversights. In this study, we propose a
novel approach for automating the identification process using image processing and machine learning algorithms.
Specifically, we leverage advanced techniques such as deep learning with ResNet-50, and Random Forest algorithms
to accurately classify images of medicinal plants and raw materials. Additionally, we integrate a leaf disease detection
system using Keras to further enhance the functionality of the platform. The developed system includes a user-friendly
website with features such as a blog page for sharing information and seamless integration of the image processing
algorithms using the Django framework. Investigational results display the efficacy of the anticipated method in
precisely discovering medicinal plants and raw materials, paving the way for applications in various domains.
Keywords: Machine learning algorithms, Deep learning, ResNet-50, Random Forest, Keras, Leaf disease detection,
Django integration, Plant identification system.
Paper ID - 0170

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 16

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Enhancing Traceability and Transparency in Agriculture: Blockchain-Based Tagging of

Farm Produce
G Manisha, T.Thilagam, Ananthi.S.N and S.Gunanandhini
Today’s challenges for the farmers who produce our fruits and vegetables are numerous. Physical work is required
in the agriculture industry for a number of reasons. The fact that without the actual presence of farmers at the
agricultural farm, evaluation of the field’s soil moisture level and many other factors is quite difficult. Applications of
blockchain technology in agriculture that we promoted are gaining popularity. Peer-to-peer networks with intelligence
are in high demand, therefore smart agriculture has addressed the use of block chain-based Internet of Things (IOT)
systems to encrypt, monitor, and analyze agricultural data. Agricultural data may be transmitted in a way that is
more unchangeable, transparent, and decentralized with the use of block chain technology. As a result, we are able to
offer a comprehensive picture of agricultural cultivation, farmers get significant relaxation, and crop development is
unaffected by these circumstances.
Keywords: Blockchain Architecture, IoT, Farm Products, Supply Chain.
Paper ID - 0175

Enhancement of Hugging Face Transformers for Synthetic Media Verification

Vignesh H, Vignesh P, Nandhakumar K P and Dr.Anuradha M
This abstract presents a presentation scheme to prepare the hugging face transformer for synthetic media verification
and emphasizes the training aspect necessary to increase accuracy. With the widespread threat of deepfake
propagation, this research seeks to optimize the training methods, model architecture and improve the efficiency of
hugging face transformers by carefully managing datasets and providing moving training methods faces such as
opponent training and self-supervised learning hugging is included to enhance the discriminative capability of the
phase transformer. Furthermore, research engages in elaborate refinement methods to adapt artificial media to
subtle pre-trained models, thus increasing their accuracy and generalizability are increased Improvements suggested
through rigorous testing and evaluation show significant improvements in strengthening hugging face transformers
for robust synthetic media verification change is helpful in the process.
Keywords: Deepfake, Datasets, Media Verification.
Paper ID - 0176

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 17

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Carbon Storage and Sequestration Potential of Aboveground Biomass of Neem Trees

in Southern Regions of Chennai
Mrs Arumai shiney, Ms. Keerthana S, Ms. Harini A and Mr. JONAH S
Urban areas are increasingly facing challenges due to climate change and environmental degradation. This necessitates
the exploration of nature-based solutions to address these issues. The study focuses on investigating the carbon storage
and sequestration potential of neem trees in the southern regions of Chennai, India. Neem trees are commonly found
in urban landscapes due to their resilience, adaptability, and ecological benefits. By conducting field assessments
and analysis, we were able to quantify the carbon content of neem tree biomass and evaluate its role in reducing
atmospheric carbon dioxide levels. Our methodology included measuring tree dimensions, such as diameter at breast
height (DBH) and height, and analyzing tree components like branches, leaves, and trunk wood for carbon content.
We used established allometric equations to estimate biomass and carbon stocks. Initial findings indicate that neem
tree biomass has a significant carbon storage capacity, especially in mature trees with substantial carbon sequestration
potential. The aboveground biomass of neem trees plays a crucial role in urban carbon stocks, emphasizing the
importance of these trees in climate change mitigation efforts. Moreover, our study delves into factors that influence
carbon storage in neem trees, such as age, health, and environmental conditions. We also discuss the implications
of urban forestry practices, such as tree planting programs and maintenance strategies, in maximizing the carbon
sequestration benefits from neem tree populations. This research provides valuable insights in to contribution of
neem trees to urban carbon dynamics and highlights their potential as a nature-based solution for climate change
mitigation in Chennai’s southern regions. By shedding light on the carbon sequestration potential of neem trees, this
study informs sustainable urban forestry strategies and policy interventions aimed at enhancing climate resilience and
environmental sustainability.
Keywords: diameter at breast height(DBH), bacteria, TBGP.
Paper ID - 0192

Machine Learning-Based Predictive Modeling for Cardiovascular Disease

Kiruthiga S, Kanishka A and Shri Vidhya K
Heart disease remains a major health challenge globally, prompting the need for effective prediction models to aid in
early diagnosis and treatment. This paper presents a study on predicting heart disease using machine learning,
specifically employing the Logistic Regression algorithm. Utilizing a dataset that includes a range of clinical and
demographic features, the Logistic Regression model was trained and evaluated. The model achieved an accuracy of
85.25%, demonstrating its capability to correctly classify patients at risk of heart disease. This result highlights the
potential of Logistic Regression as a reliable tool for heart disease prediction, offering a balance between simplicity
and performance. The findings suggest that Logistic Regression can be effectively used for early detection and risk
assessment in clinical settings, potentially improving patient outcomes through timely intervention.
Keywords: Heart Disease Prediction, Logistic Regression, Machine Learning, Classification Accuracy, Early
Detection.

Paper ID - 0202

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 18

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Analysis of Hybrid Encryption

Dr.ChitraDevi .D, Chandrasekar.K.V, Karthikeyan.J and Sribalaji.E
This paper introduces a new method for secure communication that combines the best aspects of two encryption
techniques. It does this by taking advantage of the strengths of both symmetric and asymmetric encryption, resulting in
a more secure and efficient system. Our method aims to address the challenges of key management and computational
overhead while ensuring robust protection of sensitive data. The proposed scheme begins with the generation of
a random symmetric key for each session, ensuring fast encryption and decryption processes. Subsequent to the
generation of a symmetric key for message encryption, the key itself is encrypted utilizing an asymmetric algorithm,
such as RSA. This two-step process facilitates secure key exchange between communicating parties. By leveraging
this hybrid approach, the overall encryption process maintains a high level of security while achieving efficiency in
message transmission. Furthermore, we introduce a dynamic key update mechanism to enhance the security of the
system. This mechanism periodically updates the symmetric key used for encryption, This approach mitigates the
potential for key compromise, thereby bolstering the overarching security posture of the communication channel.
To evaluate the performance of our optimal hybrid encryption scheme, we conduct comprehensive simulations and
comparisons with existing methods. The results demonstrate that our approach offers improved efficiency compared
to traditional asymmetric encryption techniques, without compromising on security. Additionally, the dynamic key
update mechanism proves to be effective in mitigating potential security vulnerabilities. In conclusion, this paper
presents an optimal hybrid encryption scheme that addresses the performance of the larger data and small amount of
data. The proposed approach offers a practical solution for chat system large data trade off, such as online transactions,
communication between IoT devices, and secure messaging platforms.
Keywords: Hybrid encryption, RSA, cipher text, decryption.
Paper ID - 0212

Recommendation System for NFT Platform

Dr. K A Varun Kumar, Gopika M Nair and M Pranita
The 21st century has witnessed the emergence of transformative technologies, with blockchain being one of the most
notable. A blockchain functions as a digital ledger composed of a growing list of records, known as blocks, which are
cryptographically linked to the preceding block. One specific application of blockchain is the creation of Non-Fungible
Tokens (NFTs), which are unique units of data (tokens) stored on the blockchain and cannot be interchanged with
other digital assets. NFTs verify ownership of digital assets such as music, artwork, video game components, and
recipes. NFTs have established themselves as a novel form of digital asset on public blockchains, distinguished by
their non-fungibility and uniqueness. Since early 2021, the NFT market has experienced rapid growth and increasing
mainstream adoption. This project introduces a platform for minting, storing, collecting, buying, selling, and resale
NFTs, with a strong focus on security. Recognizing the disruptive potential of NFTs in redefining asset ownership,
this platform aims to create a robust market environment. Key features include an automatic price detection system
and a recommendation algorithm designed to connect customers with the most relevant NFTs.
Keywords: NFT, Blockchain, Recommendations system, Deep Learning.

Paper ID - 0226

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 19

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Smart Ports: Utilizing AI-Driven Predictive Analytics and Simulation for Operational
Excellence
Balika J Chelliah, Sarghi Kaur Gahra, A.Senthilselvi and S.Senthil Pandi
Using artificial intelligence (AI) smart port management gives a revolutionary way to maximize port operations by
means of enhanced technological integration. Usually depending on conventional scheduling algorithms and
rudimentary analytics, current port management solutions result in poor resource use and operational inefficiencies.
These approaches provide higher turn-around times, congestion, and environmental damage as they lack the
adaptability and predictive powers needed to properly manage contemporary marine logistics. This study presents a
sophisticated approach that combines AI-driven predictive analytics with simulation modeling to tackle these
difficulties. The suggested methodology improves upon current methodologies by integrating real-time data inputs
from Iot sensors and machine learning algorithms to forecast operational disturbances and optimize scheduling. The
program specifically utilizes Random Forests and Neural Networks for predictive analytics. It leverages previous
maintenance records and sensor data to accurately predict equipment breakdowns and optimize port operations.
Simulation modeling is employed to generate a digital depiction of port operations, allowing for the assessment of
different management methods in various scenarios without the actual dangers associated with the real world. In
order to evaluate the efficacy of the proposed model, various performance indicators including prediction accuracy,
operational throughput, and cost savings are assessed. The study showcases that utilizing AI technology leads to a
substantial enhancement in predicted accuracy and operational efficiency when compared to conventional
approaches. This offers a strong alternative to reduce delays and improve the overall performance of ports.
Keywords: Smart Port Management, Artificial Intelligence (AI), Machine Learning (ML), Simulation modeling,
Operational efficiency, Predictive Modeling, IoT Sensors.
Paper ID - 0268

Tranqsoul – A Mental Health Assistance App

Jayanthi.M, Arumai Shiney.S,Adaikkammai.A, Selvakumaran.S,Poonguzhali.C and Rajavinu.N
This study presents a novel approach that combines supervised learning techniques for mental health analysis with
the integration of an AI chatbot serving as a virtual therapist. The research aims in developing the comprehensive
method which is able to accurately predicting stress levels and delivering personalised interventions to individuals
across diverse contexts. The methodology involves identifying relevant features associated with mental health, which
comprises physiological indicators such as sleep patterns, heart rate, and physical activity, as well as psychological cues
obtained through self- reported emotions. These features are collected using wearable devices, surveys, and other data
collection methods. Central to this study is the integration of an AI chatbot designed to provide virtual therapeutic
support. Leveraging natural language processing algorithms, the chatbot engages with users to offer personalised
interventions based on their stress levels and associated features. By amalgamating stress level analysis with virtual
therapeutic support, the system aims to deliver tailored interventions in real-time, thereby fostering improved mental
health outcomes.
Keywords: AI Chatbot, Artificial Intelligence, Supervised Learning, Machine Learning, Mental Health, Virtual
Therapist.
Paper ID - 0269

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 20

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Advanced Underwater Object Detection: Integrating Enhanced SSD with

Comprehensive Image Enhancement Techniques
Ashok P, Indravahini B S, Niroshini B, Hamsasini B and Nirmaladevi G
This paper presents a novel approach for detecting objects underwater using the Single Shot MultiBox Detector
(SSD). The method involves analyzing underwater videos, identi- fying objects, and applying advanced single-image
enhancement techniques and color restoration methods to improve image clarity and quality, which are often
compromised due to light ab- sorption and scattering in water. The approach begins with video frame extraction and
preprocessing to remove color distortions and enhance visibility. These improved frames are then fed into the SSD
model for real-time object detection, classifying various underwater objects. The improvement strategies incorporate
modern image dehazing methods, color correction techniques, and contrast enhancement, all of which contribute to
increasing the accuracy and reliability of detection results. The effectiveness of this technique is demonstrated
through extensive experiments conducted in murky and low-light underwater conditions. Com- pared to traditional
methods, there is a significant improve- ment in detection performance, resulting in higher precision and recall rates.
This approach is ideal for many underwater applications, such as marine biology for tracking aquatic life, underwater
archaeology for discovering and preserving relics, and environmental monitoring to assess and manage underwater
ecosystems. Consequently, this paper highlights the potential of combining sophisticated image enhancement
techniques with ro- bust object recognition systems to address the unique challenges of underwater imaging, offering
great promise for real-world applications and advancing underwater exploration and detection technologies.
Keywords: Single Shot MultiBox Detector (SSD) ; Image Enhancement; Color Restoration.

Paper ID - 0284

Exploring the Impact of Pharmaceutical Supply Chains on the Advancement of

Sustainable Development Goals: A Comparative Study Across Cases
Padma Prabha C, Poomagal A, Dinesh S, Balakrishnan S, Poornima A.S and Renuka
Vidhyashankar
This study examines the impact of pharmaceutical supply chains on the environment, society, and economy, through
a comprehensive cross-case analysis that looks at both Indian and chosen multinational corporations. The
multinational corporations selected are Johnson & Johnson (J&J), Novartis, and Teva Pharmaceutical Industries;
the Indian pharmaceutical industries are represented by Sun Pharmaceutical Industries Ltd., Dr. Reddy’s
Laboratories Ltd., and Cipla Limited. This research examines supply chain practices of pharmaceutical businesses,
focusing on similarities, variations, and influencing factors with respect to sustainability results. Key research
findings highlight the variety of perspectives on social responsibility, environmental sustainability, and economic
contributions that are influenced by supply chain methods, company size, and other factors such as geolocation.
Keywords: Environmental Sustainability, Supply chain, society.
Paper ID - 0297

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 21

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Short Review on Classifying Normal and Diabetic Foot Infrared Images: Existing
Machine Learning and Deep Learning Techniques, Limitations and Future Trends
Mahalakshmi S and Lokesh S
Plantar foot surface temperature is considered an significant characteristic in Type II diabetes. Because, abnormal
temperature changes in the foot are initial signs of foot disorders. In diabetes mellitus, diabetic foot ulcer is termed as
the major issue. So, designing efficient techniques for foot ulcer detection and prevention is essential. Researchers used
infrared thermograph techniques to analyze the temperate of the plantar region, which is a non-contact and non-invasive
model. Distributing the plantar temperature among the diabetic-affected individuals didn’t follow any particular
patterns and observing the changes were also seems to be complicated. So, abnormal temperatures distributed in the
Infrared (IR) foot thermogram images are widely utilized in the initial detection of diabetic foot before ulceration
to tackle various limitations. Here, various limitations are attained from the human interactions, thus alternative
computer-based diagnosis techniques are considered to offer a good support system with superior accuracy in the
classification phases. Hence, this conference survey aims to discuss and clarify the present research work on the
classification of normal and diabetic foot infrared images. This research work elaborates on the existing literature
work associated with the normal and diabetic foot infrared image classification models. Different datasets used for
the validations are collected and tabulated. A chronological review of the developed model is described in the survey.
Various experimental tools utilized to compute the developed framework are elaborated. Multiple deep learning
and machine learning algorithms utilized in the implementation of the developed framework are analyzed. Several
complications that need to be tackled in the classical mechanism are detailed in the research gaps section. Thus, this
research work helps budding researchers to gain more information about their studies.
Keywords: Diabetic Foot Ulcer; Infrared Images; Chronological Review; Dataset; Research Gaps; Literature Works;
Experimental Tools; Deep Learning; Machine Learning.
Paper ID - 0298

Driving Social Impact And Inclusive Growth: Role Of Indian Social Stock Exchanges
Dr Poornima A S, Dr Poomagal A, Dr Padmaprabha C, Dinesh S and Balakrishnan S
This paper investigates the transformative role of Social Stock Exchanges (SSEs) in the realm of social impact financing.
Through an in-depth analysis of SSEs, the paper explores their significance in addressing the financing gap for achieving
Sustainable Development Goals (SDGs) by 2030, particularly in the context of India. The eligibility criteria for
entities seeking listing on SSEs are examined, shedding light on the diverse range of projects and funds raised through
these platforms. Additionally, the paper delves into the operational mechanisms, investment avenues, and impact
measurement frameworks associated with SSEs. Furthermore, it explores the intersection of mutual funds and SSEs,
elucidating how donations can be channeled towards social causes through these financial instruments. The paper
concludes with recommendations for enhancing transparency, investor confidence, and sustainable growth within the
SSE ecosystem, thereby contributing to the advancement of impact investing and inclusive development agendas.
Keywords: SDG, SSE, SVYM, NGOs, NPO, FPEs.

Paper ID - 0300

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 22

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Hierarchical Bayesian Modeling for FVC Prediction in Pulmonary Fibrosis and

Low-Cost Spirometer Incorporating Internet of Things
Sumithra M, Sundari S, Deepa V, Nagaraj P, Dhiliphan Rajkumar Thambidurai and Magesh
Kumar S
Lung disease remains a significant public health concern in India, with a rising prevalence attributed to various
environmental and lifestyle factors. Recent statistics reveal that chronic obstructive pulmonary disease (COPD) affects
approximately 57.8 million people in India, while pulmonary fibrosis accounts for a substantial portion of respiratory-
related morbidity and mortality nationwide. Despite the growing prevalence, accurate lung function diagnosis and
monitoring remain challenging, particularly in resource-constrained settings. This study presents a novel approach
utilizing hierarchical Bayesian modelling in conjunction with low-cost IoT-based spirometry technology for predicting
forced vital capacity (FVC) in pulmonary fibrosis patients. Leveraging real-time data from the Indian population,[7][8]
where respiratory diseases are prevalent, our research underscores the critical need for reliable and accessible spirometry
measurements for effective disease management. We begin by elucidating the epidemiological landscape of lung
disease in India, highlighting the alarming rates of COPD and pulmonary fibrosis. Recent studies suggest that
when integrated into clinical practice, spirometry data can significantly improve diagnostic accuracy and treatment
outcomes for respiratory conditions. Leveraging data from the Indian population, where respiratory diseases are
prevalent, our research underscores the critical need for reliable and accessible spirometry measurements for effective
disease management. Our proposed methodology integrates the YFS201 flow sensor with an ESP8266 microcontroller,
providing a cost-effective solution for real-time measurement of airflow. Through hierarchical Bayesian modeling,
we demonstrate the capability of our approach to accurately predict FVC in pulmonary fibrosis patients, thereby
facilitating early detection and personalized treatment strategies. By incorporating spirometry data into clinical
practice, our research aims to empower healthcare professionals in India and beyond to make informed decisions,
optimize patient care, and mitigate the burden of lung disease.
Keywords: Bayesian modeling, Hierarchical modeling, IoT, Spirometry, Pulmonary fibrosis, Forced vital capacity
(FVC), Real-time data, Respiratory healthcare.

Paper ID - 0302

Reliable Communication in VANET Environment through Mobility aware clustering

and Multi Hop Routing
Jemima Havila Catherine A, Dr. A. Maria Christina Blessy, Dr. K. Danesh and Dr. V. Diana
Earshia
This research introduces a novel communication approach for Vehicular Ad-Hoc Networks (VANETs) utilizing
clustering and routing techniques to enhance routing reliability. The proposed protocol considers a fleet of vehicles
equipped with GPS devices, enabling the collection of crucial vehicle details such as speed, direction, and position.
Initially, vehicles are grouped into clusters using the Mobility-aware LEACH technique, leveraging vehicle speed to
ensure cluster stability and mitigate sudden Cluster Head (CH) changes and cluster re-formation issues.
Cluster-based routing is employed to improve communication efficiency by reducing the burden on vehicles and Road
Side Units (RSUs). The gathered information within clusters is aggregated by CHs and routed to RSUs using the
Adaptive Osprey Optimization based Routing (AdO Route) algorithm. This algorithm incorporates multiple factors
including node distance, residual energy, relative speed, and link stability, thereby optimizing communication
efficiency in VANETs.
Keywords: VANET communication, optimal routing, clustering, link stability, residual energy.
Paper ID - 0304

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 23

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Performance Analysis of Active-Quasi Z-Source Inverter fed Induction Motor using

SVM
T. Muthamizhan, B. Naveen and P.P.Narenthira Sai Raam
This research proposes a novel method to govern a single-stage active-quasi Z source (qZS) inverter-fed induction
motor drive by integrating proportional-integral (PI), sliding mode control (SMC) techniques with the Space Vector
Modulation (SVM) technology. The active qZS inverter, with its inherent voltage buck-boost capability and enhanced
reliability, is a promising topology for renewable energy integration and electric vehicle applications. The SVM
technique are employed to produce switching signals for the inverter switches, ensuring optimal utilization of the
available voltage levels and minimizing harmonic distortion. The PI controller is utilized for speed regulation to
achieve robust and stable motor performance under varying load conditions. Additionally, a sliding mode controller is
implemented to enhance the system’s robustness against parameter variations, disturbances, and uncertainties. The
suggested control strategy is validated by means of extensive simulation investigation. The results determines the
improved dynamic response, enhanced efficiency, and robust performance of the single-stage cascaded qZS inverter-fed
induction motor drive compared to traditional control methods. The effectiveness of the proposed approach highlights
its potential for real-world applications in renewable energy systems and electric vehicles.
Keywords: active-quasi ZSI, PI, Sliding mode controller, space vector modulation, induction motor (IM).
Paper ID - 0306

Exploring Students Perception and Behavioral Intentions in Online Learning

Dinesh S, Balakrishnan S, Poornima A.S, Padma Prabha C, Poomagal A and Renuka
Vidhyashankar
The present study is developing an integrative conceptual framework that combines relevant-context elements into
well-established IS Success and UTAUT models to explore how their direct and indirect variables affect online learning
BI. The research measures online learning behavioral intention. A systematic questionnaire was used to obtain data
from 202 school and college members. Analysis is done using SPSS. Study uses descriptive research approach and
random sampling. The results demonstrated that online learning quality strongly affects satisfaction and behavior.
System, information, and service quality strongly impact behavior. The behavioral intention was greatly impacted by
students’ conviction in e-learning’s future and their desire to incorporate it into every topic. The behavioral intention
was greatly impacted by students’ conviction in e-learning’s future and their desire to incorporate it into every topic.
According to the research, perceived online learning material convenience has a beneficial influence. Variance explained
by each component and total variance by all components. Seven removed parts Seven components make up the ideal
solution. Later, internet learning will make acquiring new abilities from afar easier.
Keywords: Learning Management System, Self-Learning Materials, Synchronous method, Asynchronous method.
Paper ID - 0315

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 24

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Autoencoder and Decoder for Efficient Network Intrusion Detection in Internet of

Vehicles
Pranav S A, Sathya Priya S and Hariharan B
The Internet of Vehicles (IoV) is transforming transportation connectivity worldwide by connecting infrastructure,
vehicles and communication technologies. While this real-time connectivity increases productivity, safety and security,
it also poses serious security risks due to unauthorized access and criminal activity because it relies on legacy systems is
not detected by traditional signature-based detection systems new threats May not be detected can catch it. This study
compares an auto-encoder-based intrusion detection system designed to address the unique challenges of the Internet
of Vehicles (IoV) with traditional supervised methods such as SVM and unsupervised methods such as single-class
SVM and K-means clustering. With the help of its decoder, the autoencoder improves interpretability by precisely
reconstructing the input data, identifying abnormalities, and visualizing them. It trains on typical IoV network traffic
data. Reducing false positives and increasing detection accuracy, this unsupervised process doesn’t require a large
amount of labelled data. In order to enable efficient and proactive defense against new cyber threats, the article uses
this comparison to show how superior autoencoders are at guaranteeing high security and dependability for Internet
of Vehicles (IoV) systems.
Keywords: Anomaly Detection, Autoencoders, Internet of Vehicles (IoV), K-means, Long Short-Term Memory
(LSTM), Network Traffic, One-Class SVM.
Paper ID - 0323

Promoting Feline and Canine Hydration: Design and Evaluation of a Gravity-Fed

Water Dispenser with Automatic Lid
Harshitha Seetharaman, Jai Udhaya S and Raj Kumar K
This document presents a new automatic pet water dispenser design with a microcontroller-controlled sliding door.
An Arduino board and Servo motor manages a chosen mechanism (e.g., linear actuator) to open the lid upon detecting
a pet’s presence via a PIR sensor. This touch-free access promotes hygiene and pet comfort. For user convenience,
a separate refill mechanism ensures a consistent water supply, independent of the Arduino and the Servo motor
system. This could be a gravity-fed reservoir or a connection to a main water line. This simplifies the design, reduces
maintenance, and eliminates the need for water level sensors within the dispenser itself. An optional LED provides
visual feedback on dispenser status or low water level. This design offers a unique blend of pet-centric features, user
convenience, and efficient water dispensing, making it a valuable tool for modern pet care.
Keywords: Automatic pet water dispenser, microcontroller-controlled sliding door, Arduino board, Servo motor,
PIR sensor, gravity-fed reservoir, modern pet care.
Paper ID - 0326

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 25

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Crime Defender - A Proactive Measure For Community Security

S. Juliafaith, A.M Sermakani, T. Veena, D.Chithra and R.Devprasad
The project’s goal is to create a comprehensive system that uses information derived from First Information Reports
(FIRs) for hotspot identification, predictive modeling, and an unresolved case reminder system. After the data is
meticulously gathered and encoded, machine learning techniques like Support Vector Machines, Gradient Boosting
Equipment, and randomly generated forests, for instance, are taught in order to recognize orderly rankings of FIR
cases. Stakeholders can obtain valuable information for setting agendas for interventions and allocating substantial
finances by employing spatial analytics to identify hotspots based on geographic proximity. To strengthen
investigative efforts and enhance case management procedures, a strong reminder system is also incorporated to flag
and score outstanding incidents.
Keywords: First Information Reports(FIR),Machine Learning(ML),Support Vector Machine(SVM),Gradient
Boosting(GB),Random Forest(RF).
Paper ID - 0327

Exam Preparation Assistance Chatbot using Retrieval Augmented Generation

Kumar P, Haresh M and Hayagreevan V
Exam preparation requires the usage of study material to learn information. This is followed up by testing the
knowledge by attending mock tests. Mock tests are usually prepared by teachers while taking into consideration the
syllabus for the test and also the pattern of questions asked in the previous examinations. This helps in preparing a
comprehensive set of questions that help the student evaluate their knowledge and help them evaluate their
performance. The process of creating mock tests is time intensive and requires considerable effort from teachers to
create them. This paper aims to work on aiding teachers in this process by utilizing the power of Artificial
Intelligence and Large Language Models. Generative Artificial Intelligence has gained immense popularity due to its
ability to generate natural language responses to query relating to a large knowledge base. The model proposed in
this paper utilizes a smaller and limited knowledge base to train the model to maximize processing efficiency for
normal computers. The model also is powered by Retrieval Augmented Generation process to enable it to tap into
external knowledge resources such as study materials provided by the student and generate appropriate responses to
the queries from the user. This helps provide students with personalized mock test preparation software and reduces
the time spent by teachers to create mock tests and help them focus on aiding students with their learning process.
This optimizes the learning experience for both the teacher and the student.
Keywords: RAG, LLM, chatbot, BERT, NLP.

Paper ID - 0328

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 26

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Agricultural Product Price and Crop Prediction based on Data Science Technique
Kumar P, Vijayaraj A, Senthil Pandi. S and Venkatesh Prabhu Balakrishnan
Agriculture serves as a crucial catalyst for economic growth and forms the foundation of developing countries’
economies. Farmers are suffering losses in their agricultural operations due to a lack of appropriate industry
expertise. Machine learning is a crucial approach for estimating the cost and productivity of farming. In relation to
this specific situation, we have devised a model that will aid farmers in choosing the optimal crop to cultivate
throughout each season and evaluating the associated expenses. By employing cost forecasting, farmers can mitigate
the risk of suffering losses. We employed the supervised machine learning approach (SMLT) to analyze the crop
dataset. To ascertain the algorithm that achieves the highest level of accuracy, we conducted a comparison analysis
of the different algorithms. This paper will generate a forecast that will help farmers determine the most fruitful
crop to cultivate. The forecast will consider multiple parameters, such as temperature, humidity, geographical
location, land area, and rainfall.
Keywords: Crop Prediction, Agri Product Forecasting, Data Science.
Paper ID - 0329

IoT-Enhanced Wireless Sensor Network for Precision Agriculture: Advancing

Environmental Monitoring and Resource Optimization
R. Banu Prakash, Dr. V. DhilipKumar, Dr. K. Durairaj, Nuti Dhruv and C. Alamelu
Precision agriculture has advanced significantly as a result of the Internet of Things’ (IoT) quick development,
particularly in terms of resource management and environmental monitoring. In this paper, an IoT-Enhanced
Wireless Sensor Network specifically designed for precision agriculture with an emphasis on Indian paddy cultivation
is introduced. The system provides comprehensive environmental factor monitoring by utilizing a variety of sensors,
such as NPK sensors, air quality, UV index, temperature, humidity, and soil moisture. Its ESP32 microcontroller
and GSM module combination ensures dependable data transfer and remote access. Techniques for gathering and
analyzing data are covered, as well as the system’s design, implementation, and integration issues. Improved
irrigation and resource management efficiency, as seen by early findings, may result in higher crop yields and more
environmentally friendly practices. The use of IoT technology to agriculture is proving to be quite advantageous, and
there are even ideas for improving and growing the system.
Keywords: Agriculture, IoT, Sensor, Cultivation, Crops
Paper ID - 0331

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 27

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Unauthorized Access Detection System using Machine Learning with Honeypot

Integration
Mrs.D.Thamizhselvi, Aswin Kumar K and Ajith Raj N
In cases of unauthorized access, this poses a major security risk to the organizational servers. The project is for the
development of a high-end detection system by integration of honeypots with machine learning to identify and mitigate
unauthorized access attempts in real-time. Honeypots lure attackers to a masqueraded vulnerable system, capturing
every detail about the malicious activity. That retrieves detailed information about malicious activities. In this feature
extraction for anomaly detection, the features used are sourced from server logs, firewall logs, network traffic data,
and authentication logs. This forms the basis for a complete dataset applied in the development of machine learning
models with the accuracy of detection of suspicious behavior. All this monitoring is done in real-time, accompanied by
automated responses that guarantee correct and timely action execution against detected threats. This is the way the
system manages to leverage traditional security measures with the power of innovative honeypot technology to deliver
maximum accurate and effective unauthorized access detection, making this an organization’s major invention in
mission-critical infrastructure security. The approach provides enhanced security and useful insights about attackers’
behavior so proactive threat management measures are taken in time.
Keywords: Unauthorized access detection, machine learning, honeypots, real-time monitoring, and network security.
Paper ID - 0338

Fake Manipulation Detection in Social Network (FACT-HIVE)

Avinaash Venkat B, Dhakshin Vikash V, Mrs.Thamizhselvi D, Suganthi P and Dr.Punitha A
Fake manipulation detection is most important integration in current era of social media, when everybody can create
and spread misinformation in a very short time. In relation to fake news detection, sentiment analysis for a given text
means the identification and sentiment categorization of the emotional tone expressed in such content. This is based
on the assumption that fake news tends to contain language that misleads deliberately or was sensationalistic in nature
and can thus be detected through sentiment analysis. The enhanced User Experience and User Interface with trained
modules of machine learning dataset is used for clear output Though capable of detecting certain patterns indicative
of fake news, sentiment analysis methods are not perfect techniques for spotting fake news stories that are written
in a more tempered language or designed to make a person feel good. Moreover, Natural Language Process-NLP is
implemented for text classification based on graphical representation and Support Vector Machine. Functional We
implement the Decision Tree Algorithm and Random Forest, Python Flask for integrating the website to the backend.
Further, the accuracy of the Sentiment Analysis may get affected by various aspects like sarcasm, irony, cultural
differences in used language. Also, the product will include three major detection frameworks to ensure nations’
safety. Therefore, the menace of fake resource needs to be fought with solutions that include fact-checking and source
verification.
Keywords: Random Forest, Decision Tree, Algorithm Training, Flask, NLP-Natural Language Process, Support
Vector Machine (SVM).

Paper ID - 0339

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 28

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Machine Learning-Based Threat Detection in Crowded Environments

Cherin Yacoob Wattacheril, Dr. G. R. Hemalakshmi, Ashin Murugan, P.N.V. Abhiram, Harisankar
G and Ansu M George
This paper presents the design and implementation of an intelligent system that integrates machine learning and
computer vision to create an advanced framework for detecting anomalies and threats in crowded public spaces.
The system continuously analyzes video feeds from strategically placed cameras, processing visual data in real-time to
identify unusual or suspicious activities. Leveraging advanced machine learning algorithms, the system processes these
video streams by learning from historical data and adapting to new patterns over time. It is capable of identifying
events such as unattended objects, aggressive behavior, or unauthorized access. The system builds behavioral profiles
of individuals within the monitored environment, analyzing factors such as movement patterns, interactions, and
crowd dynamics. Alerts are triggered whenever deviations from expected behaviors are detected. The system also
prioritizes privacy by anonymizing individuals, focusing on tracking movement patterns rather than facial recognition.
It ensures compliance with privacy regulations through robust safeguards. Upon detecting an anomaly, the system
either notifies security personnel or activates automated response mechanisms, facilitating rapid interventions such
as deploying security teams or securing specific areas. The design is scalable, allowing for coverage of large public
spaces like airports, stadiums, and shopping centers, and can adapt to varying environmental conditions and crowd
densities. Continuous learning from false positives and negatives enhances algorithm performance, ensuring ongoing
improvement. Regular audits and updates are also conducted to maintain optimal functionality.
Keywords: artificial intelligence, object detection, threat detection, tracking, behavioral modeling, pattern matching.

Paper ID - 0345

Enhanced Breast Cancer Prediction through Block Processing of Gene Data and
Random Forest Regression
J. Godly Gini and S.Padmakala
The uses Random Forest Regression (RFR) in conjunction with block processing of cancer gene data to propose a
unique method for the earlier prediction of breast cancer. Our approach starts with gathering and pre-processing
large genomic datasets, with a particular emphasis on genes frequently linked to breast cancer. Segmenting the data
into smaller, more manageable units improves the accuracy and processing efficiency. To find the most pertinent
genetic markers, a thorough feature selection process is applied to each block. These variables are then loaded into
a Random Forest Regression model, which was selected due to its capacity to represent intricate gene relationships
and its resilience when dealing with high-dimensional data. A large dataset is used to train and validate the RFR
model, guaranteeing a fair representation of the various subtypes of breast cancer. When compared to conventional
approaches, our results show a significant improvement in the predicted accuracy and early detection skills.
Keywords: Random Forest Regression, Gene expression, Breast cancer, Bag of words, Text mining, block processing.
Paper ID - 0363

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 29

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Decentralized Real-Time Communication:WebRTC and WebSockets

forPeer-to-PeerFile Sharing
Nachiappan C, Navajeevan M, Sathish Kanna L and Ms R Dhivyabharathi
Real-time communications need file transmission, but conventional techniques frequently rely on centralised servers,
raising possible privacy and performance issues. In order to solve these problems, this study suggests a decentralised
method that makes use ofWebRTC (Web Real-Time Communication) inside the same network. In the conventional
paradigm, data is momentarily stored on a relay server, which facilitates file transfers between a client and recipient.
However, there may be privacy hazards associated with this strategy as it uses third-party software. The suggested
decentralised method does away with the requirement for a centralised server by using WebRTC to create peer-to-peer
connections directly amongst clients on the same network. With no need for intermediate processing or storage, this
method facilitates direct peer-to-peer communication, therefore increasing efficiency, decreasing latency, and enhancing
privacy.
Keywords: WebRTC, Internet, File System, Node Js.
Paper ID - 0369

Predicting Stock Market Web App using LSTM Model and Facebook Prophet
Sarvesh Susindran, Sanjay Nagarajan, Perinban Prabu and Ms.Dhivya Bharathi
The Prophet and LSTM (Long Short-Term Memory) models’ combined powers are presented in this project as a
comprehensive method of stock price prediction through a single Python script. The script preprocesses historical
stock data for both models using information received from yfinance.Time series forecasting is done with the Prophet
model, which projects stock prices for the next 365 days and uses Plotly to visualise the results. The script divides
the data into training and testing sets, scales the data, then trains an LSTM model on the training set
simultaneously. For a certain time period, the closing prices are predicted using the LSTM model, and the forecasts
are assessed using root mean squared error (RMSE). Using Plotly, the script further illustrates the difference
between the real and forecasted stock values.This research offers an integrated approach to stock price prediction by
combining the powers of sequential data processing of the LSTM model with the forecasting skills of Prophet. It
draws attention to how well these models complement one another in explaining various facets of stock price
behaviour and stresses the significance of incorporating machine learning forecasts into a more comprehensive
approach to investing analysis.To sum up, this study demonstrates how Prophet and LSTM models may be used in
concert to predict stock prices, offering important new perspectives on how these models can be used in financial
forecasting. It emphasises how important it is to make well- informed decisions and seek professional advice when
using machine learning models for investing.
Keywords: Streamlit,Pandas,NumPy,Keras(TensorFlow), yfinance,Prophet(Facebook),Plotly,LSTM,Slider(UI
interaction),Data caching.
Paper ID - 0370

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 30

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Exam Proctoring System using Machine Learning

Hariprasad V, Alister Francis Fernandez, Pragadeesh N and Dr.N.Thilgavathi
The rise of online education has created a need for strong solutions to oversee exams and maintain academic honesty.
Secure Proctor steps in as a modern platform aiming to transform how online exams are supervised, using advanced
technologies like artificial intelligence (AI) and computer vision. This paper delves into SecureProctor’s structure,
design, and components, showcasing its abilities to ensure the fairness and integrity of online assessments. By actively
monitoring student actions in real-time and employing features such as facial recognition, speech detection, head
pose analysis, and cheating behavior detection, Secure Proctor offers a complete solution for conducting secure and
equitable online exams. With its focus on leveraging cutting-edge technologies, Secure Proctor strives to meet the
evolving needs of online education while upholding the principles of academic integrity and fairness.
Keywords: Online exam proctoring, artificial intelligence, computer vision, facial recognition, speech detection, head
pose analysis, cheating behavior detection.
Paper ID - 0371

Enhancing Energy Efficiency in Hybrid Vehicles using Model Predictive Control with
Reinforcement Learning
Senthil Pandi S, Bala Subramanian C, Vaijayanthi.S and Chaithra I V
In order to improve hybrid car energy efficiency, this research looks into integrating Reinforcement Learning (RL)
and Model Predictive Control (MPC). Real-world settings present challenges for traditional control systems because
of uncertainties and variability. Through the integration of RL’s flexibility and MPC’s predictive power, this study
seeks to create novel control algorithms that enhance hybrid electric vehicles’ energy management. Through the use
of real-time environmental data, the suggested approach enables cars to dynamically modify their control strategies,
enabling effective power distribution between electric propulsion systems and combustion engines. To show how the
combined MPC-RL framework can increase energy efficiency while still meeting performance standards, case studies
and simulation data are provided. By enhancing energy-efficient hybrid vehicle control systems, this research helps
to promote environmentally friendly transportation methods and lessen the influence on the environment.
Keywords: Reinforcement Learning, Model Predictive Control, Deep Q Networks, Hybrid Vehicles, Energy
Management.
Paper ID - 0373

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 31

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Uncovering Characteristics for Entrepreneurial Success and Intention; Focusing on

Moderating Effects of Entrepreneurial Orientation
Dr. S. Avinash, Dr. M. Thamizhselvi, Dr. Anugragha.S.S, Dr. I. Shanmugapriya and S. Murugan
The study identified the characteristics essential for entrepreneurial success and intention, with a particular focus on
understanding the moderating effects of entrepreneurial orientation. Entrepreneurial success is a complex interplay
of personal attributes, environmental factors, and strategic behaviors. The investigation delves into the foundational
traits such as passion, risk-taking propensity, innovativeness, and adaptability, which are commonly associated with
successful entrepreneurs. Practical implications for educational programs, mentorship initiatives, and policy
development are discussed to cultivate these characteristics in aspiring entrepreneurs. The study identified the task
of age in shaping entrepreneurial orientation, considering how individuals at different life stages approach and engage
in entrepreneurial activities. Entrepreneurial orientation, innovativeness, and risk-taking within an organizational or
individual context, is explored as a dynamic factor that can either amplify or mitigate the impact of personal traits
on entrepreneurial outcomes. Through a comprehensive analysis of age-specific considerations, the study provides
nuanced insights into how different generations approach entrepreneurship and how interventions can be tailored to
address their unique needs. The findings contributed to a deeper understanding of characteristics, age, and
orientation. By recognizing the moderating effects of entrepreneurial orientation, policymakers, educators, and
support networks can design targeted interventions to enhance the likelihood of entrepreneurial success and intention
across diverse demographic groups. Ultimately, this study offers practical recommendations for stakeholders
interested in fostering a thriving entrepreneurial environment that harnesses the strengths of individuals and
maximizes their potential for success.
Keywords: Positive Experience, Proactive Behavioral Tendency, and Perceived feasibility, entrepreneurial success
and intention, Perceived desirability.
Paper ID - 0383

Exploring The Attitude Towards Entrepreneurship, Choice Of Business, Attributes,

And Perception Of Entrepreneurs: A Road Map To Success
Dr. R. Meenambigai, Dr. N. Saranya Devi and Dr. Yogita Saurav Gupta
The journey of entrepreneurship is a dynamic process shaped by various factors, including personal attributes, the
choice of business, and perceptions of entrepreneurs. This road map to success aims to explore the intricate interplay
of these elements and their collective impact on entrepreneurial endeavors. Understanding the significance of
personal attributes is paramount, as traits such as resilience, adaptability, and risk-taking propensity are crucial in
navigating the unpredictable terrain of business. This research delves into the correlation between these attributes
and entrepreneurial success, emphasizing the need for a self-aware and growth-oriented mindset. The choice of
business is another pivotal aspect that significantly influences an entrepreneur’s trajectory. This road map
investigates the strategic decision-making process behind selecting a particular industry. It delves into the alignment
between an entrepreneur’s passion, skills, and market demand, shedding light on the strategic considerations that
contribute to sustainable business models. Perception plays a fundamental role in shaping an entrepreneur’s reality.
The study explores how entrepreneurs perceive challenges, opportunities, and their own capabilities. Investigating
the impact of mindset on decision-making and problem-solving, the road map elucidates the role of a positive,
proactive outlook in overcoming obstacles and achieving long-term success. The amalgamation of these aspects
creates a detailed framework for entrepreneurial success. This study offers useful lessons for prospective
entrepreneurs, mentors, and policymakers by examining the complex relationships among personal traits, company
decisions, and perceptions. This roadmap seeks to enhance the development of a robust and empowered
entrepreneurial environment, promoting innovation, growth, and social impact.
Keywords: Resilience, Adaptability, Self-efficacy, Confidence attributes, innovation, choice of business, perception
entrepreneurs and Risk-taking propensity.
Paper ID - 0384

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 32

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Content Analysis of Education and Awareness Campaigns in Metaverse;

Opportunities And Ethical Standards
Dr. S. Sathyasundari, Dr. C. Velusamy, Dr. K. Arulini, E. R. Vadivel, S. Uma Maheswari and S.
Murugan
The advent of the metaverse presents transformative opportunities for education and awareness campaigns, offering
immersive and interactive experiences that traditional media cannot contest. The study conducted a content analysis
of various educational and awareness campaigns implemented within the metaverse, highlighting their innovative
approaches, effectiveness, and the potential for broader societal impacts. Through a systematic review of campaigns
across different platforms, the research identified key opportunities, such as personalized learning environments,
gamification, and enhanced engagement through virtual reality and augmented reality technologies. Furthermore, it
delves into the ethical considerations inherent in these digital spaces, including data privacy, digital equity, and the
psychological effects of prolonged VR exposure. The findings underscore the importance of establishing robust
ethical standards to guide the implementation of educational content in the metaverse. By navigating the balance
between innovation and ethical responsibility, stakeholders can harness the full potential of the metaverse to foster
meaningful education and awareness while safeguarding users’ rights and well-being. Metaverse in education
revolutionizes learning by offering immersive experiences, fostering global collaboration, personalizing learning
journeys, enhancing practical skills, promoting innovation, ensuring accessibility, and supporting sustainability. The
study concluded that embracing these technologies prepares students to thrive in a digitally driven world and equips
them with essential skills for lifelong learning and future success.
Keywords: Metaverse, Education, Awareness Campaigns, Personalized Learning Virtual Reality, Digital Equity,
Data Privacy Augmented Reality Gamification and Ethical Standards.
Paper ID - 0385

Transforming Market Dynamics, E-Business and E-Commerce in Hospitality and

Tourism
Dr R. Monisha, M.Jaiganesh, Dr. L. Sujatha and Dr. I. Shanmugapriya
The evolution of e-business and e-commerce has revolutionized how consumers interact with hospitality and tourism
services. Moreover, e-commerce has streamlined business operations within the hospitality and tourism sector. From
hotel management systems to online payment gateways, technological innovations have enhanced efficiency and
reduced costs for service providers. Traditional players now face competition from online travel agencies,
peer-to-peer accommodation platforms, and other disruptive models. However, amidst the opportunities presented
by e-business and e-commerce, challenges also emerge. Data security and privacy concerns loom large in an
increasingly digitalized environment, necessitating robust cyber security measures to protect sensitive information.
Moreover, the digital divide poses barriers to access for certain segments of the population, highlighting the
importance of inclusive strategies in digital marketing and service delivery. The field of information technology (IT)
has profoundly transformed tourism management, revolutionizing how businesses operate, interact with customers,
and deliver experiences. By analyzing various methodologies, metrics, and frameworks for evaluating tourism
websites, researchers have contributed valuable insights into website design, usability, content quality, and
effectiveness in engaging and converting visitors.
Keywords: E-business, E-commerce, Hospitality, Tourism, Digital Transformation, Market Dynamics, Consumer
Behavior, Business Operations, Competition, Data Security, Digital Inclusion.
Paper ID - 0387

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 33

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Exploring the Confronts Faced by Women Entrepreneurs -An Insight into Problems,
Prospects and Development; an Empirical Study
Dr R.Monisha, Dr. Veto Dey, Dr. N. Jayapriya and Dr. I. Shanmugapriya
The study’s overarching goal is to shed light on the many obstacles and possibilities that women business owners
confront by investigating the complex problems they face. This in-depth analysis probes the worldwide situation of
female entrepreneurs, including their prospects, threats, and position. The conversation seeks to shed light on global
trends, provide insights into creating an environment that supports women entrepreneurs, and identify the problems
they confront by looking at the changing landscape from different angles. Furthermore, the research explored the
role of education and skill development in empowering women entrepreneurs. Entrepreneurs are engaged in various
levels of business activity, both inside their own country, within their area, and on a worldwide scale. Female
entrepreneurs comprise barely one third of all entrepreneurs. Amidst the period of globalization, women
entrepreneurs face significantly amplified hurdles. Their involvement is now causing significant transformations in
the global economy. Globally, it is believed that over 33% of commercial organizations are controlled by women. In
India, the status is virtually unchanged.
Keywords: Women Entrepreneurs, Problems, entrepreneurs Satisfaction, Global Context, Prospects and
Development.
Paper ID - 0388

Enhancing Voter Identity Verification Through Cloud Computing Enabled Biometric

Authentication-Modern Voting
Chitra Sabapathy Ranganathan, Kabaleeswaran S, Dr. P L Kishan Kumar Reddy, Dr. P.
Selvarani, C. Srinivasan and Rajarajan S J
There is a possibility that the reliability and accessibility of voting systems will be significantly improved because of
developments in technology. To solve the problem of providing voters with an identity that is safe and accurate, the
research suggests combining the technologies of the Internet of Things (IoT) with biometric authentication. Using
Internet of Things devices, voters can have their identities verified in real-time at voting sites if the user registers
distinctive biometric characteristics, such as fingerprints, facial features, and iris patterns. Increasing safety is the goal
of this multifactor authentication method, which incorporates voter IDs, secure QR codes, and biometric data. Privacy
concerns may be alleviated using biometric template protection, which conceals real biometric data while allowing for
precise identification matching. The system prioritizes scalability and ease of use to ensure that it can support many
voters and a wide variety of user requirements. The proposed voting system has the goals of reducing instances of
voter impersonation, improving accessibility for people of all demographics, and contributing to the development of a
more open and trustworthy voting environment.
Keywords: Voter Identification Verification, Internet of Things (IoT), Real-time Verification, IoT-enabled Biometric
Authentication, Security.
Paper ID - 0389

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 34

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Intelligent Security System for e-Bikes using Smart Lock with Tamper Detection
Dr. L. Chitra, V. Rattan Kumar, K. Devabalaji, P.Veeramuneeswaran, A. Mohamed anas and S.
Anbarasan
Electric bikes (e-bikes) have emerged as a popular alternative mode of transportation in urban areas, offering a
sustainable and convenient means of travel. With advancements in battery technology and motor efficiency, e-bikes
provide an environmentally friendly solution for commuting and recreational activities. However, alongside the growing
popularity of e-bikes, concerns about theft and safety have become increasingly prevalent. Traditional bike locks, such
as padlocks and chains, have long been the go-to security measures for bicycle owners. However, these conventional
locks are often inadequate in deterring determined thieves equipped with sophisticated tools. Moreover, the rise in
e-bike theft incidents has highlighted the need for more robust security solutions tailored specifically for electric bikes.
Additionally, safety concerns related to electric bike batteries have come to the forefront. While e-bike batteries are
generally safe when used properly, incidents of battery malfunctions leading to fires or explosions have been reported.
As such, ensuring the safety of electric bike owners, as well as protecting their valuable investment from theft, has
become a pressing issue in the e-bike community.
Keywords: Electric bikes, e-bikes, smart electronic locking systems, mobile app integration, security, safety.
Paper ID - 0393

Data Mining Approach for Emotional Regulation and Social Adjustment among
Adolescents
Saravanan.S and Tamizharasi.K
The goal is to examine teenage emotional regulation and social adjustment using sentiment analysis. Adolescent
emotional control affects social relationships and well-being. Sentiment analysis helps identify trends and insights
in social media messages and diary entries. The goal is to discover emotional states and sentiment patterns that
correspond with social adjustment. The mood exhibited in teenagers’ written material might reveal their mental
health and social behaviour. Creating a framework to forecast emotional regulation disorders and social adjustment
concerns is the objective. This strategy may improve teenage emotional and social well-being via treatments and
support networks. Positive adolescent development practices may improve from the findings. The experimental group
has a 14.2% mean difference in emotional regulation, whereas the control group has 0.3. About social adjustment in
experimental group, the overall difference in mean percentage is 3.4 whereas in control group is only 0.5. It indicates
that the level of emotional regulation and social adjustment is improved by the life skill training program among
adolescents. Positive relationships are found between emotional regulation and social adjustment. The occupation of
father and mother and the type of family has got association with the level of emotional regulation in the experimental
group and the age of adolescents got association in the control group.
Keywords: Sentiment Analysis, Emotional Regulation, Social Adjustment, Adolescents, Predictive Modeling.
Paper ID - 0400

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 35

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Study on Spatial Distance Optimization of Delivery of Mails from the Nearest Postal
Location
T.A. Rajasekaran, Vijayalakshmi. P and Rajendran. V
The study’s main objective is to develop a model using the Travelling Salesman Problem (TSP) technique to create
efficient routes for postmen delivering articles in their beat areas. The goal is to minimize spatial distance while
meeting customer service standards in the shortest time. The methodology analyses geographical data, beat areas,
and past delivery patterns to formulate TSP instances for each postman’s route. The 2-opt algorithm optimizes the
routes. The model’s performance is evaluated by comparing delivery time and spatial coverage to the manual routing
system. The study aims to enhance delivery efficiency and service quality, benefiting both postmen and customers.
The successful application of the TSP-based RL approach significantly optimized mail delivery routes, reducing travel
distance and time. On average, the model achieved a 15% reduction in delivery time compared to conventional routing.
This enhanced efficiency and customer satisfaction, providing clear, concise, and optimized routes for postmen. The
research contributes to modernizing postal services through spatial distance diversification and route optimization.
The combination of TSP and RL techniques revolutionizes delivery processes, reducing operational costs and improving
the overall customer experience. This study’s outcomes showcase the power of advanced algorithms for solving real-
world challenges and hold promise for future logistics and delivery optimizations.
Keywords: Travelling salesman problem (TSP), 2-opt algorithm, spatial distance, RL problem, geographical data.
Paper ID - 0407

Big Data Analytics for Pattern Recognition and Technological Decision-Making

Vidhya. N and Dr. C. Meenakshi
The purpose of this study’s analysis of big data is to clarify the following ideas and classifications regarding big data,
sorts of big data, what they are, and what characteristics they have as determined by the literature review. The
discussion continues through the effective result it might produce thereby promising a bright future. The terminology
and concepts of big data intellectuals and the information technology industry that pay closer attention to big data
are to be discussed. Data is generated and retrieved at a rate that quickly exceeds the threshold range in the digital
and computing world. The amount of data and pace of market expansion both rise when information is shared and
transferred at the speed of light through wireless and broadband networks. When compared to conventional database
systems, high-performance analytics of big data is the effective framework for the analysis and pattern development
of processed data.
Keywords: Big data connotations, Technologies in Big data, Categories, and Characteristics in big data, Map Reduce,
Apache, HADOOP.
Paper ID - 0408

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 36

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Review of AI-Driven Machine Learning Solutions for Modern Agriculture

K. Suganthavalli and Dr. C. Meenakshi
Artificial intelligence (AI) has been more prevalent in the agricultural sector in recent years. Sector challenges,
there are many obstacles to overcome to increase the crop production namely reduced soil preparation, pest invasion
Insufficient data leading to wrong result prediction hence the poor output, and wide breach between farmers and
evolving technologies. The proposal of applying AI techniques in agriculture is to ensure its flexibility, precision,
reliability, and goodness. The study summarizes the many AI-based approaches to weed, disease, crop, and soil
management solutions. Several approaches are used to increase the yield, and the benefits and drawbacks of the
application are examined. To produce high yields of fruit, plants must have a perfect balance between vegetative
development (such as root, stem, and leaf growth), reproductive growth (such as flower and fruit growth), NNs, and
GA. This allows for the best nutrient concentration (NC) set points. One way to forecast plant growth is to look at
the ratio of stem diameter to total leaf length.
Keywords: Artificial intelligent applications, Forming, Soil usage, Soil test, Disease identification, Crop quality,
Irrigation monitoring.

Paper ID - 0409

Real-Time Emotion-Based Music Recommendation System Using YOLOv5 and

Spotify API
J. Sujithra, Karthik Balaji B M and Yashwanth J
Music is a universal language that evokes emotions and influences mood. Recent advances in affective computing
and multimodal fusion have enabled innovative music recommendation systems. This work explores the relationship
between facial expressions and music preferences, proposing a novel music recommendation system. A system is
developed that captures and interprets users’ emotional states with high accuracy, achieving high mAP (mean Average
Precision) using YOLOv5, and recommends personalized music playlists. YOLOv5 and Spotify API are utilized to
create a seamless and intuitive user experience.
Keywords: Artificial intelligence, Machine Learning, Multimodal fusion, motion recognition, Music Recommendation,
YOLOv5, Spotify.
Paper ID - 0410

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 37

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Smart Well Networks for Adaptive Groundwater Management Integrating Cloud

Computing and Wireless Sensor Technologies
V G Sivakumar, Dr. S. Vimaladevi, Dr. R. Thenmozhi, Dr. P. Epsiba, S. Sujatha and M. Nalini
This research presents a new method for managing groundwater that combines cloud computing with wireless sensor
technology to create what are called ”Smart Well Networks” (SWNs). Innovative solutions are needed for
sustainable management of groundwater, which is a major worldwide concern due to pollution and depletion. The
use of wireless sensors placed within wells allows SWNs to gather data in real-time, allowing for the continuous
monitoring of groundwater levels, quality, and other relevant characteristics. For the purposes of storing, analyzing,
and making decisions, this data is sent to a cloud computing platform. With the help of cloud-based technology,
stakeholders may quickly react to changing groundwater conditions by implementing adaptive management plans.
Highlighting its ability to improve groundwater management practices via the provision of actionable insights
generated from comprehensive and up-todate data, the study delves into the design, features, and advantages of
SWNs. Evidence from models and case studies shows that SWNs may optimize the use of groundwater resources
while providing their sustainability in the long run. Modern groundwater management presents difficult issues;
SWNs provide a potential solution via their creative integration of technology.
Keywords: Remote Sensing, Water Resource Management, Environmental Monitoring, Sensor Networks, Data
Fusion.
Paper ID - 0419

Efficient Sports Training Periodization through Cloud-Based Support Vector Machines

Dr. Barkathulla A, Mothiram Rajasekaran, Dr. P L Kishan Kumar Reddy, G. Manikandan, G.
Bhuvaneswari and R. Priyanka
A unique technique to optimize sports training periodization tactics is proposed in this paper, which utilizes
cloud-based support vector machines (SVMs). Static planning, which is at the heart of many traditional
periodization systems, could not be flexible enough to meet the demands of modern athletes or maintain their
changing performance indicators. Athletes’ biometrics, past performances, environmental variables, and training
procedures are just a few examples of the many data inputs that may be dynamically analyzed with the help of
SVMs hosted in the cloud. Training plans are created for each athlete based on their unique traits and objectives
using machine learning algorithms and real-time processing. Through enhanced flexibility and training regimen
efficiency, our trials show that this technique leads to better performance results than standard periodization
strategies. Athletes and coaches alike may benefit from cloud-based systems’ scalability and accessibility, which
allows for easy incorporation into preexisting training frameworks. It highlights the incredible power of modern
machine learning approaches to transform sports training methods. It opens exciting possibilities for developing
more effective and personalized tactics for athlete development across many athletic disciplines.
Keywords: Performance optimization, Personalized training, Athlete development, Dynamic analysis, Training
regimens, Athlete monitoring.

Paper ID - 0421

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 38

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Smart Gloves for Hand Injury Prevention in Manufacturing Plants Using IoT Sensors
and One-Class SVM Integration
Dr. MD Ashfaqul Hasan, Gurumoorthi Gurulakshmanan, Rajeshkumar Sampathrajan, Bharat
Tidke, C. Srinivasan and R. Kamalakannan
Manufacturing plants require preventative measures to reduce hand injuries, a serious occupational danger. This
research proposes a new approach to this problem by integrating a One-Class Support Vector Machine (SVM) with
Internet of Things (IoT) sensors into smart gloves. The smart gloves monitor the grip strength, the angle of the fingers,
and any dangers in the immediate surroundings. To detect potentially harmful trends in the data gathered from these
sensors, a method called one-Class SVM is used. The technology notifies the worker and any other necessary individuals
immediately upon detection, allowing them to respond quickly and effectively to any possible threats. This method
improves workplace safety and efficiency by combining IoT sensor technology with machine learning algorithms. It
allows manufacturing companies to manage the hazards of hand injuries proactively. The proposed technique might
help make industrial workplaces safer and more efficient by reducing the number of accidents sustained by workers’
hands.
Keywords: Wearable technology, Data analysis, Abnormal pattern detection, Hazardous conditions Risk detection,
Workplace safety, Proactive intervention
Paper ID - 0423

Predictive Analytics for Sales Demand Forecasting using HML Model

Sujithra J, Nithya Shree S and Sathyabama R
Demand forecasting is essential for strategic planning in various industries. Accurate sales forecasts enable better
decisions in inventory management, resource allocation, and financial planning. By using advanced machine learning
algorithms, sales forecasting can be significantly enhanced. The idea of advancement is creating a Demand Forecasting
Software that utilises HML - Hybrid Machine Learning Model (LSTM and XGBoost algorithms) to deliver precise and
actionable sales predictions. This software processes datasets from sources like historical sales data, market trends, and
customer behaviour. LSTM, a specialised recurrent neural network, captures complex temporal correlations, making
it ideal for predicting sales influenced by seasonality, promotions, and other time-dependent factors. XGBoost, excels
at identifying interactions between different dataset features, improving predictive accuracy by recognizing intricate
patterns. The accuracy rate from the HML model is about 92.5%. This empowers firms to optimise sales strategies
and maximise profits by adapting to market changes and continuously learning from new data.
Keywords: Demand Forecasting, Deep Learning, HML, LSTM, XGBoost, Sales, predictions.

Paper ID - 0427

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 39

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT-Driven Green Building Materials and Life Cycle Assessment with Gradient
Boosting Machines
Chitra Sabapathy Ranganathan, A. Arokiaraj Jovith, Dr. P. Selvarani, S. Saravana Kumar, S.
Sujatha and Dr. K. A. Niranjan Kumar
To evaluate the long-term viability of sustainable building materials, this research proposes a new method that
combines the Internet of Things (IoT) with Gradient Boosting Machines (GBM). The need for reliable ways to assess
the environmental impact of construction materials has grown in tandem with the growing relevance of ecological
concerns in industry. Using IoT sensors, our proposed technique tracks material characteristics, energy usage, and
environmental implications over the product’s life cycle in real-time. It analyzes the data obtained to predict the
environmental performance and evaluate the sustainability of green building materials using GBM, an advanced
machine learning technique. It shows that our method effectively assesses the environmental impacts of different
building materials over their life cycles through case studies and empirical validation. This will help architects,
engineers, and legislators make better decisions about sustainable construction. More eco-friendly structures and
infrastructure may be created with the help of an IoT framework, which provides an effective and scalable way to
speed up the adoption of green construction materials.
Keywords: Ecological footprint, Sustainable construction, Environmental performance, Building materials, Life cycle
stages, Sensor technology
Paper ID - 0429

Smart Home Security System with Integrated Motion Detection and Facial
Recognition
Dr. V.R.Kanagavalli, Ms.Janani S and Ms.Madura S
The increasing concerns over theft in urban areas necessitate advanced and reliable security solutions. This paper
presents a smart home security system with integrated motion detection and facial recognition aims at enhancing
urban safety through real-time monitoring and alert mechanisms. Despite the deployment of various security
systems, theft remains a significant issue, resulting in financial and emotional distress. This paper proposes passive
infrared (PIR) sensors and advanced facial recognition technology to detect and identify potential intruders. The
implementation focuses on creating a user-friendly, scalable solution that minimizes energy consumption and ensures
real-time monitoring. The paper underscores the importance of integrating IoT and facial recognition technologies to
develop a sustainable, ethical, and effective theft detection system. The paper concludes with insights into the
development process, challenges faced, and future opportunities for system enhancement to further bolster urban
security.
Keywords: IoT, Theft Detection, Urban Security, PIR Sensors, Facial Recognition, OpenCV, Real-time
Monitoring, Arduino Uno, Smart Surveillance.
Paper ID - 0430

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 40

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Flight Simulation Trainer with LMS using Virtual Reality (VR)

Gomathy G, Kalaiselvi P, Aditya S, Nawin Viswajith B, Navaneetha Krishnan R and Mohamed
Suhail Y
This project explores integrating Virtual Reality (VR) into flight procedure training to enhance pilot education and
proficiency. Traditional methods often lack the immersive experience essential for effective learning. By using VR,
pilots can engage in realistic flight scenarios, practice procedures, and simulate diverse conditions interactively. The
project will develop VR modules focusing on key flight procedures—takeoff, landing, navigation, and emergency
protocols—featuring high-fidelity visuals, realistic cockpits, and interactive elements. Additionally, an AI-driven
Learning Management System (LMS) will track and assess pilot performance, offering insights into their progress.
Comparative studies will evaluate the effectiveness of VR-based training against traditional methods.
Keywords: Flight Simulation, Flight Trainer, Pilot, Interactive, Virtual Reality (VR), Learning Management
System (LMS).
Paper ID - 0439

Real-Time Snoring Monitoring and Intervention with IoT and Long Short-Term
Memory Network
Chitra Sabapathy Ranganathan, Kabaleeswaran S, M Vadivel, S Prabha, C Srinivasan and E
Lavanya
Millions of people across the globe suffer from snoring, a widespread sleep condition that disrupts their everyday
lives and may cause a host of health problems. A promising area for snoring treatment in recent years has been the
combination of machine learning methods with Internet of Things (IoT) sensors. An innovative method for monitoring
and intervening in snoring in real-time using IoT and Long Short-Term Memory (LSTM) networks is presented in
this research. The wearable sensor that tracks snoring patterns while you sleep is an integral part of the proposed
system using IoT capabilities. Before being sent to a central processing unit for analysis, the sensor gathers raw data,
including audio recordings and movement signals. An LSTM network quickly and accurately detects instances of
snoring by processing the collected data. The user receives immediate feedback via a mobile app when they snore,
allowing them to take action to reduce the issue. Extensive testing and verification show that the proposed approach
works in real-time snoring incident detection. Additionally, there is encouraging evidence that combining intervention
measures, such as postural changes or mild vibrations, might improve sleep quality and decrease snoring episodes.
The device is a great tool for those who want to manage their snoring issues successfully since it is noninvasive, has
real-time capabilities and has intervention mechanisms.
Keywords: Sleep patterns, Health technology, Intervention strategies, Wearable technology, Sleep tracking, Sensor
data processing, Health informatics.
Paper ID - 0447

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 41

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Intelligent Robotics for Sorting Clothing and Textile Waste using Cloud-Integrated
Recycling Systems and CNN
Chitra Sabapathy Ranganathan, Kabaleeswaran S, S P Vimal, Dr. V. Kannagi, M. Muthulekshmi
and Dr. M. Meganathan
The textile industry has a significant problem dealing with massive quantities of textile and clothing waste. To
address this, this paper introduces a new method for automating textile waste sorting using Convolutional Neural
Networks (CNNs), cloud-integrated recycling systems, and intelligent robots. Using CNNs, our proposed system
combines advanced robotics with sophisticated computer vision capabilities. Using characteristics like fabric type,
color, and condition, robots can sort textile waste effectively. To further facilitate scalability and flexibility in dealing
with high waste quantities, the system uses cloud computing infrastructure to process data in real time and make
decisions. We lay forth the plan for the system and how it will work, including the robotic sorting mechanism, CNNs
models for item identification, and the cloud-based integration that will make everything run smoothly. It conducts
experimental trials to assess the system’s performance, showing that it efficiently sorts textile waste, reduces human
work, and improves recycling efficiency. The results show great potential in solving the problems of textile waste
management. This might lead to a more sustainable and eco-friendly strategy in the textile sector.
Keywords: Sustainable Fashion, Automation, Waste Sorting, Circular Economy, Waste Reduction, Automated
Sorting.
Paper ID - 0448

Cloud-Driven Autonomous Drones for Dynamic Emergency Medical Response Using

Convolutional Neural Networks
P. Karthikeyani, D. David Neels Ponkumar, S. Hemalatha, M. Tamilselvam, M. Muthulekshmi and
C. Dhanesh
This research presents an innovative method for improving emergency medical response by using autonomous drones
powered by Convolutional Neural Networks (CNNs) and controlled by cloud computing. The proposed system
incorporates advanced technology to speed up help delivery in emergency conditions requiring rapid medical
intervention. Using CNNs, drones can detect and recognize objects in realtime, vital for quickly diagnosing
life-threatening medical emergencies. Drones can make quick decisions and navigate themselves using the vast
computer capacity made available by cloud computing. The system uses dynamic routing algorithms to maximize
drone deployment and respond quickly to changing emergency dynamics. The experimental results demonstrate the
framework’s effectiveness and scalability, highlighting its capacity to transform emergency medical care. The
system’s seamless integration image processing shows an enormous step forward in enhancing emergency response
capabilities. Drones may now effectively provide lifesaving help by navigating complicated situations autonomously,
made possible by the combination of advanced technology. It presents a viable route for improving outcomes in
critical conditions by employing AI-driven drones for dynamic emergency medical intervention.
Keywords: Real-time processing, Dynamic routing algorithms, Crisis management, Healthcare technology, Remote
sensing, Emergency response systems.

Paper ID - 0449

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 42

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Cloud-Enabled Electronic Waste Tracking and Traceability Solutions using Random

Forest Algorithm
Raveendra N Amarnath, V Vijaya Baskar, Dr. V. Kannagi, Dr. S. Kolangiammal, M.
Muthulekshmi and G. S. Gayathri
The environmental effect and intricate electronic waste (e-waste) supply chain make its management a significant
challenge. Better e-waste management is possible with cloud-enabled monitoring and traceability technologies. To
make e-waste tracking and monitoring systems more accurate and efficient, a new method that uses the Random Forest
algorithm is proposed. This system allows tracking ewaste at every stage of its lifespan, from collection to disposal,
using cloud computing, real-time data gathering, and predictive analytics. The Random Forest algorithm forecasts
the location and eventual disposal of e-waste objects depending on ownership, condition, and location. This algorithm
is renowned for its sturdiness and capacity to manage massive datasets. It shows that our proposed method optimizes
e-waste management procedures, improves resource allocation, and minimizes environmental impact via case studies
and simulations. Deploying cloud-enabled e-waste monitoring and traceability systems in real-world settings presents
several challenges, including scalability, security, and practical application issues. It helps to develop sustainable waste
management procedures.
Keywords: Waste management, Supply chain management, Predictive analytics, Environmental impact, Resource
optimization, Real-time data.
Paper ID - 0450

A comprehensive survey on Intrusion Detection Systems in IoT-Enabled Wireless

Sensor Networks: Techniques, Challenges and future directions
Poonguzhali C, Tapas bapu B R, Kalaivani K, Kaviya M, Madhubala S and Sharon Chrysolite C
The growth of Internet of Things (IoT) devices have greatly improved the capabilities and applications of wireless
sensor networks (WSNs). Due to their open and modular design, wireless sensor networks supporting IoT are
vulnerable to various security issues, including but not limited to unauthorized access, data mining, and competitive
cyberattacks. In order to protect these networks from malicious attacks, intrusion detection system (IDS) has
become an important first line of defense. This survey provides a comprehensive review of state-of-the art IDS
techniques designed for IoT wireless sensor networks, focusing on classical, machine learning, and advanced deep
learning. In particular, we report the recent integration of two optimization methods: Generative Adversarial
Networks (GAN), Gorilla Alliance Optimization (GTO), and Coati Optimization Algorithm (COA). Despite
progress, challenges such as limited resources, timely completion, and capacity building remain significant. Through
critical comparative analysis, we identify gaps in current research and suggest future directions, including the use of
new technologies and model engines to improve the efficiency and responsiveness of IDS against security breaches.
This research is designed to provide a valuable resource for researchers and practitioners who want to develop robust
and adaptable IDS systems for IoT-enabled WSNs.
Keywords: Intrusion Detection System (IDS); IoT-enabled Wireless Sensor Networks (WSNs); Deep Learning;
Machine Learning; Security; Optimization Algorithms; Real-time Detection; Anomaly Detection; Federated
Learning; Blockchain; Coati Optimization Algorithm (COA); Gorilla Troops Optimization (GTO).
Paper ID - 0451

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 43

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Real-Time Speed Detection in Sports Events Using Cloud-Sensor Fusion with Support
Vector Machines
E. N. Ganesh, Mothiram Rajasekaran, K. Sangeethalakshmi, S. Murugan, Dr. S. Karthikeyan and
Senthil P
This research presents an innovative approach to monitoring sports events for real-time speed detection using Support
Vector Machines (SVM) and cloud-sensor fusion technologies. The suggested solution takes use of cloud computing
to efficiently process and analyze data by combining feeds from many sensors placed strategically around the sports
stadium. The effectiveness of this method is shown by practical studies carried out in real-life sporting contexts,
particularly in relation to the monitoring of athletes’ speeds. In comparison to more traditional methods, the results
show our approach significantly improves calculation speed and accuracy. A strong option can reliably identify speeds
in the dynamic and fast-paced environment of athletic events is the combination of sensor data in the cloud with
SVM-based classification algorithms. This development shows potential for several uses, such as optimizing training,
real-time event streaming, and performance assessment. It provides a complex but realistic framework for detecting
sports speeds in realtime, which improves viewers’ understanding of athletes’ performances and the quality of the
games they watch.
Keywords: Sports events, Cloud computing, Sensor fusion, Sports technology, Live monitoring, Athletic performance,
Speed measurement.
Paper ID - 0454

Optimizing Harvesting Operations with Cloud-Connected Robots for Fruit and Nut
Crop Yield Enhancement with CNN
Dr. M.Santhanalakshmi, Mothiram Rajasekaran, Dr. G. Kumar, C. Viswanathan, V.
Amirthalingam and Dhivya V
This research introduces a new method for improving the productivity of fruit and nut crops by combining
cloud-connected robots with convolutional neural networks (CNNs) in harvesting. Conventional harvesting
techniques often encounter inefficiencies and workforce scarcity, resulting in poor crop production. Our proposed
method utilizes cloud connected robotic devices with convolutional neural network (CNN) based vision systems to
automate harvesting and maximize production. The CNN models are taught to reliably classify mature fruits and
nuts under different environmental circumstances, allowing precision harvesting operations. Moreover, transmitting
information to the cloud enables immediate data analysis and decision-making, resulting in easier-to-implement
flexible harvesting plans considering variables like weather variations and crop conditions. We analyze the design and
execution of the proposed approach, emphasizing its capacity to transform harvesting methods in farming. By
conducting experiments and analyzing case studies, we provide evidence of the efficacy of our method in enhancing
agricultural productivity, decreasing labor expenses, and enhancing overall operational efficiency. It explores novel
possibilities for implementing sustainable agriculture methods via robots and machine learning in handling crops.
Keywords: Agriculture technology, Real-time data analysis, Robotic harvesting, Automation, Labor efficiency,
Remote sensing.

Paper ID - 0455

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 44

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

AI-Driven Yoga Evolution for Advancing Mindfulness and Well-being through

Cloud-connected Practices
Chitra Sabapathy Ranganathan, Dr. T. Senthil Kumar, E. Sivanantham, Aarthy.S.T, S. Murugan
and M. Nalini
Yoga, a conventional practice focused on mindfulness and overall well-being, is significantly changing with Artificial
Intelligence (AI) and cloud computing technology. This research examines the potential synergies between AI and yoga
to improve mindfulness practices and foster overall wellness in the era of digital technology. AI algorithms produce
personalized yoga routines that adapt to individual requirements, talents, and objectives. The routines are constantly
improved using feedback from users and physiological data gathered from wearable devices, promoting a personalized
and adaptable approach to practicing yoga. The cloud connection allows effortless access to an extensive collection of
yoga materials, such as instructional videos, guided meditations, and community support networks. Using AI-powered
data analytics, individuals may get valuable information about their development, assess their current yoga practice,
identify problem areas, and obtain personalised recommendations for improvement. The conventional practice of yoga
is updated and made more attainable, enabling people to develop mindfulness, cope with stress, and improve their
general well-being in a progressively connected society.
Keywords: Adaptive Practices, Digital Transformation, Wearable Devices, Data Analytics, Guided Meditation,
Remote Wellness.
Paper ID - 0456

Intelligent Defect Detection and Classification in Manufacturing Execution Systems

with IoT
Chitra Sabapathy Ranganathan, Aarthy.S.T, Dr. S. Prabha, C. Srinivasan, M. Rajmohan and
Malarvizhi S
In today’s industrial environment, competitiveness and customer happiness depend on product quality. One
potential way to improve Manufacturing Execution System (MES) fault identification and categorization is to use
Internet of Things (IoT) capabilities in conjunction with sophisticated machine learning algorithms. Using
Convolutional Neural Networks (CNNs) and IoT devices, this research proposes a new method for intelligent flaw
detection and classification. Throughout production, the proposed system’s IoT sensors gather real-time data on
product performance and quality. These sensors take images of the produced parts, which are then input into CNNs
to identify and classify defects automatically. CNNs have a stellar reputation for their ability to analyze images. It
can learn complex patterns and characteristics from simple pixel data, improving their accuracy in defect
classification. It provides real-time defect detection, allowing prompt intervention to fix problems and reduce
production losses. MES’s built-in fault identification and categorization capabilities allow for more efficient
coordination and optimization of production processes. This paper proves the effectiveness and feasibility of the
proposed method in actual production settings using case studies and empirical validation. The data shows an
increase in overall production quality, a decrease in scrap and rework, and an improvement in the precision of defect
identification. It supports producers’ commitment to providing customers with superior-quality goods and equips
them with actionable information for continual process improvement.
Keywords: Product quality, Real-time monitoring, Production optimization, Production efficiency, Automated
inspection, Sensor technology, Anomaly detection
Paper ID - 0458

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 45

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Interactive Simulation Tool for Cloud Resource Allocation Strategies and Performance
Analysis
Devesh Kumar Bandla, Burri Deeleep Sanjay Reddy, Myla Greeshmanth Reddy and Dr. B, Yamini
The ”Interactive Simulation Tool for Cloud Resource Allocation Strategies and Performance Analysis” is to optimize
the efficiency and efficacy of cloud resource management. This application provides a web-based interface that allows
users to simulate different resource allocation algorithms and examine their effects on important performance indicators
such as cost, response time, throughput, and resource utilization. The tool offers a thorough performance study by
using complex techniques such as Least Connections, Weighted Distribution, Round Robin, Priority Scheduling, and
synthetic workloads.. The results underscore its capability to handle diverse cloud environments, from small-scale
setups to large enterprise infrastructures, making it an invaluable asset for optimizing cloud resource utilization and
achieving significant cost savings. Future work will focus on real-time data integration and expanding the range of
strategies to further enhance the tool’s practical utility.
Keywords: Cloud Resource Allocation, Performance Analysis, Resource Management, Dynamic Allocation, Workload
Simulation, Cost Optimization, Response Time, Throughput, Resource Utilization.

Paper ID - 0462

Gender Equality and Women’s Empowerment as Essential to Food Systems and

Economic Justice
Dr R. Monisha, Dr. S. Prabhu, Dr. Harish. M, Dr. RM. Sivagama Sundari, Dr. Indumathi. N and
S. Murugan
The objective of the systematic review and research agenda is to examine the correlation among food systems,
gender equality, and women’s empowerment. The study conducts a comprehensive analysis of empirical evidence to
identify the primary factors contributing to gender disparities in food systems. It assesses the impact of women’s
empowerment initiatives on food security, nutrition, and agricultural output. Augmenting women’s empowerment
via education, resource accessibility, and inclusion in decision-making significantly enhances food security and
nutritional outcomes. The major aim of systematic review is to analyse and consolidate existing knowledge about
the relationship between gender equality, women’s empowerment, and food systems. In addition to this, it intends to
evaluate the impact that efforts aimed at empowering women have had on food security, nutritional outcomes, and
agricultural output. In conclusion, the purpose of this presentation is to provide evidence-based recommendations to
policymakers and practitioners about the incorporation of gender perspectives into food policy and programming.
Gender parity and the empowerment of women are crucial for establishing enduring and robust food systems. The
complex connection between gender dynamics and food systems highlights the need for comprehensive strategies that
tackle structural disparities and use women’s contributions to enhance food security and promote economic progress.
Attaining gender equality in food systems is not just an issue of fairness, but also a practical need for improving
agricultural output and ensuring food security. Women have a crucial role in all aspects of the food system,
including producing, processing, distributing, and consuming food.
Keywords: Women’s empowerment, Nutrition, gender equality, Agricultural Productivity, Systematic Review,
Sustainable Development and Policy Integration.
Paper ID - 0464

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 46

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Mapping the Mind of the Retail Investor: A Comprehensive Analysis of Behavioral

Biases in Individual Investment Decisions
Dr Subalya S, Dr. N. Jayanthi, Dr.R.Tamilmaran and Dr. T. Rekha Kiran Kumar
In this study, the researchers delve into what influences retail investors when they make decisions in the stock
market. The investigation identified some common biases including loss aversion, overconfidence, herding behavior,
representativeness bias and recency effect by surveying 385 respondents who were all retail investors. These biases
significantly affect investment decisions thus often leading to suboptimal financial outcomes. Similarly, it examines
financial literacy levels and finds out that financial literacy leads to reduced levels of certain biases. Additionally,
study look at demographic factors namely age groups, gender, educational backgrounds, annual income and their
influence towards cognitive bias. Results from the study showed that to improve decision making about investing
people should improve financial literacy and be guided by professionals whenever necessary. This research
contributes to behavioral finance literature because it identifies psychological as well as technical facets affecting
individual participants’ mindsets within capital markets thereby providing an avenue for stabilizing them while also
giving tips on smarter investment strategies which could lead us closer towards stability in financial markets world
overt.
Keywords: retail investors, cognitive biases, loss aversion, overconfidence, herding behavior, representativeness bias,
recency effect, financial literacy, behavioral finance, investor psychology.
Paper ID - 0467

A Deep Learning Approach to Sign Language Recognition for Speech-Impaired

Individuals
Deepak T and K. Dinakaran
This research shows that many people with speech impairments struggle to find employment due to concerns about
their ability to communicate with colleagues. To address this challenge, a web application has been created that
integrates computer vision and deep learning techniques. The AI-driven application is trained to recognize various
signs and translate them into text, facilitating understanding among all users. This work will evaluate different models
and select the one with the best performance based on accuracy and minimized loss.
Keywords: Computer vision, deep learning, speech impairments, employed, web application.
Paper ID - 0498

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 47

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Predictive Analytics Techniques for Enhancing Peripheral Vascular Catheter Care

Bundles
Ambiga C and Sasi V
Predictive analytics in peripheral vascular catheter management may improve patient outcomes and reduce
complications. The main goal is to utilise data to predict and reduce catheter hazards. Machine learning algorithms
are used to detect infections, thrombosis, and catheter dislodgement early, allowing for prompt management.
Predictive models provide healthcare practitioners vital information to improve catheter care bundles and enable
more accurate and personalised therapy. This strategy may reduce catheter-related problems and improve patient
safety, making vascular access management more proactive. Thus, predictive analytics improves peripheral vascular
catheterisation clinical procedures and standards. PVCCB Analytics Dataset displays Predictive Model Performance
Metrics 1 has F1 score, accuracy, precision, and AUC are important. Models A to C have accuracy values from 85.40
to 91.0, precision values from 80.2 to 89.1, recall values from 82.8 to 90.2, F1 scores from 81.5 to 89.6, and AUC
values from 0.86 to 0.93. In Risk Stratification Distribution 2, high, low, medium risk levels, 120-250 patients,
Infection incidence varies from 3.1 to 15.2, compliance rate from 70.5 to 95.2, duration from 10.2 to 20.1 days, and
complications from 1.2 to 8.3.
Keywords: Predictive Analytics, Peripheral Vascular Catheter, Machine Learning, Patient Outcomes, Clinical
Decision-Making.
Paper ID - 0500

Evaluating Buzzy Technique’s Effect on Pain and Parental Satisfaction Using

Wilcoxon Signed-Rank Test
Parimaladevi. L and Dr. Tamizharasi. K
The Buzzy approach is tested for its ability to reduce discomfort and improve parental satisfaction during pediatric
needle operations. The Wilcoxon Signed-Rank Test is used to compare pain ratings and parental satisfaction before
and after Buzzy gadget usage. The purpose is to establish whether the Buzzy approach substantially reduces child
pain perception and enhances parental satisfaction, offering a non-pharmacological pain treatment solution in clinical
practice. To determine the Buzzy technique’s statistical significance, pain and satisfaction ratings will be analyzed.
This assessment will help determine how the Buzzy device may be used in pediatric care, which might guide future
pain treatment strategies that priorities patient comfort and parental satisfaction. First BuzzyPainData instance
results for random 5 patients at different timepoints were discussed. Prebuzzy 1 of 5 patients has a value of 17-58,
Postbuzzy 1 of 5 has 24-65, Postbuzzy 2 has 33-74, Postbuzzy 3 has 42-83, and Postbuzzy 4 has 42-81. Data for
random 5 patients at different timepoints was addressed in BuzzySatisfaction instance 2. The value ranges from
13-44 for Prebuzzy 1 of 5 patients, 25-56 for Postbuzzy 1, 37-68 for Postbuzzy 2, 48-79 for Postbuzzy 3, and 10-89 for
Postbuzzy 4.
Keywords: Buzzy Technique, Pain Management, Parental Satisfaction, Wilcoxon Signed-Rank Test, Pediatric
Procedures.
Paper ID - 0501

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 48

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Influence of ICT on the Academic Achievement of Engineering Students and the

Moderating Role of Socio-Economic Status
Dr Krithika. M, Aarthi Suresh, Mr.T Koteswara Rao, S. Murugan and Sowmya R
Information and communication technology, or ICT, encompasses the various kinds of instruments and resources
used for information creation, dissemination, publication, archiving, and management. Concerns regarding the use of
ICT in the education sector have been growing recently among educators. It is still unclear whether ICT improves
instruction or if it is merely propaganda or publicity that has little bearing on students’ academic achievement. This
essay attempts to investigate the connection between students’ academic achievement and their use of ICT. whether
the two variables have a significant relationship and how important socioeconomic status is. Numerous studies have
been conducted with an emphasis on ICT and how it affects academic performance. In attempting to determine the
moderating influence of socioeconomic status, this study is distinctive. Additionally, the study’s primary focus is on
students enrolled in professional engineering programs at various private colleges and universities. The study’s main
conclusion was that there is a positive correlation between ICT use and academic achievement and socioeconomic
status.
Keywords: ICT usage, Academic performance, Socio economic Status, Information Communication, Digital
Competencies, Digital Infrastructure.
Paper ID - 0502

Impact of Gender and Technological Advancement on Employee Productivity in the

Post-Pandemic Era
Sarath Kumar. C, Dr Krithika. M, C. Srinivasan and Sunantha Sri B
The primary aim of this research is to investigate the impact of technological advancements and gender on employee
productivity in the post-pandemic era. This research investigates the relationship between gender inequalities and the
implementation of advanced technology in professional settings by analysing a sample of 294 individuals. Furthermore,
the study investigates the impact of various factors, including internet literacy, acceptance of remote work, and
perceived advantages of technology, on employee productivity. Moreover, the research investigates the psychological
legitimacy of remote work, considering gender-specific psychological differences that could impact productivity results.
The research findings will offer significant insights into the influence of gender dynamics and technology utilization
on productivity levels in modern work settings. These insights hold significant importance for both employers and
employees as they navigate the changing work environment following the pandemic. They assist in the formulation
of strategies aimed at maximizing productivity and cultivating a favourable work atmosphere for individuals of all
genders.
Keywords: Digital technologies, gender disparities, ANOVA, Employee productivity, IT Sector, Pos-pandemic.
Paper ID - 0503

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 49

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Advanced Load Monitoring system for Energy Audits using Programmable Meters
Dakka.Obulesu, K. Shiva Kumar and A.S.S.Murugan
The purpose of this study is to determine the energy consumption of a load in units and to compute the associated
costs in order to improve the efficiency of energy audits. In this study, we compute the power factor, apparent power
(S), reactive power (Q), active power (P), and IRMS of a connected load. Finally, we create a programmable meter
that makes it simple for a layperson to understand how much energy is spent by a specific load at a given moment.
Keywords: energy audit, active power, reactive power, apparent power, power factor.
Paper ID - 0509

Artificial Intelligence and Machine Learning: Developing the Future of Text Analytics
and Natural Language Processing (NLP)
N.K.Senthil Kumar, Rajasekaran.A, K.Saraswathi, Srinadh Unnava, V.Samuthira Pandi and
Shobana D
Natural language processing (NLP) and text analytics are two areas within the fast developing field of machine learning
(ML) and artificial intelligence (AI). A new age of machine language understanding is dawning, and this research delves
deeply into how AI and ML are improving NLP’s capabilities and setting the stage for it. From traditional rule-based
natural language processing systems to the rise of sophisticated ML algorithms capable of learning and adapting
from massive datasets, we follow their evolution. The groundbreaking work done by deep learning models—including
RNNs, LSTMs, and the groundbreaking transformer architecture—is highlighted in particular for the remarkable
improvements in accuracy and efficiency of language tasks. Moreover, the article delves into how pre-trained language
models like BERT and the incorporation of transfer learning have revolutionised the discipline, enabling the lightning-
fast creation of NLP applications in a wide range of domains. In addition, we discuss the difficulties that come with
these developments, such as the importance of privacy in data-driven ML methods, the ethical considerations around
AI’s bias and fairness, and the necessity for stronger and more broadly applicable models. A prospective view on
how AI and ML may transform text analytics and natural language processing is included in the study’s conclusion.
More open and reliable natural language processing (NLP) systems may be possible in the future because to initiatives
like explainable AI and multimodal learning. With the further development of AI and ML comes the possibility of
revolutionising many industries and reshaping human-computer interaction via the processing of natural language at
a high level of sophistication. The paper highlights these enormous opportunities.
Keywords: Multimodal Learning, Ethical AI, Bias and Fairness, Privacy, Data-Driven Approaches, Human-Computer
Interaction.

Paper ID - 0514

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 50

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT- Powered Smart Electric Automobile Ecosystems: Using Intelligent Infrastructure

and Connected Technologies for Innovative Mobility
S.Balaji, Shobana D, V.Samuthira Pandi, K.Makanyadevi, Lakshmi Priya J and C Muralidharan
The automotive industry has been among the most transformed by the Internet of Things (IoT). Intelligent electric
automotive ecosystems, which combine IoT technology with electric cars, will change how we commute, travel, and
interact with our cars. IoT-powered smart electric automotive ecosystems leverage intelligent infrastructure and
linked technologies to offer creative mobility options. Starting with sensors, networking, data analytics, and machine
learning in electric cars, the study examines IoT fundamentals. These ecosystems are supported by intelligent
infrastructure including smart charging stations, vehicle-to-grid (V2G) technology, and enhanced traffic management
systems. car-to-everything (V2X) communication, smartphone apps, and cloud services improve electric car
functionality and user experience, according to the research. Innovative mobility services enabled by IoT-powered
smart electric automotive networks are explored in this research. Automated driving, real-time traffic information,
predictive maintenance, and personalized in-vehicle experiences are examples. They may improve traffic flow,
emissions, road safety, and user convenience, according to the study. IoT implementation in electric automotive
ecosystems is also examined in the study. IT security, data privacy, standardization, and user trust are among these.
Secure data management, transparent data management, and user-centric design help reduce these difficulties,
according to the report. Strategic ramifications for stakeholders in IoT-powered smart electric automotive ecosystem
development and implementation are also discussed. Automakers, technology, government, and energy companies.
The study underlines the need for collaboration to build a conducive regulatory framework, invest in R&D, and
foster collaborations to speed the implementation of these breakthrough technologies. In conclusion, IoT-powered
smart electric automotive ecosystems have the potential to change mobility. With intelligent infrastructure and
connected technologies, these ecosystems enable more sustainable, efficient, and user-friendly transportation
solutions. This research contributes to the automotive industry’s IoT debate and advises policymakers, industry
executives, and technological developers on this developing field’s difficulties and prospects.
Keywords: Real-Time Navigation, Predictive Maintenance, Autonomous Driving Features, Personalized In-Vehicle
Experiences, Cybersecurity Threats, Data Privacy Concerns.

Paper ID - 0520

Precision Medicine with Deep Learning: Enhancing Biomedical Applications with

Superior Data Analysis and Customized Medical Solutions
Srinath Rajagopalan, S.Kavitha, V.Samuthira Pandi, Lakshmi Priya J, M.Shanmuganathan and N.
V. S. Natteshan
The emergence of deep learning technologies has been a major boon to precision medicine, a novel strategy for patient
care that adapts medical interventions to each person’s unique traits. Deep learning’s potential in precision medicine
is the subject of this study, which investigates how to apply sophisticated neural network designs for better data
processing and individualised medical solutions. The study starts by taking a look at where precision medicine is
at the moment, drawing attention to the difficulties of analyzing complicated biomedical data and the importance
of tailored treatment plans. Further exploration of deep learning principles follows, touching on different kinds of
neural networks that excel at processing and understanding biomedical data, including convolutional neural networks
(CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). Proving that deep learning
can improve biomedical applications is a crucial part of the study. Among these applications of deep learning are the
following: the prediction of medication responses, the study of genetic information, and the identification of illness
biomarkers. Case cases are shown in the research where deep learning models have improved diagnostic accuracy
and treatment efficacy by discovering previously invisible patterns in biomedical data. The paper also discusses the
difficulties of using deep learning for precision medicine, including the significance of interpretability and confidence in
AI systems for healthcare, the danger of overfitting models, and the necessity of big, high-quality datasets. In order to
overcome these obstacles, the research delves into methodologies such as regularization methods, data augmentation
approaches, and the building of explainable AI models. In addition, the study highlights how deep learning could help
find novel medications and treatment methods. Deep learning has the potential to optimize clinical trial designs, find
new therapeutic targets, and speed up drug development by evaluating massive volumes of biomedical data. Finally,
the study highlights how deep learning can revolutionize precision medicine. Deep learning might completely transform
healthcare by facilitating improved data analysis and the creation of personalized medical solutions. This, in turn,
could lead to more efficient medical procedures and better patient results. Results from this study shed light on where
deep learning applications in healthcare and biological research are headed and what they can do now.
Keywords: Genetic Information Analysis, Disease Biomarkers Identification, Drug Response Prediction, Medical AI
Systems, Data Augmentation Techniques, Regularization Methods
Paper ID - 0521

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 51

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Wearable Technology and Cloud Computing Integration for Adaptive Cognitive Load
Management
S P Vimal, Palaniraj Rajidurai Parvathy, John Benito Jesudasan Peter, Brinda P, S. Srinivasan
and R Sankar
Nowadays, people must deal with more complex cognitive tasks; hence they need ways to regulate their cognitive
load effectively. One potential solution to the problem of cognitive load is wearable technology, which can track
physiological and behavioral data in real-time. To create adaptive cognitive load management systems, this article
investigates the possibility of integrating wearable devices with cloud computing infrastructure. Wearable devices
may gather data, process it, and analyze it to fine-tune cognitive load treatments in real-time by tapping into the
storage and processing capacity of the cloud. Individuals’ cognitive capacities and the needs of their specific situation
may be considered via the proposed integration, which allows for individualized feedback and treatments. Cloud
analytics also make it easy to aggregate data from several users, which is great for building adaptive algorithms and
getting a better comprehensive understanding of how cognitive load patterns play out on a larger scale. Many fields
might benefit greatly from this integration, such as healthcare, education, and workplace performance enhancement.
To fully use cloud computing and wearable technologies for cognitive load management, however, issues including
data protection, interoperability, and algorithm improvement must be resolved. Human performance and well-being
may be improved, which can be achieved through multidisciplinary cooperation and technological improvements.
Keywords: Real-time monitoring, personalized feedback, Data analytics, Data privacy, Human performance,
Dynamic adjustments.

Paper ID - 0530

Predictive Modeling of Chronic Pain Flares with Cloud-Enabled Wearable Sensors

and Recurrent Neural Networks
M. Vadivel, Kabaleeswaran S, Rajeshkumar Sampathrajan, P. Sivalakshmi, S. Srinivasan and
Anitha G
Healthcare providers continue to face a major challenge in chronic pain treatment, which calls for creative solutions
that can be implemented quickly. It provides a new approach to chronic pain flare prediction by mixing recurrent
neural networks (RNNs) with wearable sensors communicating with the cloud. It created a model that can predict
when pain will worsen by continuously monitoring physiological data, such as skin conductance, heart rate variability,
and movement patterns, gathered by wearable sensors and fed into RNNs. It can accurately forecast the start of
pain flares by using deep learning to examine complicated temporal patterns in sensor data. To provide proactive
and individualized treatment of chronic pain, the cloud-enabled architecture allows for real-time analysis and smooth
connection with current healthcare systems. By allowing preventative treatments and enhancing patients’ quality of
life, The promising results of our validation study demonstrate that our technique may revolutionise the treatment of
chronic pain.
Keywords: Physiological signals, Healthcare technology, Real-time analysis, Proactive management, Personalized
medicine, Health informatics.
Paper ID - 0531

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 52

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT-Enabled Plant Root Monitoring for Improved Water and Nutrient Uptake with
Long Short-Term Memory
Chitra Sabapathy Ranganathan, Kabaleeswaran S, Dr. MD Ashfaqul Hasan, M. Vadivel, S.
Srinivasan and T. Annalakshmi
This research presents a novel method for improving root monitoring in agricultural systems via the use of Long
Short-Term Memory (LSTM) networks and the Internet of Things (IoT). The goal is to improve water and nutrient
absorption. Ineffective resource management and lower crop yields are common results of using antiquated technologies
to track plant roots, which lack both real-time data and accuracy. The proposed IoT system uses sensors to monitor
soil moisture, nutrient levels, and root activity in real time, giving valuable information about plant health and
growth dynamics. LSTM networks, a subset of recurrent neural networks, are trained on the acquired data to
accurately forecast the root’s behavior in the future by capturing its relationships throughout time. With this predictive
capacity, growers can water and fertilize plants precisely according to their individual requirements, making the most
efficient use of resources and reducing waste. With the help of the IoT even massive agricultural operations can
be remotely monitored and controlled, allowing for proactive management and intervention. To improve water and
nutrient absorption efficiency, this in turn increases crop output and helps to save the environment. It provides a
viable alternative for sustainable agriculture.
Keywords: Crop productivity, Resource management, Real-time monitoring, Remote sensing, Precision irrigation,
Fertilization strategies.
Paper ID - 0532

Gesture Recognition and Human-Computer Interaction for User Control Applications

using Embedded Sensors
Dr. Ramakrishnan Raman, Dr. R. Meenakshi, Ramya. R, Dr. Meenakshi Kaul, S. Srinivasan and
A. Prabha
Gesture recognition and human-computer interaction (HCI) have garnered interest recently because they can provide
intuitive and natural interfaces for several applications. This paper proposes real-time gesture detection and HCI
technique using embedded sensors. Our method uses integrated sensors and machine learning techniques to recognize
gestures without extra equipment or complicated setups. Real-time gesture detection is achieved by carefully placing
integrated accelerometers and gyroscopes on the person or surroundings. These sensors send user motions to a
central processing unit. The system employs deep neural networks to analyze sensor data and properly detect
motions. It evaluates our system using numerous user gestures in trials. Our approach accurately recognizes several
motions in real-time. Our system’s accuracy and efficiency outperform existing gesture recognition algorithms. Our
technology also controls virtual reality, interactive gaming, and smart home automation. Real-time gesture detection
makes HCI smooth and immersive. This eliminates traditional input devices and makes interactions more natural.
The suggested approach is portable, inexpensive, and requires little hardware. Embedded sensors may assist
wearable devices, IoT systems, and smart surroundings without extra hardware. Finally, integrated sensors enable
real-time gesture detection and HCI. Our framework perceives motions with accuracy, productivity, and adaptability.
HCI integration allows intuitive and natural interactions in many disciplines. This work advances gesture detection
and HCI technologies to improve user experiences.
Keywords: Real-time Gesture Recognition, Human-Computer Interaction, Embedded Sensors, Virtual Reality,
Gaming.
Paper ID - 0533

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 53

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Integrating MQTT Protocol for Smart Greenhouse Management and Environmental

Control System
Dr. Nelson Kennedy Babu C, Dr. A. Deepa, Dr. S. Sankar, B. Prasad, T. Geetha and Dr.
Praveenkumar S
The proposed system integrates the smart greenhouse management and environmental control system with the MQTT
protocol. The Internet of Things technology has made real-time monitoring and management of greenhouse operations.
Due to its efficiency, scalability, and support for low-power devices, MQTT has become popular with IoT applications.
This research utilizes the MQTT protocol to connect sensors and actuators to the main control unit in a smart
greenhouse. The proposed system optimizes resource utilization, automates procedures, and improves plant growth
and production. MQTT integration reduces network bandwidth utilization, improves message dependability, and
simplifies system design. The control unit can monitor and make decisions in real time using MQTT’s publish-
subscribed method to provide sensor data including humidity, temperature, and intensity of light, pH, and soil moisture.
Web-based MQTT application lets greenhouse manager’s control and monitors the system remotely. This function
allows remote monitoring of environmental factors and control settings, improving greenhouse management flexibility
and responsiveness. Integrating the MQTT protocol into an innovative greenhouse management and environmental
control system improves data transmission, automation, and remote access.
Keywords: Internet of Things, Real-time monitoring, Sensor data, Remote accessibility.
Paper ID - 0534

Cooperative Transmission and Analysing Packet Size For Optimal Routing in Wireless
Network
Mothiram Rajasekaran, Chitra Sabapathy Ranganathan, A. Arokiaraj Jovith, Dr. S. Rajes
Kannan, S. Srinivasan and Dr. R. Radhika
Cooperative transmission fully uses the transmit character of wireless channels and feats time/spatial variety in a
disseminated way. As a result, considerable gains in system capability as well as communication consistency may be
achieved via cooperative communication. This paper proposed Cooperative transmission and analysis packet size for
optimal routing (CTPS) IoT wireless networks. This mechanism will first analyze the varying packet sizes to
determine the best transmission method with the ideal packet size for inter-flow in error-prone wireless networks.
The network’s throughput may be improved with the help of optimal packet size analysis. The next step is to use
QoS criteria to dynamically pick the relay node for the optimum path from sender to receiver. On the other hand,
there has not been nearly enough study done to determine how and to what extent the packets’ size influences a
wireless network’s performance.
Keywords: Cooperative transmission, optimal routing, throughput improvement, packet size analysis, Wireless
Network.
Paper ID - 0535

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 54

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Wireless Sensor Networks for Environmental Management in IoT: Air and Water
Quality Using Decision Tree Algorithm
V. Nandagopal, S. Kalaichelvi, S. Saravana Kumar, K. Manikandaprabhu, S. Srinivasan and A.
Karunakaran
Wireless Sensor Networks (WSNs) are becoming very promising solutions on the Internet of Things (IoT) paradigm
for environmental observing. This study uses Decision Tree (DT) algorithms to examine WSNs for environmental
management, water quality monitoring, and air quality monitoring. WSNs monitor air quality by measuring
temperature, humidity, particle matter, pollutant gases, and atmospheric pressure. WSNs also measure pH, dissolved
oxygen, turbidity, and stream pollution to assess water quality. DT algorithm classifies the acquired data to identify
anomalies and predict the occurrences of pollution. WSNs and DT provide continuous navigation and provide air
and water pollution response at the earliest. This work covers WSNs for environmental monitoring using IoT,
focusing on water quality, and air quality. DT algorithms for data processing provide real-time choices, early
environmental problem detection, and improved resource management.
Keywords: Wireless Sensor Networks, Internet of Things, Decision Tree algorithm, Pollution control.

Paper ID - 0536

Real-Time Monitoring in Healthcare: Addressing Technical and Ethical Issues with

Digital Twin Technology
V. T. Vithya and P. Valarmathie
With the use of dynamic virtual reproductions of physical systems, Digital Twin technology is quickly becoming a
game-changing tool in healthcare that allows for improved real-time patient health monitoring. This work examines
the use of digital twins for real-time healthcare monitoring, emphasizing the ethical and technical issues. We analyze
the core technical issues, including data integration, system scalability, and interoperability, highlighting how these
challenges impact the effectiveness of Digital Twin systems. Additionally, we address critical ethical concerns such
as data privacy, informed consent, and equity in access, emphasizing the importance of ethical considerations in
deploying these technologies. This article offers a thorough overview of how Digital Twin technology might be utilized
to enhance patient care while navigating the related issues through an examination of existing methods, case studies,
and developing trends. The findings offer insights and recommendations for advancing real-time monitoring capabilities
in healthcare, ensuring that technological innovations are aligned with ethical standards and contribute positively to
patient outcomes.
Keywords: Digital Twin, real-time monitoring, healthcare technology, virtual replicas, data integration, system
scalability, interoperability, data privacy, informed consent, equity in access, ethical considerations, patient care, case
studies, emerging trends, technological innovations.
Paper ID - 0538

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 55

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Patient-Centered Care in the Metaverse: Augmented Reality and Virtual Reality for
Enhanced Surgical Experiences
Aparna P and Valarmathie P
Patient-centered care will undoubtedly undergo a transformation with the introduction of the Metaverse and
Augmented and Virtual Reality (AR/VR) technology, especially in the area of surgical experiences. This study
investigates the use of AR and VR in the Metaverse to build interactive, personalized, and immersive surgical
settings that are tailored to each patient’s specific requirements. These technologies can boost patient participation,
lower anxiety, and improve overall surgical results by replicating pre-operative procedures, offering real-time
guidance during surgery, and easing post-operative care. Additionally, the study looks at how AR and VR might
improve patient-provider communication, leading to more educated choices and customized treatment regimens. The
advantages for patient-centered care are significant, even while the integration of these technologies into patient care
comes with certain challenges, such as cost, accessibility, and the requirement for strong data security measures.
According to this research, surgery’s future is in the Metaverse, where AR and VR will significantly alter the patient
experience and eventually result in more efficient and compassionate medical care.
Keywords: Metaverse, Patient-Centered Care, Augmented Reality (AR), Virtual Reality (VR), Surgical
Experiences, Immersive Healthcare.
Paper ID - 0541

Efficient Energy Monitoring in Home Appliances using IoT

Thangapalani L, Lieo Ambrouse E, Karthikeyan M C and Kavin Aarya A.R
As our homes use more and more energy, finding ways to optimize this consumption has become crucial for both saving
money and protecting the environment. IoT-based Smart Energy Management Systems (SEMS) offer an innovative
solution by bringing together advanced sensor technologies, data analytics, and machine learning algorithms to monitor
and manage energy use efficiently. This paper introduces a comprehensive framework for SEMS, designed to tackle
the issue of energy inefficiency in households. By employing components like the ESP32 microcontroller, current
transformers (CT), voltage sensors, optical sensors, and temperature sensors, the system can collect and process
data in real-time. Machine learning models then analyse this data to predict energy usage patterns and provide
personalized tips for saving energy. With an easy-to- use interface available on mobile and web platforms, users can
easily access their energy consumption data, make informed decisions, and actively manage their energy use. By
promoting sustainability, lowering costs, and encouraging user involvement in energy conservation, SEMS pave the
way for smarter, more efficient homes.
Keywords: IoT, Smart Energy Management Systems, ESP32 microcontroller, data analytics, machine learning
algorithms, energy consumption, user-friendly interface.
Paper ID - 0550

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 56

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Improving The Quality Of User Experience In The Context Of An Online Car Rental
System Services With The Use Of Real Time Data Analytic
Mithun Kumar S.R and Ardly Melba Reena .B
In this paper, we present the development of an online car rental system in order to achieve avoiding ease and efficiency
concept in a real-time transaction based offer published Every Time car reservation services. The system has been
developed in the form of an web app employing a most modern tech stack using React. Back-end — Node.js, front-
end/ js and CSS js and Express. Backend: node js, Database Management: AWS RDS My sql. The main deliverers
of this project are user-friendly interface, cars availability & booking in real-time and seamless payments. This way,
users can quickly collect car information, book online and follow special features for their in-app rentals. The backend
architecture features horizontally scalable and reliable data processing, whereas the frontend offers a seamless user
experience.
Keywords: React JS, Css, Node JS, Express JS, Database.
Paper ID - 0551

Dual-Module Blood Bank Web System: The Donor and the Receiver Integration
Baranibabu S and Nizmi shaik
The purpose of this paper is to minimize the steps inclusive in blood donation process. It focuses on the practice
of blood donation and comes up with an Android application developed to enable patients get a convenient manner
of donating blood. The application is designed from the patients and donors point of view. It also has a validation
for the new and old clients, with open registration and login in new and old client’s selections options, to check and
confirm personal details as well as locate near by donation centres. Blood is required in almost all surgeries performed
in the current world, and the requirement of blood is continually rising due to new medical technologies that are being
developed. But things like scarcity and poor supply are still a problem to date. Driving people to make a donation is
not enough, when there is no well-coordinated blood management program in the country[1].
Keywords: Blood donation management, Donors, Android application, Donation locations.

Paper ID - 0555

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 57

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Enhancing Reading Comprehension for Mobile Users: A Flutter-Based Application

with ChatGPT API for Instant Word Meaning Retrieval
G. Abay Ragav and K. Dinakaran
This research work introduces a mobile application known as the “Comprehensive Article Reader,” built with Flutter
and interfacing with the ChatGPT API. The app has additional features such as retrieving the meaning of any word
in an instant just by holding down the word. Looking up a word’s meaning through conventional means can be
rather a tedious affair and disrupts the reading process. That is why this app is designed to help you solve this issue
by giving you a fast and simple method to find out the meaning of unknown words. The application was designed
and intended to be easy to use, for as many different kinds of users as possible. They show that the benefits of this
managed vocabulary-only reading app include significant gains in vocabulary knowledge and reading achievement.
More improvements could be the expansion of other languages and other enhancements like offering synonyms in real
time.
Keywords: Flutter, ChatGPT API, Mobile Application, Word Meaning Retrieval, Reading Comprehension,
Vocabulary Enhancement, Firebase.

Paper ID - 0557

Feast Finder - A Recipe Application

Mohammed Afeef Abdulla and Mangaleswaran M
The focus for this work is to develop a website in which people can explore multiple cuisines and get access to the
recipes on the website. Along with that, I have integrated a Chabot for the user’s queries. When people find it
difficult to find their recipes with the health issues they have we will provide them with a personal nutritionist for
their problem by filling out a simple form which is connected to a database.
Keywords: Chabot, Web application, NLP, Firebase.
Paper ID - 0558

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 58

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Intuitive Online Table Booking System for Restaurants

Chetan Annamalai M and Muthukumar G
The aim of this project is to design and develop a user-friendly website for restaurant table reservations. The website
facilitates the customers to browse available tables, select preferred seating arrangements, and make reservations.
Keywords: Table Reservation System, Web Application Development, Online Reservations, Table Availability,
Personalized Dining Experience.
Paper ID - 0559

Weather Application
Loganathan C and Muthukumar G
The goal of this project is to build a fully-featured weather app, that tells the user exactly what they need & when it
matters most. It will take advantage of modern web technologies such as html, css and JavaScript to provide a nice
user experience which can be accessible from every device on almost every platform. The weather app also provides
real-time forecasts, interactive maps, customizable alerts and location-based services. The user will be shown with a
search option, where by clicking on it they can simply enter the name of city or zip code and also this application
allows location services to fetch automatically. Weather app can pull weather forecast from notable reliable api servers
like Open Weather Map and Weatherstack making sure your forecasts are accurate and true.
Keywords: Weather Forecasting, Visual Studio Code, API.
Paper ID - 0560

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 59

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Test Hub using PHP

Bhagya Sree S and Nizmi shaik
This paper presents a method for creating effective assessments to measure student learning. This project introduces
the design and implementation of an online system to provide effective and efficient assessment to students. After
each test is completed, the system provides instant feedback by displaying the score. The template combines powerful
back-end functionality with an intuitive front-end interface to provide a seamless user experience. The system uses
Web technologies such as HTML, CSS, and JavaScript, and back-end systems such as PHP to achieve high-quality data
and external functionality. Overall, the program aims to provide students with effective user reviews that demonstrate
their knowledge and understanding of various topics and subjects.
Keywords: Online Examination System, Online Exam Web Application, PHP, MYSQL, Test Hub using PHP, Test
Hub
Paper ID - 0561

Trip Guidance with Recommendation and Shortest Route Using AI Algorithm

EZHILARASI A and SEVANTHI P
The tour guidance app enhances travel with personalized recommendations based on travel month, weather, and
seasonal attractions. It provides detailed insights into each location’s history, culture, and landmarks, enriching user
experiences. The app also promotes sustainable tourism, supports local economies, and facilitates cultural exchange.
By integrating advanced technology, it empowers responsible and impactful travel.
Keywords: Machine learning, HTML, CSS, Flask web application.
Paper ID - 0562

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 60

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Impact Of Yogic Practices And Skill Development On Physiological And Psychological

Metrics In Kabaddi Players Using Advanced Technology
Dr. C. Kala, Dr. C. Selvaraj and Dr. P. Ramesh
Our goal is to use cutting-edge technology to study how yogic practices and skill development affect physiological
and psychological measures in kabaddi players at the national level. Examining how these behaviors and abilities are
improved by using current technology tools is one of the objectives. Measuring how much better players feel physically,
emotionally, and mentally is observed. Optimal player health and performance may be achieved via tailored treatments,
and modern technology allows for accurate monitoring and study of these benefits. Results could provide light on
how to better coach players and formulate plans for their growth. This study’s objective was to ascertain how The
Influence of Yogic Practices and Skill Development on a Few Physiological and Psychological Parameters in National
Level Kabaddi Player the 20 female kabaddi players and the 10 female kabaddi players were chosen from Vinayaka
missions kirupanathavariyar Engineering College and Physical education is offered at Vinayaka Missions College in
Salem. They were between the ages of 18 and 22, according to college statistics. Thirty volunteers were chosen at
random, separated into three equal groups (two experimental and one Control), and then randomly assigned to each
group. Consequently, there were 10 participants in each group.
Keywords: Physiological, Psychological, and Kabaddi, Sports, Yoga.
Paper ID - 0563

MapMed: A study on Mapbox tools and API Integration for locating nearby Health
Facilities
Aayushi Iyengar, Vertika Singh and Dr. S Saravanan
This study delves into the Health Facility Locator web application, which leverages state-of-the-art geolocation
technology to efficiently link users with nearby healthcare facilities. Motivated by the escalating demand for prompt
medical attention and the challenges individuals face in identifying nearby healthcare facilities during emergencies,
the project strives to bridge the gap between people and medical services across diverse urban and rural landscapes.
By embracing dynamic innovation, the platform tackles the urgent challenge of enhancing healthcare accessibility,
with a focus on reducing response time in case of emergencies and bolstering the well-being of the community.
Through its customizable features and user-friendly interface, the app serves as a crucial tool in facilitating timely
and informed healthcare decisions, ultimately contributing to improved health outcomes and greater resilience within
communities. This study explores creation of maps utilizing open-source platforms like Mapbox, Leaflet, OSM, etc.
it also uses Java script for interactivity, CartoCSS for map design, HTML for layer integration, react framework for
responsiveness and sleek design, and data in the format of a Geojson file. Its seamless integration of technology and
healthcare services marks a significant step towards addressing the complex demands of modern healthcare systems,
fostering a more responsive and inclusive approach to healthcare provision.
Keywords: Mapbox, Web Development, Graham’s Scan, Health facilities, Hospitals, TOPSIS.
Paper ID - 0565

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 61

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Resume Parsing Matching Talent Recruitment Platform

Mr. P. Senthil, E. Arun, B. Lingeswaran, M. Midun, L. NaveenNarayanan and V. Saravanan
Finding a rewarding gift is a truly important task that is regarded as one of the main conditioning factors for people.
The model we have suggested is principally to prize the details and statistics from the capsule and ranking the capsule
grounded on the preference of the company associated and its conditions using the Natural Language Processing
(NLP) ways. Hiring is a simple and efficient procedure when the capsule is parsed and ranked. Colorful nanosecond
data are contained in a capsule, and any reputable parser must extract these data, which include things like address,
design, education, and experience. First, we will create a job gate where employees and candidates can upload their
resumes for any open positions. Then, using natural language processing, we will parse the required data to create
an information-rich structured capsule. Additionally, resumes will be ranked based on the skills that the company is
looking for workers chops in the handed capsule.
Keywords: Resumes, Natural Language Processing, Information Extraction, Skill Set, Prioritization.
Paper ID - 0570

AI Powered Book Recommendation for Online Shopping

Mugilan N V and K Dinakaran
E-commerce is fast gaining ground as an accepted and used business paradigm. More and more business houses are
implementing web sites providing functionality for performing commercial transactions over the web. It is reasonable
to say that the process of shopping on the web is becoming common place .‘Customer is our god’ mainly this website
is based on this formula. After choosing books he bought into the Paypal process like VISA or MASTER credit cards
or any Debit cards are accepted on this website. Customer is happily shopping at his rest place. once a customer
enters with his own username and password, at that time automatically one shopping cart will be created, once the
user selects a book it will add to cart. incase the user thinks the selected book is not useful for me, then deletes that
book from the shopping cart. Customer selected some book, but in his credit or debit card haven’t that much balance,
then he was logout from the website, the selected books are stored at cart with specific users with his allotted carts,
after somedays he bought those books then automatically deleted from the cart.
Keywords: VISA, AI, E- Commerce, DIY.
Paper ID - 0582

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 62

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

An Analysis of Awareness Regarding the Impact of the National Education Policy

(NEP) 2020 Among Teachers and Students in Higher Education Institutions for
Sustainable Growth
Arjita Jain, Sandeep Bhanot, Kiran Kakade, Kasturi Naik and Dhananjay Mankar
The 2020 National Education Policy (NEP) aims to transform the Indian education system by supporting outcome-
based education for sustained advancement. This research investigates the understanding, perception, and satisfaction
levels of professors and students at different Higher Education Institutions (HEIs) on NEP 2020 for sustainable
development. Using a mixed-method approach, 309 students and 56 teachers from various disciplines completed
standardised questionnaires scored on a 1-5 scale. An analysis indicated high levels of awareness, with 96.4% of
instructors and 74.8% of pupils acquainted with NEP 2020. However, just 57% reported institutional attempts to
educate about the policy, which is inadequate to achieve major change. Teachers in the Commerce and Management
professions reported greater levels of satisfaction than those in other disciplines. The results indicate a favourable
attitude towards NEP 2020, but emphasise the need for greater institutional measures to successfully execute its
recommendations and boost Indian universities’ worldwide status for sustainable development.
Keywords: Sustainability, Higher Education Institutes, New Education Policy 2020, Students, Teachers.
Paper ID - 0603

Generation Z and the Sustainable Paradigm Shift: A Perceptual Study of Personal

and Organizational Values in Mumbai’s HEIs
DrSandeep Bhanot, Arjita Jain, Dhananjay Mankar, Kiran Kakade and Sushma Patil
This study explores the changing values of Generation Z students in higher education institutions in Mumbai, with a
specific focus on how sustainability is being incorporated into their personal and organisational values. The
examination centres around four fundamental categories: family, societal, civic, and work ethic principles. Data was
collected from a sample of 503 students across three distinct age groups using a 5-point Likert scale. The findings
suggest that while there is a significant focus on preserving strong familial bonds and promoting equal chances, there
is a growing concern regarding the treatment of women and children, along with an enhanced acknowledgement of
the significance of sustainability. Generation Z highly values fascinating and difficult jobs, autonomy, a healthy
integration of work and personal life, and environmentally sensitive practices in their professional pursuits. This
study emphasises the significant significance of sustainability in shaping the beliefs and behaviours of the next
generation, with significant implications for both society and the workplace.
Keywords: Students, Higher Education Institutes, Values, Family Values, Social Values, Civic Values, Work Ethic
Values
Paper ID - 0604

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 63

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Sustainable Volunteering among Generation Z: An Attitudinal Survey

Sandeep Bhanot, Arjita Jain, Pankaj Natu, Kiran Kakade and Dhananjay Mankar
This research examines the beliefs, motivations, and attitudes of Generation Z in relation to sustainable volunteering.
The research underscores the vital importance of Gen Z, who make up a substantial section of the world’s population,
in tackling societal issues through volunteerism, with a strong focus on community involvement. The study utilises
a combination of qualitative and quantitative approaches, namely conducting in-depth interviews with 20 individuals
from the Gen Z generation to identify motivational variables, as well as administering a structured questionnaire to
312 participants. The study centres on four primary motivations: professional advancement, self-consciousness, the
aspiration for well-being, and making a positive impact on society. The study investigates the connections between
motives, attitudes, and job performance by applying the theory of planned behaviour. The structural model exhibited
a satisfactory fit, as all indices met the required parameters, hence confirming the robust associations between motives,
attitudes, and performance in Gen Z volunteers.
Keywords: Student Volunteering, Generation Z, Attitude, Motives, Job Performance.
Paper ID - 0605

Operational Strategies and Leadership in Industry 4.0: Impact on Customer

Experience (CX) and Sustainable Development
Dr. Jayant Brahmane, Dr. Kiran Kakade, Brig (Dr) Rajiv Divekar, Dr. Arjita Jain, Prof. Subhash
Yadav and Dr Shilpa Shinde
This study examines the crucial significance of Industry 4.0’s operational characteristics in promoting corporate
performance in rapidly changing marketplaces. Industry 4.0 is linked to increased productivity, enhanced product
quality, and efficient resource utilization, which are essential for sustainable growth. The research highlights the
importance of operational strategy and leadership in shaping customer experiences during product development. As
current technologies saturate the market, innovation becomes crucial to generating new products. Industry 4.0
necessitates new strategies, leadership, and operational capabilities to foster innovation and sustainable development.
This empirical study, based on primary data from industry experts, identifies key variables related to the operational
aspects of Industry 4.0 and sustainability.
Keywords: Sustainability, Strategies, Industry 4.0, Leadership, technologies, Customer experience (CX)
Paper ID - 0606

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 64

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

The Role of Education for Sustainable Development in India: Challenges and Effective
Implementation Strategies
Dr. Kiran Kakade, Dr Shilpa Shinde, Brig (Dr) Rajiv Divekar, Prof. Subhash Yadav, Dr. Arjita
Jain and Dr. Jayant Brahmane
Education for Sustainable Development (ESD) is indispensable in India for the purpose of confronting the nation’s
economic, social, and environmental obstacles. ESD equips individuals with the necessary knowledge, skills, and
values to promote sustainability. The National Education Policy 2020 underscores the importance of incorporating
environmental education into all levels of formal education, with a particular emphasis on teaching training, experiential
learning, and the promotion of sustainable practices. Inadequate infrastructure, funding, teacher preparation, and
socioeconomic disparities, however, impede the effective implementation of ESD. An approach that is multifaceted,
including curriculum reform, public awareness campaigns, and community engagement, is required to surmount these
challenges. In the study, the factor analysis emphasized the importance of important variables such as public awareness,
community engagement, and research in the advancement of sustainability efforts. Creating a more inclusive and
sustainable future in India is possible by prioritizing ESD, which will equip citizens to address current and future
sustainability issues.
Keywords: Sustainable Development, Education for Sustainable Development (ESD), Green Education, Inclusive
Growth, National Education Policy (NEP) 2020.
Paper ID - 0607

The Role of Emotional Intelligence and Transformational Leadership in Fostering

Sustainable Leadership in Higher Education
Dr. Kiran Kakade, Dr Shilpa Shinde, Dr. Pravin Kumar Bhoyar, Prof. Subhash Yadav, Dr. Jayant
Brahmane and Prof. Anjali M. Kulkarni
The study investigates the correlation between transformational leadership and emotional intelligence (EI) in higher
education, focusing on their impact on sustainability leadership. Effective leadership in academic environments is
contingent upon emotional intelligence, which is characterised by self-awareness, empathy, and emotional management.
This ability impacts both personal and organisational success. Transformational leadership, which fosters motivation,
commitment, and innovation, is highlighted as a key driver in promoting sustainability by enhancing organisational
culture and long-term outcomes. The research investigates the correlation between EI and transformational leadership,
aiming to provide insights into how emotionally intelligent leaders can contribute to sustainable practices in higher
education. Using structural equation modelling (SEM), the study shows how emotional intelligence (EI) has a big
effect on how leaders act, which in turn leads to sustainability, good management, and the overall success of the
institution. This research underscores the significance of combining leadership strategies with emotional intelligence
to foster a sustainable and resilient academic environment.
Keywords: Emotional Intelligence (EI), Sustainability, Leadership, Empathy, Self-awareness.
Paper ID - 0608

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 65

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Analyzing Different Strategies Launched For Solving Food Insecurity Problems in

India And Tamilnadu
A. Sindhuja and Dr. B. Venugopal
The United Nations Organization and other governments of several countries still face food insecurity problems.
Tamilnadu state and India are also facing the same problem, which impacts millions of people and worsens socio-
economic inequalities. Before implementing various strategies, it is essential to understand the existing methods
and their limitations. This paper provides a detailed survey on various national and state-level surveys in India and
Tamil Nadu. It analyzes strategies like distribution, food security, and particular state programs, including government
actions and community-based involvements. The focus, effort, reach, % of the influence, and limitation of the strategies
are analyzed to rectify the problems to achieve Sustainable Development Goal 2, No Hunger in 2030. It explores the
quantitative data, strategy, and output of the strategies to improve the food security performance measures. The
findings and suggestions are summarized to create India, particularly Tamilnadu, as a sustainable region globally.
Keywords: SDG-2, No-Hunger, Food Security, Strategies India, Tamilnadu, Agenda-2030.
Paper ID - 0609

Demographic Influence On It Workers’ Work-Life Balance During Covid-19 Pandemic

Bharathi Kannamma. V and Dr Krithika. M
This research examines how demographic characteristics affect IT professionals’ work-life balance to illuminate their
challenges and opportunities. To better understand the experiences of IT workers during this critical period, it is
helpful to examine how various demographic groups dealt with the demands of the IT industry and the circumstances
caused by the pandemic. There has been a lot of talk about how the nature of labour has changed since the epidemic,
and our study contributes to that conversation. It gives us important insight into the need to tackle disparities in
work-life balance across different demographic groups to overcome future challenges and seize future opportunities.
Keywords: Demographic factors, work-life balance, IT professionals, pandemic, Age, Gender, Work Experience.
Paper ID - 0611

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 66

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Understanding the Dynamics of Job Satisfaction, Personal Factors, and Retention in

Seafaring
Dr. I. Shanmugapriya, Aarthi Suresh, Dr. Krithika. M, Dr S Arul Kumar,S. Murugan and K.
Revathik
All-level sailors’ work satisfaction and turnover are examined in this research. This research seeks to identify seafarer
work satisfaction and retention variables. Seafarers’ quality and retention must improve to support the maritime sector.
This research examined how individual traits affect work satisfaction and retention. A total of two hundred employees
participated in this study, and a non-probabilistic convenient random sampling method was employed to choose the
samples. A methodical and organized questionnaire was utilized to gather the primary data. Additional sources of
data, such as articles, journals, and websites, were utilized to gather information. The percentile analysis was employed
to examine the distribution of demographic variables, while Pearson’s Correlation was utilized to analyze, deduce, and
examine the hypothesis regarding the categorical data comprising dependent and independent variables. Consequently,
this methodology was adhered to using SPSS-21. A positive and statistically significant correlation has been identified
between employee retention and job satisfaction and variables such as personal factors. A reciprocal relationship exists
among the variables PFT (personal factor), JS (job satisfaction), and R(retention). This study exclusively comprises
responses from 200 seafarers. As result of the study, that personal factors influence the employment satisfaction of
seafarers, which subsequently affects their retention. Thus, improving employment satisfaction among seafarers is
essential to avoid low retention rates in the marine industry.
Keywords: Retention, Personal factors, Job satisfaction, Seafarers, Correlation.

Paper ID - 00612

IMU Based Inference System for Vehicles

Vikram Adithya Anand, Dr R Lathamanju and Dr V Arulkumar
Roadways are the most commonly used channel of transport. Statistically, most transport related deaths are seen on
roadways. This study is about an IMU based inferencing system that collects data through an inertial measurement
unit and a GPS. The data is used to generate an inference. The IMU data (ie) the accelerometric and gyroscopic data
are processed to generate tilt sensitive pitch and roll angles which are processed along with corresponding GPS data
to survey a section of a roadway and assign it a suitable score based on the ease of travel in the corresponding channel.
The scores generated are in comparison to other roads. Through data from multiple nodes which have employed the
same channel, a comparative score is generated which can be used for route planning by businesses and civilians alike.
Keywords: IMU, Road Quality, Route Planning, Accident Prevention, Cloud inferencing.

Paper ID - 0617

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 67

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Underwater Image Enhancement and Object Recognition Using CNN Algorithm

Vijayalakshmi. P, Seetharaman. M and Praveen. E
The research aims to improve underwater image quality due to the scattering and absorption of light, resulting in poor
image quality and reduced visibility. In this study, we propose a novel approach for underwater image enhancement
and object recognition using Convolutional Neural Network, or CNN algorithms with the integration of a median
filter, implemented in MATLAB. The median filter serves as a preprocessing step to reduce noise and enhance image
clarity, while the CNN algorithm is employed for object recognition in the enhanced images. Experimental results
demonstrate significant improvements in image quality and object recognition accuracy compared to existing methods.
The proposed framework offers a promising solution for underwater applications such as marine biology, underwater
surveillance, and underwater robotics, where clear imaging and accurate object detection are essential.
Keywords: Underwater Image enhancement, object recognition, Median filter, convolution neural network.
Paper ID - 0618

Use Of 4 Enterprise Technologies In The Food Supply Chain To Enhance Visibility

And Streamline Operations
Santosh M, Ayshwarya R, Janane S and Revathy S
From farm to fork, food can taint or become dangerous at any stage. Concerns over timely delivery and food safety
are shared by stakeholders and customers. Thus, a visible food supply chain (FSC) is required, and this can be
achieved using cutting-edge technologies. Nevertheless, the implementation of these technologies is expensive and
time-consuming. Thus, for the parties participating in the FSC, operational effectiveness—which accounts for cost,
time, and waste—has taken precedence. The goal of this study is to assess the literature using content analysis in order
to determine how Industry 4 technology affect production chain’s distinguishability and operative effectiveness. It is
discovered that the FSC views blockchain, the IoT and RFID is having a lot of promise. While other technologies like
robots, edge computing, and artificial intelligence can be very helpful to the FSC, they are not currently implemented
in a way that is effective or feasible. The implementation of a technological cost-sharing scheme by supply chain
organizations is also explored in this study. Our analysis covers sixteen new Industry 4 technologies and illustrates
how they affect cost-sharing arrangements and the FSC. The results of this study help businesses choose the best
technologies for their supply chain and share technological costs. Lastly, a conceptual framework is put forth to
demonstrate how Industry 4 technology might be used in the future to increase distinguishability and operative
effectiveness in the FSC.
Keywords: Food supply chain (FSC), Industry 4(IoT, cloud computing, Block chain, RFID) Content analysis,
Blockchain Integration, Cost-Sharing Mechanism, Simulation and Comparative Analysis, Operational effectiveness,
Distinguishability.
Paper ID - 0619

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 68

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Real-Time Asset Tracking with IoT Core API and Lora Technology using Multiple
Sensors
Dr.Lathamanju R, Kishore G, Venkatesh Prasath J and Krishnavel K
This project aims to create a robust real-time asset tracking system leveraging IoT and LoRa technology. By
harnessing a suite of sensors—GPS for precise location tracking, accelerometers to detect speed and movement
changes, gyroscopes for orientation and rotation data, alongside temperature and humidity sensors for environmental
monitoring—the system collects comprehensive data from assets. This information is processed through
microcontrollers and transmitted via LoRa transmitters for efficient long-range communication. Upon reception, the
LoRa receiver forwards this data to another microcontroller, connecting to both an display and an IoT platform.
This setup allows for immediate visualization of asset information, empowering users to monitor and manage assets
effectively. The system’s multifaceted sensor array and seamless communication architecture promise enhanced asset
security, streamlined logistics, and the ability to respond proactively to environmental variations, ultimately
optimizing asset management and ensuring the integrity of sensitive goods or environments.
Keywords: IOT (internet of things), LoRa(long-range), Asset Tracking.

Paper ID - 0631

Secure E-Voting Technology System Using Blockchain And Authentication Via Face
Recognition
M.P. Kumar, Dr.R.G.Kumar, R. G. Santhi, Sampathi Sai Vamsi, Chellu Mani Ratnam and K.
Muhammad Ashiq
Unprecedented for this purpose, an online voting system is being proposed as a ballot framework [1] for Indian political
decisions. Since a high security secret word is verified for each citizen before the vote is accepted in the Political Race
Commission of India’s basic data collection, our suggested solution offers a higher level of protection. The elector
can verify whether their vote was cast for the appropriate rival party, which is an added feature of the model. An
individual can vote in this approach from both their preferred location and beyond their dispersed supporters. In the
proposed system the counting of the votes will be done consequently, in this manner saving an immense time and
empowering Political decision Magistrate of India to report the outcome inside an extremely brief period. Encoding
the democratic information with the SHA256 calculation fills security needs.
Keywords: SHA256, OTP, LBPH, PC, UML.
Paper ID - 0634

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 69

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Harnessing AI for Robust Deep Fake Detection in Image

B. Pavan Kumar, Dr.R.Elankavi, K. Kesava, M. Krishna Dinesh, K. Susmitha and N Pallavi
In the realm of modern computer vision, the emergence of powerful tools has enabled the creation of increasingly
convincing deepfake content. Leveraging the capabilities of Generative Adversarial Networks, these advanced
techniques manipulate various forms of media, including images, audio, and videos, flawlessly blending them into
different contexts. Consequently, Deepfake technology poses a significant threat to the authenticity and
trustworthiness of visual content on the internet. The deep learning-based method for deepfake detection is
presented in this project. In order to identify trends and anomalies linked to modified content, we train a neural
network on a dataset of actual and deepfake images. Our model provides a reliable and efficient method for detecting
deepfakes by utilizing the capabilities of deep neural networks to automatically extract pertinent characteristics and
generate precise predictions.
Keywords: Artificial Intelligence, Deep Fake Detection, Image Forensics, Convolutional Neural Networks, VGG16,
MobileNet, Deep Learning, Image Manipulation, Computer Vision, Authentication.
Paper ID - 0639

Enhancing Dental X-Ray Segmentation using Deep Learning

B. Sarvesan, Dr.J.Sridhar, S Soumya, Vaddi Tejaswini, Gopi Yamini and Shasidhar Avula
Dental X-ray image analysis plays a crucial role in diagnosing periodontal diseases, which significantly impact oral
health. In this approach, we propose a hybrid deep learning Model for classifying dental X-ray images into periodontal
and non-periodontal categories. Our method combines the strengths of VGG16 and MobileNet architectures, leveraging
VGG’s robust feature extraction capabilities and MobileNet’s efficiency. The hybrid model is trained end-to-end, fine-
tuning the convolutional base of VGG while preserving its early layers. We evaluate the model’s performance on a
dataset comprising periodontal and non-periodontal images, achieving competitive results in terms of accuracy and
generalization. Our approach demonstrates promising potential for assisting dental professionals in early detection
and classification of periodontal diseases, contributing to improved patient care and treatment planning in dental
healthcare.
Keywords: Dental X-ray images, Deep Learning, image Segmentation, Hybrid Algorithm(VGG16 and MobileNet).
Paper ID - 0640

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 70

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Accident Detection on Roads and Tunnels using Deep Learning Technique

N. Babu, R. Sandhya, N.G. Saikiran, Saravanan Meghana, V. Maheswara Reddy and P.
Sarathkumar
This examination presents an inventive way to deal with mishap characterization inside burrows utilizing profound
learning calculations. Given the extraordinary difficulties presented by burrow conditions, for example, restricted
perceivability and bound spaces, successful mishap location is principal for guaranteeing quick reaction and security.
Using a dataset containing different passage mishaps, we prepared and assessed various profound learning models.
Our outcomes show a huge improvement in order precision contrasted with customary techniques. The proposed
framework shows potential for ongoing checking and cautioning in burrow foundation, underscoring the utility of
profound learning in improving transportation security in obliged conditions.
Keywords: CNN, Mobile-NET, UML, Trama focus model.
Paper ID - 0642

IoT-Enhanced Deep Learning Model for Elderly Motor Function Assessment in

Rehabilitation Devices
Sakthisaravanan B, Mothiram Rajasekaran, Arul Prasath A, N Mohankumar, S Murugan and R
Creesy
This research presents a novel method for evaluating the motor function of older people in rehabilitation equipment,
which makes use of the Internet of Things (IoT) and deep learning models, namely Recurrent Neural Networks (RNNs).
As patients undergo rehabilitation, the IoT sensors in their equipment record vital parameters like mobility, balance,
and more in real time. RNNs are trained on this processed data to identify patterns suggestive of motor activity by
analyzing sequential data. During rehabilitation sessions, RNNs can evaluate the motor function of older people in
real time using a dataset that includes labeled sensor data and associated evaluations. The patient and their doctor
may benefit from the system’s personalized recommendations, which can help with specific actions to improve motor
function and rehabilitation outcomes for the elderly. The potential for this method to improve rehabilitation programs
and the results achieved by older patients is substantial.
Keywords: Real-time assessment, Personalized feedback, Healthcare, Rehabilitation progress, Assistive technology.
Paper ID - 0662

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 71

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT and AI-Enabled Smart Contact Lenses for Proactive Glaucoma Management
G Geethamahalakshmi, Mothiram Rajasekaran, Sivanesan T M, Pramod Pandey, S. Murugan and
V Praveena
A novel approach for early identification and ongoing monitoring is urgently needed to prevent vision loss caused
by glaucoma, a major worldwide health concern. This paper provides smart contact lenses, including the Internet
of Things (IoT) and artificial intelligence (AI), for the active treatment of glaucoma. These spectacles use IoT
protocols to transmit data seamlessly and include small sensors to measure real-time intraocular pressure (IOP). To
intervene promptly, AI algorithms examine the collected data for small changes that may indicate the advancement
of glaucoma. Non-invasiveness, continual monitoring, and individualized treatment are just a few benefits of this
proactive monitoring system. Timely treatment modifications are made possible by the early warnings it provides to
patients and healthcare providers, which can avert irreparable deterioration of eyesight. An exciting new direction
in glaucoma treatment is the development of smart contact lenses that combine IoT technology with AI, providing a
simple and effective way to track the disease’s development. These smart lenses’ creation, operation, and prospective
influence on the state of the art in clinical practice and the results achieved by patients.
Keywords: Early Detection, Vision Loss, Healthcare Technology, Personalized Care, Treatment Adjustment, Disease
Progression.
Paper ID - 0664

Apparel Production Paradigms through a Technological Tapestry of AI Driven Smart

Mannequin Automation and Image Processing Precision
C S Manigandaa, M Bindu Sudeeksha, Challapalli Manikantaa, M Jyothsna, V.D.Ambeth Kumar
and P.Sindhu
This invention introduces a paradigm shift in apparel production by integrating AI-driven smart mannequin automation
and precise image processing technologies. The system is designed to enhance the retail experience by expediting
garment selection and optimizing fit and aesthetic suitability. Utilizing advanced artificial intelligence, the smart
mannequin accurately measures customers’ body sizes and analyzes their skin tones to curate personalized garment
recommendations. This innovative approach not only reduces the time spent on shopping but also improves customer
satisfaction by ensuring precise fit and style alignment. Additionally, the system contributes to efficient inventory
management and alleviates the workload of retail personnel, particularly during peak hours. This technological
advancement offers valuable insights into customer preferences, allowing businesses to tailor their offerings more
effectively. The invention represents a significant leap forward in the textile industry, blending scientific precision with
fashion, and paving the way for contactless fashion selection and personalized shopping experiences.
Keywords: Smart Mannequin, AI-Driven Automation, Image Processing, Apparel Selection, Personalized Shopping
Experience, Textile Industry Innovation.
Paper ID - 0665

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 72

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Climatic Oracle: Unveiling Future Weather Trends with Data Science

Periasamy J K, Sree Nidhi S, Gunasundhari N and Sharlatha R
The ”Climatic Oracle” initiative is a groundbreaking project that merges meteorology and data science to
revolutionize weather forecasting. By leveraging real-time data integration, advanced analytics, and dynamic
learning mechanisms, this project aims to provide precise and timely solutions to weather-related challenges. At its
core, the project features a robust data collection process, preprocessing, and feature engineering to create a
comprehensive dataset, which is then utilized by various machine learning models and ensemble techniques to deliver
accurate short-term and long-term weather forecasts. Specialized models for extreme events and risk assessment
tools enable early warnings, empowering communities and decision-makers to take proactive measures. The system’s
adaptability to changing conditions and continuous learning through a feedback loop ensure forecasts remain
relevant and accurate, while ethical considerations and bias mitigation strategies ensure fairness and transparency in
forecasting outcomes. Community engagement initiatives, including citizen science, enrich the forecasting model
with real-time local observations, fostering a collaborative approach to weather prediction. International
collaboration and secure data sharing protocols establish a global network for collaborative forecasting, addressing
the challenges posed by climate change on a global scale. With a dedicated research and development component,
the ”Climatic Oracle” project integrates emerging data science techniques, ensuring it remains at the forefront of
innovation and transforms weather forecasting into a dynamic ecosystem that adapts to the ever-changing climate.
Keywords: Climate Change, Data Analysis, Climate Simulation, Parallel Computing.
Paper ID - 0668

Augmented Reality Applications in Education: Challenges and Opportunities

M.Krishnamurthy, P. Kabilamani, B. Manimaran, T.Kavitha, P.Nagarajan and N.Ashokkumar
Augmented Reality is used to boost education by offering the students the facilities of immersive and interactive
learning experiences. This research deals with the problems and the possibilities of the incorporation of AR applications
in the schools through the literature review and the experimental research. The comparison of marker-based AR
algorithms shows the information about marker detection accuracy (85-92%), tracking stability (7-9) and rendering
efficiency (25-30 FPS), which stresses the importance of the balance between these three factors for the best AR
experience. The evaluation of Simultaneous Localization and Mapping (SLAM) algorithms also shows that the mapping
accuracy (88-92%) and the trajectory estimation (0) are reliable. The Artificial Reality (AR) controller above the
user’s head should record the movement of the user to the left and right as well as real-time performance (20-30
FPS), thus proving the necessity of the correct spatial mapping and the efficient trajectory estimation in the AR
environment. Besides, the comparison of image recognition algorithms shows that the detection accuracy (85-92%),
processing speed (25-40 ms), and robustness (7-9) are the main factors for the scene, thus, the need for fast and
accurate object recognition for smooth AR interactions is emphasized. In general, this research gives meaningful
information about the possible of AR technology to boost learning outcomes, on the other hand it also highlights the
important factors that should be taken into account in order to accomplish its integration into educational practices.
Keywords: Augmented Reality, Education, Marker-based AR, SLAM, Image Recognition.

Paper ID - 0669

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 73

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Drone Detection and Drone Type Classification Using Deep Learning Technique
Ashokkumar.N, Nagarajan.P, Kavitha.T, R. Bhairavi, Arulmary A and Balamanikandan.A
The demand and usage of drones are increasing day by day, and with this increased popularity, new types of drones
are coming into the market for various purposes. However, due to the inflation in the usage of drones, their security
has become a major concern. As a result, it is required for drone users to be well aware of drones surrounding them.
To address this issue, a complete drone detection and classification scheme has been proposed that depends on deep
learning. The scheme involves two parts: drone detection using YOLOV2 and drone classification using Convolutional
Neural Networks (CNN). In the existing method, Support Vector Machine (SVM) is used to categorize the drone type
as Tricopter or Quadcopter. The results of the proposed deep learning and Artificial Intelligence technology executed in
MATLAB are promising.It’s worth noting that the detection and classification of drones using deep learning algorithms
is an active area of research. There are several other approaches that have been proposed in recent years, such as using
radio frequency compressed signals to detect and classify UAVs 1. Another study proposed a hybrid deep learning
model that combines LSTM and Bi-GRU classifiers to provide enhanced object detection in drone imagery for search
and rescue operations 2. These approaches show great potential for improving the accuracy and efficiency of drone
detection and classification.
Keywords: Drone detection, classification, YOLO, CNN, SVM Deep learning
Paper ID - 0671

Particle Swarm Optimization Based Intelligent Smart City Parking Guidance System
Ashokkumar.N, Dr C Venkataramanan, Nagarajan.P, C. Kanmani Pappa, P. Kabilamani and
K.P.Porkodi
Smart cities have the power to raise economic development, enhance the quality of life for city dwellers, and solve some
of the problems that plague large metropolitan areas. We provide a Particle Swarm Optimization (PSO) approach to
find optimal hyper parameter values for local machine learning models in a fuzzy logic (FL) scenario. Our technique
is assessed by comparing the results of two case studies. We present a Particle Swarm Optimization (PSO)-based
strategy for fine-tuning the hyperparameters of local ML models in a FL scenario. We analyse the results of two case
studies to see how well our proposed method works. In order to estimate traffic patterns, we first take into account the
services provided by smart cities and use a simulated environment built from an experimental transportation dataset.
We think about cloud services and employ a real-time telemetry dataset to foretell when a machine would break down
due to a component failure.
Keywords: Particle Swarm Optimization, smart city, memetic algorithm, street parking system, Pollution, Going
green, Saving energy
Paper ID -0672

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 74

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Deep Learning: Techniques, Taxonomy, Applications, and Future Directions

Mohana Sundari V, Mabel Rose R A, Sassirekha S M, Nalini M, Girija P and Siva Subramanian R
Deep learning has become one of the key AI techniques of the modern world and has changed many fields by its
capability to learn from data, which is often very complex. The presented survey paper aims at describing
fundamental techniques and taxonomy of deep learning, various applications, and potential perspectives for further
research. The paper starts with presenting the concept of deep learning and its origins as well as emphasizing the
important position of DL in the modern development of AI. It then goes further into deep learning workflow and
frameworks and presents feedforward neural networks, CNN, RNN, generative adversarial networks, attention
mechanisms, and transformers. An overview of deep learning frameworks is discussed, including supervised,
unsupervised, semi-supervised, reinforcement, transfer, and self-supervised learning. The survey further continues to
provide a detailed description on how deep learning is being widely used in computer vision, natural language
processing (NLP), speech recognition, self-driving cars, disease diagnosis and stock price forecasting. The issues
related to challenges and limitations include data dependency, interpretability, overfitting, high computational
burden, and ethical concerns are presented along with ongoing work and directions for future investigations. This
includes explainability of AI, incorporation of symbolic AI methods, improving the resilience and security of models,
breakthroughs in hardware, as well as expansion into future domains such as quantum computing and robotics.
Finally, this survey paper summarizes existing literature and predicts future research direction, emphasizing on how
deep learning will revolutionalise technology and how it may foster development in various fields.
Keywords: Deep Learning, Artificial Intelligence, Machine Learning, Neural Networks.

Paper ID - 0673

IoT and Data Analytics in Healthcare

Sekar G, John T Mesia Dhas, Anandaraj B, Nalini M, Sathya V and Siva Subramanian R
The use of IoT devices and data analysis in healthcare has changed the way patients are treated, hospitals and clinics
are managed, and diseases are studied. This paper aims at discussing the possibilities, difficulties and tendencies in the
use of these technologies. Some of the primary IoT use cases are in healthcare where IoT devices are used in telehealth
applications such as remote patient monitoring, smart hospitals, chronic disease management, and eldercare. Big data
analytics improves effectiveness in the predictive, diagnostic, prescriptive, and descriptive models in the medical field.
This paper covers integration issues like scalability, linkage of data, and workflow compatibility as well as privacy,
security, and legal issues. Some future trends include IoT development with 5G and new devices, AI and genomics,
interprofessional research, and policy. Thus, the objective of this paper is to present the review of the current state of
IoT and Data analytics applications in healthcare, as well as future prospects to help the stakeholders for leveraging
the benefit of IoT and Data analytics in healthcare applications.
Keywords: IoT, Data Analytics, Machine Learning Artificial Intelligence, Healthcare.
Paper ID - 0674

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 75

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

An Improved Artificial Intelligence Assisted Sign Language Recognition Methodology

using Modified Deep Learning Principle
B.Vasumathi, N Aparna, A V. Allin geo, R.Thiagarajan, Pravin Kulurkar and R.Krishnamoorthy
Sign language is the primary mode of communication for millions of people worldwide, particularly for those who are
deaf or hard of hearing. However, the lack of widespread knowledge of sign language within the general population
often creates barriers to effective communication. This may be addressed by AI-driven automated sign language
recognition (SLR) systems that allow for real-time translation between sign language users and non-users. Using
a tweaked version of the Deep Learning (DL) concept, this research details a new approach to AI-assisted SLR. A
hybrid architecture is used by the system to extract spatial features, analyze temporal sequences with Long Short-Term
Memory (LSTM) networks, and improve accuracy by focusing on critical areas of the input with attention processes.
The model outperforms previous models with an impressive accuracy of 98.33% after being trained and evaluated on
the Sign Language MNIST dataset. This high level of accuracy, coupled with its computational efficiency, makes the
suggested methodology ideal for real-time sign language interpretation systems. The methodology has the potential
to significantly improve accessibility and communication for the hearing-impaired population. Future work can extend
the system’s capabilities to handle dynamic gestures and expand its applicability to a wider range of sign languages.
Keywords: Sign Language Recognition, Convolutional Neural Network, LSTM, Attention Mechanism, Artificial
Intelligence, Sign Language MNIST, Deep Learning, Spatial-Temporal Analysis.
Paper ID - 0677

ELNN: A Novel Approach to Identify Periodontal Disease from Panoramic

Radiographs in Earlier Stages using Enhanced Logical Neural Networks
Bhuvaneshwari Karthikeyan,V.Balaji Vijayan,Kotteeswaran R,M.K.Vidhyalakshmi.Krishnamoorthy
R and R.Thiagarajan
Periodontal disease is a prevalent condition that can lead to serious dental complications if not detected and treated
early. In this paper, we propose an Enhanced Logical Neural Networks (ELNN) model for identifying periodontal
disease at early stages from panoramic radiographs. The ELNN model integrates AlexNet, a convolutional neural
network (CNN) for feature extraction, with XGBoost for classification, creating a robust hybrid architecture. The
dataset used includes 17, 654 labeled images collected from hospital records over the last two years. Our preprocessing
techniques involve resizing, grayscale conversion, noise reduction, and segmentation to ensure optimal data quality for
feature extraction. The ELNN model outperforms traditional machine learning models, such as Logistic Regression,
Support Vector Machine (SVM), and standalone deep learning models, achieving an accuracy of 97.77%. The model
demonstrates superior precision (96.45%) and recall (96.89%) compared to other approaches, ensuring high reliability
in distinguishing early-stage periodontal disease from healthy and advanced cases. The results suggest that the ELNN
model has strong potential for clinical applications in dental diagnostics, especially for early detection, which is critical
for effective treatment.
Keywords: Periodontal Disease, Panoramic Radiographs, Enhanced Logical Neural Networks, AlexNet, XGBoost,
Early Detection, Dental Diagnostics, Deep Learning.

Paper ID - 0678

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 76

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Logical Design of Superficial Learning Methodology to Identify Dental Diseases

using Predictive Classification Principle
Bhuvaneshwari Karthikeyan, Pooja Bhagwat, Kishor patil, Shraddha Walekar Ghaisas,
R.Thiagarajan and R.Krishnamoorthy
Dental disease detection is a critical aspect of oral healthcare, as early diagnosis can significantly improve treatment
outcomes. In this study, we propose a novel Superficial Learning Methodology (SLM) for classifying dental diseases
using image data from the ”Oral Diseases-The Dental Condition Dataset, ” which consists of 1, 296 images
representing six dental conditions: caries, calculus, gingivitis, tooth discoloration, ulcers, and hypodontia. The
proposed SLM integrates a cascaded ResNet for feature extraction and a Support Vector Machine (SVM) for
classification. Several data preprocessing techniques, including image resizing, augmentation, normalization,
CLAHE, and Gaussian filtering, were applied to enhance the model’s performance. The SLM model was evaluated
using accuracy, precision, recall, and F1-score, achieving an overall accuracy of 98.02%, surpassing traditional
machine learning and deep learning models. The combination of ResNet’s deep feature extraction capabilities with
SVM’s margin-based classification proved highly effective in classifying dental conditions with high precision and
recall. Additionally, the model demonstrated competitive computational efficiency in terms of training time and
complexity, making it suitable for practical clinical applications. This study highlights the potential of integrating
deep learning and machine learning techniques for accurate dental disease classification.
Keywords: Superficial Learning Methodology, ResNet, SVM, Dental Disease Classification, Feature Extraction,
Deep Learning, Image Preprocessing, Dental Conditions, Machine Learning.

Paper ID - 0679

Experimental Evaluation of a Secured Blockchain based Data Management Scheme for

Patient-Centric Applications in Healthcare Industry
A. Sevuga Pandian, G.Sundar, P.Patchaiammal, AMOL L. Mangrulkar, R.Thiagarajan and
R.Krishnamoorthy
The healthcare industry is increasingly moving toward digital systems for managing patient records and data, driven
by advancements in electronic health records (EHRs), wearable technologies, and patient monitoring devices. This
research proposes a secured blockchain-based data management scheme designed to enhance privacy, security, and
accessibility in patient-centric healthcare applications. By integrating blockchain technology with advanced encryption
techniques, such as AES (Advanced Encryption Standard) and RSA (Rivest–Shamir–Adleman), this system ensures
that sensitive patient data remains protected throughout storage and sharing processes. Key features include smart
contracts for automated consent management, a private blockchain for immutable data storage, and role-based access
control (RBAC) to restrict data access to authorized parties. The blockchain-based system prevented all unauthorized
access and data tampering attempts, achieved 100% encryption and decryption success rates, and maintained an
average latency of 3.2 to 5.0 seconds. The system achieved an overall accuracy rate of 98.75% in preventing data
breaches and unauthorized access, significantly outperforming traditional systems. Although there is a slight trade-
off in terms of latency and throughput, the system’s enhanced security and scalability make it a viable solution for
large-scale healthcare data management
Keywords: Blockchain, AES Encryption, RSA Encryption, Smart Contracts, Role-Based Access Control, Healthcare
Data Management, Privacy, Security, Scalability, Decentralized System.
Paper ID - 0680

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 77

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Smart and Intelligent Robotic Design to Rescue Human from Disaster Conditions
using Artificial Intelligence Assistance
Reddi Khasim Shaik, V.Balaji vijayan, Kotteeswaran R, AMOL L. Mangrulkar, R.Krishnamoorthy
and R.Thiagarajan
In disaster scenarios such as earthquakes, floods, and collapsed buildings, timely rescue operations are crucial to
saving lives. This paper proposes a smart and intelligent robotic rescue system that utilizes advanced Artificial
Intelligence (AI) to assist in human rescue efforts. The system integrates Convolutional Neural Networks (CNN) for
human detection and Long Short-Term Memory (LSTM) networks for path planning, enabling autonomous navigation
through hazardous environments. Key components of the system include sensor fusion using infrared, ultrasonic, and
LIDAR technologies to ensure high-accuracy detection of survivors and obstacles. The proposed model was evaluated
against nine existing models, outperforming them in critical metrics. The human detection accuracy of the proposed
model is 97.70%, and the average rescue time is reduced to 4.50 minutes, compared to other models. Additionally, the
system achieved the lowest path deviation (4.22%) and communication latency (32.18ms). These results demonstrate
the model’s superior efficiency and effectiveness in real-time disaster response scenarios. The combination of AI and
sensor integration proves to be a reliable and life-saving tool for rescue teams.
Keywords: Robotic Rescue System, Disaster Response, Artificial Intelligence, CNN, LSTM, Sensor Fusion, Human
Detection, Path Planning, Wireless Communication, Real-Time Monitoring.
Paper ID - 0681

A Smart and Secured Anomaly Detection Scheme for Internet of Things (IoT)
Powered Devices using Federated Learning Technology
G. Sundar, P.Patchaiammal, AMOL L. Mangrulkar, Sameer Sharma, R.Krishnamoorthy and
R.Thiagarajan
In the rapidly expanding realm of Internet of Things (IoT), ensuring the security of connected devices is paramount.
Smart homes, which rely on an array of IoT devices like cameras, motion sensors, and door locks, are particularly
vulnerable to anomalies that may indicate security breaches. This paper proposes a novel anomaly detection scheme
leveraging Federated Learning technology to enhance the security of IoT-powered devices while maintaining data
privacy. Unlike traditional models, which rely on centralized data collection, Federated Learning enables local
anomaly detection models to be trained on each device without transferring raw data. The proposed model
integrates AutoEncoder for dimensionality reduction and LSTM for detecting temporal anomalies in IoT
environments. Evaluated against nine existing models, the proposed solution achieved an accuracy of 97.19%,
significantly outperforming state-of-the-art models such as XGBoost (91.78%) and Deep Neural Networks (90.55%).
Moreover, the model reduced communication overhead by 35% and showed a 180ms latency, making it highly
efficient for real-time anomaly detection. This research demonstrates that Federated Learning can offer robust,
scalable, and privacy-preserving solutions for anomaly detection in smart homes.
Keywords: Federated Learning, IoT, Anomaly Detection, Smart Homes, Privacy, Autoencoder, LSTM, Security,
Machine Learning, Temporal Data.

Paper ID - 0682

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 78

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT Powered Energy Optimization and Monitoring System for Smart Buildings using
Learning based Artificial Intelligence Association
C. Meenakshi,S. Meyyappan,M.Vijayakarthick,A.G. Ganesh Ram,B. Vinoth and Thiagarajan R
Energy consumption in smart buildings is a growing concern as these environments become more complex with
increased energy demand for heating, ventilation, air conditioning (HVAC), lighting, and other appliances. This
paper presents a novel IoT-powered energy optimization and monitoring system for smart buildings, leveraging a
hybrid learning-based approach combining Reinforcement Learning (RL) and Supervised Learning (SL). The
proposed model optimizes energy consumption both reactively, by adjusting energy usage in real-time, and
proactively, by predicting future energy demands based on historical data. The system utilizes various IoT sensors to
collect data on environmental parameters such as temperature, occupancy, and appliance status. By employing this
hybrid model, we achieve enhanced accuracy, energy savings, and occupant comfort. The proposed model was
evaluated against nine existing energy optimization models, and it achieved an accuracy of 95.34% in predicting
energy demand, outperforming traditional models like XGBoost (89.10%) and LightGBM (89.32%). Additionally,
the proposed model achieved energy savings of 24.89%, while maintaining a response time of 0.64 seconds and an
occupant comfort level of 96.89%. These results demonstrate the superiority of the proposed RL-SL model in
enhancing the energy efficiency of smart buildings without compromising comfort.
Keywords: IoT, Energy Optimization, Smart Buildings, Reinforcement Learning, Supervised Learning, Energy
Savings, Occupant Comfort, Machine Learning, Energy Efficiency.
Paper ID - 0683

Enhancing Efficiency, Collaboration and Innovation Through Transparent Systems

Dr. Gnana Jeslin J, Glory Sangeetha. R, Dr Uma Maheswari G, Dr. Raja Suguna M, T.Anand
and Mrs.E. Lavanya
Transparent systems are key to improving efficiency, collaboration and innovation in an organization. These systems
make data and processes available to everyone, i.e. a company runs with less overhead spillage, while the speed is
increased by which decisions can be made. Transparency in an organization Level support team cooperation and
relationship of Work on delivery and efficiency Together. In addition, a transparent environment promotes innovation
Thinking, creating open communication channels and channels Development. The abstract above is a preview of the
value that transparency provides as an underpinning to organizational success in terms of productivity, teamwork,
and creativity.
Keywords: Transparent System, Task Visibility, Idea Sharing, Workflow Management

Paper ID - 0688

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 79

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Video Frame Transmission Using Semantic Frame Segmentation over Deep Series
Network with AWGN Channel
Ashok S, Alex Joseph K, Kessavan M, Susendhiran E, Prabhu.V and Venkat S
Abstract—Video analysis relies on segmentation of objects of interest within a video sequence.Segmenting entities in
videos is a few of the most frequently acclaimed and thoroughly explored strategiescomputer vision applications that
has shown outstanding performance improvements due to advances in deep learning techniques. Using deep learning,
we will present a systematic literature review of video segmentation advances, highlighting their advantages and
disadvantages. The proposed method uses the semantic segmentation for the Frames obtained from video conversion.
Using images from the current frame, semantic encoders are designed and processed through a serial semantic
network. QAM (16) supports higher data rates and spectral efficiencies since it uses Quadrature amplitude
modulation (QAM). By using Monte Carlo simulations with additive white Gaussian noise (AWGN), it is possible to
calculate the bit error rate (BER) of QAM. The complexity increases with the size of the constellation.
Segmentation and communication network for semantics. In addition to the effectiveness of semantic segmentation
measures such as worldwide preciseness, class reliability, IoU, weighted IoU, and BF score, the Signal to Noise Ratio
(SNR) and Symbol Error Rate (SER) were determined.
Keywords: semantic segmentation, video, SNR, AWGN channel, QAM 16 encoding and decoding.
Paper ID - 0690

Enhancing Prediction Accuracy through Random Forest in Classification and

Regression
Ignatious K Pious, Rajalakshmi A, Prem Kumar R, Varun C M, Nalini M and Siva Subramanian R
Random Forest is a well-known type of ensemble learning, which combines a number of decision trees to improve
the prediction ability and reduce the risk of overfitting. This paper aims at discussing in detail Random Forest with
emphasis on basic concepts such as decision trees and ensemble approaches including bagging. Here, we discuss the
factors like training process, prediction procedure, and feature significance measurement. The paper covers a range of
applications including classification, regression, anomaly detection and feature selection. We also describe the strengths
of the algorithm, overfitting, and the ability to perform on different tasks. But issues like high computational costs,
issues with model interpretability, and biases in the imbalanced datasets are also solved, or at least partially dealt
with. Emerging trends and future developments are discussed, and they focus on advancements in accuracy, realtime
management, and the interaction with deep learning. This survey clearly shows how Random Forest is still useful and
can be further improved for it to be effective in the contemporary machine learning techniques.
Keywords: Random Forest, Ensemble Learning, Decision Trees, Bagging, Feature Importance, Classification.
Paper ID - 0695

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 80

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

“Post-COVID-19 Adoption of Digital Financial Services: Analysing Usage Patterns

and Demographic Influences in Maharashtra State”
Kiran Kakade, Anjali Kulkarni, Ameya Patil, Pravin Bhoyar, Jayant Brahmane and Subhash Yadav
Information technology has severely influenced numerous facets of human existence, particularly the banking sector.
The need for financial literacy is growing, as the financial landscape is complex and many people remain uninformed,
leading to financial stress and poor decisions. Fintech companies have emerged as a solution to this issue by providing
personalised platforms for financial literacy and easy access to formal financial channels. The COVID-19 epidemic has
expedited the integration of digital technologies and heightened the demand for fintech services. Nonetheless, owing
to poverty and insufficient financial literacy, a considerable segment of the population in undeveloped and developing
nations is unable to utilise the services offered by fintech companies. This study seeks to address the research gap by
analysing the factors affecting the adoption of digital financial services in India. The results will aid in formulating
regulations to enhance the fintech sector and guarantee financial inclusion for the majority of the populace.
Keywords: Financial Technology, digitalisation, banking, payment Gateway, Covid-19, Pandemic, financial inclusion,
DFT.

Paper ID - 0696

OPEN EYE: An Information Gathering Tool Using OSINT Framework

A. M.Sermakan, P.Sreejith, A.Leela Krishna. S.Lokesh, Kaushik Narayanan.C.VR and Jaya siva
subramaniam.N
In an age of digital connectivity, Open Source INTelligence (OSINT) has emerged as a critical tool for information
collection across a range of fields, such as threat analysis, cybersecurity, and investigative journalism. The main aim
of this framework is to create a component that has an effective and efficient information collection in order to increase
OSINT capabilities. In order to gather useful intelligence data, the proposed initiative focuses on utilizing a variety of
internet sources, including social media platforms, open databases, and web archives. To automate the extraction and
analysis of pertinent data, the framework integrates machine learning models, data mining strategies, and sophisticated
search engines. This automation reduces human mistake, which improves accuracy while simultaneously speeding up
the information-gathering process. The proposed method emphasizes appropriate information processing and ethical
aspects regarding OSINT activities.
Keywords: OSINT, Open Source Intelligence, Search Algorithms, Information Gathering, Public Databases, privacy
in Social Media.

Paper ID - 0697

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 81

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Construction of Smart Automation System using Cisco Packet Tracer

Mrs. Maheswari A, Dr. Raja B, Mohamed Eghiya Kamal and Peer Arif P
Water is given to plants via irrigation systems in a single direction. Devices and sensors that are connected to
the Internet allow users to operate and monitor remotely in the Internet of Things (IoT) domain. In order to
achieve this goal, this research article will employ the most recent version of Cisco Packet Tracer 7.3.0 (64-bit), a
simulation programme for Cisco packet tracers. Here, temperature, humidity, and lawn sprinkler sensors are just a few
examples of the study technology. In order to develop a smart automation water system with numerous components,
including Together, these instruments monitor the surroundings to enhance the drainage system and encourage robust
development. Because each of the aforementioned gadgets is linked to the home gateway, users can control and keep
an eye on them from a tablet, computer, or smartphone. Simulation findings demonstrate the successful integration
of smart devices into building portals, such as environmental monitoring sensors and sprinkler systems. Farmers and
homeowners have benefited from the technology as it made it simple for them to grow and nurture plants while also
remotely protecting the environment.
Keywords: IoT, Network Simulation Tool, Intelligent Irrigation Solution.

Paper ID - 0703

Psychological Escalation of Gaandness State and Analysing the Triggering Subfactors

Contributing to Mental Outbreak
Vincent Gnanaraj T, Chenni Kumaran J, Bhavani R and Mohan A
Abstract—The unique concept of ”Gaandness” displays a multifaceted state with combination mental and physical
decline driven by factors such as stress, boredom, laziness, failures, tiredness, and deteriorating health. This paper
seeks to identify and analyse the subfactors that contribute to the psychological escalation of these primary factors,
ultimately exacerbating the overall state of Gaandness.
Keywords: Psychology, Mindset, Mental Outbreak, MCS
Paper ID - 0706

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 82

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Foreign Language Learning Portal with TTS

Dr G Adiline Macriga, Sri Shakthi K and Priyatharshini
Foreign language learning is a complex process that may be impacted by a number of elements, such as learner
characteristics, learning materials, and teaching methods. In an increasingly globalized world, the ability to
communicate across language barriers is vital for effective collaboration and understanding. To address this
challenge, we propose the development of a Multilingual Translator Application—a versatile and user-friendly tool
which can help to facilitate seamless communication between individuals speaking different languages by translating
input text to desired language and using TTS to speak the translations aloud. Foreign language learning poses
challenges, complicating communication between speakers of different languages. Meeting the demand for seamless
cross-cultural interaction necessitates an inventive solution. This involves integrating language learning and
translation within a dynamic framework. Our goal is to develop an innovative platform that utilizes text-to-speech
technology designed to translate input text into various target languages and can speak the translations aloud, while
providing performance analysis based on different parameters. The innovation lies in the creation of a transformative
language platform that not only combines language learning and translation but also leverages adaptive technologies
by combining language learning and translation in a cohesive manner.
Keywords: TTS, Text Translation, Foreign language learning
Paper ID - 0708

Secure and Scalable Blockchain-Based Electronic Health Record System Enhancing

Data Interoperability and Patient Privacy
Shyamala Kumari, Prasanth J, Sanjeeviram C.M and Prashanth K
Blockchain focusing on protecting the pri- vacy and security features of interoperability. Blockchain inherent attributes
of data integrity and security. This blockchain provides a more efficient and secure option than client server based
electronic health record system. Mainly focusing on protecting Block chain technology helps to protect database from
manipulation due it to fetching the privacy and security and access control blockchain that uses consensus decentralized
data management. Blockchain ensures that all transactions from manipulation due to its features of interoperability
and immutability health records.
Keywords: Blockchain, EHR, IPFS, Access control, Healthcare, Data privacy, Security, Healthcare
Paper ID - 0709

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 83

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Comprehensive Examination of the Advancements in Deep Learning Models for

Enhanced Disease Prediction
Sasirekha.K and Joe Prathap P.M
The field of human disease prediction holds great promise for revolutionizing healthcare through early diagnosis and
customized treatment plans. Therefore, studies on this region is crucial. A short time ago, deep learning has been
increasingly incorporated into many different sectors of artificial intelligence, owing to its exceptional performance and
ability to autonomously acquire features. In the field of medicine, particularly in the realm of deep neural learning, the
accuracy rate surpasses that of doctors. This paper provides an outline of the challenges faced by deep learning systems
in predicting human diseases. Despite these challenges, deep learning has great promise for enhancing human disease
detection and prediction. Addressing these issues will require collaboration between machine learning researchers,
healthcare professionals, and policymakers in order to guarantee that deep learning models in healthcare are safe,
effective, and morally sound.
Keywords: Deep learning, machine learning, human disease prediction, diagnosis.
Paper ID - 0711

Machinelearnpro: Redefining Predictive Maintenance through Data-Driven

Approaches
Dr. Anand K, Dr. Ananthajothi K, Dr. Vinodkumar S and Dr.N. Duraimurugan
In the manufacturing industry, predictive maintenance is an essential strategy for avoiding equipment breakdowns
and reducing interruptions. This paper aims to use machine learning techniques to transform the predictive
maintenance systems in factories. By studying past data on equipment malfunctions, the paper intends to highlight
the significant role of machine learning in decreasing downtime and improving maintenance plans. Just as there’s a
pressing need for quick and accurate document verification in the current digital era, the manufacturing sector is
dealing with increasing difficulties in preventing equipment failures and reducing operational disruptions. Within
this context, our paper titled ”MachineLearnPro: Redefining Predictive Maintenance through Data-Driven
Approaches” aims to address these challenges by harnessing the potential of machine learning. In the past,
manufacturing facilities have depended on reactive maintenance methods, which often result in unexpected downtime
and operational inefficiencies. This paper aims to overcome these challenges by using historical data on equipment
failures and applying sophisticated machine learning algorithms. The proposed system goes beyond traditional
rule-based maintenance schedules by using predictive models that can detect patterns and early signs of equipment
failures. Similar to how the Anchor Model transformed text recognition by understanding subtle spatial and
semantic connections, the machine learning algorithms used in this study are designed to thoroughly analyze data on
equipment failures, allowing for proactive measures. These algorithms, similar to the contextual approach of the
Anchor Model, interpret complex relationships within the historical data on equipment failures, laying the
groundwork for predictive maintenance strategies that can anticipate potential malfunctions and streamline
maintenance schedules. This paper seeks to revolutionize predictive maintenance methods by adopting machine
learning techniques. It aims to help manufacturing plants move from reactive to proactive maintenance strategies.
The research aims to show how these algorithms can drastically reduce unplanned downtime, improve maintenance
schedules, and ultimately boost operational efficiency in manufacturing plants.
Keywords: Predictive Maintenance, Machine Learning Algorithms, Equipment Failures, Downtime Reduction,
Maintenance Optimization, Manufacturing Industry.
Paper ID - 0712

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 84

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Deep Belief Networks for Brain Tumor Recurrence and Survival Rate Prediction
M. Sathish, M. Shafiya Banu, Kannan Shanmugam, P. Thenmozhi, C. Srinivasan and Sermakani A
M
Critical issues in neuro-oncology include predicting patient survival and the recurrence of brain tumors. Due to their
inadequacy in capturing intricate patterns in medical data, traditional prediction models often fail to provide accurate
and generalizable results. To overcome these challenges, a new method uses Deep Belief Networks (DBNs). Generative
graphical models, such as DBNs, are excellent at learning hierarchical feature representations from high-dimensional
data, which makes them ideal for complex pattern-based medical prediction tasks. Our proposed system uses DBN to
analyse genetic information, imaging characteristics, and patient clinical data to forecast survival rates and recurrence
rates of brain tumors. Train the DBN in an unsupervised fashion; first, use supervised learning to fine-tune it. Using
a dataset containing a variety of patient scenarios, we compare the model’s performance to that of more conventional
machine learning techniques. Insights into tumor recurrence and patient survival may be gained from the data,
which show that the DBN model offers improved prediction accuracy and resilience. Deep learning algorithms can
revolutionize personalized treatment regimens and enhance patient outcomes in neuro-oncology.
Keywords: Brain Tumor Recurrence, Survival Rate Prediction, Neuro-Oncology, Medical Data Analysis, Predictive
Modeling.
Paper ID - 0713

Advancing Telestroke Services Technology with Cloud and AI Solutions for Enhanced
Care
Mothiram Rajasekaran, R. Meenakshi, Dr. P. K. Dhal, Dr. R. Aiyshwariya Devi, S. Sujatha and R.
Kamalakannan
Telestroke services have become an essential component of stroke therapy, especially in areas with few specialists’
medical facilities. To further improve telestroke services, this paper investigates the possibility of integrating cloud
computing with artificial intelligence (AI) technologies. With the scalability, accessibility, and cost-effectiveness of
cloud infrastructure, healthcare professionals worldwide may communicate and share data easily. Machine learning
algorithms, image analysis tools, and other forms of AI are enhancing telestroke services by giving doctors access to
sophisticated decision-making capabilities. Better patient outcomes result from these systems’ capacity to facilitate
quicker and more precise diagnosis and treatment planning. Predictive analytics powered by AI can identify patients
at risk early on and provide individualized treatment plans that can better meet each patient’s requirements. By
combining cloud and AI technology, telestroke services can improve patient care by analyzing large datasets, allocating
resources more efficiently, and fostering better teamwork among specialists. It may perform beyond geographical
restrictions and ensure that stroke patients all around the globe have equal access to high-quality treatment. The
potential is to transform stroke care delivery using data-driven insights and improved decision-making skills. It
simplifies processes and improves efficiency.
Keywords: Stroke care, Healthcare technology, Personalized care, Remote healthcare, Patient outcomes.

Paper ID - 0714

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 85

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Dynamic Traffic Flow Optimization with YOLO-Based Object Detection

Dr P Chitra, Divyesh S and Vibusha P
Abstract—There is a direct need for effective traffic management solutions owing to the growing urbanization and
vehicular volume. Most conventional traffic control systems only use static timing to adjust the flow of vehicles, which
can be manual and result in circuit delays. This paper proposed a smart traffic signal management system, where the
input images are used to change the timings of signals with dynamically managed flow in real-time. This estimates
the traffic density, vehicle count, lane occupancy and classifies them vehicles like cars/buses/trucks/motorcycles with
a machine learning algorithm using advanced image processing techniques. Some of these features include emergency
vehicle preemption, suspicious vehicles detection and adaptive signal control for smooth traffic operations. It uses
object detection models to interpret the state of traffic and adapt signal timings based on live conditions. These data
inputs do away with fixed signal timing and sequence that make you wait longer, increasing congestion. Simulation
results show that traffic throughput increased, delay decreased and the safety was improved with image-driven smart
traffic management as a scalable solution for right now cities.
Keywords: Computer Vision, Machine Learning, RNN(YOLO)

Paper ID - 0722

Water Quality Monitoring System Using Maps

Iyswariya A, Sai Sharan P, Valliappan PL, Sanjay S and Surya K
At present, water scarcity presents a significant challenge, compounded by concerns over its declining quality.
Contaminated water poses serious threats to both human health and ecological balance. To combat these issues,
innovative strategies for monitoring and managing water quality are imperative. This initiative introduces a
comprehensive, technology-driven solution aimed at enhancing the efficacy of water quality surveillance and
intervention efforts. Leveraging IoT technology, the project utilizes sensors to evaluate key water quality parameters
such as Total Dissolved Solids, Turbidity, and pH. Deviations from established standards trigger alert notifications,
delivered via SMS through GSM to users and neighbouring communities. Furthermore, upon detection of
abnormalities, water supply from the source is temporarily halted to prevent further contamination. Notably, sensor
data is stored in a database for future analysis, aiding in the development of targeted treatment methods.
Additionally, the system utilizes geospatial mapping, plotting contaminated areas on Google Maps for easy
visualization by users and governmental agencies. This initiative offers a holistic approach to water quality challenges
by integrating real-time data collection, geospatial analysis, proactive alerts, and automated supply regulation. It
also paves the way for long-term improvements in water resource management beyond immediate health issues.
Keywords: Water quality, IoT, GSM, Alert, Database, Google Maps.
Paper ID - 0730

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 86

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Orphan Guard: A Website for Orphanage Management

Pathmanaban J, Vigneshwari M, Vivekanandan G, Ilamathi K B, Krithika S and Deepika S
Orphanages, particularly smaller and lesser-known institutions, face critical challenges due to significant deprivation
in essential areas such as food, education, shelter, health, and security. The lack of awareness about these orphanages
exacerbates their struggles, leading to inadequate donations and support, which directly threatens the well-being of
their residents. Furthermore, issues such as irregular donation payments, verification difficulties, and the absence of
accurate information about these institutions intensify the crisis. Additionally, the need for streamlined adoption
processes and comprehensive care for both orphaned children and elderly residents highlights the multifaceted nature
of these challenges. Addressing these issues necessitates a concerted effort to raise awareness, improve support systems,
and implement effective solutions to ensure the holistic well-being of individuals residing in orphanages.
Keywords: small orphanages, deprivation, awareness, inadequate donations, Institutional information.
Paper ID - 0736

Predicting the Results of Cricket Matches using Deep Learning Method

Kumar P, Senthil Pandi S, Karthikeyan N and Karthikeyan N
Consequently, being a multi-format and multi-variable game, cricket raises a lot of challenges in respect to making
a perfect prediction of the match. The paper proposes a new deep learning-based prediction approach for One Day
International (ODI) cricket, using Long Short-Term Memory Network combined with an attention mechanism. While
traditional machine learning-based models have shown some promise, they still suffer from the inability to capture
long-term dependencies within a cricket match sequential data. The LSTM architecture inherently tends to learn these
temporal patterns really well; hence, it is particularly suited for this task. The attention mechanism further enhances
this model, where the critical moments in the match are solely responsible for the outcome. Based on this, detection
will be done with an extensive dataset covering more than matches of various cricket formats: ODI, T20I, and Test
matches. The dataset is a collection from ESPNcricinfo and other official cricket databases, including ball-by-ball
information with relevant contextual features: performance metrics from teams, player statistics, weather conditions,
and venue information. With this great performance, it was much higher than the best performance of traditional
machine learning approaches by as high as 94%. This work provides new insights into applying deep learning to sports
analytics and opens up more possibilities toward innovation in predicting the results of cricket matches.
Keywords: ODI Cricket, Deep Learning, LSTM.
Paper ID - 0739

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 87

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Multimodal Fusion for Depression Detection and Severity Estimation Using Deep
Learning
Senthil Pandi S, Kumar P, Salman Latheef T A and Varsha S P
This research presents a unique approach for automatic depression identification and severity estimation based on
multimodal data fusion based on deep learning. In particular, a specific convolutional recurrent neural network
structure is used in the suggested method that combines the answers from clinical surveys, voice analysis,
neuroimaging, and facial expression recognition. Using modality-specific encoders and an attention mechanism, the
model dynamically modifies each data set’s contribution to ensure accuracy in both detection and severity estimate.
This fully trained, end-to-end model is ideal for determining depression severity and detection. Our methodology
greatly outperforms existing methods in testing, with low mean absolute error in severity assessment on the PHQ-9
scale and excellent diagnosis accuracy for depression on a large dataset of participants. The results show that this
might be accomplished extremely well by integrating the two deep learning methods into a more comprehensive and
accurate depression evaluation, with far-reaching implications for mental health research and clinical practice. To
truly improve and validate this model, more research should incorporate longitudinal data and additional modalities.
Keywords: Deep Learning, Medical Diagnosis, Fusion, Severity.
Paper ID - 0740

Hybrid ACO-SA Algorithm for Bi-Objective Multi-Workflow Scheduling in Amazon

Cloud Environments
Senthil Pandi S, Kumar P, R.M.Suchindhar and Mithun Dineshkumar
In cloud computing systems, efficient workflow scheduling is essential for maximizing resource usage, reducing operating
expenses, and achieving performance goals. Conventional scheduling algorithms sometimes fail to achieve a balance
between conflicting goals, such lowering cost and makespan (total execution time), especially in settings with many
workflows, complicated task dependencies, and fluctuating resource needs. In order to overcome these difficulties
in AWS cloud settings, this study presents a unique method that combines Ant Colony Optimization (ACO) with
Simulated Annealing (SA) in a hybrid algorithm.In order to accomplish bi-objective optimization, the suggested
hybrid ACO-SA algorithm makes use of both SA’s probabilistic acceptance method and ACO’s worldwide exploration
capabilities. Through the integration of various strategies, the algorithm efficiently navigates the multi-dimensional
search space, providing solutions that strike a compromise between cost-effectiveness and makespan. The technique is
implemented and scaled using AWS services including Lambda, CodePipeline, S3, and Amazon EC2, which guarantees
flexibility and resilience in managing a range of workflow scenarios. the algorithm’s superiority over traditional methods
in terms of makespan reduction, cost efficiency, and adherence to deadlines. The findings underscore its potential for
enhancing operational efficiency and scalability in real-world cloud computing applications. This study contributes to
advancing scheduling techniques in cloud environments and suggests avenues for further research in dynamic adaptation
and integration with advanced machine learning techniques.
Keywords: Bi-objective optimization, Ant Colony Optimization (ACO), Simulated Annealing (SA), AWS services.

Paper ID - 0741

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 88

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Random Forest Bayesian Optimization Deep Transformer-Based Heterogeneous

Spatiotemporal Graph Neural Network for Identifying Parameters in QKD
Ilakkiaselvan Dhandapani, R.J.Kavitha, P.Ananadavalli, T.Thamizhmani, V.Balamurugan and
E.Elakkiyachelvan
This study presents a comprehensive evaluation of the Random Forest Bayesian Optimization Deep Transformer-Based
Heterogeneous Spatiotemporal Graph Neural Network (RFBO-THSGNN) algorithm, a proposed deep learning-based
method for channel estimation in MIMO systems. The results demonstrate the superiority of RFBO-THSGNN in terms
of accuracy, precision, Secure Key Rate(SKR) generation, transmission distance, and computational time. In channel
estimation, RFBO-THSGNN achieves the highest accuracy, ranging from 88% at 100 meters to 99% at 500 meters.
It also outperforms other algorithms in precision, secure key rate generation, and transmission distance. Notably,
RFBO- THSGNN exhibits a significant improvement in accuracy and precision as the distance increases, making it
more robust to channel distortion and noise. Furthermore, it achieves a higher secure key rate and transmission
distance compared to other methods. In terms of computational time, RFBO-THSGNN demonstrates a significant
advantage, requiring less than 130 seconds across all distances. Overall, the results suggest that RFBO-THSGNN is
a promising solution for MIMO channel estimation, offering a superior balance of accuracy, precision, security, and
computational efficiency.
Keywords: Deep Learning, Random Forest, Bayesian Optimization, Spatiotemporal Graph Neural Networks, Secure
Key Rate Generation, Deep Transformer.

Paper ID - 0743

Morphological And Statistical Operations Based On Segmentation And Classification

Of Skin Cancer Images
S. Anantha Sivaprakasam, V.Saravana Kumar, N. Srinivasan and M.Kavitha
Cancer remains one of the primary causes of deaths worldwide. Skin cancer poses serious medical concerns for many
people worldwide. Dermoscopy can help detect this preposterousness to determine whether visible areas on skin
contain benign or malignant cancerous tumors. Melanoma or non-melanoma cancer of the skin are usually the two
forms most likely to result from skin cancer development. Computer tools designed for skin cancer detection use a
precise segmentation method to analyze clinical features that indicate tumour risk in order to calculate their probability.
For this, relevant components in digital images must first be isolated using segmentation techniques that isolate them
accurately from one another. Due to the complex nature of cells, automating their processing can be an extremely time-
consuming and laborious task for pathologists. In this paper we offer an easy and innovative method to classify and
segment cells of skin. As part of its preliminary processing stage, this procedure begins with de-nosing, de-correlation
and color segregation operations being executed on images. Two new methods - Morphological as well as Statistical
Edge Based Segmentation and Morphological and Statistical Region Based Segmentation Techniques are introduced
and described here to separate skin images into individual nuclei of lesions. Once segmented color components have
been segmented separately, they are combined for an ultimate segmentation outcome. After extracting nuclei from
their cells and extracting their morphological features from them, two techniques previously discussed outperform
standard segmentation methods in terms of performance. Morphological and Statistical Edge Segmentation based on
Morphology is superior to Morphological and Statistical Region based Segmentation because nuclei can be identified
based on their particular character of morphology; classification proves accuracy of segmentation is evident and overall,
it stands at 96%.
Keywords: Dermoscopy, Classification, Morphological operation, Segmentation and Statistical operation.

Paper ID - 0744

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 89

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Enhanced Clustering Method For Segmentation Of Hyperspectral Satellite Images

V.Saravana Kumar, Kavitha M, S. Anantha Sivaprakasam, Bavya, N. Srinivasan and Saravana
Kumar
In this manuscript, it has been demonstrated that segmentation progress can be monitored on hyperspectral remote
sensing satellite images. A novel procedure using K-Means’ method of seeding with care for splitting hyperspectral
satellite images was devised. With its help, reduction bands on scenes were performed using narrowing regions
exhibiting most variance across each cluster and finally segmentation process via Particle Swarm Cluster [PSC] was
employed on reduced bands; also, statistical analysis of effect was employed when testing set ups related to these
procedures was also employed.
Keywords: K-Means, Particle Swarm Clustering algorithm, Fast K- Means and Careful seeding.
Paper ID - 0747

Secure Data Exchange in Cloud Computing: Enhancing Confidentiality, Integrity, and

Availability Through Data Partitioning and Encryption
Mohammed Ali Shaik, Vupulluri Sudha Rani, Afshan Fatima, Masrath Parveen, Dr.Juhi
Juwairiyyah and Nikhat Fatima
This paper explores advanced encryption methods for ensuring the security of the cloud with special reference to the
optimization of the block cipher and stream cipher techniques and the use of hybrid models of encryption. Genetic
optimization techniques used will apply genetic algorithm and machine learning cipher to improve on the encryption
control and incorporate real-time response to new threats. At the same time, machine learning models are applied to
learn with regard to encryption patterns and improve procedures of encryption. Furthermore, simulated annealing is
applied for the optimization of the encryption parameters achieving an overall balance between security and
performance. Besides, this methodology reinforces data protection against the risks of a single point of failure and
guarantees efficient data management in cloud computing, which, in turn, helps to gain more confidence in cloud
technologies. For results: https://github.com/niharali/SecureDataExchange.
Keywords: cloud security, annealing, secure data exchange, optimized block ciphers, encryption.
Paper ID - 0748

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 90

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Smart Water Dispenser: Integrating VoiceCommands and Facial Gestures

Shanmuga Sundar, Dhanushkumar A, Shanmuga Vadivu Pandy S, Jeevanandam L and
Dharunkumar A
In this paper, we introduce a novel water dispensing system that leverages voice recognition and head movement
tracking to provide a seamless, hands-free user experience. Traditional water dispensers require manual operation
for selecting and dispensing hot, cold, or normal water, which can be inefficient and inconvenient. Our system
addresses these issues by integrating advanced voice detection algorithms and real-time head movement tracking
technology. Users can issue verbal commands to specify their preferred water temperature, while head gestures
are employed to refine and confirm their selection. This dual-interface approach not only enhances usability but
also caters to individuals with physical disabilities, improving accessibility and ease of use. We present the system’s
design, implementation, and preliminary user testing results, demonstrating its potential to transform traditional water
dispensing methods into a more intuitive and inclusive solution. This innovation aims to streamline user interaction
and set a new standard for smart appliance interfaces.
Keywords: Smart water dispenser, voice detection, nose movement tracking, microcontroller, hands-free operation,
speech recognition
Paper ID - 0751

Smart Health Monitoring System Using IoT Sensors in Cloud Environment

Vigneswari J and B.Yamini
This project will propose an extensive architecture of an IoT-based cloud health monitoring system that utilizes IoT
sensors. A few sensors are interfaced with the system, including a DHT11 for humidity and temperature
measurement, an HBR (heart beat rate) sensor, and a SpO2 sensor for oxygen saturation monitoring, using
NodeMCU as the primary microcontroller. These sensors continue collecting data, which through Wi-Fi is uploaded
into the cloud and analysed as well as saved on the ThingSpeak platform. Among its components is the EDA sensor,
which could measure the heart rate of the user and tell so much about emotional and stress levels. With cloud
computing, medical practitioners can go through analysing, visualizing, and remotely monitoring data pertaining to
patients efficiently. In case the systems find any abnormal reading, then the alert systems in the framework will
immediately notify both the patient and the healthcare provider. Such a system is cost-efficient and scalable for
continuous health monitoring through the integration of IoT with cloud computing. The patients suffering from
chronic diseases find it very useful. The proposed framework concerns patient care, trying to improve the ability to
perform health care interventions, accuracy in data collection, and ability to utilize real-time analytics and machine
learning models for individualized treatment regimens.
Keywords: IoT, Real-Time Health Monitoring, NodeMCU, Sensors, Cloud Computing, ThingSpeak, Machine
Learning.
Paper ID - 0764

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 91

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Understanding AI Model Collapse: Causes, Impacts and Solutions

S. Sheeba Rachel, Karthik Balaji B M and Saiganesh V
Artificial intelligence (AI) models have become integral to many applications, from autonomous systems to data
analysis. However, a critical issue affecting their reliability is AI model collapse, which results in a sudden and
significant degradation of model performance. This work explores the phenomenon of model collapse in depth, outlining
its causes, impacts, and strategies for mitigation. Key causes include overfitting, underfitting, adversarial attacks, data
drift, and catastrophic forgetting. The consequences of model collapse can be severe, impacting accuracy, trust, and
security in high-stakes applications. To address these challenges, this work discusses various mitigation strategies such
as regularization, ensemble methods, and continual learning techniques. Real-world examples illustrate these issues
and solutions, highlighting the importance of developing robust AI systems. The research concludes by identifying
future research opportunities aimed at enhancing model stability and resilience. Understanding and addressing Al
model collapse is crucial for advancing reliable and trustworthy AI technologies.
Keywords: AI Model Collapse, Overfitting, Adversarial Attacks, Data Drift, Catastrophic Forgetting, Mitigation
Strategies.

Paper ID - 0768

A Study On Menopausal Symptoms And Perceived Stress Among Middle – Aged

Women In An Urban Community
Bavanipriya V and Abirami M
Women in midlife are more susceptible to physiological life cycle changes and substantial hormonal swings,
potentially resulting in stress, anxiety, and depression. The study aims to establish a correlation between stress and
menopausal symptoms in middle-aged women. A cross-sectional study using a Modified Menopause Rating Scale
(MRS) Questionnaire surveyed 106 middle-aged women aged 40 to 60 to identify physical, psychological, and
urogenital symptoms. The participants’ stress perceptions were then evaluated using the Perceived Stress Scale. The
mean age of menopause in this study was 47.2 ± 5.6 years. The most prevalent menopausal symptoms were joint
and muscle pain (97.3%), physical and mental fatigue (81.1%), and sleep disturbances (88%). Subsequent symptoms
included heat flashes, perspiration, and despair. Peri-menopausal women exhibited considerable differences compared
to post- and pre-menopausal women. The correlation between menopausal symptoms and stress in middle-aged
women is significant. Stress is integral to menopause, a significant life transition. Menopause symptoms include
sudden physiological and psychological changes that may lead to sleep disturbances, exacerbated by stress.
Keywords: Menopause, Middle – aged women, Stress, MRS, PSS.

Paper ID - 0771

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 92

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Emotion-Based Frequency Recommendation and Healing System Using Speech

Analysis
Vignesh Kumar M, Chintamakula Mehereesh, Busetty Praneeth, Boppudi Bhargav and Boyapati
Kumar
In this paper, we introduce the Emotion-Based Frequency Recommendation and Healing System using Speech
Analysis that focuses on treating a user’s emotional needs using speech analysis methods. The system recognises the
basic emotion of speakings including happy, sad, fear, anger and neutral through machine learning algorithm. The
therapy part prescribes a frequency based therapy once the emotion is recognized, like binaural beats or isochronic
tones for users to regulate their emotions. In this context, the system is designed to follow the users’ emotions
fluctuation, and as a result, the therapeutic interventions are delivered based on the users’ emotional experience in
real-time. This paper describes the proposed system, methodology, and the system architecture as well as the
evaluation outcomes.
Keywords: Emotion Recognition, Speech Analysis, Frequency-Based Therapy, Machine Learning, Real-Time
Systems.

Paper ID - 0776

Solar Energy and Visible Light Communication for Eco-Friendly Communication

Systems-An Overview
P.Gandhimathi, A.Senthil Kumar, P Tharcis, Nirmala Baby and B. Anitha Vijayalakshmi
Renewable energy solutions leverage natural, constantly replenished sources for power generation with solar energy
being one of the most prominent techniques. Solar panels convert sunlight into electricity powering a wide array of
devices and systems. Meanwhile, Visible Light Communication (VLC) is an innovative wireless technology that uses
visible light typically from Light Emitting Diodes (LEDs) to transmit data. Unlike conventional Radio Frequency (RF)
communication, VLC utilizes light waves offering benefits such as high data transmission speeds, enhanced security and
access to an expansive unregulated spectrum. When solar-powered LEDs are integrated into VLC systems they serve
dual functions, providing both illumination and a medium for data transmission. This synergy significantly reduces the
overall energy consumption of VLC systems as the communication power is derived from renewable solar energy. By
incorporating solar LEDs the reliance on conventional power sources is minimized, lowering both energy consumption
and operational costs. Moreover, VLC’s ability to achieve high data rates is enhanced in an environmentally friendly
way.
Keywords: Renewable Energy, Solar Energy, VLC, LEDs, Sustainability, Energy Efficiency, Wireless Communication,
Data Transmission.
Paper ID - 0778

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 93

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Learning Plant Anatomy through Ar & Vr

Uma Mageswari, Rajasekar A, Dharunkumar A, Dinesh R, Jashwanth Sathish and Vasanth B
This work reports on the development and evaluation of a cutting-edge teaching tool for plant anatomy that uses
augmented and virtual reality (AR and VR). The minute the details and spatial diversity of plant systems are frequently
difficult to explain using conventional teaching approaches. We developed an immersive learning environment that
improves students’ comprehension and engagement by utilizing AR and VR technologies. The system’s architecture,
instructional materials, and findings from a user study including college and high school students are described in this
report. The results emphasize how the potential of AR and VR in botanical education affects human language and
show notable gains in learning outcomes and student engagement.
Keywords: Augmented Reality (AR), Virtual Reality (VR), Plant Anatomy, Immersive Learning Environment,
Student Engagement, Learning Outcomes.
Paper ID - 0780

Automatic Following Shopping Cart with Bluetooth Connectivity and Obstacle

Avoidance
Suganeshwaran M, Kumaran K and Saranya G
This paper presents the design and development of an autonomous shopping cart that follows the user through the
use of ultrasonic sensors and Bluetooth communication. The cart is designed to provide hands-free shopping by
autonomously tracking the user’s movements and maintaining a set distance. The core functionality is powered by an
Arduino microcontroller, which processes sensor data and controls the cart’s movement. DC motors provide forward
and backward motion, while a servo motor steers the cart in the direction of the user. The system includes an
integrated obstacle detection mechanism using ultrasonic sensors to prevent collisions, ensuring safe navigation in
crowded environments. Audio feedback is provided to the user in real-time, announcing directional changes such as
“Turning left” or “Turning right.” The Bluetooth module enables seamless communication with the user’s smartphone,
allowing the cart to receive commands like starting, stopping, or adjusting the following mode. This shopping cart
aims to enhance user convenience, particularly for individuals with mobility challenges, and represents a significant
advancement in automation technology for retail environments. The proposed system offers a novel, accessible, and
efficient solution to the limitations of traditional shopping carts by combining autonomous navigation with user-
friendly features, contributing to a better shopping experience for a wide range of users.
Keywords: bluetooth, obstacles avoidance, sensors, motors.
Paper ID - 0782

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 94

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Hybrid Machine Learning Approach for Accurate Railway Traffic Forecasting

P Vinayagam, Kanagamalliga S, M.V. Hariharan and S Niranjan
For efficient operations and efficient traffic management, railway traffic forecasting is essential. Conventional
forecasting systems frequently have trouble representing nonlinear relationships and temporal dependencies, which
results in subpar accuracy and reliability. These methods are based on traditional machine learning algorithms and
statistical techniques like linear regression and ARIMA. Furthermore, these models are unable to account for
seasonality and traffic variations that occur in the actual world. To tackle these limitations, the study suggests a
novel hybrid approach called Gradient-Boosted Recurrent Neural Network (GBRNN), which combines
Gradient-Boosted Machines (GBMs) and Recurrent Neural Networks (RNNs). The GBRNN combines RNNs more
especially, Long Short-Term Memory (LSTM) units for temporal dependency capture with GBMs for advanced
feature extraction. With a prediction accuracy of 89.2%, the proposed method outperforms the existing techniques,
as shown by its lower Mean Absolute Error (MAE) of 4.32 and Root Mean Square Error (RMSE) of 6.78.
Conversely, the greater MAE and RMSE values of existing systems indicate less accurate forecasts. Moreover, traffic
volume is shown to be the most significant component by the feature importance analysis of the GBRNN model,
outperforming other variables such as weather and train delays. The results highlight how well the GBRNN performs
in improving operational decision-making and forecasting accuracy in railway traffic management. The continuing
improvement of the model and its adaptation to changing traffic patterns will be the main goals of future studies.
Keywords: Video Compression, Mobile Applications, Energy Efficiency, Hardware Optimization, Sustainable
Computing.

Paper ID - 0783

A Novel Machine Learning approach for Real-Time Correction of Atmospheric

Distortion in Multispectral Satellite Images
Sivasakthi Thanigainathan, Anousouya Devi M, Keerthivasan K, Dharanyadevi P, Kalpana S and
Keerthivasan H
An extensive study of atmospheric distortion correction in multispectral satellite images is presented in this work.
Utilizing thorough testing on several datasets, assess the effectiveness of the suggested approach. The proposed
methodology includes atmospheric modeling, preprocessing images, applying correction algorithms, and validation
procedures. Examine the effects of different atmospheric elements, such as gases and aerosols, and use quantitative
metrics like picture quality evaluations and cross-checks with real data. The new dehazing approach greatly improves
the clarity and interpretability of multispectral satellite images by tackling the problems caused by haze-induced
deterioration. The efficiency of the approach is seen in fields including forestry, urban planning, agriculture, and
disaster relief. A better understanding of environmental dynamics facilitates informed decision-making for sustainable
resource management. This work advances satellite image atmospheric correction techniques, which have ramifications
for various earth observation uses.
Keywords: Atmospheric distortion correction, multispectral satellite images, dehazing approach, Environmental
dynamics.

Paper ID - 0784

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 95

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Optimizing Agricultural Yields using AI and Machine Learning

Vinayagam P, Kanagamalliga S, Hariharan M V and Niranjan S
The paper explores the profound impact of AI and ML on sustainable farming practices and the optimization of
agricultural production. The article highlights significant developments in data-driven decision-making for producers,
such as autonomous systems, predictive analytics, and precision agriculture. Modern precision agriculture utilizes
advanced technology to continuously monitor the health of crops, while predictive analytics leverages cutting-edge
techniques like Support Vector Machines and regression models to forecast yields using historical data and present
circumstances. Through the integration of AI, autonomous robots play a crucial role in minimizing chemical usage and
labor costs by enabling precise pesticide application and effective weed removal. There are still lingering challenges
related to data accessibility, scalability, quality, and adoption. Addressing these challenges requires the implementation
of comprehensive training programs and enhanced data acquisition methods. It will empower farmers and ensure the
successful integration of AI and ML in agriculture. Through the implementation of these innovations, the agriculture
sector has the potential to see significant improvements in output, environmental impact, and food security.
Keywords: Agricultural Optimization, Data-Driven Farming, AIEnhanced Crop Management, Machine Learning,
Precision Farming, Sustainable Yield Prediction
Paper ID - 0785

House Authentication Using Finger Vein Based On Anatomical Features of Vein

Patterns
D.Chithra, T. Veena, A.M Sermakani, S. Juliafaith and P. Senthil
Finger vein recognition, a method of biometric authentication, utilizes pattern recognition techniques based on finger
vein images located beneath the skin’s surface. Serving as a biometric authentication system, Finger Vein ID compares
an individual’s vein pattern with previously collected data. With a focus on bolstering home security, our objective is
to offer straightforward and adaptable solutions for safeguarding sensitive information within residential settings. The
integration of finger vein authentication at the home entry level ensures that only authorized individuals gain access.
By leveraging finger vein authentication for home security, we aim to explore its various applications and underscore
its effectiveness in ensuring the privacy of personal data within the confines of homes.
Keywords: FEBA classification, finger vein biometrics, Matching vein anatomy, Cloud-based authorized, biometrics
verification.
Paper ID - 0789

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 96

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Design and Development of Virtual Reality Headset-Controlled Pick and Place Robot
Arm
K Kaviya Sanjay, K Sreehari, G Shanmugasundar, Su Suganthi, R Preethi and J Kirthan
This paper presents the design and development of a virtual reality (VR) system that enables users to control a
pick-and-place robot arm through natural, intuitive movements. Leveraging VR technology, users wear a headset and
motion-tracking gloves, allowing them to interact with the robot in real-time as if they were directly manipulating
objects in the physical world. This project is inspired by the technology depicted in the movie Ra.One, where a
character controls a virtual entity through similar means. The primary objective of this system is to improve the
precision, ease, and intuitiveness of robotic control, which is critical in various fields such as manufacturing, assembly,
and remote operations. The integration of VR with robotics allows for an immersive experience, where users can see
the robot’s actions in a virtual environment, offering feedback and enhancing control accuracy. Initial experiments
demonstrate that this VR-based control system provides significant advantages over traditional control methods,
including better user engagement and higher precision in performing tasks. This work contributes to the ongoing
development of advanced human-robot interaction technologies and opens up new possibilities for remote operation
and training applications.
Keywords: Virtual Reality(VR), Robotics, Pick-and-Place Robot, Human-Computer Interaction, Real-Time Control,
ImmersiveTechnology, MotionTracking, Wearable Technology.
Paper ID - 0790

ANTI-CONDOR (The Phishing Detector using Random Forest Algorithm)

Denish Manova M, Jeevanandam L, Shanmuga Vadivu Pandy S, Gopinathan S, Rajasekar A and
Radhika Rajaram
Cybersecurity still faces a great challenge regarding phishing, which normally evades the conventional detection
methods. This paper suggests an original approach of integrating random forest algorithms into browser extension
and mobile apps to improve phishing detection. The browser extension works on the spot by analyzing URLs and
web page content in real time, evaluates features such as URL structure analysis, domain reputation checking, and
content similarity assessment for distinguishing legitimate websites from phishing ones. The mobile app also provides
these functionalities for smartphones thereby protecting them against opening up links in messages or social media
that could be phishing attempts. This system has a friendly user interface and can effectively detect different types
of phishing attacks to ensure users protect their digital identity and sensitive data while additional improvements are
made towards increasing its efficiency as well as customization capabilities.
Keywords: Phishing detection, Random Forest algorithm, Cybersecurity, URL analysis, Decision-making processes,
Anti-phishing tools, Real-time analysis
Paper ID - 0791

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 97

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

AI Legal Documentation Assistant

Gopinathan S, Radhika Rajaram, Sivagar Mr, Jayapriya M, Samsthana K L and Jeyanthini E N
The proposed approach aims to simplify the process of legal attestation process for individuals and small businesses
in India through the use of advanced AI algorithms. The system allows users to upload or input legal documents,
which are then pre-processed to sanitize and tokenize the text. With LegalBERT, the documents are encoded and the
complex legal language is simplified with T5. Relevant legal entities and clauses are extracted with BiLSTM and the
document is summarized with Longformer. Finally, user-friendly output or responses are generated using GPT-4. The
resulting simplified text, extracted entities, summarized document and responses are displayed on the website. This
method ensures document accuracy through integration with legal databases and provides options for consulting legal
experts on complex issues. This innovative strategy promotes inclusion and legal literacy, bridges the gap between the
general public and legal complexity.
Keywords: Legal simplification, AI-driven, LegalBERT, T5, Longformer.
Paper ID - 0792

Counterfeiting Detection System: A Solution to Combat Product Counterfeiting

Amit Kumar Gupta, Ruchi Rani Garg, Harsh Khatter and Mangal Sain
Counterfeiting is a growing problem impacting the global marketplace, especially burgeoning economies like India. It
hampers economic growth and leaves consumers struggling to differentiate between genuine products and fakes. In
response, this research paper introduces an innovative solution - the ”Counterfeit Detection System.” This system
employs QR codes linked to a manufacturer’s database, offering a reliable tool for real-time product authentication.
When a QR code is scanned, the system validates the product’s authenticity, ensuring consumers are purchasing
genuine items. The system aims to protect consumers and manufacturers, enhance supply chain transparency, and
fortify brand trust. While the initial focus is on branded clothing, the principles underpinning the system can be
applied across various industries. In a wider perspective, this research emphasizes the significance of innovative, tech-
based solutions in safeguarding consumers and businesses from the far-reaching negative effects of counterfeit products.
As we navigate the era of digital consumption, resources like the Counterfeit Detection System become increasingly
vital in upholding the integrity of the global market. This study strives to spotlight the potential of such technology in
combating the counterfeit market, ultimately aiding in establishing a more secure and reliable shopping environment.
This paper provides guidance for manufacturers, retailers, consumers, and policymakers interested in comprehending
and tackling the intricate problem of counterfeiting.
Keywords: Counterfeiting, Supply chain transparency, QR Code, Digital consumption, Global Marketplace.

Paper ID - 0795

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 98

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Digital evidence extraction and analysis of Disk Image

Udhayakumar S, Sai Pavan Rangu S, Abhiram Patel U and Tata Seetha Rama Sai Vamshi Krishna
In today’s investigations concerning cybercrime, virus detection, and legal actions, the forensic analysis of digital
evidence—especially from disk images—is essential. One essential tool in this field is the Disk Image Analyser Tool
(DIAT), which gives investigators the capacity to examine disk images in great detail, find buried information,
recognize malicious code, and provide evidence that is useful in court. The usefulness, approaches, and importance of
DIAT in forensic analysis are all thoroughly examined in this work. It talks about the key components of DIAT,
such as how to parse disk pictures, and partitions, pull out metadata, find anomalies, Database Tables and make
investigative procedures easier. This work also emphasizes the useful uses of DIAT in forensic contexts, including
malware signature identification, file system artifact analysis, and digital timeline reconstruction. The effectiveness
and drawbacks of DIAT are evaluated via a study of case studies and experimental assessments, providing insight
into how it might improve forensic investigations and progress digital forensic techniques. Additionally, some
improvements and future approaches for DIAT are suggested to enhance its capacity to handle the changing
demands of digital forensic investigation.
Keywords: Disk image analysis, forensics, disk image, data hiding, Digital Evidence, evidence extraction,
extraction tools, file sorting, Keyword search.
Paper ID - 0808

Hybrid Model For Email Spam Detection Using Multi-Modal Knn and Svm
I Vasudevan, Denis Amirtharaj, A.Jaisuriya, R.M.Dilip Charaan, S.Ashok Kumar and Leena Jenefa
Email Fraud is a one of the major problem in our society nowadays, with quick rise of internet frauds, spams. Some
people was using this for illegal and evil purposes like phishing and fraudulent. By creating a fake profile and fake
account, the spammers are pretending like a genuine person in the spam emails and become much easy for them
to spam. In this paper, was going to propose a method for email fraud detection that combines the strengths of
the Naive Bayes algorithm and Support Vector Machine (SVM) in machine learning techniques. The Naive Bayes
algorithm known for its simplicity and effectiveness in handling large datasets and it used to model their relationships
between words in emails and their properties of being spam or ham. Meanwhile, SVM is able to separate classes in
high-dimensional spaces and it also used for the accuracy classification. By integrating these two approaches, the
proposed method aims to improve the detection of spam emails by using the advantages of both algorithms. This
mixed-breed model offers a strong solution to the challenge of distinguishing between spam and not spam emails. Most
of the existing methods have the less accuracy in detecting the spams. In this paper, we have done by using SVM and
Naive Bayes algorithm, our approach to email fraud detection achieves higher accuracy of 97.49% and fast processing
speed compared to other proposed methods.
Keywords: Machine learning (ML), Artificial intelligence (AI), Support Vector Machine (SVM), Uniform resource
locater (URL), Naive Bayes (NB).
Paper ID - 0811

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 99

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Data Discovery on Prostat Cancer through Meta Hybrid Learning using Ensemble
Deep Autoencoder
K Nattar Kannan and E.Sathesh Abraham Leo
Purpose of Study is focus onthe early diagnosis of prostate cancer, which is a major concern for the health of people
all over the world, requires the use of cutting-edge imaging techniques such as magnetic resonance imaging (MRI).
The methodology and techniques used in this research presents a novel approach that makes use of ensemble deep
autoencoders as a means of detecting prostate cancer in MRI scans. The purpose of the ensemble framework is to
improve the robustness and accuracy of the detection process by capitalizing on the strengths of many autoencoder
models. Major Findings of this research is the autoencoders have been optimized for the process of extracting
complex characteristics from MRI scans. The approach known as ensemble learning takes all these distinct
representations and combines them into a single diagnostic model that is both more comprehensive and reliable. In
summary, Experiment results indicate that the proposed ensemble deep autoencoder system performs better than
individual models, indicating its potential as a reliable instrument for the accurate early identification of prostate
cancer in MRI scans.
Keywords: MRI images, Prostate cancer, Ensemble learning, Deep learning, Autoencoders.
Paper ID - 0816

Advanced Data Mining Techniques For Crop Yield Predictive Modeling: The
Strategic Modified Gradient Boosting Regression (Smgbr) Approach
Natvar Sardarbhai Patel, Dr. Bhavesh M Patel and Sirajbhai A Nagalpara
Agricultural productivity is critical for economic stability, particularly in agrarian regions like Banaskantha District,
North Gujarat, where cabbage farming significantly contributes to local livelihoods. Effective crop yield prediction
models are essential for planning, resource allocation, and sustainable agricultural practices. This study presents the
Strategic Modified Gradient Boosting Regression (SMGBR) model, designed to improve the accuracy of cabbage
crop yield forecasts. Unlike traditional Gradient Boosting Regression (GBR) models, the SMGBR model
incorporates a dynamic learning rate adjustment, which enhances its ability to handle complex, non-linear
relationships in agricultural datasets. The study utilizes an extensive dataset collected over twelve years (2010-2021),
which includes critical variables such as historical crop yield records, detailed meteorological data, and soil health
metrics. These factors are integrated into the model to refine predictive accuracy. The results indicate that the
SMGBR model outperforms conventional approaches, delivering more reliable and precise yield forecasts. The
improvements in prediction accuracy achieved by the SMGBR model are particularly beneficial for agricultural
planners, policymakers, and farmers. This model can guide more informed decision-making on crop management,
resource distribution, and long-term agricultural planning, ultimately promoting both economic and environmental
sustainability. By offering precise, data-driven yield predictions, this research contributes to optimizing agricultural
output while reducing waste and supporting the ecological balance in cabbage farming. The findings underscore the
importance of advanced machine learning techniques in fostering resilience and sustainability in agricultural sectors.
Keywords: Dynamic Learning Rate, SMGBR, Crop Yield Prediction, Gradient Boosting Regression, Machine
Learning.
Paper ID - 0825

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 100

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Timber Identification Based on the Grain Structure using Learning Algorithms

Kumar P, Senthil Pandi S, Jain Bai B and Sathish Kumar Kannaiah
Lumber is used for many purposes all over the world. Grain structure is a characteristic of wood that can be used
to identify different species. It refers to the pattern formed by the wood fibers as they grow. The grain can vary
widely depending on the tree species, its growth conditions, and the part of the tree from which the wood is taken.
Identifying the type of wood is really a difficult task for a normal person. A subject-matter expert is always expected
for this purpose. Examine the grain pattern closely to compare it with known patterns of different species. While
grain structure is a valuable tool for identification, it’s important to consider other factors like color, texture, and
density for a more accurate determination. The integration of these characteristics can enhance the precision of
timber identification. This study aims to determine the type of wood through grain structure analysis. Deep learning
algorithms can facilitate this achievement. A comparison of 3 different types of CNN model i.e., OwnNet, AlexNet
and LeNet is done. LeNet model seems to produce the highest accuracy, So LeNet model is being used for processing.
The cross-section of the wood is captured and uploaded in the web application. The data is processed using the
classification-based algorithm (CNN – LeNet) on Neural Networks for analyzing and identifying the type of wood.
Then the common name and scientific name are displayed immediately on the web application.
Keywords: Timber, OwnNet, AlexNet, LeNet, CNN, Deep Learning
Paper ID - 0826

Text-to-Cadence: Synthesizing Rhythmic Voice Through Tacotron2 and Waveglow

Kumar P, Senthil Pandi S, Muqaddam Aaqil Sheriff and Sathish Kumar Kannaiah
The voice represents a complex mechanism employed by humans for the purpose of communication. As human
beings, we possess the remarkable capacity to articulate our thoughts through vocalization, or more accurately, to
manipulate molecules in a manner that conveys meaning. Each individual possesses a distinct quality to their voice,
an attribute that remains beyond our control. Conventional approaches have predominantly concentrated on the
advancement of text-to-speech models, attaining exemplary performance levels. This article introduces an innovative
methodology, text-to-cadence, designed to elevate the level of personalization. We are pleased to present text-to-
cadence, a sophisticated method that takes both text and the desired artist’s name as input, generating an audio file
that features their rhythmic vocal interpretation of your text as output.
Keywords: text-to-speech, rhythmic voice, music, waveglow, TACOTRON2.
Paper ID - 0827

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 101

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Analysis And Prediction Of Bitcoin Prices Utilizing The Data Science Methodology
Kumar P, Senthil Pandi S, Bala Subramanian C and Sathish Kumar Kannaiah
Bitcoin is one of the many advanced monetary standards used overall for electronic trades and money-related targets.
Bitcoin has piqued the interest of both financial backers and scientists ever since Nakamoto first proposed it in 2008.
Bitcoin is a decentralized mechanized cash that utilizes encryption techniques, decentralized arrangements, and various
cycles to approve trades and guarantee security. Bitcoin can function as a digital asset and payment system, serving
as a form of virtual currency. The recent surge in Bitcoin’s prices has garnered significant attention from both the
media and the general public. Because of its standing and eccentricity in cost changes, Bitcoin has received a lot of
attention from monetary patrons, markets, examiners, and the media. The primary goal of our article is to dissect the
typical fluctuations in bitcoin prices. We hypothesize that artificial intelligence strategies will aid in comprehending
the excessively complex components of bitcoin. The goal of our paper is to develop an artificial intelligence model
that can identify examples from verifiable data and make calculations to predict Bitcoin’s price.
Keywords: Bitcoin Prices, Digital Transactions, Cryptocurrency, Blockchain, Data Science.
Paper ID - 0828

Stock Market Portfolio Valuation using CPU based parallelism

Dr Kumaran K, Sarath Rajan Senthilkuma, P Kiranteja, Arun Karthik Anand Kumar and P K
Desigan
In the past decade, the volume and variety of financial instruments has grown exponentially. Hence, portfolio
valuation has become a computationally intensive task, especially for large portfolios and complex financial models.
This research explores the application of CPU-based parallelism to accelerate the valuation process. By utilizing the
multi-core architecture of modern processors, we aim to significantly reduce computation time without compromising
accuracy. The study investigates the implementation of parallel algorithms for various valuation methodologies,
pricing models, and risk analysis. We develop a system where we calculate a user’s portfolio using parallel
computation. We divide a portfolio into sub-portfolios and using Python’s multiprocessing module, distribute the
workload across multiple cores of the CPU. The performance of the proposed method is evaluated on different
portfolio sizes and compared with serial methods of valuation. The results show that parallel processing speeds up
the calculation by 77% compared to serial mode of processing. Parallel method of valuation was also found to be
more efficient for large portfolio sizes. The findings contribute to the development of efficient and scalable portfolio
valuation systems, enabling faster decision-making and risk management. The findings of this study accelerate the
development of high-performance computing solutions for the financial industry.
Keywords: Portfolio Valuation, Parallelism, High performance computing, Financial Modeling, Computational
finance.
Paper ID - 0830

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 102

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

An Experimental Analysis On Optimizing Lithium Ion Battery Lifespan Predictions

With Xgboost And Bayesian Techniques
Keren Persis p, Dr. Saranya S, Dr.S.Sivasakthi and Swaroop Gannamani
The goal of this study is to assess the performance of the XGBoost algorithm in predicting the Remaining Useful Life
(RUL) of lithium-ion batteries. With the increasing demand for reliable and efficient battery health monitoring systems,
accurately forecasting the RUL of batteries has become crucial, especially in applications involving electric vehicles,
renewable energy storage, and portable electronics. This study focuses on comparing different optimization techniques
applied to XGBoost, including parameter grid search and Bayesian optimization, to determine the most effective
approach for improving prediction accuracy.The dataset used in this analysis was sourced from Kaggle, containing
approximately 6500 records of lithium-ion battery data.The findings from this study emphasize the effectiveness of
XGBoost in RUL prediction, with optimization techniques playing a crucial role in improving its performance. The
base XGBoost model, while reasonably accurate, benefited significantly from hyperparameter tuning.In terms of MSE,
the Bayesian-optimized XGBoost model reduced the error from 0.00266 (grid search) to 0.00141, a significant reduction
that demonstrates its efficiency in minimizing prediction errors. Similarly, RMSE was reduced from 0.052 to 0.0375,
and MAE decreased from 0.00219 to 0.00178, indicating that the Bayesian optimization technique was able to fine-tune
the model more effectively than grid search.By achieving an R² score of 0.9997 and minimizing MSE, RMSE, and
MAE to extremely low values, the Bayesian-optimized XGBoost model offers a promising solution for applications
requiring precise battery health predictions.
Keywords: XG Boost, Pbounds, Parameter tuning, Mean Square Error, RSquared, Mean Absolute Error.

Paper ID - 0834

Accuracy Enhancement in Detecting the Driver Drowsiness using CNN

Priyanka K, Senthil Pandi S, Srinivasan K S and Kumar P
Real-time detection and mitigation of driver fatigue is possible through the use of drowsy driver detection and alarm
system, which incorporates computer vision and machine learning techniques. In facial and ocular features
identification, it involves a haar cascade classifier which utilizes the OpenCV library in tracking a driver’s face and
eyes. Ensuring accurate detection of pertinent facial features crucial for spotting drowsiness, In turn, these faces and
eyes are then fed into Convolutional Neural Network (CNN) model to predict whether a driver is awake or asleep.
This CNN model was trained using data containing different types of faces and eyes that show fatigue this therefore
helps to accurately determine if the person behind the wheel is conscious or not. Thus, this CNN model uses deep
learning capabilities to decide about when to alert drivers in advance of car accidents as a result of becoming sleepy
while driving. Implementation of the system is versatile and can, therefore, be embedded in different automotive
platforms and environments. Whether integrated into vehicles or installed in already existing driver assistance
systems, the alert system for drowsy driving makes travel safe through continuous monitoring of the driver’s
wakefulness. Real-time alerts raise an alarm by warning with audible or visible signals to reduce the chance of
accidents due to drowsy driving. This will prove how the combination of computer vision and machine learning can
make an intelligent system that can detect fatigue among drivers and act accordingly to promote road safety and
avoid road accidents due to impairments arising from drowsiness.
Keywords: haar cascade classifier, OpenCV, CNN.
Paper ID - 0836

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 103

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Exploring the Interplay between AI-Generated Art and Human-Created Art: A

Comparative Analysis
Shanu Khare, Navjot Singh, Sivakamy N, Veeramanickam M.R.M and Muthukumarasamy S
This research paper investigates the interaction between AI-generated art and human-created artwork, supplying a
comparative analysis that sheds mild at the evolving dynamics of artistic expression. As artificial intelligence
increasingly con- tributes to the creative process, this study cautiously examines the specific functions and reception
of AI-generated artwork alongside the conventional practices of human artists. Through a curated choice of
numerous works of art and an exploration of pertinent literature, the research seeks to discern the unique strengths
and weaknesses of every shape, contemplating their effect at the artwork global and the broader implications for the
future of creativity. In addition to the classy concerns, the studies delves into the moral dimensions of AI in the arts,
exploring questions of authorship, bias, and possession. By navigating the problematic stability between
technological innovation and human ingenuity, this take a look at targets to offer valuable insights into the
coexistence of AI and traditional artistic practices, contributing to a nuanced understanding of the transformative
capability and moral demanding situations posed by using the integration of synthetic intelligence within the current
artwork landscape.
Keywords: Artificial Intelligence; AI-generated art; Ma- chine Learning; Neural Networks; Creative Process;
Compar- ative Analysis; Human-Created Art; Contemporary Art; Digital Creativity; Aesthetics; Authorship; Ethical
Considerations; Al- gorithmic Art; Technological Innovation; Digital Age; Artistic Expression; Reception; Bias in AI;
Ownership in Art; Transfor- mative Potential

Paper ID - 0838

Optimizing DNA Cryptography: using HPC Leveraging GPU and Parallel Processing
Shreyank Saksena, Ishaan Kanade, Suyash Agrawal, Debesh Biswas and Kumaran K
This paper introduces the DNA-Genetic Encryption Technique, newly designed cryptographic technique that aims
to improve security through processes of multiplication and genetic functions. D-GET converts digital information
into a binary form that is then encoded into DNA sequences. In it, the data undergoes several rounds of reshaping,
encryption, crossover, mutation, and final reshaping to achieve high unpredictability and diffusion. This implies that
D-GET ensures assurance by repeating the stages at least three times, therefore making it safe. The encrypted
information can be transmitted in text or image forms, which is more complex and flexible enough to be deciphered.
The same happens in the decoding process at the receiver’s end. In addition to that, DGET not only embeds a technique
of multi-format conversion but also complexities cryptography attacks: due to the multilevel defense mechanism, a
variety of cryptanalytic attacks can be opposed by providing a significant number of different key sequences with
considerable uncertainty. Experimental results confirm the robust protection of the proposed D-GET scheme-minimal
inter-correlation between original and encrypted data while being identical in terms of integrity and exact accuracy
of recovered information. These outcomes indicate the potential of this approach to provide higher security of data
using new types of operations applied to cryptographic objects.
Keywords: DNA cryptography, genetic operations, multi iteration encryption, parallel processing, data security,
crossover, mutation, diffusion, cryptanalysis.
Paper ID - 0839

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 104

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Prevention Of Sql Injection

Sathya V, Anirutth SA and Mohamed Safresh H
SQL Injection attacks are a method used to gain unauthorized access to systems. To combat these attacks, software
solutions are developed that incorporate unique values and employ robust authentication mechanisms to verify
legitimacy. This serious security vulnerability allows attackersto exploit weaknessesin web applications or systems.
To prevent such attacks, software design emphasizes strategies for analyzing and addressing malicious behavior.
Various algorithms are utilized for manual scanning, based on a peak and conquer approach that leverages different
time and space parameters to detect potential threats.
Keywords: Queries, authentication, cybersecurity, legality, parameters.

Paper ID - 0843

An Integrated Xgboost And Bilstm Model For Advanced Remaining Useful Life (Rul)
Predictions In Aircraft Maintenance
Sakthivel Janarthanan and A. Anthonisan
Accurate prediction of Remaining Useful Life (RUL) in aircraft maintenance is critical to ensuring operational
efficiency and safety. This study proposes an integrated XGBoost-BiLSTM model for advanced RUL predictions in
aircraft components. The model leverages XGBoost for feature selection to identify the most relevant features from
multivariate time-series data, reducing the dimensionality of the dataset and improving computational efficiency.
BiLSTM (Bidirectional Long Short-Term Memory) is employed to capture long-term dependencies in the data,
enabling more precise temporal predictions. The proposed model is evaluated using performance metrics such as
accuracy, precision, recall, F1-score, and Root Mean Squared Error (RMSE) and is compared with nine existing
models, including Random Forest, Decision Tree, Gradient Boosting, Support Vector Machine (SVM), CNN-LSTM,
and GRU. The proposed XGBoost-BiLSTM model outperforms all the other models, achieving an accuracy of
94.76% and the lowest RMSE of 0.1524. In addition, the model demonstrates superior precision (93.45%), recall
(92.56%), and F1-score (93.00%), making it highly effective for RUL prediction in aircraft maintenance. The results
indicate that the hybrid approach enhances prediction accuracy and reduces errors, offering a robust solution for
predictive maintenance.
Keywords: XGBoost, BiLSTM, Remaining Useful Life (RUL), Aircraft Maintenance, Feature Selection,
Time-Series Data, Predictive Maintenance.
Paper ID - 0844

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 105

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Analyzing Global Development: A KMeans Clustering Approach to the 2023 Legatum

Prosperity Index
Ramya P, Subedha Varatharaj, C Amritha, S Hemalatha and Nithiyasree P
This paper provides an in-depth analysis of global country development using the 2023 Legatum Prosperity Index
dataset, which evaluates countries across dimensions such as Safety and Security, Governance, Personal Freedom,
Economic Quality, Health, Education, and Social Capital. By employing Exploratory Data Analysis (EDA), the
study uncovers trends and patterns, offering insights into the factors influencing prosperity. Using the KMeans
clustering algorithm, countries are grouped into clusters with similar development profiles, distinguishing developed,
developing, and underdeveloped nations. The analysis highlights the top 10 performing countries in key dimensions
like Governance, Health, and Education, providing valuable insights into the drivers of national prosperity. The
clustering results reveal how countries with strong Governance and Health systems tend to perform better in overall
prosperity, while others lag due to deficiencies in these areas. It aims to guide policymakers by identifying key areas
of improvement, offering a data-driven approach to enhancing national well-being. Future work could incorporate
additional datasets, such as GDP and Human Development Index (HDI), and explore alternative clustering methods
to gain a more comprehensive understanding of global development patterns.
Keywords: Exploratory Data Analysis (EDA), KMeans clustering algorithm, Governance, Health, and Social Capital,
global prosperity.
Paper ID - 0850

IoT-Enabled Safety Helmet for Coal Miners: Real-Time Monitoring, Data Collection,
and Analysis
Radhika Rajaram, Gopinathan S, Ranjith Kumar, Prajeeth Kumar, Harish V and Reddy Balaji
Elumalai
The inherent dangers associated with coal mining, including exposure to toxic gasses, the risk of rock falls, and the
ever-present threat of explosions, have long posed a significant challenge to the industry in safeguarding the well-being
of its employees. In recent years iot platforms have emerged. Using Iot platforms we can create a safety helmet for
coal miners that can help monitor their environment, collect critical data, and enable real-time analysis. The purpose
of this project is to create a smart safety helmet that can provide real-time data for the mining environment and we
used ESP and another sensor for data collection and cloud for the dashboard. Provides a cost-effective, efficient, and
reliable alternative to mining workers.
Keywords: Internet of Things (IoT), Coal mining safety, Real-time monitoring, Sensor integration, Environmental
monitoring, Health monitoring, Safety helmet, Data collection, Data analysis, ESP8266 microcontroller, DHT sensor,
MAX30105 sensor, Remote Monitoring
Paper ID - 0852

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 106

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Hand Gesture Recognition for Smart Control of Electrical Appliances using Computer
Vision
Uday Kumar Rajanala, Naga Kanaka Bhavani Chinni, Gopika Sandaka and Raziya Shaik
The human-driven field of computer interface hand gesture recognition has been the subject of vigorous activity in
computer vision and machine learning. In response to the increasing need for intuitive and sometimes touch-free
interfaces, hand gesture controls gained popularity for the purpose of controlling electrical devices in smart homes
and automation systems. The main aim of the current research is to utilize hand gesture recognition algorithms
developed using computer vision for compatible control of several electronic devices. This system does so through
image processing and the application of machine learning, gesture commands from the users are interpreted and
carried out by switching on/off devices or changing their state. It is evident that the proposed approach is beneficial
especially for people with mobility problems as normal physical interaction with computer devices is not required. The
talk describes the basic principles of the system including gesture detection, gesture recognition, and incorporation
of electrical appliances. Data collected from system implementations in practice indicate high levels of operational
efficiency and effectiveness of the solution thus favorably controlling smart appliances.
Keywords: Hand gesture recognition, Computer vision, Raspberry Pi Pico.
Paper ID - 0860

Mental Health Prediction of Students Using Machine Learning Method

Dr. B.R. Sathishkumar, M. Kavin Kumar, S.G. Paveen and S. Poorna Vignesh
In India, student dropout rates are influenced by a myriad of economic, social, and institutional factors, highlighting
the urgent need to address mental health among students. This study presents a novel approach to assessing students’
emotional well-being by integrating questionnaire-based assessments with visual data analysis. Utilizing machine
learning techniques, we identify trends in students’ responses, providing feedback to promote mental health awareness
and support. Our platform fosters a positive student community, bridging empathy with technology. The proposed
methodology leverages a unique dataset to facilitate the early detection of mental health issues, enhancing the accuracy
and reliability of predictions. This paper identifies thematic clusters in students’ emotional states, underscoring its
innovative contributions to the field. By implementing a robust data collection process and ensuring high-quality
visualizations, this study aims to set a new standard for mental health evaluation among students, ultimately striving
for improved mental health outcomes.
Keywords: Machine Learning, Mental Health, Visual Analysis, Students.

Paper ID - 867

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 107

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Hybrid Approach for Diabetic Retinopathy Detection using Support Vector

Machine
Senthil Pandi S, Shobana Lakshmi R and Jain Bai B
Diabetic Retinopathy is an eye disease that has been linked with diabetes mellitus. Diabetic Retinopathy is actually
the main cause of blindness in working-age people, and almost 93 million people suffer from it. When such a disease
is discovered in time, one’s progress of vision impairments could be slowed down or managed at best. This makes it
difficult because the disease is usually hardly ever symptomatic for early diagnosis and treatment. At the moment,
the diagnosis of diabetic retina is currently a very long and cumbersome process that pertains to the assessment and
evaluation by an ophthalmologist or other qualified medical practitioner of digital color fundus images of the retina
in search anomalies resulting from the disease. Through the breakdown of the identification and decision-making
procedures, an automated Diabetic Retinopathy screening approach will help in managing or controlling Diabetic
Retinopathy progression. The study offers an automated classification method based on various lighting and field of
view to analyze fundus images used in assessing the severity of Diabetic Retinopathy. This technique attains 89.2%
sensitivity, 90.9% accuracy, 88.8% specificity, and 0.924 AUC for right classification of the images in five classes: from
0 (with no Diabetic Retinopathy) up to category 4 defined as proliferative Diabetic Retinopathy.
Keywords: Segmentation, fundus Image, Machine Learning, CNN.
Paper ID - 0875

Quantum Key Distribution-Based Security Framework for Wireless Sensor Networks:

Enhancing Resilience Against Classical and Quantum Cyber Threats
S. Senthilkumar, K.K. Shandhosh Shree, R. Rajaganapathy, P. Krishnamoorthy, L. Ramachandran
and M. Kavitha
The requirement of efficient security protocols to protect confidential information from ever evolving cyber threat
has been highlighted by the fast implementation of wireless sensor network (WSN) in numerous important domains,
including healthcare monitoring, environmental surveillance and military operations. Despite their feasibility,
traditional cryptographic approaches are utilized behind the computing capability of recent attackers, including the
possibility of future quantum computer attacks. In order to revolutionize WSN security, this study proposes utilizing
quantum cryptography and other concepts from quantum computing into the existing framework. This research
leads to develop a communication protocol that is extremely safe and against the cyber-attacks. This protocol
utilizes the quantum key distribution (QKD) to protect data and granting its confidential. In addition to improving
security, the new architectures begin with change that makes WSN more capable of dependable and secure
operations in environment where data protection is essential. A complete framework for protecting WSNs from new
cyber threats in the future while keeping data transmissions and efficient process with reliability is discussed in this
study. This proposed method enhances the dependencies in WSN installation across various industries, which is
important for applications that need strong security measures. Evaluation results shows that the proposed method
outperformed all existing methods in terms of relevant metrics.
Keywords: Cyber-attacks, Quantum Key distribution, Wireless sensor network, Strong security measures, data
transmission
Paper ID - 0880

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 108

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Designing And Fabrication Of Panoramic Cooling System

B. Vijaya Ramnath, V. Ravi Raj, R M. Sanjay Kumar and S. Gananathji Naveen Kishore
To develop energy-efficient environment-friendly direct evaporation air conditioning cooling fans for hot climates. The
advanced manufacturing 360-degree Cooling air-providing system will allow a person to sit on any side of the system
during the summer season. Simple 360-degree evaporating cooling is achieved by direct contact with water particles
and moving air steam. When the dry air is allowed to pass through a wet cooling pad. The temperature of incoming
air is reduced with an increase in specific humidity. The low-temperature air is pushed towards the vertical rotating
blades which increases the pressure of the output air. This project is based on the studies of the different air-cooling
systems in 360-motion air flow which cools the air in all 360 directions all around whereas normal or conventional air
cooler cools air in only one direction. This cooler makes the people to sit anywhere in the room as their preference.
Keywords: Cooling Fan, Water particle, Air Steam, 360 motion.
Paper ID - 0881

GenoCryptNet: The Future of Secure Communication through DNA

Shravya Munugala, Harsh Panchal, Suhani Goel and Padmanaban R
Steganography has advanced to encompass different mediums, such as DNA sequences, for a secure data- hiding
technique. This paper introduces an innovative algorithm that uses the least significant data, the least significant
bit of the DNA codons, and Encryption Techniques to hide data in DNA sequences. The target of the proposed
algorithm is to preserve the security, capability, and usability of DNA sequences, lessening the probability of cracking
and execution time. The algorithm is assessed using performance metrics like the cracking probability, the capacity,
the payload, and the bits per nucleotide. Data security has become a significant concern in the rapidly developing
field of information technology, and DNA cryptography is a recent way to address that. Therefore, the presented
algorithm relating to DNA steganography is a significant innovation for creating the best balance as information
security technology continues evolving.
Keywords: Encoding, Decoding, Encryption, Decryption, Cryptography, Information Security.

Paper ID - 0882

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 109

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

An Implementation of Smart Agricultural Communication System using IoT and

Bigdata Analytics
Dr. S. Raja, Dr. T. Guhan, Dr. M. Lalithambigai, Mr. P. Boopathi, Dr. S. S. Suganya and Dr. M.
Umamaheswari
This paper evaluates a big data analytics and Internet of Things (IoT)-based Smart Agricultural Communication
System (SACS). With the increasing need for sustainable farming practices and the advancements in Big Data and
IoT technologies, SACS offers a workable solution to raise agricultural sustainability, productivity, and efficiency.
The evaluation considers several criteria, such as the overall performance of the system, analytics algorithms, data
processing techniques, and system design. Through empirical research and testing, the paper examines the utility,
stability, and scalability of SACS, shedding light on both its potential benefits and drawbacks in modern agriculture.
This research work outcome provides useful information for researchers, practitioners, and stakeholders involved in
developing and implementing Smart Agricultural Communication Systems.
Keywords: Smart Farming, Data-Driven Agriculture, Sensor Networks, Agricultural IoT, Crop Monitoring,
Agricultural Data Analysis.

Paper ID - 0883

Optimizing Crop Selection with Bigdata and IoT Sensor Technology in Modern
Agriculture by Univariate Feature Selection
R. Mahesh Kumar, G. Sujatha, B. Lavanya, Dr. R. Vijayabhanu, Dr. Sasikala Dhamodaran and D.
Saranya
In order to enhance agricultural practices, the integration of cutting-edge technologies is examined in the research
”Optimizing Crop Selection with Big Data and IoT Sensor Technology in Modern Agriculture by Univariate Feature
Selection”. It focuses on optimizing crop selection through the use of Internet of Things (IoT) sensor technology and
big data analytics. A statistical method called univariate feature selection aids in determining the most important
variables influencing crop development and yield. Real-time data on crop conditions, weather, and soil conditions are
gathered with IoT devices and evaluated with big data techniques. Through data filtering, univariate feature selection
identifies critical characteristics that affect crop success. With this method, farmers can choose crops depending
on market demand and environmental factors by using data to inform their selections. Big data and Internet of
Things (IoT) technology work together to give farmers meaningful insights that improve productivity, profitability,
and sustainability. Accurate crop selection highlights the revolutionary potential of these cutting-edge techniques in
contemporary agriculture by maximizing resource utilization, cutting waste, and improving yields.
Keywords: Real Time Data and Precision Farming, Data-Driven Decisions, Efficiency and Sustainability, Yield
Optimization, Agricultural Innovation.
Paper ID - 0887

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 110

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Novel Approach for Waste Classification Using Active Deep Learning

Raja K, Anandaperumal E, Abhishek M B, Senthilselvi A, Senthil Pandi S and Kaavya R
Classification of waste on a large scale is complicated, making it difficult to sort and recycle the waste. Many existing
systems use models like CNN and architectures such as ResNet, DenseNet, etc. These models perform well in waste
classification, but the classification of waste remains complicated due to the inherent variability and ambiguity in
waste images. Existing models may struggle with uncertain or ambiguous data, leading to misclassification and
reduced overall accuracy. To address these challenges, combining active learning with deep learning can be beneficial.
Active deep learning is a concept that improves the model by eliminating uncertainty about the data. This approach
will enhance model performance and outperform existing systems. By developing a model for waste classification
that combines ResNet50 and active learning, uncertainty and losses can be reduced, resulting in better performance
compared to existing systems.
Keywords: CNN, Resnet50, Active deep learning.
Paper ID - 0895

EDUHUB - An Integrated Learning Management System Using DJANGO

Devi Arumugam, Amirthasaravanan Arivunambi, K. Dhivya, Robinbritto V, P. Dharanyadevi and
H.Keerthivasan
EduHub is an innovative educational technology solution that leverages Django, a powerful Python web framework,
alongside HTML, CSS, and JavaScript to provide a comprehensive Learning Management System (LMS). This
seamlessly integrated platform caters to educators, administrators, and students, offering a unified environment for
coursework management, assessments, communication, and collaboration. With its user-friendly interface and
customizable dashboards tailored to individual user roles, EduHub ensures an intuitive experience for all
stakeholders. Through HTML and CSS, the platform delivers visually appealing and responsive designs, enhancing
usability across devices. Key features such as course management, student progress tracking, assessment and grading
tools, collaborative learning functionalities, and seamless communication channels are powered by JavaScript for
dynamic interactivity and real-time updates. These features enrich the teaching and learning experience, fostering
engagement and academic success. Furthermore, EduHub incorporates Python Django for backend functionalities,
empowering administrators with comprehensive tools for user management, course scheduling, reporting, and system
configuration. This backend integration ensures efficient oversight and resource optimization. For scalability and
adaptability in mind, EduHub accommodates institutions of varying sizes and aligns with specific pedagogical
approaches, branding guidelines, and technological infrastructure. By combining HTML, CSS, and JavaScript with
Python Django, EduHub revolutionizes education delivery by streamlining processes and creating a dynamic and
engaging learning environment.
Keywords: Django, Eduhub, blended learning, paedogogy, Python, custom dashboards.
Paper ID - 0900

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 111

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

AGI With Human

Lithish M, Denish Manova M, Jashwanth Sathish, Kailash A, Sathyanarayanan P and Arwind
Ragaw S.K
Artificial General Intelligence (AGI) is finally here. Humans have always depended on computers since they were
created, but now this reliance will take a new shape with AGI. It can think, listen to instructions, and interpret
human language while learning continuously from various tasks. This paper looks at how humans interact with AGI
and the benefits and disadvantages of the growing relationship with these intelligent systems. This paper will address
various issues including changes in our modes of communication, taking into account the moral ramifications of people
working together with AGIs, or how AGIs affect decision-making processes. The fact that it can read between the
lines or even interpret complex social situations helps in improving creativity as well as productivity; however, it can
also lead to dependence on machines, prejudice, and loss of individuality among other dangers. The abstract outlines
all possibilities that lie ahead for humanity when dealing with AGIs and calls for their careful design and regulation
so that society may gain from them.
Keywords: Artificial General Intelligence (AGI) Human-AGI interaction, Communication modes, Moral implications,
Machine dependence, Bias and prejudice, Individual autonomy.
Paper ID - 0910

Hybrid Deep Learning Approaches for Predictive Modeling of Aluminium Gallium

Nitride with Rime Optimization Algorithm
M.Priscilla, Dr.A.Mohan Babu and Dr.Radhika
High electron mobility transistor (HEMT) derived from gallium nitride (GaN) is a promising candidate for the
upcoming generation of high-power and higher-frequency electronic applications. GaN power semiconductor devices
have extraordinary belongings in comparison with their Silicon Carbide (SiC) and Silicon (Si) complements and
possess the latent to substitute the ubiquitous Si power device. However, the main technical limitations are
preventing their active usage through the power electronics communities. These are performing as an interference to
the commercial usage of GaN-based electronic methods. GaN HEMTs are almost identical to conventional
field-effect transistors (FET). Similar to FET it contains additionally 3 terminals are drain, gate, and source which
demonstrate the subsection of voltage-controlled Power switches. The variance is, in HEMT we are applying the
heterojunction in between aluminum gallium nitride (AlGaN) and GaN rather than the accepted area in FET.
Therefore, this study develops a novel Hybrid Deep Learning Approach for the Predictive Modeling of Aluminium
Gallium Nitride with Rime Optimization (HDLA-AlGaNRO) model. The proposed HDLA-AlGaNRO technique is
designed to accurately predict the switching behaviors of the devices without the need for delving into their
underlying geometry and physics. It encompasses two stages such as prediction and hyperparameter tuning. At the
primary stage, the HDLA-AlGaNRO model applies a hybrid of residual convolutional neural network (CNN) with
the bi-directional gated recurrent unit (RCNN-BiGRU) algorithm can be exploited for an accurate prediction
process. In the final stage, the rime optimization algorithm (ROA) is used for hyperparameter tuning to enhance the
predictive accuracy and optimize key parameters. The stimulated outcome investigation of the HDLA-AlGaNRO
model occurs and the outcomes are examined in terms of changing features. The experimental study indicates the
superiority of the HDLA-AlGaNRO model across the existing advanced approaches.
Keywords: Deep Learning; Aluminium Gallium Nitride; Rime Optimization; High Electron Mobility Transistor;
Prediction
Paper ID - 0919

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 112

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Multifaceted Feature Extraction and Machine Learning Approaches for Mortality Risk
Prediction in Pediatric Intensive Care Units
Shib Kumar Saraf and Solaimurugan Vellaipandiyan
In an Intensive Care Unit scenario, estimating the risk of a patient dying is useful for improving patient care and
efficiently utilizing limited resources. Traditional scoring systems are available, but modern and promising methods
from datadriven techniques have been shown to improve mortality prediction, specifically to Pediatric Intensive Care
Units(PICUs).This research focuses on developing and implementing machine learning prediction techniques for
mortality risk that uses a large dataset extracted from a single hospital database comprised of multiple tables using
rigorous data preprocessing and cleaning work. The multiple tables in the large hospital database provide a
collection of patient data that this research effectively organizes and integrates. The report includes patient
demographics, admission details, and ICU stay details. Patient demographics, admission specifics, and information
about ICU stays are among the elements of the hospital database that aid in the synthesis of a patient profile. This
profile combines biometric information, admission details, measures associated with ICU stays, and whether the
patient had an outcome of survival or survival outcome. In this paper, an approach is demonstrated to work with a
huge single hospital patient dataset to merge classes and perform the feature extraction process with the use of
various machine learning models for mortality risk prediction of the patients . This work contributes to the field of
medicine, where disparate data is integrated, and advanced machine learning algorithms are used to improve
mortality risk estimates and clinical decisions.
Keywords: Machine Learning in Healthcare, Clinical Prediction Models, Feature Engineering, Predictive Analytics,
Mortality Prediction, Pediatric ICU, Feature Extraction, Machine Learning

Paper ID - 0920

A Comparative Analysis of Corn Leaf Disease Classification Using Advanced CNN

Architectures
Kappala Vikash and M. Kalyan Ram
The agricultural sector is critical to producing highquality food while also contributing considerably to the growth of
economies and populations. Plant diseases, on the other hand, can result in significant crop losses and even species
extinction. Early and accurate diagnosis of plant diseases using automated methods can improve food production
quality while minimizing economic losses. Deep learning has recently enhanced the accuracy of picture classification
and object detection systems. This study focuses on four types of maize leaves that have been damaged by specific
diseases: blight, common rust, grey leaf spot, and healthy leaves. A total of 1306 samples were obtained for blight, 574
for common rust, 1146 for grey leaf spot, and 1164 for healthy leaves. Five advanced deep neural networks (DNNs)
are used to classify these corn leaf diseases: CNN, AlexNet, SqueezeNet, Xception, and DarkNet. These models’
performance is measured using metrics including validation accuracy, test accuracy, precision, recall, F1 score, and
area under the curve (AUC). CNN had a classification accuracy of 92.6%, AlexNet had 94.3%, SqueezeNet had 95.7%,
Xception had 97.3%, and DarkNet53 had 97.4%. The findings reveal that the deep learning models utilized in this
study outperform typical machine learning classifiers at detecting corn leaf illnesses.
Keywords: Corn Leaf Diseases, Classification, CNN, AlexNet, SqueezeNet, Xception, DarkNet53, Optimizers.
Paper ID - 0921

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 113

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

MindGuard : Digital Aid for Smartphone Addiction

Hariharan M, Kavitha R, Monish Kiran S and Ezhumalai M
In a time when smartphone use and digital connectivity are ubiquitous, worries about excessive screen time and its
effects on mental health are becoming more and more pressing. Our project’s main goal is to develop MindGuard, a
sophisticated machine learning and natural language processing tool that employs Random Forest and AdaBoost to
forecast and analyze usage trends in order to solve this problem. The system monitors information about
smartphone usage, such as communication patterns, screen duration, and application interaction. Textual
information is analyzed using NLP techniques to identify behavioral clues that may indicate addiction. Using this
data, machine learning algorithms such as Random Forest and AdaBoost are used to create predictive models that
determine usage patterns linked to addiction and evaluate risk. Through the integration of various technologies, the
system offers users individualized feedback and real-time information, empowering them to successfully understand
and change their smartphone habits. With its all-encompassing approach to tracking, anticipating, and treating
smartphone addiction, this cutting-edge method encourages better digital habits and overall wellbeing.
Keywords: Random Forest, Smartphone Addiction, Predictive Model, Productivity Enhancement .

Paper ID - 0925

Voice-Activated Email System: Enhancing Accessibility with Speech-to-Text

Integration
Srinivasan A, Meenakshi B and Swathiha R R
Email is a widely used tool for communication in today’s society, particularly in professional settings where it is
crucial. However, text reading and keyboard input are required for traditional email systems, which some users
could find challenging. The voice-based email system proposed in this project allows voice commands to be used
for email composition, sending, and receiving. The solution enables users to connect with their email accounts using
simple voice commands thanks to speech-to-text technology. Furthermore, an embedded AI chatbot function improves
user interaction by offering recommendations, helping with email management, and responding to questions about
email content. For those who want or need hands-free communication, this innovative solution improves usability by
eliminating the need for typing or visual focus. In addition, the system is made especially user-friendly for visually
challenged users, allowing them to send and receive emails efficiently and independently. This solution provides
a seamless email experience by utilizing AI chatbots and a Python-based architecture, enhancing accessibility and
efficiency for all users—including the blind.
Keywords: Voice-based email, Speech-to-text, Accessibility, Visually impaired, Python, Hands-free communication,
Email automation.
Paper ID - 0939

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 114

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IoT Enabled Smart Reminder System

Satya Jagu, Manju Bhargavi Pilli, Samuel Devanaboina and Rushikesh Dhornala
Abstract—Alzheimer’s affliction is an irreversible nerve-related disorder that affects the cortex, memory loss, and
eventually impacting the ability to perform daily activities. To address this problem, we would like to make a smart
device called as IoT-Enabled Smart Reminder System, which is helpful for the Alzheimer’s patients. It aims to provide
gentle clues for medication adherence, daily routines, and important appointments. The system architecture consists
of four main components: IoT devices, LCD, and Buzzer, the mobile based interface, the buzzer gives the beep sound,
LCD fixed for displaying the ON or OFF and for displaying the names. An IoT-Enabled smart reminder system
integrates IoT devices to create a connected network that can send reminders and notifications tousers. Finally, this
system can be used to remind users about tasks, appointments, medications schedules and many more. The project
aims to provide an effective, user –friendly, and connected solution for detecting and managing the reminder system.
Keywords: Alzheimer, Arduino, Microcontroller, Receiver, Transmitter, Wi-fi module.
Paper ID - 0941

Enhanced Automatic Number Plate Recognition using Yolov7, Resnet, and Image
Rectification Techniques
Dr.M.Kathiravan, Dr.Vijay R, Mr.A.Irumporai, Dr.R.Buvanesvari, Mr.Vengatramana R and Dr. V.
Kaliraj
ANPR (Automatic Number Plate Recognition) has revolutionised crime detection and traffic management. These
days, systems that still rely on older versions of the YOLO (You Only Look Once) algorithm are outdated, slow,
and sometimes replaced by newer computer vision technology, or a ”basic machine learning approach” that is more
accurate and reliable. This research enhances YOLOv7 by segmenting images into regions using an N x N grid. This
research streamlines the process of partitioning images into bounding boxes and detections, specifically targeting tighter
border cases. This research also exploits ResNet (Residual Network Architecture), which allows residual functions to
learn easy identity mappings using layer inputs, resulting in improved learning capacity. Furthermore, the method
incorporates an Image Rectification algorithm to rectify images affected by snow, dust, and low light (during bad
weather). In this study, propose a convolutional neural network model specifically for Indian number plate detection,
which train and validate on the MNIST digit dataset and large real-world Indian number plate datasets captured
in various lighting conditions, both daytime and nighttime, using a camera. The system maintains a high level of
reliability and processing efficiency by leveraging advanced hardware (NVIDIA RTX 3060) that takes approximately
25 seconds to process an image and decode its number plate. The experimental analysis outcomes illustrate model
advantages over existing methods.
Keywords: Number Plate Recognition, YOLOv4, ResNet Discriminative Correlation Filtering, RTX3060.
Paper ID - 0942

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 115

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Dynamic optimization of Traffic management using Gen AI

Mr. S. Jegadeesan, M.Harin Sowmiya, R.Ambika and S.Thanusha
Dynamic optimization of traffic management using cloud GenAi is a sophisticated technique strengthened for the
maximum improvement of urban traffic flow coupled with the relief of congestion through the adoption of
cutting-edge image processing and deep learning techniques. Basically, the system begins with the process of image
taking of vehicles in the dataset. Images of the cars are pre-processed using resizing and grey-scale conversion. This
cloud-infrastructure feature provides integration with external data sources like weather and road incidents, thereby
sharpening the prediction of traffic flow. The server will compute further based on the Signal Switching Algorithm
that has the idea of optimizing flow through switching between multiple alternate stop settings. The process
involved in the extraction of key features in an image makes use of statistical measures and LBP. After that, these
images are separated into training sets and test sets for the development as well as evaluation of the detection model
of a vehicle which would use YOLO. The vehicle counts per unit length is then calculated in order to obtain the
traffic density and then forwarded to the cloud server in order to store it. The accuracy and error rate quantifies the
performance of the system, and the result is reported in the form of comparison graphs and tables. The web
application interface also facilitates further accessibility and engagement with the facility of registration, login,
uploading images, and retrieving results.
Keywords: Dynamic optimization, Transport networks, Generative AI, Shortest path detection, Image generation,
Traffic detection, Image classification, Movement detection, Urban planning
Paper ID - 0944

A Non-invasive Efficient Interpretation of Heart Beat Monitoring System

N Shivaanivarsha, Sai Santhiya G, Rajalakshmi K, Lokith Sharan R, Karthikeyan S and Pavita S
Health monitoring is a very essential phenomena in today’s day-to-day life. Heart rate and oxygen saturation, being
an important parameters for one’s overall health, it is important to monitor them regularly to maintain our health
in good condition. This research aims to design a intelligent system for monitoring heart rate and oxygen saturation
at low cost. The developed system monitors the heart rate and oxygen saturation from finger along with position
detection using Raspberry pi PICO and LORA technology. An accelerometer is used to track the subject’s position,
and a pulse sensor, based on PPG (PhotoPlethysmoGraphy), measures the subject’s heart rate and oxygen saturation.
The monitored data are then displayed and validated at web page using LORA technology. Further, the data are also
get stored in a cloud using IOT and been utilized for future uses. In this module, utilization of LORA technology
indeed provides an efficient system through long range communication covering up to 2 kilometers. It can be employed
in clinical fields and various fields including telemedicine.
Keywords: Pulse sensor, LORA communication, IOT, accelerometer, python, webpage.
Paper ID - 0956

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 116

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Machine Learning in Healthcare: Opportunities and Challenges

Peer Mohamed Appa M.A.Y, Sudha K, Pooja E, Lekha D, Ezhilvendan M and Gayathri S
Advancements in Machine Learning are revolutionizing healthcare by innovating in diagnostic and healthcare support
technologies. The study explores the core ML strategies in healthcare including supervised and unsupervised models
as well as their role in predicting diseases and in monitoring real-time. Despite ML’s great promise challenges including
privacy of data and ethical issues restrict its widespread acceptance. To address these problems, emergent approaches
like federated learning and explainable AI are unfolding. To realise the full potential of this technology, ML for health
care requires a collaborative effort from the health care professional, AI analytics specialist, and the policy makers.
In addressing those challenges this work also assesses the current state of application of ML in healthcare as it looks
at the challenges and the way forward to enhance the uptake of healthcare technology such as IoT and Blockchain
towards developing a personalized healthcare system.
Keywords: Artificial intelligence, health technology, precision treatment, imaging, diagnosis.
Paper ID - 0957

Schemes Paaru! - A Multi-Platform Chatbot for Government Scheme Information in

India
Dhanushprakash.V.C, Balaji.A, Malathi, Sripriya.T, Arthy .G. and Sinthia.P
This paper introduces ”Schemes Paaru!”, a Flutter-based chatbot application designed to provide easy access to
information about government schemes across India. In a nation with numerous social welfare programs, bridging the
information gap between citizens and government initiatives is crucial. Leveraging OpenAI’s GPT-4 Turbo model,
with text or audio input, ”Schemes Paaru!” provides up-to-date information on central and state government schemes.
By empowering individuals with knowledge about government schemes, ”Schemes Paaru!” makes it easier to make wise
decisions, especially when trying to reduce poverty. The article also emphasizes how ”Schemes Paaru!” stands out from
other chatbot solutions thanks to its intuitive user interface and smooth interaction with OpenAI’s language model.
By democratizing access to scheme information, ”Schemes Paaru!” fosters social inclusion and citizen engagement,
embodying a novel approach to leveraging technology for societal benefit. This innovation represents a significant
step towards enhancing transparency and accessibility in governance, ultimately contributing to a more informed and
participatory Society.
Keywords: Chatbot, Government Schemes, OpenAI, GPT-4, Flutter, Multi-Platform, Speech Recognition, Text-to-
Speech, India.
Paper ID - 0964

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 117

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Aqua Garbage Cleaning RO Boat

Kamalakkannan Sivaraman, Vinoth Kumar.Ls, Sathish Kumar.M, Sathish Kumar.M, Saravanan.A
and Sarath Kumar.D
The innovative water cleaning ro boat is a pioneering solution designed to address environmental challenges in aquatic
ecosystems. It employs a carefully selected set of components to efficiently collect floating debris on the water’s
surface. At its core, the boat utilizes a propulsion system comprised of a DC gear motor and a conveyor. The DC
gear motor provides the necessary thrust to navigate through water, while the conveyor system sweeps debris into a
collection area onboard. This combination enables the boat to traverse waterways methodically, ensuring thorough
cleaning of the surface. To facilitate remote operation and control, the boat is equipped with a bluetooth module. This
module allows operators to communicate with the boat wirelessly, directing its movements and monitoring its progress
from a distance. This functionality enhances the boat’s versatility and usability in various environmental conditions.
Powering the boat is a Li-ion battery, which provides the necessary energy for its operation. This battery ensures
that the boat can operate for extended periods without the need for frequent recharging, enhancing its efficiency and
effectiveness in cleaning tasks. Overall, the innovative water cleaning ro boat represents a practical and sustainable
solution for maintaining the purity of water bodies. By utilizing a combination of propulsion, control, and power
components, it offers a cost-effective and environmentally friendly approach to aquatic cleanliness.
Keywords: Arduino UNO, Arduino IDE, Bluetooth Module, L298N Drive, DC Gear Motor
Paper ID - 0965

Systematic Review of Security for Health Records using Blockchain

Shivalingappa P and Nagaraja G S
IoT has deeply permeated almost every walk of life, and smart healthcare has emerged as one of the major domains
that stands out as one of the prime sectors reliant on the infrastructure and solutions involving IoT. IoT-empowered
smart healthcare has further enhanced the field of medicine by introducing wearable and mobile devices, facilitating
diagnosis that is even more efficient, accurate, and timely, due to extensive sharing of health data. It is also subject
to various challenges and unresolved issues arising due to traditional security approaches in smart healthcare. It
also possesses special security requirements, while recently blockchain technology is showing promising solutions for
addressing security concerns. The paper presents an in-depth review of the challenges and unresolved issues in smart
healthcare due to traditional security methods, together with unique security requirements in the sector. It also looks
at the potential of blockchain technology as a strong security solution and discusses unique challenges within healthcare
while offering an analysis of different blockchain- based security approaches.
Keywords: EHR, HITECH, IOT, UTXO.
Paper ID - 0967

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 118

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Adaptive Development of the StaySmart Booking System through Agile Methodology

Saraswathi P, Adeline Joanna V, Shanmuga Priya AR, Subhadharshini V and Prabha M
A software program called StaySmart Booking System enables users to make the reservations for room stay through
online. The goal of this method is to lessen the staff’s manual labor and streamline the reservation process for rooms.
The system allows the users to view the available rooms, choose the desired room and check the availability of the
room on the selected dates. It is also a platform that connects people who are seeking shared accommodation, helping
them find compatible flat mates and suitable accommodation options. Users of the platform can post ads, establish
profiles, and communicate with possible roommates in addition to seeking for apartments according to amenities,
location, and cost. The system is equipped with features such as room availability check, reservation management,
room type selection, room status update, payment gateway integration, etc. The system also provides the option to
view the room availability calendar and make a reservation accordingly. Users can also cancel their reservations or
modify them based on their requirements. Overall, the StaySmart Booking System provides a intuitive interface for
clients who engage through this platform.
Keywords: Online Booking, User Friendly interface, Room Status Update, Real time Tracking and control.

Paper ID - 0968

Dual-Level Contrastive Learning with Reverse Translation for summarisation

Joanna Samuel, Nandithaa I N, Nithyanjali Maruboina and Dr. Deva Hema D
Text summarisation aims to create brief and precise summaries from large amounts of textual information. Although
recent advancements have improved summary brevity, significant room remains for enhancing ROUGE scores,
especially with increase in beam width. We present a novel model, Dual Level Contrastive Learning with Reverse
Translation (DC-RT), which utilizes contrastive learning with data augmentation, including reverse translation, to
improve accuracy. Reverse translation serves as a key augmentation strategy by translating summaries to another
language and back resulting in enriched training data and enhanced robustness of the model. Additionally, we
introduce a new scoring function during training to further refine output quality. Exceptional ROUGE scores are
achieved using this framework, ensuring concise and readable summaries even with increased beam width.
Experiments on the CNN/DailyMail (achieving a47.82 ROUGE-1 score with a 0.017 variance) dataset demonstrates
that there is a significant improvement in the precision and succinctness of summaries. Notably, our model surpasses
the output of BRIO, the cutting edge model, setting a new benchmark in the field.
Keywords: Reverse translation, Data Augmentation, Contrastive Learning, Conciseness, KL-divergence, Text
Summarization.

Paper ID - 0969

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 119

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Prediction of Loan Approval in Banks using Machine Learning Algorithm

Mathan Kumar Mounagurusamym, Dr. P A Manoharan, Dr. J. Anvar Shathik, A.Pandiaraj, N.
Ramshankar and Naveen G
Normally, the banking sector gains profit from different kinds of sources, but the main factor in their profitable growth
is giving loans to their customers. A bank’s profit or loss is determined by the quantity of the loan. A huge number
of people are taking loans from banks and not clearing their dues. So there is a tedious process for banks to identify
them and collect them. This in turn leads to following up on a complex verification process and issuing loans to their
customers. Customer satisfaction is mandatory in every field, but in the banking sector, it is essential to identify
genuine applicants and satisfy their needs, as well as to keep bankers free from non-payable customers. The manual
method of identifying the right person and providing a loan to them may cause misconceptions. Several studies in
this field suggest various kinds of approaches to identifying applicant status. Therefore, the use of machine learning
(ML) approaches in the banking sector to resolve difficulties faced by bankers is becoming more popular. This reduces
the problems faced by bankers and makes their applicants satisfactory. The time taken for this process is too long. It
is essential to select the best ML approach from the different kinds of classifier algorithms available. The attributes
chosen for this study include the applicant’s education, type of work, applicant income, loan amount, co-applicant
income, credit history, and property area. The proposed study reviews ML approaches such as K-nearest Neighboring
(KNN), Logistic Regression, Decision Tree and Support vector Mechanism (SVM). Among those, KNN outperforms
the other three algorithms, and the efficiency obtained by KNN is 87.50%, Logistic Regression is 83.512%, Decision
Tree is 77.09%, and Random forest (RF) is 74.49%.
Keywords: Loan, Bank, Machine Learning (ML), K-nearest Neighboring (KNN), Logistic Regression, Decision Tree,
Support Vector Mechanism (SVM).
Paper ID - 0973

K-Nearest Neighbors in Machine Learning: Theory, Practice, and Advances

Manjunathan N, Vijaya Prabhu R, Sudha K, Lekha D, Ezhilvendan M and Gayathri S
K-Nearest Neighbors (KNN) is a basic model in a machine learning field used for classification or prediction analysis
owing to its efficiency. The following paper will be a survey paper focused on elaborating the theory of KNN, its
distance learning nature and effects of the selection of (k) and distance measure. We consider different options of
KNN and the generalization of the algorithm such as weighted KNN and other distance measurement methods and
note the feature scaling. Subsequently, we look at the use of KNN in different domain including; healthcare, finance
and investing, image recognition and recommender systems to note its versatility. This paper also reviews the strengths
and weaknesses of KNN: this technique belongs to the class of non-parametric methods, but it may turn out to be
sensitive to data with high dimensionality, and it is also known to be slow as a method when it works with big data.
In an effort to improve KNN, modern trends in dimensionality reduction, ensemble learning, and distributed systems
are discussed and how these advancements overcome the old problems. Last, the paper summary discusses how KNN
is still used in present day machine learning and how further enhancements could be made. Thus, this paper’s purpose
is to offer an extended description of KNN so that it will enable users to apply the method proficiently in different
practical problems.
Keywords: KNN, Machine Learning, Non- Parametric Models, Classification, Big Data.
Paper ID - 0974

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 120

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Iterative Deepening Chess Engine with Alpha Beta Pruning

Dr. E. Kodhai, Dr. E. Bhuvaneswari, Dr. V. Anjana Devi and S.T. Preethi
An essential component of developing a chess engine is its depiction of the chess board, which influences the way the
engine moves over the board and follows the rules. One way to lessen the strain on the chess engine’s hardware is
to use the minimax algorithm. To enhance this searching algorithm, a most promising approach becomes vital. One
such a searching algorithm is Alpha-Beta Pruning Algorithm. The main concept of the algorithm is to search the tree
for unwanted nodes and delete them. Thus, to enhance the chess engine, it is required to refine it through iterative
development. Few optimization techniques are incorporated to enhance the search algorithm. To evaluate the progress
of software, it is tested by comparing it with its previous version. To enhance the consistency and precision, arbitrary
test points are tested along with the critical bug fixing. Search is refined further in decision-making and hence Search
proficiencies are strengthened. Finally, Analysis is made to keenly observe the improvement and based on it is further
categorized.
Keywords: chess engine, alpha- beta, pruning, minmax, interative deepening.
Paper ID - 0983

Assessing the Efficacy of ML Techniques for Forecasting Healthcare Consumer

Readmission: A Comparative Analysis of Risk Factors and Healthcare Interventions
Loganayagi S, S. Alagu Thangam, Dr. V.R.Vimal and Dr.T.Suresh Balakrishnan
This study evaluates the efficacy of machine learning techniques for predicting patient readmissions, focusing on the
comparative analysis of various algorithms in identifying risk factors and the potential for optimizing healthcare
interventions. Healthcare professionals now prioritize preventing avoidable hospital readmissions because of the
substantial effects it has on patient outcomes and healthcare expenditures. Machine learning is a viable solution to
this problem because of its capacity to analyse enormous volumes of data and identify significant patterns. In order
to determine how well machine learning models, including Random Forest, Support Vector Machine (SVM), Logistic
Regression, and Neural Networks, predict readmission risks based on variables like age, comorbidities, length of
hospital stay, and past treatment history, the study evaluates these models’ accuracy and performance. Data was
collected from electronic health records (EHRs) encompassing a wide range of clinical, demographic, and social
factors. The results demonstrated that machine learning algorithms could significantly improve the prediction of
readmissions, with Random Forest outperforming other techniques from a precision and recall perspective.
Moreover, the study highlights the potential of machine learning in recommending timely, personalized healthcare
interventions, such as tailored discharge planning and patient monitoring, which could reduce the likelihood of
readmission. The findings highlight the revolutionary potential of machine learning in enhancing predictive
healthcare systems, improving patient outcomes, and optimizing resource utilization.
Keywords: Machine Learning, Patient Readmission, Risk Factors, Healthcare Interventions, Predictive Modelling,
EHR.
Paper ID - 0986

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 121

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Integrating Sustainability Development Goals into Business, Marketing, Finance and

Engineering for a Better World
Mr.S.Amarnaath and Ms.G.Deepana
To drive a meaningful and fostering better world incorporating the major areas of business, Business marketing,
Business Finance and Engineering with Sustainable development goals. This paper Explores how a company or an
Institution can incorporate all the 17 SDG Goals given by the United Nations to create sustainable values that
enhance innovation and ensure sustainable long-term growth. In Business, the SDG is embedded into the areas
of Corporate Governance, maintenance, Operation and Making Sustainable and strategic decisions. In the area
of Business marketing, the SDG encompasses ethical consumption, transparency between the consumers and the
corporate and Sustainable Campaigns. In the area of Business Finance, the SDG plays a vital role in transferring
investments into ventures, green finance, Investment, and social governance. In the field of Engineering.SDG focuses
on minimising material usage.Transforming the Environment into an Eco-friendly Environment by using the ideas of
the 3R Approach and also by innovating new renewable materials in places of non-renewable materials.By allowing
these fields in the SDG, it is possible to create an equitable, eco-friendly surrounding.
Keywords: SDG, Business, Marketing, Finance and Engineering.
Paper ID - 0987

Incorporating Sustainable Development Goals (SDGs) into Marketing Strategies: A

Path to Business Growth and Global Impact
Mr.S.Amarnaath and Ms.G.Deepana
This article looks at the unification of the United Nations’ Sustainable Development Goals (SDGs) and modern
marketing concepts. It considers how it is possible to link businesses’ quests for profit with addressing social issues
such as poverty reduction, social equity, decent work conditions and responsible consumption. The paper uses a data-
driven approach and case studies that exemplifies the conflict between effective brand strategies and SDG marketing to
provide evidence that such alignment also attributes brand benefits, and eventually translates into business expansion.
The paper also looks at the major limitations of SDG marketing, including how to avoid greenwashing and lack of
transparency, and recommends how companies can manage these issues.
Keywords: Sustainable Development Goals (SDGs), Marketing, Corporate Social Responsibility, Consumer Behavior,
Innovation, Transparency.
Paper ID - 0988

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 122

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Swarm-Based LSTM for Temperature Forecasting Using Big Data Analytics

Mathankumar Mounagurusamy,, Pandiaraj A, Ramshankar N, Naveen Gandhi Anbullam, Dhivya
V and Jeeva K
Over the previous few periods, global warming, driven by contamination, the emission of conservatory gases, and the
use of non-environmentally friendly dynamism sources, has become a pressing issue. This phenomenon is causing a
steady increase in the Earth’s overall temperature, which is having profound and detrimental effects on both human
populations and ecosystems. Millions of people are at risk of losing their livelihoods due to these changes. One
significant consequence of global warming is the escalation of high temperatures during the summer months,
resulting in heat-related illnesses and even premature fatalities. To mitigate these risks and better understand
climate patterns, researchers have turned to machine learning techniques. Specifically, they have employed
algorithms like autoregressive combined poignant averages, collaborative learning, and extensive short-term
remembrance networks to forecast temperature trends. This article introduces a novel approach known as CPSO to
optimize the hyper parameters within Long Short-Term Remembrance networks. These hyper parameters are
fine-tuned by minimizing the mean squared error during the validation of LSTM models. The resulting optimized
LSTM hyper parameters are then used to predict temperatures in Chennai, a city heavily impacted by rising
temperatures. The CPSO-LSTM model’s effectiveness is assessed using a publicly available 25-year dataset of
temperatures in Chennai. The evaluation is conducted using MATLABR2020a, with the mean squared error and
mean absolute error serving as key performance metrics for the temperature predictions. Significantly, the
CPSO-LSTM model outperforms traditional LSTM algorithms in several aspects. Notably, it significantly reduces
training time to just 25 minutes while using 200 training epochs and 150 hidden neurons. Moreover, it achieves a
lower RMSE of 0.250, as opposed to the out dated LSTM’s RMSE of 0.35. This improvement in accuracy is
promising, as it can have a positive impact on various applications, ranging from climate modeling to public health
planning.
Keywords: Climatic modification; big data; infection; predicting group intelligence; deep learning
Paper ID - 0990

Survey on Text Mining using Bert and Probabilistic Topic Modelling

Varshni S V, Kavitha D, Dharaniya D, Sangeetha J and Kaliraj V
Abstract— The method transforming free-form content into structured format with the purpose of identifying
significant patterns and fresh insights is often referred to as text mining and text data mining. Companies are able
to investigate and find by utilising cutting-edge analytical techniques like Naive Bayes, Support Vector Machines
(SVM), and other deep learning algorithms, they may uncover hidden correlations within their unstructured data.
Using text Mining tools, for instance, enables you to quickly identify unfavorable sentiment from different social
media posts and comments so we may take action and address the issue. A text Mining technique called keyword
extraction mechanically extracts the most important and frequently used words and expressions from a document. It
assists in identifying the main points made in the text and in summarizing it. It lets companies quickly find valuable
information in texts such as emails, social media postings, support tickets, chatbots, and other types of text.
Businesses can use text mining to foresee potential threats from competitors, respond promptly to production or
delivery issues, and offer more individualized customer care. Text mining is used by businesses for a variety of
purposes, including production, IT, marketing, sales, and customer support. In this paper, we have discussed Text
Mining and how Probabilistic Topic Modelling and BERT are related to Text Mining.
Keywords: Text Mining, NLP, BERT, n-grams, Probabilistic Topic Modelling.

Paper ID - 0993

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 123

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Plant Leaf Disease Detection using CNN

Abirami A, Prabhu K, Kaliraj V, Mahesh Vaijainthymala Krishnamoorthy and Dharaniya.R
In our country, most farmers face the same issue in the field of agriculture. The issues in agriculture are based on
the weather, irrigation, moisture of the soil, and humidity. The major issue is plant disease. The diseases may cause
harm to the plants in various forms; there are bacterial, fungal, and viral causes of disease. These diseases reduce the
yield of crops by up to 50%. We can identify the type of disease that attacked the crop and take remedies to save it
using images of disease-affected plants. Several crops are attacked by the disease; such crops include paddy, wheat,
tomato, eggplant, hyacinth beans, ladies’ finger, maize, etc. The plant diseases are found using the convolution neural
network CNN. The accuracy is high when we use the CNN algorithm. The future work of the paper is to increase the
accuracy of the algorithm.
Keywords: CNN, image processing.
Paper ID - 0994

A survey on detection of oil-spill in satellite-based Synthetic aperture radar (sar)

images using neural Network
Saranya T V, Justindhas Y, Satish Srinivas S, Ahamed Ali S and V.Kaliraj
The use of satellite and airborne remote sensing has become standard practice for global oil spill monitoring. When
oil leaks into the water, it is an immediate crisis. Monitoring oil spill on the sea surface is made possible using
optical remote sensing. On the sea’s surface, there is a moving oil leak. An essential part of preventing and
mitigating oil spills is quick and effective monitoring of the location, size, and effects of the spill. Only a small
sample of data may be collected due to the influence of cloud and weather, the limits of the satellite revisit duration,
and other factors. The capacity to learn sample characteristics using a single supervised classifier in the case of small
samples is constrained, which can not meet the needs of accurately monitor oil spill. By using neural network the oil
spill regions has been extracted in radar image. In this paper we will be studying the survey of various papers
related to oil spill detection.
Keywords: Convolutional neural networks (CNNs), DEEPLABV3, feature extraction, oil spill, segmentation,
synthetic aperture radar (SAR), U-NET.
Paper ID - 0995

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 124

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Survey On the Facial Recognition Of Humans With Masks Post Covid using Artificial
Intelligence
Satish Srinivas S, S. Ahamed Ali, Saranya TV, Justindhas Y and V.Kaliraj
Face detection is the process of identifying human faces in digital images or videos. With the emergence of COVID-19,
the use of masks has become widespread, which has presented a new challenge for face detection systems. Mask-based
face detection is a variation of traditional face detection that aims to detect faces even when individuals are wearing
masks. Facial recognition is a technology that uses algorithms to identify or verify individuals based on their facial
features. This technology can be used in various applications such as security, access control, attendance management,
and more. Recognizing individuals wearing masks can be a challenging task due to the reduced visibility of facial
features. One approach to overcome this challenge is to use neural networks with more layers, such as Convolutional
Neural Networks (CNNs), which can be trained to recognize individuals based on their facial features, even when they
are wearing a mask.
Keywords: CNNs, YOLO, R- CNNs, MTCNN, CCTV.
Paper ID - 0996

Face Authentication System using Face Recognition and Firebase

Muhemin Sheriff M, Bhuvaneswari S, Balakrishnan, C, Muralitharan G, Kaliraj V and Dharaniya R
In this paper, we would like to propose a face recognition system that utilizes face recognition technology that has
machine learning and artificial intelligence concepts and a real time back end cloud database i.e. Firebase. The
proposed system is designed to overcome the drawbacks of old fashioned ways of marking attendance in this modern
day era with high accuracy and efficiency. This paper says how the face recognition concept is used in a student’s
attendance system or a student authentication system with a real-time cloud database where one can track their
attendance live. Face recognition is a difficult topic in image visualization and Open CV, and it has received a lot of
interest in recent years because of its numerous applications in multiple fields. Face recognition has many methods
now days. Based on the face data accretion methods, there are three categories: techniques that are based on intensity.
Those that deal with images; those that deal with video which have numerous frames and those that require extra
sensory data.
Keywords: Face Recognition, Face detection, Artificial Intelligence, Firebase cloud, Cloud database.
Paper ID - 0998

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 125

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Decoding Mental Health through Social Media with Dual-Stream AI

Senthil Pandi S, Kumar P, Salman Latheef T A and Karupannan P
Mental health disorders have now become a huge concern in the world health industry, offering a unique opportunity
for early detection and intervention through social media. This paper introduces an NLP-enhanced dual-stream CNN-
LSTM model to detect multiple mental health disorders from social media content. Such advanced natural language
processing techniques combined with a hybrid deep learning architecture improve accuracy as well as robustness in
mental health classification. There are two streams moving in parallel: the CNN to capture local features from text
and the LSTM to model long-term dependencies, both of these augmented with NLP-based feature extraction. The
dual-stream architecture captures the short-term linguistic patterns as well as the long-term contextual information.
Further NLP extensions are in the area of topic modeling and sentiment analysis, which add to the model’s mental
health indicator understanding. This work introduces a viable paradigm for large-scale monitoring of social media for
mental health through timely pertinent implications toward early intervention and public health initiatives.
Keywords: Health Records, Dual-Stream, CNN-LSTM.
Paper ID - 1001

AgroFusion: Combining Multiple Deep Learning Techniques of Data to Improve Crop

Management and Forecast Yield
Senthil Pandi S, Kumar P, Salman Latheef T A and Karupannan P
AgroFusion is a state-of-the-art deep learning framework that combines GNNs, LSTMs, and CNNs under one
architecture. The AgroFusion framework has calculated a broad collection of agricultural data-including
multispectral satellite imaging, the time-series readings from sensors, and spatial linkages among the fields-to provide
highly accurate insights into crop recommendations, disease diagnosis, and yield predictions. Though the LSTM
manages to capture long-term temporal correlations in environmental factors, the GNN really captures the
complicated spatial interaction among agriculture farmlands. Through an adapted attention mechanism, the
performance of the CNN in extracting relevant information from the remote sensing images and minimal alterations
of crop condition improves. This combines the outputs of these components through a special cross-modal attention
layer to allow for comprehensive analysis that leverages several data modalities. Experimental results show a
significant rise in accuracy in agricultural insights in comparison with traditional methods. The novel architecture
provides farmers with a strong tool for data-driven decision-making and sustainable practices, thereby ultimately
making agricultural management and productivity more efficient in the face of modern challenges.
Keywords: Agrofusion, Deep Learning, GNN, CNN, LSTM.

Paper ID - 1002

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 126

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Enhanced Software Deployment and Integration with an Integrated CI/CD Pipeline

Senthil Pandi S, Kumar P, R.M.Suchindhar and Karupannan P
This article will present a new approach for enhancing CI/CD pipelines in the deployment of automotive software
based on the cloud. The automobile industry has become dependent more and more on complex software systems;
therefore, reliable procedures for deployment are essential. The proposed system integrates LSTM neural networks
to exploit predictive analytics and contribute toward better decision-making at each phase of the software
development lifecycle. This system ranks test cases according to the probability of failure; it optimizes resource
allocation; automates code reviews; and reduces the manual involvement dramatically by analyzing historical data
and real-time feedback.Important aspects of architecture include predictive deployment manager, smart build
orchestrator, and an automated monitoring system, and everything is designed to really work well within a cloud
context. Significant advantages with regard to deployment time as well as resource utilization, and early mistake
identification over conventional CI/CD systems have been found when experimental results are compared with them.
This novel approach successfully enhances the capability and security level of software deployment for cars, while
also providing a scalable framework for further studies in machine learning-enhanced CI/CD systems, potentially
applied to other high-stakes industries, such as aerospace and healthcare.
Keywords: CI/CD, Automotive Software, machine learning, LSTM, predictive analytics, cloud deployment,
resource optimization, error detection.
Paper ID - 1004

Improving Wind Power Forecasting using Hybrid Ensemble Methods

Kumar P, Senthil Pandi S, Karthikeyan N and Karupannan P
Accurate prediction of wind power will maintain grid stability by efficiently managing energy. To this end, this paper
proposes a state-of-the-art hybrid model that incorporates machine learning into deep learning techniques to better
carry out short-term wind power forecasting. The proposed model incorporates GRUs for temporal dependency,
followed by the application of CNNs to identify spatial features, and lastly refines using SVMs for post-processing
corrections. The use of an attention mechanism that dynamically focuses on the most relevant historical data chunks
would improve predictive accuracy in this model. The ensemble approach thus reduces the error of predictions and
enhances robustness by training several instances of the model on several subsets of data containing meteorological
information. Testing this hybrid architecture on an extensive dataset from a wind farm yields results that show this
architecture indeed provides an effective and useful solution to forecasting while being able to capture subtle patterns
that exist in the wind power data. It enables the integration of renewable energy sources into power networks more
effectively and pushes for more environmentally friendly ways to manage energy.
Keywords: Wind Power, Ensemble Methods, CNN, SVM.
Paper ID - 1005

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 127

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

HydroNet-Monitoring Water Health: A Comprehensive Approach to Evaluation and

Forecasting Quality
Kumar P, Senthil Pandi S, Karthikeyan N and Karupannan P
Among the main motivations of making forecasts on water quality, related needs are identified in public health
management and environment. A novel hybrid approach can be described as combining ensemble approaches with
deep learning to improve the prediction capability. In fact, it is the integration of Random Forest ensemble with
Convolutional Long Short-Term Memory network, which subsequently allows spatial and temporal trends within
water-quality data to be incorporated. In this, the model was trained over a large dataset of water samples originating
from various sources, with considerable water quality indicators. Our hybrid methodology shows higher predication
accuracy along with robustness compared to the traditional classic techniques associated with approaches of machine
learning. The ConvLSTM part of the model is efficient for handling complex temporal dependencies and overfitting
of the random forest ensemble improves the generalization and interpretability of the model. Observably, from the
feature importance analysis, pH and dissolved oxygen are the most critical measurements associated with water
quality. The architecture proposed covers real-time data collection, preprocessing, two-stage pipeline of the prediction
with data augmentation besides the hyperparameter optimization techniques. The results of the above architecture
show appreciable improvements in both computational efficiency and the predictions’ accuracy. In the process, the
contribution advances a discipline that provides more flexible and reliable frameworks for predicting water quality,
likely to find application in early warning systems and well-informed policy-making for the sustainable management
of water resources.
Keywords: HydroNet, hybrid deep learning, water quality prediction, ConvLSTM, Random Forest, spatial-temporal
patterns, non-linear relationships.
Paper ID - 1006

Deep Learning for Sign Language Interpretation With Conventional Neural Network
A. Senthilselvi, Ballela Avinash Reddy, Charan Deepesh Kristam, Rachaputi Yeswanth Vardhan
and Senthil Pandi S
Deep Learning For Sign Language Interpretation With Conventional Neural Network project aims to create a sign
language recognition system in real-time using CNNs, which includes voice output integration. The system can
effectively identify hand movements that represent letters of the alphabet and translate them into spoken words,
improving communication for those who cannot speak or have difficulty hearing. The recognition model is educated
with a strong dataset of American sign language (ASL) and incorporated with TensorFlow Lite for efficient
operation on mobile devices, guaranteeing portability and convenience. The user interface enables easy interaction,
including the ability to add gestures, listen to them, add spaces, and delete the input. Instant translation of sign
language gestures into spoken words is made possible with real-time processing, ensuring a smooth user experience.
Although the system shows excellent precision in controlled environments, additional efforts are necessary to enhance
its effectiveness in different settings, hand positions, and lighting situations. This project is a major advancement in
making communication easier with sign language recognition and voice output.
Keywords: Sign language, American sign language, conventional neural network.
Paper ID - 1007

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 128

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A Novel Approach to Improve Crop yield using Machine Learning

A.Senthil Selvi, Gollapally Abhiram Sai, Abhinand TV, Jayadev Nukala, Syed Juniad and Senthil
Pandi S
Agriculture is considered as the mainstay and source of revenue in India which contributes to 54. Accounting for 6%
of the population and close to 14% of the total GDP of the country. However, it has undergone a lot of challenges
that hampers its functionality in this research despite being central in this study. One major constraint is that the
type of soil and climate varies greatly from one region to another in India and they are also always changing due to
Global Warming. This difference complicates the search for uniform and reliable product yields making it very hard
for farmers to achieve high productivity. To solve these complex problems, this study proposes the development of a
new solution: an elementary site identification model. Improve on the precise and timely decision-making process in
relation to agriculture. It has a great potential in various fields, as it is able to identify strict correlation with a large
amount of data without needing it to be pointed out by someone. When these techniques are applied to agricultural
data they will present an appropriate model for crop selection in terms of type of soil, climate and production history
of crops. Apparently, intelligence offers them proper information in line with their circumstances prevailing at the
time they are working on. Farmers will be able to practice better decision making with regards to which crops to grow,
at what season, resource utilization and improved yields from the recommendations coming out of the data. Through
this objective, the undefined nature of crop production is reduced and the productivity of input like water, fertilizers
and pesticides is optimized. This makes farming more lucrative reducing the chances of its decline or shrinkage hence
promoting its sustainability as well as rapid growth. Altogether, this research will go a long way in impacting Indian
agriculture positively by providing solutions whenever such issues come up in the course of pursuing bigger objectives.
Keywords: GDP, SVM, Random Forest, CNN, LSTM.
Paper ID - 1009

Towards Safer Environments: CNN-LSTM Framework for Accurate Fire Detection

Saranya V and Senthil Pandi S
Fire detection systems are highly important in giving early warnings and emergency responses. However, this sector
often encounters a number of challenges due to a good level of false alarms that cause unnecessary mobilization of
resources and a lack of belief in the system. This paper is meant for the presentation of a strong framework in
the reduction of fire detection false alarms using an advanced classification model. The proposed system contains
three crucial phases: preprocessing, feature extraction, and classification. It uses state-of-the-art image enhancement,
noise reduction, and background subtraction techniques with adaptive thresholding during the system’s preprocessing
phase of the input data to enhance its quality. In this way, it ensures that features irrelevant to fire detection
are eliminated and that the quality of data about fire either captured by surveillance footage or sensor readings is
improved. Deep learning techniques are proposed in feature extraction, specifically Convolutional Neural Networks that
automatically capture intricate patterns associated with fire occurrences, flame color, texture, and motion dynamics.
This classification uses the architecture of the LSTM to concentrate on critical fire-related features, which will further
enhance the accuracy in distinguishing events between fire and non-fire conditions. Training and testing datasets are a
rich set of fire and non-fire instances from publicly available fire surveillance datasets, enriched with real world smoke
sensor and thermal camera data. Standard metrics of performance like accuracy, precision, recall, F1- score, and false
alarm rate will be considered in order to validate the proposed framework comprehensively, covering fire detection and
its false alarm reduction. The experimental results showed that the false positives drastically decreased, proving that
the framework indeed supported enhancing the reliability of fire detection systems.
Keywords: Fire detection, image enhancement, noise reduction, CNN, LSTM.
Paper ID - 1010

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 129

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Digital Renaissance: Government Scheme Notification and Smart Fund Disbursement

as Catalysts for Empowerment in Social Reliability
Ms. Kavitha Arunachalam, Ms. Swetha S and Ms. Swetha T R
Government policies on education, health, welfare, infrastructure, and agriculture are key to improving society,
improving quality of life, meeting basic needs, encouraging economic growth and promoting sustainable development
permanent presence is encouraged but a lack of awareness of these services often leads to uneven distribution of
benefits. To address this gap, we developed an app that instantly notifies eligible individuals or families of the
introduction of new government policies. Our solutions use technologies such as SQLite, Mobile Backend as a Service
(MBaaS), and AI-driven scheduling algorithms using Monte Carlo simulation and Dynamic Programming, ensuring
optimal performance for optimal performance. Additionally, by using machine learning algorithms to assess
eligibility, this system streamlines the distribution of resources, providing timely information to those most in need.
This new approach helps promote equitable distribution of government resources and promote positive social change.
Our mission is to empower individuals by connecting them with the support they need, ultimately creating an
inclusive and prosperous society. This holistic approach enables the government to make a meaningful impact,
delivering a brighter and more equitable future for all.
Keywords: Government Schemes, Notification, Transparency, awareness, MBaaS, SQLite, Monte Carlo algorithm.
Paper ID - 1026

Blockchain-Based Voting System With Fingerprint Authentication and Zero

Knowledge Proofs
R. Sudharsan, L. Giridharan, Anto Micheal Infant and Dr. Suresh Annamalai
Voting plays a crucial role in democracy as it is the mechanism through which the will of the people is translated into
policies. Ensuring the security, reliability, and privacy of the voting process is necessary to maintain the legitimacy
and integrity of the system as a whole. The immutability of voting systems based on blockchain has increased
their popularity. Noteworthy advancements in the field of blockchain have been made in the recent decade. It has
never been easy to create a secure voting process that preserves fairness and privacy while offering technology systems’
adaptability. This research project introduces a method to leverage and integrate a permissioned blockchain, biometric
authentication and zero-knowledge proof onto the traditional voting system. The main goal is to enhance the current
voting system by making it more secure while ensuring voter’s privacy.
Keywords: Blockchain, Voting, Zero-Knowledge Proof, Biometric Authentication

Paper ID - 1028

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 130

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Improving Cloud Burst Prediction with Meteorological Analysis Driven by Machine

Learning
Jagadeeshwaran S, Srinivasan Rama Krishnan, Vignesh Kumar A and Raja Priya D
An innovative ”Improving cloud burst prediction with Meteorological Analysis driven by Machine Learning” initiative,
developed within the Disaster Management domain by the Ministry of Power. This system leverages the capabilities
of machine learning to comprehensively analyze a wide range of meteorological parameters and weather patterns, with
the primary aim getting the result of whether it is yes or no. Cloudbursts, characterized by their abrupt and intense
rainfall, pose significant risks, including flash floods, landslides, and potential harm to both infrastructure and human
lives. Thus to combat this issue that may arise we have also provided the required preventive measures that is to
be taken at the event of such crisis. The Meteorological Department uses this indicator to determine the likelihood
of a cloud burst occurring in order to communicate with the public. The Indian subcontinent, noted for its diverse
terrain and distinct monsoon patterns, is under increasing threat from these extreme precipitation events. As climate
change accelerates, understanding and properly anticipating these occurrences has become crucial for catastrophe
management and mitigation. This conversation highlights the growing concern over cloudbursts and severe rainfall in
India, highlighting the critical need for improved forecast and analysis methodologies.
Keywords: Cloudburst Prediction, Machine Learning.
Paper ID - 1029

Advancing Emotion Detection In Sentiment Analysis With Concept-Level Computing

And Machine Learning
Dr.M.Kathiravan, Dr.R.Bhuvaneshwari, Ms.Ramya M, Dr. Kaaliraj S, Mr.A.Irumporai and
Mr.Vengatramana R
This study introduces an innovative approach to sentiment analysis and opinion mining, overcoming the limitations of
traditional techniques by employing a concept-level analysis framework. Leveraging linguistic insights, common-sense
reasoning, and sophisticated machine learning, the proposed method transforms unstructured text into analyzable data,
resulting in a significant precision enhancement. Achieving a 92.26% precision rate, our model outperforms existing
methods, particularly in parsing complex sentences with conjunctions and emotional variance. This methodology
marks a significant advancement in web-based sentiment interpretation, providing an intricate, accurate, and holistic
tool for analyzing online discourse and public sentiment.
Keywords: Sentiment Analysis, Opinion Mining, Sentic Computing, Machine Learning, Support Vector Machines.

Paper ID - 1036

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 131

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

PlantMed -An Automated App for Monitoring the tasks of Farmers

B.Sundarambal, S.Manju and R. Aarthi
Farmers and terrace gardeners use PlantMed, a sophisticated mobile application, to track ailments and monitor plant
health through the use of machine learning and computer vision. The API focuses on various plants, and users can
upload pictures of their plants to diagnose diseases quickly using K-means and CNN network (KNN) algorithms.
The application utilizes an open API for well-being and a linear regression model to forecast production figures for
various climatic conditions, including rainfall, temperature, humidity, and wind, while also integrating current weather
information. The application offers suggestions for managing agro-health care, such as using pesticides, linking GP
outage measures with government schemes, and registering the soil condition in their vicinity using the Google Maps
API. Eva, the integrated multilingual Chabot, encourages users across languages by teaching them how to grow
plants, prevent them from diseases, and use the app. Additionally, the application provides educational content in
the form of articles, videos, and news about current agricultural trends. Some upcoming enhancements include the
incorporation of market demand, the implementation of growing crops where there is a demand for them, and the
ability to search nearby locations for agricultural equipment and supplies, thereby transforming plant medicine into a
remedy for enhancing crop productivity.
Keywords: PlantMed, agro health care, linear regression model, K-means and CNN Chabot, soil condition.
Paper ID - 1042

AI Enhanced Logbook Management for Classrooms

Saraswathi P, Keerthana.R, SobanaManikandan, Muthulakshmi.P, A.Sameeha and Sharmila Devi R
Aims to streamline classroom management by developing a web-based application that leverages artificial intelligence
(AI) to automate tasks such as attendance, on- duty requests, and student performance tracking. By using AI-driven
facial recognition, the system automates attendance tracking, reducing manual errors and administrative workload
for educators. It also digitizes the on-duty request process, allowing students to submit documentation online and
enabling staff to efficiently review and approve requests, with automated notifications keeping students informed
about the status of their submissions. Following a structured Software Development Life Cycle(SDLC), the project
ensures a systematic approach to development, enhancing classroom discipline, reducing administrative burdens, and
promoting efficient management of student records. Ultimately, this AI- powered solution creates a more organized
and productive learning environment, enabling educators to focus more on teaching and less on administrative tasks.
The system also incorporates AI-based analytics to monitor student performance, identifying patterns and offering
insights to educators for personalized intervention. By maintaining a comprehensive student database, the
application allows for real-time tracking of attendance, on-duty status, and academic performance, enhancing overall
transparency.
Keywords: Web-based application, Artificial Intelligence (AI), Machine learning, AI-driven facial recognition,
Software Development Life Cycle (SDLC) Systematic approach.
Paper ID - 1060

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 132

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Diabetic Retinopathy Classification using Hybrid Optimized U-Net and Improved

ResNet-18 with MISH Activation
S.Nithyapriya, S.Yuvalatha, S.Prabhavathy, T.Arun, Dr S.K Muthusundar and Dr. Antonidoss A
Diabetic Retinopathy (DR) refers to damage to the retina caused by diabetes, which can cause visual impairments
or potentially lead to blindness. The process of manually identifying diabetic retinopathy is slow and can easily
be affected by human mistakes because of the eye’s complex anatomy. This paper aims to determine the optimal
model for accurately staging diabetic retinopathy (DR) across five DR categories. The proposed system involves
image pre-processing, segmentation and classification. A well-structured preprocessing framework was implemented,
integrating Median Filtering technique to decrease noise and Gamma Correction for improved image quality. Data
augmentation is performed through methods like flipping, cropping rotating, and translation of fundus images. In this
study, a hybrid optimization strategy is proposed by combining the Adam optimizer with Simulated Annealing (SA)
and Cosine Annealing for training a U-Net model for diabetic retinopathy (DR) lesion segmentation. Canny Edge
Detection is employed to discover edges correctly within the image. For DR categorisation in this work, enhanced
Resnet 18 combined with MISH activation function is used. The suggested model makes use of residual blocks in
conjunction with identity and convolutional blocks. Experiments on the APTOS dataset show that the proposed
model outperforms state-of-the-art techniques. Accuracy, precision, recall, and F1 score are all improved by the
suggested Resnet18 model, which receives scores of 99.45%, 98.64%, 98.63%, and 98.63%, respectively.
Keywords: Adam, Cosine Annealing, MISH, Resnet18, Simulated Annealing, U-Net
Paper ID - 1061

Capsule-Infused Vision Transformer: A Hybrid Deep Learning for Hierarchical

Feature Learning
S.Yuvalatha, S.Nithyapriya, R.Tamizh Kuzhali, S.savitha, Dr S.K Muthusundar and Dr.
Antonidoss A
Diabetic Retinopathy (DR) is an eye disease that affects the blood vessels in the retina and causes vision loss for
diabetic people. Microaneurysms are the early sign for DR and it is crucial for ophthalmologists to find manually and
prevent vision loss. We proposed a hybrid model by concatenating the feature detected by capsule network and vision
transformer. Before training the data, SMOTE method is used to balance the data sample and green channel image is
taken for accurate detection of DR classes. The hybrid model leverages the strength of capsule network by preserving
the spatial information by dynamic routing and vision transformer process the global image through self-attention
mechanism. The proposed model was trained and tested on DR data sample and classification accuracy of 98.1% was
achieved. This proposed model automatically detects the early sign of diabetic retinopathy. The confusion matrix is
demonstrated to show how the model’s effectiveness is in correctly classifying different stages of DR.
Keywords: Capsule network, SMOTE, Vision transformer, self-attention
Paper ID - 1062

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 133

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Decoding Emotions: A Deep Learning Framework for Speech Emotion Recognition

Shreyank Saksena, Anirudh AVS and Dr. Parkavi K
Speech Emotion Recognition (SER) has become a very significant research field, with applications from human-
computer interaction, mental health monitoring, and real-time communication systems. In this article, the diversity in
methodologies applied in SER will be systematically reviewed while representing both conventional machine learning
models, such as Support Vector Machines (SVM), and more complex deep learning architectures, including Long Short-
Term Memory (LSTM) networks, attention-based models, and graph-based techniques. The functions of convolutional
neural networks with LSTM and self-attention mechanisms are capturing spatial and temporal features significantly
responsible for improving the detection against complex emotional states like anger, fear, and sadness. Among the
feature extraction techniques critical to model performance, MFCCs and prosodic features have been more salient.
While attention-based deep learning models demonstrate reliabilities of as high as 90%, traditional methods still
provide faster real-time detection and are thus suitable for applications in domains such as telemedicine and online
learning. Yet, the challenge of recognition with noise and complexity in real-world environments is not solved. Methods
proposed include data augmentation, multi-lingual, and cross-corpus training for model robustness improvement. Its
ongoing refinements, particularly adoption of attention mechanisms and of complex feature extraction, will be more
important for higher accuracy and applicability across a wide range of real-world scenarios.
Keywords: Speech Emotion Recognition, Deep Learning, Machine Learning, Attention Mechanisms, Convolutional
Neural Networks, Long Short-Term Memory, MFCC, Graph-Based Models, Real-time Emotion Detection, Feature
Extraction, Cross-corpus Training, Data Augmentation.

Paper ID - 1084

Securing Library Assets: Leveraging Blockchain for Unbreakable Data Integrity and
Privacy
Dr .J.V.Anchitaalgammai, Mrs.S.Kavitha, Mr.S.Murali, J.Matcha Rani, R.Shreevarshini and
V.Agniselvi
In the present technological and information age, libraries are highly exposed to risks such as hacking, breaking into
the data and altering it. This paper seeks to discuss how these challenges can be solved using blockchain by offering
unassailable data integrity and even better than existing systems’ privacy options. With an ability to decentralize and
decentralize operations due to its technical characteristics, blockchain can prove useful in the process of protecting
library assets while at the same time eliminating doubts as to the honesty of operational processes in libraries. The
successes and failures of blockchain applications and theories are investigated to demonstrate blockchain’s potential
and the development of library systems.
Keywords: Blockchain, Data Integrity, Privacy, Library Management.
Paper ID - 1085

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 134

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Machine Learning Algorithms Based Approach for Detecting the LeukemiaDisease

Senthil Pandi S, Bala Subramanian C, Mithul Dev D and Kumar P
Detecting leukemia, a condition characterized by significantly elevated blood cell counts compared to healthy
individuals, typically relies on repeated full blood counts due to the challenge posed by malignant cells resembling
normal blood cells. Early identification and treatment are crucial to prevent complications. Current laboratory
procedures for leukemia detections are time wasting. Following study proposes a machine learning approach of
leukemia detection. The dataset comprising images of lifeblood smears is aggregated and processed to extract
wanted features. These are utilized to fit and examine unlike methods, including KNearest Neighbour, Decision Tree,
Random Forest, and Logistic Regression. Comparison of classifiers’ performance against multiple criteria, such as
accuracy and precision, aids in identifying the most effective classifier.
Keywords: Decision Tree Algorithm, KNearest Neighbour Algorithm, Support Vector Machine Algorithm, Random
Forest Tree Algorithm, Logistic Regression.
Paper ID - 1089

Optimizing Feature Selection for Big Data and Machine Learning: Challenges and
Future Prospects
V.Sharmila Bhargavi, T.P. Anish, Anusha S, V.Nivakumar, Dr M.Nalini and Siva Subramanian R
Feature selection is an important step in the machine learning process that improves model accuracy by filtering
out unnecessary features from higher-dimensional data, eliminating redundancy, and increasing computational speed.
It deletes features that are irrelevant or redundant, hence reduces the amount of time taken to train a model, and
increases its chances of accuracy. Filter techniques, wrappers, embed, hybrid techniques are among the most commonly
used approaches where each of them comes with its unique time and accuracy spaces. Current trends are especially
concerned with tackling issues related to big data, deep learning and time series while new upcoming application
areas include real-time system, edge AI. Feature selection is widely used in different fields such as health care, finance,
NLP, CV, and cybersecurity. Nevertheless, some issues still open concern with regard to extendibility to an extensive
amount of data, interpretability of the models, and incorporation of unsupervised learning. Subsequent studies will
be devoted to surmounting these difficulties and creating more accurate, explainable, and extensible methodologies
for emergent machine learning needs.
Keywords: Feature Selection, Machine Learning, Filter, Wrapper, Embedded.
Paper ID - 1092

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 135

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

IOT Based Continuous Blood Glucose Monitoring System for Enhanced Diabetic Care
Megala J, Divyapriya C, Gayathri G, and Logeshwari S
The system aims to regulate blood glucose levels and optimize diabetes management by leveraging IoT technology to
collect real-time data on critical health parameters, including blood glucose levels and blood pressure. MATLAB
algorithms analyze this data and deliver personalized interventions based on individual patient profiles, dynamically
adjusting insulin dosages in response to glucose trends. The simulation model integrates physiological blood glucose
dynamics with IoT-enabled sensing, data transmission, and real-time analysis, mimicking realistic glucose
fluctuations such as postprandial spikes and hypoglycemic events. It also simulates sensor measurements, wireless
data transmission, and glucose trend detection. Seamless integration with Thing Speak and Think View facilitates
efficient data transmission and visualization, providing healthcare providers and patients with timely glucose
updates. The framework allows for the testing and evaluation of different sensor configurations, data processing
algorithms, and communication protocols, aiding in the development of more effective IoT-based glucose monitoring
systems. This simulation framework contributes to the advancement of personalized diabetes management, offering a
powerful tool for improving patient outcomes and healthcare strategies.
Keywords: Innovative diabetes care through glucose monitoring and IoT-driven health systems enables real-time
blood glucose anagement and continuous vital signs tracking. Utilizing MATLAB for data analysis and Thing Speak
for insightful health data visualization, these systems support personalized interventions and predictive patient
profiling. This future-oriented approach enhances remote patient monitoring, providing tailored healthcare solutions
and decision-making support for better diabetes regulation.

Paper ID - 1095

AI-Driven Predictive Modeling for Early Detection and Progression Monitoring of

Chronic Kidney Disease Using Multimodal Data
L Lakshmi Prasanna Kumar, Vankadara Sampath Kumar, G. Ashok Kumar, Y.Nagendar, Nithya
M and A.Athiraja
Chronic kidney disease (CKD) is a critical global health issue that can lead to end-stage renal failure if not diagnosed
and managed early. Early detection and continuous monitoring of CKD progression are essential for optimizing
healthcare resources and improving patient outcomes. This research presents an artificial intelligence-driven predictive
model that integrates multimodal data, including genetic profiles, imaging, laboratory results, and clinical records, to
enhance CKD diagnosis and progression monitoring. By leveraging advanced machine learning techniques, particularly
deep learning models, the system effectively processes and analyzes these diverse data sources. The integration of data
fusion, feature extraction, and classification techniques improves the accuracy and reliability of CKD detection. Key
findings reveal a notable 12%–15% increase in prediction accuracy compared to traditional approaches, demonstrating
the potential of AI in transforming CKD management. The system is designed to assist healthcare providers with timely
interventions and personalized treatment plans while offering scalability, flexibility, and ongoing patient monitoring to
support clinical decision-making.
Keywords: chronic kidney disease, predictive modeling, artificial intelligence, multimodal data, early detection

Paper ID - 1097

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 136

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Enhancing Software Debugging Processes Through Machine Learning-Driven

Automated Bug Detection
Venkata Madhu Bindu Nalluri, Parvathraj K M M, Y.Nagendar, Kalaivani E, Prabhu A E and
Dr.Athiraja Atheeswaran
In software development, debugging is an essential but laborious process that frequently requires the manual
discovery and correction of errors. The project aims to develop an automated bug detection system powered by
machine learning to address the challenge of enhancing this process. The process involves evaluating code samples to
discover probable problems based on extracted features such Term Frequency-Inverse Document Frequency
(TF-IDF) scores, code complexity metrics, and syntactic patterns. It leverages Natural Language Processing (NLP)
and a Random Forest Classifier. Using a dataset of labeled code snippets, the suggested approach was assessed and
found to significantly enhance mistake detection efficiency as well as accuracy. The outcomes show an approximate
35-40% decrease in the amount of manual debugging work and an improvement in problem identification accuracy.
The findings demonstrate how well machine learning approaches can be incorporated into the debugging process,
providing a viable way forward for more productive software development procedures.
Keywords: automated bug detection, machine learning, software debugging, natural language processing (nlp),
random forest classifier.
Paper ID - 1098

Real-Time Vehicle Density Detection for Adaptive Traffic Signal Control Using
YOLOv5
M. Mariyammal, Rakesh S P, Ramana Ganthan S, R Poornima Lakshmi, Ayyappan S and R.
Ponnusamy
In modern urban environments, traffic congestion is still a problem that brings delays, fuel consumption, and
pollution in terms of travel. Conventional traffic signal control is based solely on fixed timers without adaptation to
real-time conditions, which amplifies the previously mentioned problems. This paper proposes developing an
intelligent traffic signal control system that adapts dynamic signal timing according to the real-time density of
detections using the YOLOv5 (You Only Look Once version 5) object detection algorithm. YOLOv5 has gained
fame because of the high speed at which it analyses live video feeds streaming through traffic cameras. It very
efficiently differentiates between plus counts the vehicles crossing from multiple lanes. Therefore, the developed
system will optimise the traffic signal switching by using vehicle density information, subsequently reducing waiting
time at intersections and offering improved traffic flow. In contrast to the static systems, the method presented here
is flexible and adaptive and would suit various changes in the daily conditions around traffic. The utilisation of
YOLOv5 makes it possible to improve the system’s accuracy in vehicle detection, even with intricate traffic patterns,
without diluting it down to real-time computation. A simulation model of the proposed model was performed using
real traffic footage from cities, and significant improvements over traditional traffic management methods were
demonstrated. Therefore, the system shows reduced congestion with better time distribution and a more efficient
distribution of green signal time with better traffic throughputs. It can, thus, be inferred that real-time object
detection combined with adaptive control of traffic lights can be a new strong combination in the development of
smarter urban traffic systems that can considerably reduce congestion and their associated environmental impacts.
Keywords: Real-Time Vehicle Detection, YOLOv5, Adaptive Traffic Signal Control, Vehicle Density, Traffic
Congestion, Object Detection, Signal Timing Optimization, Urban Traffic Management.
Paper ID - 1099

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 137

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Stego-Image Data Masking

Aswathy M P, Megiba Jasmine R, P.J.Beslin Pajila, Anish T.P., Dinesh M G and Nithyanandhan R
Due to a vast increase in security breaches and other violations, Data hiding has become a vital measure for the
protection of the integrity of an individual or a group. Image steganography is a perfect technique that exists for the
protection of data from getting altered and getting safely transmitted. Steganography serves as an excellent method
to secure information as the unauthorized party barely recognizes the secret message or a text that is hidden behind
the original or the cover image. In this project we have mainly focused on the Least Significant Bit (LSB) for hiding
the texts behind the images and build our idea through a GUI. LSB is quiet simple and an efficient algorithm in which
the least significant bit that barely changes the quality or the build of the original image is changed and is replaced
by the secret text that we want to communicate to the other users. Image preprocessing and generation of the output
stego image is done by Pillow (PIL) and OpenCV in which image binary pixels are taken as input then they are altered
with the secret text and then finally sent to the desired user.
Keywords: Data Hiding, Least Significant Bit, Data Security, Image Steganography, OpenCV, Pillow.
Paper ID - 1100

Facial Emotion Classification Utilizing Efficientnet: A Comprehensive Deep Learning

Method
Veeramalai S, Chorko C, Akshaya A and Rahul Ramamoorthy
Human-computer interaction has now advanced to rely significantly on emotion recognition through deep learning.
This paper studies the capabilities and effectiveness of the EfficientNetV2B2 model for real-time facial expression-
based emotion detection in real-world applications. For fine-tuning after training on the FER dataset, I have used
the Categorical Cross-Entropy loss function and Adam optimizer. Various data augmentation techniques have been
implemented to improve the generalization ability of the model. From our results, it is evident that all seven different
emotions, which include anger, disgust, fear, happiness, neutrality, sadness, and surprise, can be distinguished with
a great accuracy. Moreover, the architecture of the model ensures rapid inference with suitability for real-time
applications like online education, mental health tracking, and so on in the customer support system. At 88%, the
deployment results are validated.
Keywords: Emotion recognition, EfficientNetV2B2, deep learning, human-computer interaction, facial expressions.
Paper ID - 1104

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 138

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

AI-Based Mathematical Modelling for Sustainable Business and Inventory

Management
Arvind Nain, Madhu Arora, Saurabh Sharma, Anup Shekhar Chamoli, Satyam Prakash Srivastava
and Vasim Ahmad
The paper focuses on the elaboration and application of AI-based mathematical models for sustainable inventory
management, which have the full potential to improve both operational efficiency and environmental performance.
The integration of machine learning algorithms, optimization techniques, and real-time data in the proposed models
will help improve accuracy in demand forecasting, diminish waste in inventory, and reduce carbon emissions within
supply chains. Indeed, these point to cuculating on one hand, a 20-25% improvement in demand forecasting, a
reduction of inventory costs by 15%, and waste generation as high as 30%. Furthermore, AI-driven sustainability
metrics, such as the efficiency of transport and energy consumption, have been implemented that show quantifiable
measures of carbon footprint reduction for the activities involved in managing inventories. The findings hence indicate
that AI provides a transformative way of associating business goals and objectives with those that are sustainable.
Conclusions are drawn on broader implications for business sustainability and point toward further research that may
aim to optimize the role of AI in sustainability and business operations.
Keywords: Artificial Intelligence, Sustainable Inventory Management, Machine Learning, Optimization Models,
Demand Forecasting, Environmental Impact, Circular Economy, Supply Chain Management, Carbon Emissions
Paper ID - 1106

Optimization of Green Finance Using AI and Blockchain in Inventory Management

Arvind Nain, Preeti Tyagi, Mayank Pant, Devesh Chand, Satyam Prakash Srivastava and Vasim
Ahmad
Study shall examine positions assumed by Artificial Intelligence, Blockchain, and Green Finance to see how each
separately and collectively might play a role in the inventory management systems to contribute to sustainability
and financial efficiency. AI, in its data-driven predictive power, optimizes the processes of inventory through
improved demand forecasting, reduced waste, and resource usage. Blockchain ensures much-needed transparency,
traceability, and accountability throughout value chains, enabling the verifiability of more precise sustainability
metrics via smart contracts, which can automate Green Finance agreements. Integration of these technologies serves
to align inventory management toward sustainability goals of reduced carbon footprint and energy efficiency. The
paper reviews the literature, examines key models and frameworks, and discusses the potentials of AI and Blockchain
to influence sustainable practices and financial outcomes in inventory management. Future research opportunities
are outlined to address current gaps and enhance the adoption in real-world applications of the subject technologies.
Keywords: Artificial Intelligence (AI), Blockchain, Green Finance, Inventory Management, Supply Chain,
Sustainability, Predictive Analytics, Smart Contracts, Carbon Footprint.
Paper ID - 1107

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 139

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Temperature Monitoring System for Portable Incubators for Neonatal Care

Muthyala Prem Kumar and Gorthi Balaji
Neonatal babies around the globe are saved by the wider spread of Portable Baby incubators. The simple design
principle of these Portable Baby warmers or incubators with a sleeping bag and heat retention pouch helped many lives
of small premature babies in critical conditions. While the babies absorb the temperature to keep them warm, there
is a gap in measuring the temperature of babies and the warmers at once. Monitoring the temperatures of the pouch
is still a challenge for the nursing staff. With babies prone to infections, contact thermometers are not recommended.
The project aims to design an advanced temperature monitoring device for these portable baby incubators for better
performance. The proposed system integrates accurate and reliable temperature sensors and alert system to ensure
optimal thermal regulation for neonatal babies. By providing continuous monitoring and immediate notifications of
temperature deviations, this solution seeks to empower caregivers with the tools necessary for timely intervention,
thus reducing neonatal mortality and morbidity. The design also provides to be energy-efficient, user-friendly, and
cost-effective, aligning with the core principles of the Portable baby incubators. The need for constant monitoring by
nursing staff can be minimized with these innovative products.
Keywords: Baby Warmer, Neonatal care, Temperature Monitoring, Hypothermia, MLX90614 IR Sensor, TMP36
Sensor.
Paper ID - 1109

An Intelligent Agents-Based Smart Drip Irrigation System Design Using Paddy Crops
D. Lekha and P. Valarmathie
Successful agriculture leading to an abundant yield of food crops is very essential to achieve the goal. Rice is the
durable standard food for most of the people in Tamilnadu .Rice is traditional method of cultivation in the way of
flood irrigation which consumes 85% of water used especially in agriculture. Considering in Tamil Nadu’s annual
requirement in the field of rice approximately in 38 lakhs for the public distribution system (PDS), the State has a
demand on rice to cultivated the product to depend on the Central authorities or other States, as what we are
getting procured by the authorities in locally and firmly is barely sufficient for the PDS. The major factor for this is
the decline in rainfall due to adverse climatic conditions .The decline in rainfall have led to depleted water level.
Paddy crop requires strong water supply and water has to be supplied strategically also water should be kept
permanently till the growth period completes. There will be no yield if there is excess /limited or no water at all.
Therefore it is very important to continuously monitor soil moisture levels in the paddy fields and release water
according to the soil and humidity and climatic conditions. Nowadays Drip irrigation is recent trends in the
agricultural field to recover the plants from scarcity and salt affected areas. Drip irrigation allows precise amount of
water to the crop root zone and has found to be successful in paddy cultivation in Israel, Turkey and certain states
of India like Maharashtra, Bihar, Karnataka and Tamilnadu.
Keywords: Drip irrigation, Machine Learning Algorithms, Sustainable Agriculture, Internet of Things, Cloud
Storage, Wireless Sensor Systems

Paper ID - 1111

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 140

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Innovative Gym Management Platform For Effective Member Engagement And

Service
DineshKumar S and Naveenkumar P
The project is designed to simplify the processes and reduce the time spent on managing them. In the old system,
relying on paper documentation made records vulnerable to loss or misplacement, compromising security. This new
system has been developed to securely maintain and organize all records. It provides an efficient solution for securely
managing user details and storing information about staff and members, making it a valuable tool for gym operations.
Keywords: Gym management system, machine work, online registration.

Paper ID - 1112

Enerlink Guardian: Dynamic Vehicle- to-Vehicle Charging and Battery Oversight

System for EV Charging Stations
Magadevi Nirmalkumar, S. Bharathi, S. Janani and S. Lekha
This paper presents a smart charging system designed to optimize energy resource utilization in electric vehicles (EVs)
while improving safety and connectivity at EV charging stations. The system is built around two key processes: First,
an Arduino Uno microcontroller, interfaced with a DC voltage sensor connected to a 12V battery, monitors battery
levels in real-time. This data is displayed on an Android app, which also helps drivers locate nearby charging stations
to manage energy efficiently. Second, in the absence of internet connectivity, the system automatically shares the
vehicle’s location with nearby vehicles via a vehicle area network using wireless technology. This allows vehicles to
request and receive charging assistance from other vehicles in the vicinity, ensuring uninterrupted mobility and seamless
energy transfer. By integrating real-time monitoring, vehicle-to-vehicle energy management, and IoT technologies, this
solution promotes sustainable energy practices, enhances safety, and sets a new standard for smart vehicular operations
in electric mobility.
Keywords: EV, VAN, V2V, IoT, SoC, BMS, GPS.
Paper ID - 1117

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 141

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Scalable Transaction Management System: A Blockchain-Based Approach using

Solidity and Ethereum
Annie Silviya S H and Dinakaran Karunakaran
Content curation and information examination assume vital parts in upgrading mechanical learning results by
working with the revelation, association, and translation of data inside advanced learning conditions. This
exploration paper investigates the combination of content curation and information examination to upgrade
mechanical growth opportunities. Drawing upon hypothetical structures, for example, constructivism, connectivism,
learning examination, TPACK, mental burden hypothesis, social learning hypothesis, personalization hypothesis, and
inspirational speculations, this study inspects how these ideas advise the plan and execution regarding viable
academic techniques. Through a complete writing survey, this paper orchestrates existing examinations to lay out a
hypothetical starting point for the proposed approach. The procedure area outlines the research plan, data gathering
techniques, and scientific methods used to study impact of content curation and information analysis on creative
learning outcomes. Results from the information examination are talked about according to the exploration goals,
featuring key discoveries and bits of knowledge. The ramifications of the discoveries for teachers, policymakers, and
specialists are inspected, alongside proposals for future examination bearings. By clarifying the synergistic
connection between happy curation, information examination, and mechanical realization, this paper adds to the
progression of proof-based rehearsals in instructive innovation.
Keywords: Blockchain, Smart Contracts, Scalability, B2B, Ledger, Transaction Processing, DOA, Decentralization,
Distributed Ledger Technology.

Paper ID - 1118

Dronav: Deep Learning based Autonomous Drone Navigation System

T. Daniya, Aditya Darapureddy, Guravana Ashok Kumar, Boyina Rajesh, Dinesh Potnuru and Sai
Amrutha Vugiri
In this paper, we present a comprehensive methodology for the development of an autonomous drone delivery
system, focusing on efficient navigation, real-time obstacle avoidance, and precise control. The proposed system
integrates Simultaneous Localization and Mapping (SLAM) for accurate localization and mapping of the
environment, combined with the A* algorithm for optimal path planning. To enhance the system’s capability to
navigate dynamic environments, we utilize a deep learning-based model for real-time obstacle detection and collision
avoidance. Furthermore, Model Predictive Control (MPC) is employed to fine-tune the drone’s flight path, ensuring
smooth and stable movement while adapting to environmental uncertainties. This multi-layered approach enables
the drone to autonomously map its surroundings, compute the most efficient route, and safely avoid obstacles during
delivery operations. The proposed method offers a robust solution for autonomous drone navigation in complex and
unpredictable environments, making it highly suitable for drone delivery applications in various real-world scenarios.
Keywords: A* algorithm, Autonomous Drones, Unmanned Aerial Vehicle, Model Predictive Control, SLAM.
Paper ID - 1119

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 142

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Tribological and Mechanical Properties of Polymer Composites Reinforced with Alkali

Treated Prosopis Juliflora, Egg Shell, and Scallop Shell
Pravinprabu T, Rajarajan S J, Mounika J and Jayakumar T
Brake pads play a crucial role in automobiles, with tribology and mechanical performance being critical factors to
consider. Asbestos brake pads were often used, later replaced by copper-based brake pads. As brake materials
improve, synthetic composites are being investigated as alternatives. Recent research indicates that composites are
emerging as effective friction materials. However, their application is hindered by inadequate thermal conductivity and
frictional stability. Enhancing the fibers through surface treatments and incorporating secondary fillers can improve
their flexibility. Therefore, the combination of supporting materials expands their application areas. This article tries
to focus on the application and evaluation of wild fruit powder, egg powder and scallop shell powder in brake pads
by focusing on natural materials. Their products are examined to determine their ability to meet the requirements.
This article examines the products of prosopis juliflora powder, egg powder and scallop shell powder that have been
relevant to brakes in recent years. Natural compounds hold considerable promise for advancing the development of
friction materials in automotive applications. The composite was tested according to ASTM standards and the results
were positive. Based on the results, the integrated model was developed and tested for clarity. Taguchi’s method
and transformation analysis were used to obtain the optimal results of wear resistance and abrasion resistance. The
comparison of the tests and analyses shows that the mixed materials of prosopis juliflora, egg shell powder and scallop
shell powder composite can be used as alternate materials for more effective brake pad.
Keywords: scallop shell powder, egg shell powder, Prosopis juliflora, abrasive wear resistance, taguchi and anova,
flexural, water absorption, natural composites.

Paper ID - 1120

Streamlit Enabled Adaptive Movie Recommendation Systems using Content-Based

Filtering Techniques
Prem Kumar R and Anitha R
This paper outlines a movie recommendation system that has been proposed and implemented using Python and
Streamlit and which relies on content-based filters solely to recommend films that match users’ interest and preferred
genres. The system takes information from the readily accessible large-scale datasets, preprocess the movie information
and then calculate the cosine similarity between films. Through content based filtering, the recommendation engine
recommends movies which are of the same genre or similar to those movies the user has expressed an interest in or
those that the user has rated highly. The system has an interactive interface made by using Streamlit, more specifically,
the program lets users enter the name of a movie and provides recommendations based on this input.
Keywords: Movie Recommendation System, Streamlit app, Machine learning, Content-based filtering, User profiles,
Movie Genres, Public datasets, Cosine similarity, Recommendation engine, GUI.
Paper ID - 1123

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 143

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Forecasting Crop Yields Using Machine Learning Techniques For Sustainable Farming
Dr ChitraDevi D M.E, Mahalakshmi G, Priyadharshini M and Reshena R
crop production plays a crucial role in agriculture planning resource allocation and food security management with
the advancement of technology and the availability of vast amounts of agriculture data, machine learning and
statistical modelling techniques have emerged as powerful tools for predicting crop yields and identifying potential
factors including crop growth. the data set utilized in crop production includes data such as whether data, soil
quality is obtained through soil sampling algorithms commonly applied in crop production including Gaussian naive
bayes this algorithm leverages the extracted features from the data set to build predictive models that estimate crop
production for specific region and the period. Additionally, it highlights the significance of Accurate crop prediction
in optimizing agriculture practices mitigating risks associated with climate change, and ensuring sustainable food
production. furthermore, the discussion challenges data availability model complexity and interpretability along with
the potential Avenue of further research to enhance the accuracy and applicability of the crop production model.
Keywords: Machine Learning, Gaussian Naı̈ve Bayes, Algorithms.
Paper ID - 1124

Advanced Recurrent Neural Networks for Nail Disease Detection: A Comparative

Analysis
Shanthalakshmi Revathy J, Menaga R and Pradeesha C
Nail diseases, though often considered minor conditions, they can indicate more serious underlying health problems
and, if left untreated, can result in infection, discomfort, or even permanent nail damage. Conditions like brittle
onychomycosis and psoriasis are frequently misdiagnosed due to their similar appearance and minor symptoms. To
address this, an automated nail disease classification system has been developed using advanced image analysis
techniques. To improve feature extraction, a comparison study was done between an Enhanced RNN that integrated
VGG-16 layers and a Basic RNN that used Long Short-Term Memory (LSTM) units. Traditional methods of
diagnosis are prone to errors and rely on slow manual assessments, while the enhanced RNN model captures intricate
spatial features with VGG-based convolutional layers followed by LSTM units that process sequential image
patterns. The Enhanced RNN provides improved accuracy over the Basic RNN, achieving 90% accuracy by the 20th
epoch. This makes it an efficient and reliable tool for the early detection and classification of nail diseases.
Keywords: Nail Disease Detection, Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), VGG16.
Paper ID - 1130

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 144

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

A CNN-Based Framework for Alzheimer’s Disease Diagnosis and Prognosis from

Multimodal Imaging Data
Balasubramanian M, Vishnu Sriram T, Gautam Kumar G, Jeo Godson Samuel J and Kanishka M
Alzheimer is a brain imbalance that has an impact on millions of individuals worldwide, primarily the elderly. Early
disease diagnosis and staging are critical for effective treatment and patient care. This study provides a unique
approach to detecting and staging Alzheimer’s disease. The dataset includes the results of MRI images of various stages
of Alzheimer’s disease. CNN models are meant to extract appropriate characteristics from MRI scans automatically,
gathering local as well as international patterns associated with illness development. A brief inspection to be carried
out to suggest the correct Approach. CNN Models classifies the Alzheimer stages and its execution metrics like
final précised result, exactness and specified outcome are calculated. The outcomes of the research show that CNN
accurately identifies Alzheimer’s disease and staging its progression. When tested on unknown data, the models obtain
high accuracy and the CNN models exhibit robustness and ability for generalization.
Keywords: Alzheimer’s disease classification, CNN, MRI, disease diagnosis, staging.
Paper ID - 1134

A Survey For Population Evaluation Using Machine Learning Techniques

B.Yuvasri and Dr.K.Ramar
Analysing crowd behaviour is a new field of study. The main objectives of this article is to identify crowd behaviour
from the source of advanced Intelligent Video Surveillance which are captured at 24*7 time span and it will analysis
the next movement of the crowd.The knowledge for the possible normal actions is organised in the form of hierarchical
modules.The actions for the behaviour that are deviated from normal behaviour are analysis and identified as abnormal
behaviour. When such a suspicious abnormal is detected, the history of abnormal behaviour is stored in cloud
computing environment and alerts control room experts.Here, VideoSurveillance has become one of the most important
elements of the safety and security framework for both municipal councils and law enforcement agencies, as it enables
real-time situation assessment, monitoring, and action taking in addition to preventive surveillance.
Keywords: Video Surveillance system, Crowd Behaviour Anlaysis, Hierarchical modules.
Paper ID - 1139

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 145

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Market Basket Insights for NIFTY 50: Identifying Financial Winners and Losers with
Eclat and Apriori Algorithms in 2023-24
S.Magesh, Dr.L.Jabasheela, T Sanjayaakash, M Rupesh Kumar and K Sanjay Balaji
This research explores the use of Market Basket Analysis (MBA) employing the Eclat and Apriori algorithms to
analyze stock market trends within the NIFTY 50 index for the financial year 2023-24. The main goal is to identify
the leading daily gainers and losers based on percentage fluctuations in stock prices while uncovering stock combinations
that frequently demonstrate correlated movements as gainers or losers. The analysis provided significant insights into
stock interdependencies, revealing that certain stocks tend to rise or fall together, influenced by factors like market
sentiment and sector performance. The Eclat algorithm identified several high-support stock combinations, while
the Apriori algorithm generated strong association rules characterized by notable confidence and lift metrics. These
findings offer valuable guidance for traders in developing effective investment strategies, highlighting the importance
of considering stock relationships alongside individual performance. Overall, the results underscore the usefulness of
MBA techniques in enhancing traders’ understanding of market dynamics, particularly regarding gainers and losers,
thus addressing a gap in traditional methodologies that primarily focus on historical data or single-stock analyses.
Future improvements could involve integrating additional data sources, real-time analytics, and advanced machine
learning techniques to further enhance predictive capabilities and broaden the research’s applicability across various
financial contexts. By tackling these areas, the study aims to contribute to more strategic portfolio management and
informed trading decisions in the ever-evolving stock market landscape.
Keywords: Market Basket Analysis, Eclat Algorithm, Apriori Algorithm, NIFTY 50 Index, Stock Gainers and Losers,
Stock Interdependencies, Investment Strategies.

Paper ID - 1141

Puzzle Progression Game Using Reinforcement Learning

Abhigyan Ghoshal, Mohammad Armaan Ali and Dr.Kumaran K
This paper presents a novel approach to the design of puzzle progression games by integrating reinforcement learning
(RL), particularly using the Q-learning algorithm, to dynamically adjust puzzle difficulty and enhance player
experience. Traditional puzzle games rely on manually crafted levels with static difficulty curves, often resulting in a
one-size-fits-all approach that may not cater to the varied skill levels of players. In contrast, our method leverages
the adaptability of RL, allowing the game to adjust in real-time based on the player’s performance, offering a
personalized, evolving challenge. The Q-learning agent is trained through trial and error, progressively learning the
optimal strategies required to solve puzzles of increasing complexity. Without needing a predefined model of the
environment, the agent explores various game states, receives feedback in the form of rewards and penalties, and
refines its decision-making process to solve puzzles efficiently. This dynamic learning capability not only enables the
agent to tackle complex puzzles but also allows for greater scalability in game design. New puzzles can be added
seamlessly, with the agent adapting its strategies without manual intervention, ensuring continued player
engagement and challenge. The framework is designed to enhance player immersion by providing tailored puzzle
difficulty, where the game’s challenge scales with the player’s skill, reducing frustration or boredom. In addition to
improving player retention, this adaptive system fosters a sense of accomplishment as players overcome increasingly
difficult obstacles. Testing has shown that RL-based agents outperform traditional rule-based systems in terms of
adaptability, efficiency, and scalability. The application of RL also opens new possibilities for game designers,
allowing them to create more interactive and responsive puzzle environments that respond to players in real-time.
This study demonstrates the potential of reinforcement learning in transforming traditional game design paradigms,
where static, pre-designed levels are replaced by dynamic, data-driven experiences that evolve with the player.
Future work can explore hybrid models integrating deep learning with RL to further enhance the agent’s ability to
solve complex puzzles, as well as introduce multi-agent environments where cooperative or competitive gameplay
could further elevate the puzzle-solving experience.
Keywords: Reinforcement learning (RL), q-learning, Dynamic difficulty adjustment, player experience.

Paper ID - 1143

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 146

Author Index

.Muthuram A, 2 AMOL L. Mangrulkar, 77, 78

Anandaperumal E, 111
A V. Allin geo, 76 Anandaraj B, 75
A. Anthonisan, 105 Ananthajothi K, 13
A. Arokiaraj Jovith, 40, 54 Ananthi S N, 7
A. Karunakaran, 55 Ananthi.S.N, 17
A. M.Sermakan, 81 Anees Fathima M, 6
A. Mohamed anas, 35 Angayarkanni Veeraputhiran, 16
A. Prabha, 53 Anirudh AVS, 134
A. Senthilselvi, 128 Anirutth SA, 105
A. Sevuga Pandian, 77 Anish T.P., 138
A. Sindhuja, 66 Anita M, 2
A.Athiraja, 136 Anitha G, 52
A.G. Ganesh Ram, 79 Anitha R, 143
A.Jaisuriya, 99 Anjali Kulkarni, 81
A.Leela Krishna. S.Lokesh, 81 Anjana Jyothi Banu, 5
A.M Sermakani, 26, 96 Annie Silviya S H, 142
A.Pandiaraj, 16, 120 Anousouya Devi M, 95
A.Prabha, 11 Ansu M George, 29
A.Prathiba, 5 Anto Micheal Infant, 130
A.S.S.Murugan, 50 Anup Shekhar Chamoli, 139
A.Sameeha and Sharmila Devi R, 132 Anusha S, 135
A.Senthil Kumar, 93 Aparna P, 56
A.Senthil Selvi, 129 Ardly Melba Reena .B, 57
A.Senthilselvi, 20 Arjita Jain, 63, 64
Aarthi Suresh, 49, 67 Arthy .G., 117
Aarthy.S.T, 45 Arul Prasath A, 71
Aayushi Iyengar, 61 Arulmary A, 74
Abhigyan Ghoshal, 146 Arumai Shiney.S, 7, 20
Abhinand TV, 129 Arun Karthik Anand Kumar, 102
Abhiram Patel U, 99 Arunachalam.M, 6
Abhishek M B, 111 Arvind Nain, 139
Abiram R, 3 Arwind Ragaw S.K, 112
Abirami A, 124 Ashin Murugan, 29
Abirami M, 92 Ashok P, 21
Abirami.J, 14 Ashok S, 80
Adaikkammai.A, 20 Ashokkumar.N, 74
Adeline Joanna V, 119 Aswathy M P, 138
Aditya Darapureddy, 142 Aswin Kumar K, 28
Aditya S, 41 Avinaash Venkat B, 28
Afshan Fatima, 90 Ayshwarya R, 68
Ahamed Ali S, 124 Ayyappan S and R. Ponnusamy, 137
Ajith Raj N, 28
Akshaya A, 138 B. Lavanya, 110
Alex Joseph K, 80 B. Lingeswaran, 62
Alister Francis Fernandez, 31 B. Manimaran, 73
Ambiga C, 48 B. Naveen, 24
Ameya Patil, 81 B. Pavan Kumar, 70
Amirthasaravanan Arivunambi, 111 B. Prasad, 54
Amirthavarshini K B, 16 B. Sarvesan, 70
Amit Kumar Gupta, 98 B. Vijaya Ramnath, 109

147
 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

B. Vinoth, 79 Dakka.Obulesu, 50
B. Yamini, 9 Debesh Biswas, 104
B.Sundarambal, 132 Deepa V, 23
B.Vasumathi, 76 Deepak T, 47
B.Yamini, 9, 91 Deepan. P, 14
B.Yuvasri, 145 Deepika S, 87
Bala Subramanian C, 31, 102, 135 Denis Amirtharaj, 99
Balaji.A, 117 Denish Manova M, 97, 112
Balakrishnan, 125 Devesh Chand, 139
Balakrishnan S, 21, 22, 24 Devesh Kumar Bandla, 46
Balamanikandan.A, 74 Devi Arumugam, 111
Balasubramanian M, 145 Dhakshin Vikash V, 28
Balika J Chelliah, 20 Dhananjay Mankar, 63
Ballela Avinash Reddy, 128 Dhanushkumar A, 91
Baranibabu S, 57 Dhanushprakash.V.C, 117
Bavanipriya V, 92 Dharaniya D, 123
Bavya, 90 Dharaniya R, 125
Betsey Neela Raju, 14 Dharaniya.R, 124
Beulah N, 8 Dharanyadevi P, 95
Bhagya Sree S, 60 Dharshan P P, 10
Bharat Tidke, 39 Dharshini S, 4
Bharathi Kannamma. V, 66 Dharunkumar A, 91, 94
Bhavani R, 82 Dhiliphan Rajkumar Thambidurai, 23
Bhuvaneshwari Karthikeyan, 76, 77 Dhivya R, 2
Bhuvaneswari S, 125 Dhivya V, 44, 123
Boppudi Bhargav, 93 Dinakaran Karunakaran, 142
Boyapati Kumar, 93 Dinesh M G, 2, 138
Boyina Rajesh, 142 Dinesh Potnuru, 142
Brig (Dr) Rajiv Divekar, 64, 65 Dinesh R, 94
Brinda P, 52 Dinesh S, 21, 22, 24
Burri Deeleep Sanjay Reddy, 46 Dinesh Subramani, 5
Busetty Praneeth, 93 DineshKumar S, 141
Divyapriya C, 136
C, 125 Divyesh S, 86
C Amritha, 106 Dr .J.V.Anchitaalgammai, 134
C Muralidharan, 51 Dr C Venkataramanan, 74
C S Manigandaa, 72 Dr ChitraDevi D M.E, 144
C Srinivasan and E Lavanya, 41 Dr G Adiline Macriga, 83
C. Alamelu, 27 Dr Krithika. M, 49, 66
C. Dhanesh, 42 Dr Kumaran K, 102
C. Kanmani Pappa, 74 Dr M.Nalini, 135
C. Meenakshi, 79 Dr P Chitra, 86
C. Srinivasan, 34, 39, 45, 49, 85 Dr Padmaprabha C, 22
C. Viswanathan, 44 Dr Poomagal A, 22
Chaithra I V, 31 Dr Poornima A S, 22
Challapalli Manikantaa, 72 Dr R Lathamanju, 67
Chandrasekar.K.V, 19 Dr R. Monisha, 33, 46
Charan Deepesh Kristam, 128 Dr R.Monisha, 34
Chellu Mani Ratnam, 69 Dr S Arul Kumar, 67
Chenni Kumaran J, 82 Dr S.K Muthusundar, 133
Cherin Yacoob Wattacheril, 29 Dr Shilpa Shinde, 64, 65
Chetan Annamalai M, 59 Dr Subalya S, 47
Chettiyar Vani Vivekanand, 13 Dr Uma Maheswari G, 79
Chintamakula Mehereesh, 93 Dr V Arulkumar, 67
Chitra Sabapathy Ranganathan, 34, 40–42, 45, 53, 54 Dr. A. Deepa, 54
Chorko C, 138 Dr. A. Maria Christina Blessy, 23
Dr. Anand K, 84
D. David Neels Ponkumar, 42 Dr. Ananthajothi K, 84
D. Lekha and P. Valarmathie, 140 Dr. Antonidoss A, 133
D. Mangaiyarkarasi, 2 Dr. Anugragha.S.S, 32
D. Saranya, 110 Dr. Arjita Jain, 64, 65
D.Anish Chandra, 8 Dr. B, 46
D.Chithra, 26, 96 Dr. B. Venugopal, 66

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 148

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Dr. B.R. Sathishkumar, 107 Dr. S. Avinash, 32

Dr. Barkathulla A, 38 Dr. S. Karthikeyan, 44
Dr. Bhavesh M Patel, 100 Dr. S. Kolangiammal, 43
Dr. C. Kala, 61 Dr. S. Prabha, 45
Dr. C. Meenakshi, 36, 37 Dr. S. Prabhu, 46
Dr. C. Selvaraj, 61 Dr. S. Raja, 110
Dr. C. Velusamy, 33 Dr. S. Rajes Kannan, 54
Dr. D. Hemanand, 12 Dr. S. S. Suganya, 110
Dr. Deva Hema D, 119 Dr. S. Sankar, 54
Dr. E. Bhuvaneswari, 121 Dr. S. Sathyasundari, 33
Dr. E. Kodhai, 121 Dr. S. Vimaladevi, 38
Dr. G. Kumar, 44 Dr. Saranya S, 103
Dr. G. R. Hemalakshmi, 29 Dr. Sasikala Dhamodaran, 110
Dr. Gnana Jeslin J, 79 Dr. Suresh Annamalai, 130
Dr. Harish. M, 46 Dr. T. Guhan, 110
Dr. I. Shanmugapriya, 32–34, 67 Dr. T. Rekha Kiran Kumar, 47
Dr. Inbamalar T M, 13 Dr. T. Senthil Kumar, 45
Dr. Indumathi. N, 46 Dr. Tamizharasi. K, 48
Dr. J. Anvar Shathik, 16, 120 Dr. V. Anjana Devi, 121
Dr. Jayant Brahmane, 64, 65 Dr. V. DhilipKumar, 27
Dr. K A Varun Kumar, 19 Dr. V. Diana Earshia, 23
Dr. K Vijayalakshm, 8 Dr. V. Kaliraj, 115
Dr. K. A. Niranjan Kumar, 40 Dr. V. Kannagi, 42, 43
Dr. K. Arulini, 33 Dr. V.R.Kanagavalli, 40
Dr. K. Danesh, 23 Dr. V.R.Vimal, 121
Dr. K. Durairaj, 27 Dr. Veto Dey, 34
Dr. Kaaliraj S, 131 Dr. Vinodkumar S, 84
Dr. Kiran Kakade, 64, 65 Dr. Yogita Saurav Gupta, 32
Dr. Krithika. M, 67 Dr.A.Mohan Babu, 112
Dr. L. Chitra, 35 Dr.Anuradha M, 17
Dr. L. Sujatha, 33 Dr.Athiraja Atheeswaran, 137
Dr. M. Jayakumar M, 2 Dr.ChitraDevi .D, 19
Dr. M. Lalithambigai, 110 Dr.D.Umanandhini Udhayakumar, 8
Dr. M. Meganathan, 42 Dr.G.Premalatha, 9
Dr. M. Thamizhselvi, 32 Dr.J.Sridhar, 70
Dr. M. Umamaheswari, 110 Dr.Juhi Juwairiyyah, 90
Dr. M.Santhanalakshmi, 44 Dr.K.Ramar, 145
Dr. MD Ashfaqul Hasan, 39, 53 Dr.Kumaran K, 146
Dr. Meenakshi Kaul, 53 Dr.L.JABASHEELA, 146
Dr. N. Jayanthi, 47 Dr.Lathamanju R, 69
Dr. N. Jayapriya, 34 Dr.M.Anuradha, 12
Dr. N. Saranya Devi, 32 Dr.M.Kathiravan, 115, 131
Dr. Nelson Kennedy Babu C, 54 Dr.N. Duraimurugan, 84
Dr. P A Manoharan, 120 Dr.N.Thilgavathi, 31
Dr. P L Kishan Kumar Reddy, 34, 38 Dr.Punitha A, 28
Dr. P. Epsiba, 38 Dr.R.Bhuvaneshwari, 131
Dr. P. K. Dhal, 85 Dr.R.Buvanesvari, 115
Dr. P. Ramesh, 61 Dr.R.Elankavi, 70
Dr. P. Selvarani, 34, 40 Dr.R.G.Kumar, 69
Dr. Parkavi K, 134 Dr.R.Tamilmaran, 47
Dr. Praveenkumar S, 54 Dr.Radhika, 112
Dr. Pravin Kumar Bhoyar, 65 Dr.S.Sivasakthi, 103
Dr. R. Aiyshwariya Devi, 85 Dr.T.S.Geetha, 14
Dr. R. Meenakshi, 53 Dr.T.Suresh Balakrishnan, 121
Dr. R. Meenambigai, 32 Dr.Vijay R, 115
Dr. R. Radhika, 54 Duraimurugan N, 13
Dr. R. Thenmozhi, 38
Dr. R. Vijayabhanu, 110 E. Arun, 62
Dr. Raja B, 82 E. N. Ganesh, 44
Dr. Raja Suguna M, 79 E. R. Vadivel, 33
Dr. Ramakrishnan Raman, 53 E. Sivanantham, 45
Dr. RM. Sivagama Sundari, 46 E.Elakkiyachelvan, 89
Dr. S Saravanan, 61 E.Sathesh Abraham Leo, 100

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 149

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Eswar Prasad. G, 14 Ignatious K Pious, 80

EZHILARASI A, 60 Ilakkiaselvan Dhandapani, 89
Ezhilvendan M, 117, 120 Ilamathi K B, 87
Ezhumalai M, 114 Indravahini B S, 21
Ishaan Kanade, 104
G Geethamahalakshmi, 72 Iyswariya A, 86
G Manisha, 17
G Shanmugasundar, 97 J Kirthan, 97
G. Abay Ragav, 58 J. Godly Gini, 29
G. Ashok Kumar, 136 J. Sujithra, 37
G. Balaji, 2 J.Matcha Rani, 134
G. Belshia Jebamalar, 7 JAGADEESHWARAN S, 131
G. Bhuvaneswari, 38 Jai Udhaya S, 25
G. Manikandan, 38 Jain Bai B, 101, 108
G. Mariammal, 2 Janane S and Revathy S, 68
G. S. Gayathri, 43 Janani P, 6
G. Sujatha, 110 Jangili Supriya, 8
G. Sundar, 78 Jashwanth Sathish, 94, 112
G.K.Bhuvanesh, 5 Jaya Kumar Sa, 11
G.Manisha, 7 Jaya siva subramaniam.N, 81
G.Sundar, 77 Jayachandiran Udayakumar, 4
Ganesh Perim, 13 Jayadev Nukala, 129
Ganeshan R, 11 Jayadharshini P, 5, 6, 10
Gaurav Singh, 11 Jayakumar T, 143
Gautam Kumar G, 145 Jayant Brahmane, 81
Gautham Anand, 1 Jayanthi.M, 20
Gayathri G, 136 Jayapriya M, 98
Gayathri S, 117, 120 Jeeva K, 123
Geetha Jenifel M, 8 Jeevanandam L, 91, 97
Girija P, 75 Jemima Havila Catherine A, 23
Glory Sangeetha. R, 79 Jeo Godson Samuel J, 145
Gogul Ram S and Dr.B.Yamini, 10 Jeyanthini E N, 98
Gollapally Abhiram Sai, 129
Jino Paulraj, 9
Gomathy G, 41
Joanna Samuel, 119
Gopi Yamini, 70
John Benito Jesudasan Peter, 52
Gopika M Nair, 19
John T Mesia Dhas, 75
Gopika Sandaka and Raziya Shaik, 107
Joshna B S, 4
Gopinathan S, 97, 98, 106
Justindhas Y, 124, 125
Gorthi Balaji, 140
Gowri M, 1
K Dinakaran, 62
Gunasundhari N, 73
K Kaviya Sanjay, 97
Guravana Ashok Kumar, 142
K Nattar Kannan, 100
Gurumoorthi Gurulakshmanan, 39
K Neela, 1
H.Keerthivasan, 111 K SANJAY BALAJI, 146
Hamsasini B, 21 K Sreehari, 97
Haresh M, 26 K. Devabalaji, 35
Hariharan B, 25 K. Dhivya, 111
Hariharan M, 114 K. Dinakaran, 47, 58
Hariharan M V, 96 K. Kesava, 70
Harini.P, 14 K. Manikandaprabhu, 55
Hariprasad V, 31 K. Muhammad Ashiq, 69
Haripreetha S, 10 K. Revathik, 67
Harisankar G, 29 K. Sangeethalakshmi, 44
Harish R, 13 K. Shiva Kumar, 50
Harish V, 106 K. Suganthavalli, 37
Harsh Khatter, 98 K. Susmitha, 70
Harsh Panchal, 109 K.K. Shandhosh Shree, 108
Harshini.M, 6 K.Makanyadevi, 51
Harshitha Seetharaman, 25 K.P.Porkodi, 74
Hayagreevan V, 26 K.Saraswathi, 50
Hemanand D, 11 Kaavya R, 111
Kabaleeswaran S, 34, 41, 42, 52, 53
I Vasudevan, 99 Kailash A, 112

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 150

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Kalaiselvi P, 41 Loganayagi S, 121

Kalaivani E, 137 Logeshwari S, 136
Kalaivani K, 43 Lokesh S, 22
Kaliraj V, 123–125 Lokith Sharan R, 116
Kalpana S, 95
Kamalakannan R, 16 M Bindu Sudeeksha, 72
Kamalakkannan Sivaraman, 118 M Jyothsna, 72
Kanagamalliga S, 95, 96 M Pranita, 19
Kanishka A, 18 M RUPESH KUMAR, 146
Kanishka M, 145 M Vadivel, 41
Kannan Shanmugam, 85 M. Kalyan Ram, 113
Kappala Vikash, 113 M. Kavin Kumar, 107
Karthik Balaji B M, 37, 92 M. Kavitha, 108
Karthik J, 4 M. Krishna Dinesh, 70
Karthikeyan M, 1 M. Mariyammal, 137
Karthikeyan M C, 56 M. Midun, 62
Karthikeyan N, 127, 128 M. Muthulekshmi, 42, 43
Karthikeyan N and Karthikeyan N, 87 M. Nalini, 38, 45
Karthikeyan S, 116 M. Rajmohan, 45
Karthikeyan.J, 19 M. Sai Venkata Adithya, 2
Karupannan P, 126–128 M. Sathish, 85
Kasturi Naik, 63 M. Shafiya Banu, 85
Kaushik Narayanan.C.VR, 81 M. Tamilselvam, 42
Kavin Aarya A.R, 56 M. Vadivel, 52, 53
Kavitha D, 123 M.Harin Sowmiya, 116
Kavitha M, 90 M.Jaiganesh, 33
Kavitha R, 114 M.K.Vidhyalakshmi.Krishnamoorthy R, 76
Kavitha.T, 74 M.Kavitha, 89
Kaviya M, 43 M.Krishnamurthy, 73
Keerthana.R, 132 M.P. Kumar, 69
Keerthivasan H, 95 M.Priscilla, 112
Keerthivasan K, 95 M.Shanmuganathan, 51
Keren Persis p, 103 M.V. Hariharan, 95
Kessavan M, 80 M.Vijayakarthick, 79
Kiran Kakade, 63, 81 Mabel Rose R A, 75
Kiran Kakade and Dhananjay Mankar, 64 Maddu Rakesh, 9
Kiruthiga S, 18 Madhu Arora, 139
Kishor patil, 77 Madhubala S, 43
Kishore G, 69 Magadevi Nirmalkumar, 141
Konijeti Sai Kalyan, 9 Magesh Kumar S, 23
Kotteeswaran R, 76, 78 Mahalakshmi G, 144
Krishnan R, 15 Mahalakshmi S, 22
Krishnavel K, 69 Mahesh Vaijainthymala Krishnamoorthy, 124
Krithika S, 87 Maheshwaran T, 1, 2
Kumar P, 12, 26, 27, 87, 88, 101–103, 126–128, 135 Malarvizhi S, 45
Kumaran K, 94, 104 Malathi, 117
Kumaran K and Vidhyalakshmi M, 3 Mangal Sain, 98
Mangaleswaran M, 58
L Lakshmi Prasanna Kumar, 136 Manisha.G, 7
L. A. Anto Gracious, 11 Manju Bhargavi Pilli, 115
L. Giridharan, 130 Manjunathan N, 120
L. NaveenNarayanan, 62 Masrath Parveen, 90
L. Ramachandran, 108 Masthan Gowtham Kommuru, 13
Lakshmanaprakash S, 16 Mathan Kumar Mounagurusamym, 120
Lakshmi Priya J, 51 Mathankumar Mounagurusamy, 123
Lakshmipriya C, 12 Mayank Pant, 139
Lalitha Krishnasamy, 10 Meenakshi B and Swathiha R R, 114
Leena Jenefa, 99 Megala J, 136
Lekha D, 117, 120 Megiba Jasmine R, 138
Lieo Ambrouse E, 56 Menaga R, 144
Lijetha C Jaffrin, 1 Mithul Dev D, 135
Lithish M, 112 Mithun Dineshkumar, 88
Loganathan C, 59 Mithun Kumar S.R, 57

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 151

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Mohamed Eghiya Kamal, 82 Naga Kanaka Bhavani Chinni, 107

Mohamed Safresh H, 105 Nagaraj P, 23
Mohamed Suhail Y, 41 Nagarajan.P, 74
Mohammad Armaan Ali, 146 Nalini M, 1, 75, 80
Mohammed Afeef Abdulla, 58 Nandhakumar K P, 17
Mohammed Ali Shaik, 90 Nandithaa I N, 119
Mohan A, 82 Natvar Sardarbhai Patel, 100
Mohana Sundari V, 75 NAVAJEEVAN M, 30
Monish Kiran S, 114 Navaneetha Krishnan R, 41
Mothiram Rajasekaran, 38, 44, 54, 71, 72, 85 Naveen G, 16, 120
Mounika J, 143 Naveen Gandhi Anbullam, 123
Mr. JONAH S, 18 Naveen Raj. A, 14
Mr. P. Boopathi, 110 Naveenkumar P, 141
Mr. P. Senthil, 62 Navjot Singh, 104
Mr. S. Jegadeesan, 116 Nawin Viswajith B, 41
Mr.A.Irumporai, 115 Nikhat Fatima, 90
Mr.A.Irumporai and Mr.Vengatramana R, 131 Niranjan S, 96
Mr.M.Balasubramanian, 14 Nirmala Baby and B. Anitha Vijayalakshmi, 93
Mr.S.Amarnaath, 122 Nirmaladevi G, 21
Mr.S.Murali, 134 Niroshini B, 21
Mr.T Koteswara Rao, 49 Nithiyasree P, 106
Mr.Vengatramana R, 115 Nithya M, 136
Mrs Arumai shiney, 18 Nithya Shree S, 39
Mrs. Maheswari A, 82 Nithyanandhan R, 1, 138
Mrs.D.Thamizhselvi, 28 Nithyanjali Maruboina, 119
Mrs.E. Lavanya, 79 Nitin Darapareddy, 8
Mrs.S.Kavitha, 134 Nivethitha. M, 14
Mrs.Thamizhselvi D, 28 Nizmi shaik, 57, 60
Ms R DHIVYABHARATHI, 30 Nukala Rohith, 9
Ms. Harini A, 18 Nuti Dhruv, 27
Ms. Kavitha Arunachalam, 130
Ms. Keerthana S, 18 P K Desigan, 102
Ms. Swetha S, 130 P Kiranteja, 102
Ms. Swetha T R, 130 P Tharcis, 93
Ms.Dhivya Bharathi, 30 P Vinayagam, 95
Ms.G.Deepana, 122 P. Dharanyadevi, 111
Ms.Janani S, 40 P. Kabilamani, 73, 74
Ms.Madura S, 40 P. Karthikeyani, 42
Ms.Ramya M, 131 P. Krishnamoorthy, 108
Mugilan N V, 62 P. Kumar, 13
Muhemin Sheriff M, 125 P. Sarathkumar, 71
Muqaddam Aaqil Sheriff, 101 P. Senthil, 96
Muralitharan G, 125 P. Sivalakshmi, 52
Murugan A, 15 P. Thenmozhi, 85
Muthamilselvan S, 4 P. Valarmathie, 55
Muthukumar G, 59 P.Ananadavalli, 89
Muthulakshmi.P, 132 P.Gandhimathi, 93
Muthyala Prem Kumar, 140 P.J.Beslin Pajila, 1, 138
Myla Greeshmanth Reddy, 46 P.Karunakaran, 6
P.N.V. Abhiram, 29
N Aparna, 76 P.Nagarajan, 73
N Mohankumar, 71 P.P.Narenthira Sai Raam, 24
N Pallavi, 70 P.Patchaiammal, 77, 78
N Shivaanivarsha, 116 P.Sindhu, 72
N. Babu, 71 P.Sreejith, 81
N. Ramshankar, 120 P.Veeramuneeswaran, 35
N. Srinivasan, 89, 90 Padma Prabha C, 21, 24
N. V. S. Natteshan, 51 Padmanaban R, 109
N.Ashokkumar, 73 Palaniraj Rajidurai Parvathy, 52
N.G. Saikiran, 71 Pandiaraj A, 16, 123
N.K.Senthil Kumar, 50 Pankaj Natu, 64
N.Ramshankar, 16 Parimaladevi. L, 48
NACHIAPPAN C, 30 Parvathraj K M M, 137

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 152

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Pathmanaban J, 3, 87 R.Shreevarshini, 134

Pavita S, 116 R.Tamizh Kuzhali, 133
Peer Arif P, 82 R.Thiagarajan, 76–78
Peer Mohamed Appa M.A.Y, 117 Rachaputi Yeswanth Vardhan, 128
Periasamy J K, 73 Radhika Rajaram, 97, 98, 106
Perinban Prabu, 30 Rahul Ramamoorthy, 138
Pooja Bhagwat, 77 Raj Kumar K, 25
Pooja E, 117 Raja K, 111
Poomagal A, 21, 24 Rajalakshmi A, 80
Poonguzhali C, 43 Rajalakshmi K, 116
Poonguzhali.C, 20 Rajarajan S J, 34, 143
Poornima A.S, 21, 24 Rajasekar A, 94, 97
Prabahar Godwin James T, 3 Rajasekaran.A, 50
Prabha M, 119 Rajavinu.N, 20
Prabhu A E, 137 Rajendran. V, 36
Prabhu K, 124 Rajeshkumar Sampathrajan, 39, 52
Prabhu.V, 80 Rakesh S P, 137
Pradeesha C, 144 Rakoth Kandan Sambandam, 10
Pragadeesh N, 31 Ramana Ganthan S, 137
Prajeeth Kumar, 106 Ramshankar N, 16, 123
Pramod Pandey, 72 Ramya P, 106
Pranav J, 4 Ramya. R, 53
Pranav S A, 25 Ranjith Kumar, 106
Prasanth J, 83 Raveendra N Amarnath, 43
Prashanth K, 83 Ravivarman R, 11
Praveen. E, 68 Reddi Khasim Shaik, 78
Pravin Bhoyar, 81 Reddy Balaji Elumalai, 106
Pravin Kulurkar, 76 Renuka Vidhyashankar, 21, 24
Pravinprabu T, 143 Reshena R, 144
Preetha Lakshmi, 4 Revathi V, 12
Preeti Tyagi, 139 Rithanya.M, 5
Prem Kumar R, 80, 143 Robert Emmanuel S, 11
Priyadarshini A, 6 Robinbritto V, 111
Priyadharshini M, 144 Ruchi Rani Garg, 98
Priyanka K, 103 Rushikesh Dhornala, 115
Prof. Anjali M. Kulkarni, 65
Prof. Subhash Yadav, 64, 65 S Hemalatha, 106
S Murugan, 71
R Creesy, 71 S Niranjan, 95
R M. Sanjay Kumar, 109 S P Vimal, 42, 52
R Poornima Lakshmi, 137 S Prabha, 41
R Preethi, 97 S Soumya, 70
R Sankar, 52 S. Ahamed Ali, 125
R. Aarthi, 132 S. Alagu Thangam, 121
R. Abirami, 11 S. Anantha Sivaprakasam, 89, 90
R. Banu Prakash, 27 S. Anbarasan, 35
R. Bhairavi, 74 S. Bharathi, 141
R. G. Santhi, 69 S. Gananathji Naveen Kishore, 109
R. Kamalakannan, 39, 85 S. Gunanandhini, 7
R. Kennady, 11 S. Hashini, 16
R. Kingsy Grace, 4 S. Hemalatha, 42
R. Mahesh Kumar, 110 S. Janani, 141
R. Meenakshi, 85 S. Juliafaith, 26, 96
R. Priyanka, 38 S. Kalaichelvi, 55
R. Rajaganapathy, 108 S. Lekha, 141
R. Sandhya, 71 S. Meyyappan, 79
R. Sudharsan, 130 S. Murugan, 32, 33, 44–46, 49, 67, 72
R.Ambika and S.Thanusha, 116 S. Poorna Vignesh, 107
R.Devprasad, 26 S. Saravana Kumar, 40, 55
R.J.Kavitha, 89 S. Senthilkumar, 108
R.Krishnamoorthy, 76–78 S. Sheeba Rachel, 92
R.M.Dilip Charaan, 99 S. Sridevi, 2
R.M.Suchindhar, 88, 127 S. Srinivasan, 52–55

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 153

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

S. Sujatha, 38, 40, 85 Sathya V, 75, 105

S. Uma Maheswari, 33 Sathyabama R, 39
S. Venkateswaralu, 2 Sathyanarayanan P, 112
S.Ashok Kumar, 99 Satish Srinivas S, 124, 125
S.Balaji, 51 Satya Jagu, 115
S.G. Paveen, 107 Satyam Prakash Srivastava, 139
S.Gunanandhini, 17 Saurabh Sharma, 139
S.Kavitha, 51 Seetharaman. M, 68
S.MAGESH, 146 Sekar G, 75
S.Manju, 132 Selvakumaran.S, 20
S.N.Ananthi, 7 Senthil P, 44
S.Nithyapriya, 133 Senthil Pandi S, 31, 87, 88, 101–103, 108, 111,
S.Padmakala, 29 126–129, 135
S.Prabhavathy, 133 Senthil Pandi. S, 12, 27
S.Santhiya, 5, 6 Senthilselvi A, 111
S.savitha, 133 Sermakani A M, 85
S.Senthil Pandi, 20 SEVANTHI P, 60
S.T. Preethi, 121 Shanmuga Priya AR, 119
S.Yuvalatha, 133 Shanmuga Sundar, 91
Sai Amrutha Vugiri, 142 Shanmuga Vadivu Pandy S, 91, 97
Sai Pavan Rangu S, 99 Shanthalakshmi Revathy J, 144
Sai Santhiya G, 116 Shanu Khare, 104
Sai Sharan P, 86 Sharlatha R, 73
Saiganesh V, 92 Sharmishtha S.K, 10
Sakthi Arunachalam S, 3 Sharon Chrysolite C, 43
Sakthisaravanan B, 71 Shasidhar Avula, 70
Sakthivel Janarthanan, 105 Shib Kumar Saraf, 113
Sakthivel M, 1 Shivalingappa P and Nagaraja G S, 118
Salman Latheef T A, 88, 126 Shobana D, 50, 51
Sameer Sharma, 78 Shobana Lakshmi R, 108
Sampathi Sai Vamsi, 69 Shraddha Walekar Ghaisas, 77
Samsthana K L, 98 Shravya Munugala, 109
Samuel Devanaboina, 115 Shreyank Saksena, 104, 134
Sandeep Bhanot, 63, 64 Shri Vidhya K, 18
Sangeetha, 3 Shruthik Kalyana Venkatesh, 10
Sangeetha J, 123 Shyamala Kumari, 83
Sanjay Nagarajan, 30 Shyamaladevi M., 8
Sanjay S, 86 Sibisurya S, 3
Sanjeeviram C.M, 83 Sinthia.P, 117
Santhiya S, 10 Sirajbhai A Nagalpara, 100
Santosh M, 68 Siva Subramanian R, 75, 80, 135
Saranya G, 3, 94 Sivagar Mr, 98
Saranya T V, 124 Sivakamy N, 104
Saranya TV, 125 Sivakumar S, 1
Saranya V, 129 Sivanesan T M, 72
Saraswathi P, 119, 132 Sivasakthi Thanigainathan, 95
Sarath Kumar. C, 49 SobanaManikandan, 132
Sarath Kumar.D, 118 Solaimurugan Vellaipandiyan, 113
Sarath Rajan Senthilkuma, 102 Sowmya R, 49
Saravana Kumar, 90 Sree Nidhi S, 73
Saravanan Meghana, 71 Sri Shakthi K and Priyatharshini, 83
Saravanan.A, 118 Sribalaji.E, 19
Saravanan.S, 35 Sridevi Sridhar, 15
Sarghi Kaur Gahra, 20 Srinadh Unnava, 50
Sariga B, 6 Srinath Rajagopalan, 51
Sarvesh Susindran, 30 Srinivasan A, 114
Sasi V, 48 Srinivasan K S, 103
Sasirekha.K and Joe Prathap P.M, 84 SRINIVASAN RAMA KRISHNAN, 131
Sassirekha S M, 1, 75 Sripriya.T, 117
SATHISH KANNA L, 30 Su Suganthi, 97
Sathish Kumar Kannaiah, 101, 102 Subedha Varatharaj, 106
Sathish Kumar.M, 118 Subhadharshini V, 119
Sathya Priya S, 25 Subhash Yadav, 81

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 154

 Proceedings of the 2024 International Conference on Smart Technologies for Sustainable Development Goals (ICSTSDG)
AUTHOR INDEX S.A. Engineering College, Chennai, T.N., 6th - 8th November 2024.

Sudha K, 117, 120 V.Agniselvi, 134

Sudharshan.S, 5 V.Balaji Vijayan, 76
Sudheksha.K, 5 V.Balaji vijayan, 78
Suganeshwaran M, 94 V.Balamurugan, 89
Suganthi P, 28 V.D.Ambeth Kumar, 72
Suhani Goel, 109 V.Harynee, 5
Sujithra J, 39 V.Kaliraj, 124, 125
Sumithra M, 23 V.Nivakumar, 135
Sunantha Sri B, 49 V.Samuthira Pandi, 50, 51
Sundari S, 23 V.Saravana Kumar, 89, 90
Surya K, 86 V.Sharmila Bhargavi, 135
Susendhiran E, 80 Vaddi Tejaswini, 70
Sushma Patil, 63 Vaijayanthi.S, 31
Suyash Agrawal, 104 Valarmathie P, 56
Swaroop Gannamani, 103 Valliappan PL, 86
Swetha. N, 14 Vankadara Sampath Kumar, 136
Syed Juniad, 129 Varsha S P, 88
Varsha V, 6
T Periyasamy, 11 Varshni S V, 123
T SANJAYAAKASH, 146 Varun C M, 80
T. Annalakshmi, 53 Vasanth B, 94
T. Daniya, 142 Vasim Ahmad, 139
T. Geetha, 54 Veeramalai S, 138
T. Muthamizhan, 24 Veeramanickam M.R.M and Muthukumarasamy S, 104
T. Veena, 26, 96 Venkat S, 80
T.A. Rajasekaran, 36 Venkata Madhu Bindu Nalluri, 137
T.Anand, 79 Venkatesh Prabhu Balakrishnan, 12, 27
T.Arun, 133
Venkatesh Prasath J, 69
T.Kavitha, 73
Vertika Singh, 61
T.P. Anish, 135
Vibusha P, 86
T.Thamizhmani, 89
Vidhya. N, 36
T.Thilagam, 7, 17
Vignesh H, 17
Tamizharasi.K, 35
VIGNESH KUMAR A RAJA PRIYA D, 131
Tapas bapu B R, 43
Vignesh Kumar M, 93
Tata Seetha Rama Sai Vamshi Krishna, 99
Vignesh P, 17
Thangapalani L, 56
Vigneshwari M, 87
Thiagarajan R, 79
Vigneswari J, 91
Thilagam.T, 6, 7
Vijaya Prabhu R, 120
Thilagavathi Narayanamoorthy, 15
Vijayalakshmi. P, 36, 68
Uday Kumar Rajanala, 107 Vijayaraj A, 12, 27
Udhayakumar S, 99 Vikram Adithya Anand, 67
Uma Mageswari, 94 Vinayagam P, 96
Vincent Gnanaraj T, 82
V G Sivakumar, 38 Vinnie Sharma, 16
V Praveena, 72 Vinoth Kumar.Ls, 118
V Vijaya Baskar, 43 Vishnu Sriram T, 145
V. Amirthalingam, 44 Vivekanandan G, 87
V. Maheswara Reddy, 71 Vivekanandan M, 3
V. Nandagopal, 55 Vupulluri Sudha Rani, 90
V. Rattan Kumar, 35
V. Ravi Raj, 109 Y.Nagendar, 136, 137
V. Saravanan, 62 Yamini, 46
V. T. Vithya, 55 Yashwanth J, 37

979-8-3315-1628-4/24/$31.00 ©2024 IEEE 155

 S.A. ENGINEERING COLLEGE
(An Autonomous Institution, Affiliated to Anna University)
Accredited by NBA, NAAC with ‘A’ Grade & ISO 9001:2015 Certified Institution
POONAMALLEE – AVADI MAIN ROAD
THIRUVERKADU, CHENNAI – 600 077

www.saec.ac.in/ieeeicstsdg

ISBN No: 979-8-3315-1628-4/24/$31.00 ©2024 IEEE