SAVITRIBAI PHULE PUNE UNIVERSITY

A PRELIMINARY PROJECT REPORT ON

“Real Time Threat Detection And Analysis

With Deep Learning”

SUBMITTED TOWARDS THE

PARTIAL FULFILLMENT OF THE REQUIREMENTS OF

BACHELOR OF ENGINEERING (Computer

Engineering) BY

Student Name: Abhijit Santosh Thange Exam No173

Student Name: Chaitanya Bajirao Nikam Exam No:174

Under The Guidance

of Prof. Roshni

Narkhede

PCET’S & NMVPM’S

NUTAN MAHARASHTRA INSTT. OF ENGG. & TECH.
Pune
 PCET’S & NMVPM’S
NUTAN MAHARASHTRA INSTT. OF ENGG. & TECH.
Pune
CERTIFICATE

This is to certify that the Project Entitled

“Real Time Threat Detection And Analysis

With Deep Learning”
Submitted by
Student Name: Abhijit Santosh Thange Exam No:173

Student Name: Chaitanya Bajirao Nikam Exam No:174

is a bonafide work carried out by Students under the supervision of Prof.Tushar

Waykole and it is submitted towards the partial fulfillment of the requirement of
Bachelor of Engineering (Computer Engineering) Project.

Prof. Tushar Waykole (Prof. Dr. Prasad Dhore)

Internal Guide H.O.D
Dept. of Computer Engg. Dept. of Computer Engg.

(Dr.Vilas Deotare)
Principal,
PCET’S & NMVPM’S
NUTAN MAHARASHTRA INSTT. OF ENGG. & TECH. Pune
 ABSTRACT

Real-time threat detection is crucial for protecting digital systems against cyber-attacks.
Traditional security tools often miss new or evolving threats, so this study explores using
deep learning (DL) to enhance threat detection and analysis. By applying deep learning
models, such as convolutional neural networks (CNNs) and long short-term memory (LSTM)
networks, our approach can quickly and accurately detect suspicious activities from network
data. This reduces false positives and adapts well to new threats. We also discuss challenges,
like data privacy and high processing costs, and suggest solutions to improve the practicality
of DL in cybersecurity. The results show that deep learning can significantly strengthen real-time
security defenses.

NMIET, Department of Computer Engineering 2024

 Acknowledgments

It gives us “Real Time Threat Detection And Analysis With Deep Learning” great
pleasure in presenting the preliminary project report on .

I would like to take this opportunity to thank my internal guide Prof. Tushar
Waykole for giving me all the help and guidance I needed. I am really grateful to
them for their kind support. Their valuable suggestions were very helpful.

I am also grateful to Prof. Dr. Prasad Dhore, Head of Computer Engineering Department,
PCET’S & NMVPM’S NUTAN MAHARASHTRA INSTT. OF ENGG. & TECH. Pune for his
indispensable support, suggestions.

Student Name: Abhijit Santosh Th`ange

Student Name: Chaitanya Bajirao Nikam

NMIET, Department of Computer Engineering 2024

 INDEX

1 Introduction 1
1.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
1.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 Problem Defination . . . . . . . . . . . . . . . . . . . . . . . . . . 3

2 Literature Survey 4
2.1 Study Of Research Paper . . . . . . . . . . . . . . . . . . . . . . . 5

3 Software Requirements Specification 10

3.1 Introduction..............................................................................................11
3.1.1 Project Scope...............................................................................12
3.1.2 User Classes and Characteristics.................................................12
3.1.3 Assumptions and Dependencies..................................................12
3.2 Functional Requirements..........................................................................14
3.2.1 System Feature 1 (Functional Requirements).............................14
3.3 External Interface Requirements (If Any)................................................14
3.3.1 User Interface..............................................................................14
3.3.2 Software Interfaces......................................................................15
3.4 NON FUNCTIONAL REQUIREMENT.................................................15
3.4.1 Performance Requirements..........................................................15
3.4.2 Safety Requirement.....................................................................15
3.4.3 Security Requirements.................................................................15
3.4.4 Software Quality Attributes.........................................................16
3.5 System Requirements...............................................................................17

3.5.1 Database Requirements..............................................................17

3.5.2 Software Requirements...............................................................17
3.6 Analysis Models: SDLC Model to be applied.........................................18
3.7 System Implementation Plan....................................................................20
4 System Design 21
4.1 system Architecture..................................................................................22
4.1.1 Data Flow Diagram.....................................................................23
4.2 UML DIAGRAMS...................................................................................24

5 Other Specifications 29
5.1 advantages................................................................................................30
5.2 application................................................................................................30
5.3 limitations.................................................................................................30

6 Conclusion and Future Scope 31

6.1 Conclusion................................................................................................32
6.2 Future Scope.............................................................................................32

7 References 33
List of Figures

4.1 System Architecture.................................................................................22

4.2 Data Flow(0) diagram..............................................................................23
4.3 Data Flow(1) diagram..............................................................................23
4.4 Data Flow(2) diagram..............................................................................24
4.5 Class Diagram diagram............................................................................25
4.6 Use case Diagram.....................................................................................26
4.7 Activity Diagram......................................................................................27
4.8 Sequence Diagram....................................................................................28
 CHAPTER 1

INTRODUCTION

1
 OVERVIEW
Human pose estimation is a challenging problem in the discipline of computer vision. It deals with
localization of human joints in an image or video to form a skeletal representation. To automatically
detect a person’s pose in an image is a difficult task as it depends on a number of aspects such as
scale and resolution of the image, illumination variation, background clutter, clothing variations,
surroundings, and interaction of humans with the surroundings . An application of pose estimation
which has attracted many researchers in this field is exercise and fitness. One form of exercise with
intricate postures is yoga which is an age-old exercise.

ecause of its many spiritual, physical and mental benefits. The problem with yoga however is that, just
like any other exercise, it is of utmost importance to practice it correctly as any incorrect posture during
a yoga session can be unproductive and possibly detrimental. This leads to the necessity of having an
instructor to supervise the session and correct the individual’s posture. Since not all users have access or
resources to an instructor, an artificial intelligence based application might be used to identify yoga
poses and provide personalized feedback to help individuals improve their form . This project focuses on
exploring the different approaches for yoga pose classification .

2|Page
 1.1 MOTIVATION

Self-Learning Assistant System needs to support the self-learners in receiving feedbacks for correct
experiences and exercises. It is very important that learning from the self-learning system should give the sa
me feeling and experience to that of learning from the professional instructors. Moreover, it should make the
self-learners more understandable and flexible. It should also attract self-learners in order to continue using
the system. The feedback function should give instructions to the self-learner, by recording the performance
and estimating how much the learner can follow the instructions from the instructor and which parts are
incorrect through similarity measurements. This will help the learners to know their weak parts and be able
to retry the wrong parts. That is the best way to let the self-learners understand and get the advantages of
doing the correct one

1.2 PROBLEM DEFINATION

▪ Yoga pose estimation is a challenging problem in the discipline of computer vision. ▪ To automatically
detect a person’s pose in an image is a difficult task as it depends on a number of aspects such as scale
and resolution of the image, illumination variation, background clutter, clothing variations, surroundings,
and interaction of humans with the surroundings. ▪ There are a number of yoga asanas, and hence creating
a pose estimation model that can be successful for all the asanas is a challenging problem

3|Page
 CHAPTER 2

LITERATURE SURVEY
4|Page
 2.1STUDY OF RESEARCH PAPER

1.Paper Name: A Proposal of Yoga Pose Assessment Method Using Pose Detection for SelfLearning

2.Author: Maybel Chan Thar1 , Khine Zar Ne Winn1 , Nobuo Funabiki 2

3.Abstract: Nowadays, Yoga is popular around the world. A lot of people are participating in it by
themselves through watching TV/videos or teaching each other. However, it is not easy for novice people
to find the incorrect parts of their Yoga poses by themselves. In this paper, we propose a Yoga pose
assessment method using pose detection to help the self-learning of Yoga. The system first detects a Yoga
pose using multi parts detection only with PC camera. Then, it calculates the difference of the specified
body angles between the pose of an instructor and that of a user. Then, it calculates the difference of the
specified body angles between the pose of an instructor and that of a user, and suggests the correction if
larger than the given threshold. The total angle difference values are calculated averagely and defined as
performance class level in Table 1. For evaluations, we applied the proposal to three persons with three
Yoga poses of basic and easy Yoga poses for beginners and confirmed that it found the incorrect parts of
each poses.

5|Page
1.Paper Name: INFINITY YOGA TUTOR : YOGA POSTURE DETECTION AND CORRECTION
SYSTEM

2.Author: : Fazil Rishan, Binali De Silva, Sasmini Alawathugoda .

3.Abstract : Popularity of yoga is increasing daily. The reason for this is the physical,
mental and spiritual benefits that could be obtained by practicing yoga. Many are following
this trend and practicing yoga without the training of an expert practitioner. However,
following yoga in an improper way or without a proper guidance will lead to bad health
issues such as strokes, nerve damage etc. So, following proper yoga postures is an
important factor to be considered. In this proposed system, the system is able to identify
poses performed by the user and also guide the user visually. This process is required to be
completed in real-time in order to be more interactive with the user. In this paper, the yoga
posture detection was done in a vision-based approach. The Infinity Yoga Tutor
application is able to capture user movements using the mobile camera, which is then
streamed at a resolution of 1280 x 720 at 30 frames per second to the detection system.

6|Page
1.Paper Name Implementation of Machine Learning Technique for Identification of Yoga
Poses

2.Author: : Yash Agrawal*, Yash Shah*, Abhishek Sharma†

3.Description : : In recent years, yoga has become part of life for many people across the
world. Due to this there is the need of scientific analysis of y postures. It has been observed
that pose detection techniques can be used to identify the postures and also to assist the
people to perform yoga more accurately. Recognition of posture is a challenging task due to
the lack availability of dataset and also to detect posture on real-time bases. To overcome
this problem a large dataset has been created which contain at least 5500 images of ten
different yoga pose and used a tf-pose estimation Algorithm which draws a skeleton of a
human body on the real-time bases. Angles of the joints in the human body are extracted
using the tf-pose skeleton and used them as a feature to implement various machine
learning models. 80% of the dataset has been used for training purpose and 20% of the
dataset has been used for testing. This dataset is tested on different Machine learning
classification models and achieves an accuracy of 99.04% by using a Random Forest
Classifier.

7|Page
1.Paper Name: : Miss Yoga: A Yoga Assistant Mobile Application Based on Keypoint

2.Author: : Renhao Huang, Jiqing Wang, Haowei Lou, Haodong Lu, Bofei Wang

3.Abstract : This paper demonstrates a Yoga assistant mobile application based on human-
keypoints detection models, which imitates the scene that real Yoga tutors guide and
supervise their students to do Yoga via the video chat. In order to provide humanize, safe
and convenient service, the core function is designed as hands-free using voice service, and
embedding fast and accurate models to detect keypoints and calculate the scores. In
addition, we propose an improved algorithm to calculate scores that can be applied to all
poses. Our application is evaluated on different Yoga poses under different scenes, and its
robustness is guaranteed.

8|Page
9|Page
 CHAPTER 3

SOFTWARE REQUIREMENTS
SPECIFICATION
10 | P a g e
 3.1 INTRODUCTION

Yoga is a safe and effective exercise to increase physical activity, especially, in strength, flexibility, and
balance, to boost physical and mental well-being. Yoga is a kind of workout for the total mind-body that
makes strengthening with deep breathing, meditation, or relaxation. Actually, Yoga is beneficial for
people who are suffering from high blood pressures, heart problems, pains, or full of stresses. Regular
yoga practices can reduce causes of their suffering. As a result, it has become growing massively and
increasingly over the past few years around the world. However, in current situations, it is difficult to join
Yoga ese guidelines include complete descriptions of the fonts, spacing, and related information for
producing your proceedings manuscripts classes for a lot of people. For example, in Myanmar, a lot of
people, particularly seniors, cannot go out by themselves to participate in Yoga classes due to
inconvenient public transportation systems for the old people, although
Myanmar is home to ancient spiritual practices including Yoga and have many Yoga schools. Seniors
often cannot drive cars. To take a taxi at each class is not feasible, too. Therefore, it is important for them
to practice Yoga at homes by themselves. However, it is not easy for novice Yoga people, particularly
seniors, to find the incorrect parts of their Yoga poses by themselves. The proposed method is for Yoga
Pose Assessment using pose detection for self-learners. The method first detects a pose using OpenPose
and a PC camera. Then, it calculates the difference of the specified body angles between the pose of an
instructor and that of a user. If it is larger than the given threshold, the method suggests the correction of
the part. With this proposal, it is expected that people can practice Yoga anywhere including home. Thus,
everyone can practice Yoga, no matter age or health. For evaluations, we applied the proposal to four
different conditions such as different body sizes, different height, different ages, and different camera
distance, with three Yoga poses, and found the incorrect parts each pose, which is expected to be
corrected by referring to the output. The paper is organized as followed for the rest of the sections:
Section 2 shows some related works in literature. Section 3 reviews OpenPose. Section 4 presents the
Yoga pose assessment method. Section 5 evaluates the proposal through applications. Finally, Section 6
concludes thewith some future works.

11 | P a g e
 3.1Project Scope

▪ Consider the potential for future enhancements and expansions, such as integrating more
advanced pose estimation models, accommodating more exercises, or exploring 3D pose
estimation. ▪ The project scope outlined here serves as a foundational framework. It can be
adjusted and expanded to suit the specific requirements and goals of your yoga and gym
pose detection project.

12 | P a g e
3.1 FUNCTIONAL REQUIREMENTS

3.1.1 System Feature 1 (Functional Requirements)

• Understanding of the problem statement.

• To know what are the hardware and software requirements of proposed system.

• To have understanding of proposed system.

• To do planning various activates with the help of planner.

• Designing, programming, testing etc.

3.2 EXTERNAL INTERFACE REQUIREMENTS (IF ANY)

3.2.1 User Interface

Application Based On Object Detection and Disease Prediction For Blind People

RAM : 8 GB

As we are using Machine Learning Algorithm and Various High Level Libraries
Laptop
RAM minimum required is 8 GB.
Hard Disk : 5000 GB
Data Set of CT Scan images is to be used hence minimum 40 GB Hard Disk
memory is required.
Processor : Intel i5 Processor

IDE : Android Visual Studio

Best Integrated Development Environment as it gives possible suggestions at the

13 | P a g e
time of typing code snippets that makes typing feasible and fast.
Coding Language : Kotlin

Highly specified Programming Language for Machine Learning because of avail-

ability of High Performance Libraries.
Operating System : Windows 10

14 | P a g e
 3.2.2 Software Interfaces

Operating System: Windows 10

IDE:Android Visual Studio

Programming Language : Python

3.3 NON FUNCTIONAL REQUIREMENT

3.3.1 Performance Requirements

The performance of the functions and every module must be well. overall perfor-
mance of the software will enable the users to work efficiently.

Performance of encryption of data should be fast.

Performance of the providing virtual environment should be fast Safety Require-

ment.

3.3.2 Safety Requirement

The application is designed in modules where errors can be detected and fixed
easily. This makes it easier to install and update new functionality if required.

3.3.3 Security Requirements

Users are authenticated using many security phases so reliable security is provided.

15 | P a g e
3.3.4 Software Quality Attributes

Our software has many quality attribute that are given below:-

Adaptability: This software is adaptable by all users.

Availability: This software is freely available to all users. The availability of the
software is easy for everyone.

Maintainability: After the deployment of the project if any error occurs then it can
be easily maintained by the software developer.

Reliability: The performance of the software is better which will increase the relia-
bility of the Software.

User Friendliness: Since, the software is a GUI application; the output generated is
much user friendly in its behavior.

Integrity: Integrity refers to the extent to which access to software or data by unau-
thorized persons can be controlled.

Security: Users are authenticated using many security phases so reliable security is
provided.

Testability: The software will be tested considering all the aspects.

16 | P a g e
3.4 SYSTEM REQUIREMENTS

3.4.1 Database Requirements

The Firebase Realtime Database is a cloud-hosted database in which data is stored

as JSON. The data is synchronized in real-time to every connected client. All of
our clients share one Realtime Database instances and automatically receive
updateswith the newest data, when we build cross-platform applications with our
iOS, and JavaScript SDKs.
The Firebase Realtime Database is a NoSQL database from which we can
store and sync the data between our users in real-time. It is a big JSON object
which the developers can manage in real-time. By using a single API, the Firebase
database provides the application with the current value of the data and updates to
that data. Real-time syncing makes it easy for our users to access their data from
any device, be it web or mobile.
The Realtime database helps our users collaborate with one another. It ships
with mobile and web SDKs, which allow us to build our app without the need for
servers. When our users go offline, the Real-time Database SDKs use local cache
on the device for serving and storing changes. The local data is automatically
synchro- nized, when the device comes online.

17 | P a g e
  Software Requirements

▪ Operating system : 64 bit Windows 10.

▪ Coding Language : Python

Hardware Requirements

▪ System Processors : Core2Duo

▪ Speed : 2.4 GHz
▪ Hard Disk : 500 GB

18 | P a g e
19 | P a g e
3.1 SYSTEM IMPLEMENTATION PLAN

The System Implementation plan table, shows the overall schedule of tasks compi-
lation and time duration required for each task.

Sr. No. Name/Title Start Date End Date

1 Preliminary Survey
2 Introduction and Problem State-
ment
3 Literature Survey
4 Project Statement
5 Software Requirement And Specifi-
cation
6 System Design
7 Partial Report Submission
8 Architecture Design
9 Implementation
10 Deployement
11 Testing
12 Paper Publish
13 Report Submission

20 | P a g e
 CHAPTER 4

SYSTEM DESIGN
21 | P a g e
4.1 SYSTEM ARCHITECTURE

22 | P a g e
23 | P a g e
4.1.1 Data Flow Diagram

In Data Flow Diagram,we Show that flow of data in our system in DFD0 we show
that base DFD in which rectangle present input as well as output and circle show
our system,In DFD1 we show actual input and actual output of system input of our
system is text or image and output is rumor detected like wise in DFD 2 we present
operation of user as well as admin.

Figure 4.2: Data Flow(0) diagram

Figure 4.3: Data Flow(1) diagram

24 | P a g e
 Figure 4.4: Data Flow(2) diagram

4.2 UML DIAGRAMS

Unified Modeling Language is a standard language for writing software blueprints.The

UML may be used to visualize,specify,construct and document the artifacts of a soft-
wareintensive system.UML is process independent,although optimally it should be
used in process that is use case driven,architecture-centric,iterative,and incremen-
tal.The Number of UML Diagram is available.

Class Diagram.

Use case Diagram.

Activity Diagram.

Sequence Diagram.

25 | P a g e
Figure 4.5: Class Diagram Diagram

26 | P a g e
Figure 4.6: Use case Diagram

27 | P a g e
Figure 4.7: Activity Diagram

28 | P a g e
Figure 4.8: Sequence Diagram

29 | P a g e
 CHAPTER 5

OTHER SPECIFICATIONS
29 | P a g e
 ADVANTAGES

▪ Real-time Feedback and Correction

▪ Personalized Workouts
▪ Objective Assessment
▪ Performance Analysis

APPLICATION

Real-time Feedback for Practitioners

▪ Fitness Apps and Wearables
▪ Fitness Equipment Integration
▪ Physical Rehabilitation
▪ Yoga and Fitness Coaching
▪ Sports Performance Analysis
CHAPTER :6 CONCLUSION AND FUTURE

SCOPE

30 | P a g e
 6.1 CONCLUSION

We applied the time-distributed CNN layer to detect patterns between key points in a single frame
and the LSTM to memorize the patterns found in the recent frames. Using LSTM for the
memory of previous frames and polling for denoising, the results make the system even more
robust by minimizing the error due to false key point detection. Since the frames of a Yoga
Images are sequential.

6.2 FUTURE SCOPE

By seeing the benefits of Yoga, career opportunities in this field are increasing in India as well as in
abroad also. After pursuing yoga courses, you can work in health clubs, yoga & pilates studios,
special needs Centre, private gym and in individual clients homes. Based on Yoga pose, we can
build a variety of applications, like fitness or yoga trackers. As an example, we present squats and
push up counters, which can automatically count user statistics, or verify the quality of performed
exercises.

31 | P a g e
32 | P
 CHAPTER 7

REFERENCES

[1] H.-T. Chen, Y.-Z. He and C.-C. Hsu, “Computer Assisted Yoga Training System”,
Multi. Tool. Appl., vol. 77, no. 18, September 2018, pp.2396923991.

[2] K.-M. Chen, W.-S. Tseng, L.-F. Ting, and G.-F. Huang, “Development and Evaluation
of a Yoga Exercise Programme for Older adults”, J. Adv. vol. 57, no. 4, 2007.

[3] H. E. Downs, R. Miltenberger, J. Biedronski, and L. Witherspoon, “The Effects of

Video Self-Evaluation on Skill Acquisition with Yoga Postures”, Journal of applied
behavior analysis, vol. 484, pp. 930-935, 2015.

[4] M. Eichner and V. Ferrari, “Human Pose CoEstimation and , IEEE Trans. Pattern
Ana. Machi. Intel, vol. 34, no. 11, November 2012, pp.2282- 2288.

[5] Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei, and Y. Sheikh, “OpenPose: Real-time Multi-
person 2D Pose Estimation Using Part Affinity Fields”, December 2018,
https://arxiv.org/abs/1812.08008.

[6] D. Osokin, “Real-time Multi-person Pose Estimation on CPU: lightweight OpenPose”,

November 2018, https://arxiv.org/abs/1811.12004.

[7] B. Xiao, H. Wu, and Y. Wei, “Simple Baselines for Human Pose Estimation and
Tracking”, August 2018, https://arxiv.org/abs/1804.06208.

[8] M. Andriluka, U. Lqbal, E. Insafudinov, L. Pishchulin, A. Milan, J. Gall, and B.

Schiele, “Pose Track: A Benchmark for Human Pose Estimation and Tracking”, April,
2018, https://arxiv.org/abs/1710.10000.

[9] Z. Cao, T. Simon, S.-E. Wei, and Y. Sheikh, “Realtime Multi-person 2D Pose
Estimation Using Part Affinity fields”, April 2017, https://arxiv.org/abs/1611.08050

34 | P a g e