“WELCOME ”

Content
1. Problem Statement
2. Introduction
3. Literature Survey
4. Objective
5. System Architecture
6. Algorithm
7. Advantages and Applications
8. Conclusion
9. References
10. Competition Certificates
Problem Statement

To design a system that predicts depression status using machine learning and natural language
processing to combine the results of facial expression and question answering.
Introduction

As we know now a days depression is a mental illness of people that’s why many suicide case is
happen. Early detection and intervention are crucial for managing depression. Our facial
emotions are expressed through activation of specific sets of facial muscles. Sometimes these
contain an abundant amount of information about our state of mind. Through facial emotion
recognition, we are able to measure the effects that content and services have on the users
through an easy and low-cost procedure. Technology can aid in the diagnosis and treatment of
mental health disorders. One approach is to use facial recognition technology, PEN testing, and
IQ testing to track and detect depression levels.
Literature Survey

YEAR OF
PAPER TITLE ABOUT PAPER PUBLICATION
AND AUTHOR
This paper provides a summary of ten depression
datasets, including information on non-verbal signs of
A Summarization of the Visual depression, data collection techniques, clinical
Arselan Ashraf ,2020
Depression Databases for definitions, and annotations, to help researchers select an
appropriate dataset for their depression detection models.
IEEE
Depression Detection
Additionally, a tabular list of the datasets is provided for
easy reference.
Researchers are developing a machine learning model
that uses images and videos to determine an individual's
level of depression and classify them into categories: Anagha Dhekne, Rasi
Minimal, Mild, Moderate, or Severe. The model
Automatic depression level Wani, October
incorporates the Beck Depression Inventory II
detection through visual input questionnaire, which is used to diagnose depression, and
26,2020
analyzes video input to produce visual graphics
representing the individual's level of depression by
comparing the results to emotion and inventory vectors.
Literature Survey

YEAR OF
PAPER TITLE ABOUT PAPER PUBLICATION
AND AUTHOR
This research paper analyzed data from a mental health
Predicting Mental health survey to identify personal or professional factors that
disorders using Machine can affect an employee's mental health and used Jyoti Kumari, R.
Learning for employees in machine learning algorithms to build models that Rajesh and Abhinav
technical and non-technical accurately predict mental health based on identified Kumar, 2016 IEEE
companies features, with the aim of developing tools to help
companies support their employees' mental health.
This research paper compares different methods of
recognizing facial expressions using appearance-based
Fusion of Features for the techniques, with a focus on HOG feature extraction, and Rahul Katarya ,
Effective Facial Expression aims to find the best ways to recognize facial Saurav Maan , May
Recognition expressions to improve recognition rates and usefulness 20,2021
in various areas of study.
Objectives

• Develop and incorporate psychometric tests designed to assess cognitive function.

• Implement facial expression recognition technology to objectively analyze emotional
states.
• Design a hybrid system architecture that seamlessly combines facial expression analysis
and cognitive function tests.
• Emphasize the importance of early diagnosis in managing depression effectively.
System Architecture

PEN & IQ Test

Fig .System Architecture

Algorithm
1. Capture Live Video:
- Initiate live video capture from the camera.
2. Face Detection:
- Apply face detection algorithms to identify and localize faces in the video frames.
3. Face Feature Extraction:
- Extract facial features from detected face regions, including key landmarks.
4. CNN Classifier:
- Employ a pre-trained Convolutional Neural Network (CNN) to classify facial
expressions.
- Output probabilities for emotions: happy, contempt, disgust.
5. Emotion Feature Detection:
- Evaluate CNN output to detect levels of happiness, contempt, and disgust.
6. PEN & IQ Test:
- Administer Psychomotor Vigilance Task (PEN test) to assess alertness.
- Conduct an IQ test for cognitive function evaluation.
7. Feature Fusion:
- Combine CNN output, emotional features, PEN test, and IQ test results.
Algorithm
8. Estimation of Depression Level:
- Employ a machine learning model to estimate depression level based on the
combined feature set.
9. Thresholding and Interpretation:
- Apply thresholds to categorize depression level (e.g., mild, moderate, severe).
- Interpret results for actionable insights.
10. Output Display:
- Present estimated depression level and relevant information.
11. Conclusion:
- Summarize findings and potential interventions based on depression level.
Project Design

DATA FLOW DIAGRAM :

Fig.5.1 - Zero Level DFD

Project Design

DATA FLOW DIAGRAM :

Fig.5.1 - One Level DFD

Project Design

DATA FLOW DIAGRAM :

Fig.5.1 – Two Level DFD

Software & Hardware Tools

❖ Software Requirements:
1. Software - Pycharm
2. Technologies – python, DL, Django
3. Database – SQLite db
4. Datasets - FER-2013

❖ Hardwar Requirements :
1. Processor - i3 or above
2. Hard Disk - 150 GB
3. Memory - 6 GB RAM
Applications

1. Counsellor use this system to detect user mental illness and depression level
2. Helpful to whole of our society for everyone who suffered from mental illness and
tracefullness.
3. Psychologist use this system to check patient psychology scenario related user thinking
4. Psychologist use this system to beginning a meditation practice to check stress and anxiety of
person or improve the sleep quality and positivity with good health
5. It helpful for students who survive from depression.
Advantages:

1. Healthcare Settings:
- Deploy in clinics, hospitals, or counseling centers for routine mental health assessments.
2. Remote Monitoring:
- Enable remote monitoring for individuals receiving telehealth services.
3. Research Studies:
- Contribute to research studies on the correlation between facial expressions, cognitive
function, and depression.
4. Educational Institutions:
- Implement in educational institutions to identify and support students experiencing mental
health challenges.
Conclusion

In conclusion, tracking and detecting depression levels using facial recognition, PEN, and IQ tests can
be a valuable tool for early detection and intervention for individuals at risk of developing or already
suffering from depression. The proposed system utilizes facial recognition technology to detect
changes in facial expressions and mood, as well as PEN and IQ tests to analyze cognitive function. By
integrating these technologies, the proposed system can provide a comprehensive assessment of an
individual's mental state, allowing for early detection. , this project has the potential to provide a cost-
effective and efficient method for detecting and monitoring depression levels in individuals. This can
lead to timely intervention and treatment, improving the quality of life of individuals suffering from
depression
Future Work

In future We will evaluate the efficiency of our proposed method using a set of various psycholinguistic
features. We show that our proposed method can significantly improve the accuracy and classification error
rate. In addition, the result shows that in different experiments Decision Tree (DT) gives the highest
accuracy than other ML approaches to find the depression.
Refrences

1. Malaysia,Teddy Surya Gunawan, Ulfiah " A Summarization of the Visual Depression Databases for
Depression Detection" , 2021.
2. Anagha Dhekne, Rasi Wani, Akshada Mulay, Pranjali Deshpande "Automatic depression level detection
through visual input", 2020.
3. Rahul Katarya , Saurav Maan " Predicting Mental health disorders using Machine Learning for employees
in technical and non-technical companies“,IEEE INTERNATIONAL CONFERENCE ON
ADVANCES AND DEVELOPMENTS IN ELECTRICAL AND ELECTRONICS ENGINEERING
(ICADEE 2020).
4. Jyoti Kumari, R. Rajesh and Abhinav Kumar, " Fusion of Features for the Effective Facial Expression
Recognition", International Conference on Communication and Signal Processing, April 6-8, 2016, India.
5. Jayshree N Lavhare, M.A Kulkarni "Mental Disorders Detection using Social Networking Sites",
Proceedings of the Third International Conference on Intelligent Communication Technologies & Virtual
Mobile Networks (ICICV 2021), IEEE Xplore Part Number: CFP21ONG-ART; 978-0-7381-1183-4.