Action Recognition for Depression Assessment Using Deep Learning

Depression is the most prevalent mood disorder worldwide having a significant impact on well-being and functionality, and important personal, family and societal effects. The early and accurate detection of signs related to depression could have many benefits for both clinicians and affected individ

Project Title

Action Recognition for Depression Assessment Using Deep Learning

Project Area of Specialization

Artificial Intelligence

Project Summary

Depression is the most prevalent mood disorder worldwide having a significant impact on well-being and functionality, and important personal, family and societal effects. The early and accurate detection of signs related to depression could have many benefits for both clinicians and affected individuals. The present work aimed at developing and clinically testing a methodology able to detect visual signs of depression and support clinician decisions.

The project aims to make a system that helps assess depression through posture analysis of the patient. It will analyze certain postures of a patient that will help maintain a record and assess whether the person is having symptoms of depression or not.

Project Objectives

• To make a system of assessment of risk factor of depression patients depending on pose estimation
• To create a system for pose estimation using deep learning
• To determine the risk factors associated with depressive symptoms in young adolescent.
• By Using statistical features extracted from poses and postures, and head pose, we characterise the behaviour associated with major depression and then generate a risk factor that the person might be at risk and is in need to consult some doctor.

Project Implementation Method

The project will be implemented using CNN (Convolution Neural Network ). The first step will be collection of dataset in the form of pictures and surveys. Then the project will be used to develop in such a way that it assess the postures of a person for set amount of days and predicts whether the symptoms indicate of depression in the person or not.   

Benefits of the Project

This project can help in medical field specially in clinical psychology. Psychologists could get help to maintain clinical record of the patients body postures which may help them assess more efficiently a patients symptoms specially when they are not around and the patient is alone.

Technical Details of Final Deliverable

The final project aims to track the patient through a video and assess its postures by converting them into images and checking them with postures used to train the machine. It will check off a certain checklist then to assess teh body posture symtoms for certain amount of days in order to assess whether the patient holds the symptoms of depression or not. 

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Medical

Other Industries

Core Technology

Artificial Intelligence(AI)

Other Technologies

Sustainable Development Goals

Good Health and Well-Being for People

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com