Skip to content

Web based Depression Detection Applicatoin using LSTM RNN Network

Notifications You must be signed in to change notification settings

RamgopalH/DepressionDetectionUsingLSTM

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Web Based Depression Detection using Recurrrent Neural Networks and Speech Analysis

This project a MFCC-based Recurrent Neural Network for automatic clinical depression recognition and assessment from speech model deployed as a Web Application. The model is a based on one of the proposed solutions of the paper Rejaibi, Emna, Komaty, Ali, Meriaudeau, Fabrice, & Othmani, Morgan-Hiring. (2022). MFCC-based Recurrent Neural Network for Automatic Clinical Depression Recognition and Assessment from Speech. Biomedical Signal Processing and Control, 71, 103107. doi: 10.1016/j.bspc.2021.103107.

The pre processing function and the model have been is slightly altered . The Dataset used is the DIAC-WOZ dataset

Required Software

  • Python (^3.10) [with PIP]
  • NPM (^9.50)
  • Node.js (^16.16.0)
  • React (^18.2)
  • Git

Running the Model on Local Machine

Clone the repository by downloading the zip file or running the git clone command like so:

git clone https://github.com/RamgopalH/DepressionDetectionUsingLSTM.git

Back End

Change to the server folder and do the following:

To set up the python packages, run the followign command o install all pytohn depemdencies

pip install numpy pandas pydub IPython librosa scipy tensorflow

Install All the required node modules using npm

npm init -y
npm install

Make sure port 5000 is free on your system or change the value of PORT in the index.js file

To start the server, run

nodemon index.js

Front End

Switch to the client folder and set up the frontend of the application

Install all required Node packages and React packages using NPM

npm init -y
npm install

Make sure sever is running before running the client with the following command

npm run dev

It displays a url in the command prompt and following this url should take you to the home page of the application.

About

Web based Depression Detection Applicatoin using LSTM RNN Network

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published