depression-analysis

depression detection by using tweets

machine learning models for predicting depression based on EEG data

Edison AT is software Depression Assistant personal.

Machine Learning Project for Depression Detection Using Tweets.

Towards Explainable Multimodal Depression Recognition for Clinical Interviews

A real time Multimodal Emotion Recognition web app for text, sound and video inputs

Statistics for Suicide Analysis for all the countries in the world using Machine Learning Algorithms to find some interesting patterns, solutions and Clues about Suicides using Data Analysis and Data Visualizations

Deep Learning based research project for predicting mental state of a person.

sMRI based depression classification using 3D volumetric convolutional networks

Can LMs generate useful synthetic data for the mental health domain?

My final year dissertation project. This project takes motor activity data from a control group and a condition group. The data is filtered, cleaned and transformed for appropriate use to find the "best" classification algorithm to identify depressed patients from non-depressed patients

Depression Detection is a speech-based classifier that analyzes emotional and acoustic features to detect depression.

This project focuses on predicting depression among students using various machine learning models. It explores relationships between key factors like sleep duration, gender, financial stress, work/study hours, and academic pressure with depression. The study leverages EDA and multiple ML algorithms to achieve high prediction accuracy.

2D and 3D deformable CNN Autoencoders

Android application for Identification of stress symptoms, comparison and remedial solutions provided through chat-bot(Neo).

An interactive one-page website that provides a compendium on neurotransmitters (dopamine, norepinephrine, serotonin, and melatonin) and their role in psychophysiology. The page analyzes symptoms of deficiency/excess, core functions, interactions, and systemic connections to disorders such as depression, ADHD, and PTSD.

Prototype for predicting the severity of depression based on machine learning models deployed over the Google Cloud Platform using Firebase.

Official repository for IEEE Confluence 2021 paper: Machine learning pipeline using hard-voting ensemble models (KNN, LR, SVM) for smartwatch-based early depression detection (89.6% accuracy).

Codes for paper：A Prompt-Based Learning Approach for Few-Shot Social Media Depression Detection

Website for depression analysis by using LSTM-based model to classify depressive tweets.