Attention-based bidirectional LSTM for Classification Task (ICASSP)

This is a Text Analysis App which can be used to find a detailed analysis of a particular text. This includes 5 main types of Analysis - Spam/Ham Detection, Sentiment Analysis, Stress Detection, Hate & Offensive Content Detection, Sarcasm Detection

Human Stress Detection project utilizes machine learning techniques to detect stress in an individual

This is is an AI-powered hearing-aid companion app that predicts sensory overload in autistic children before meltdowns occur. It analyzes early stress signals, movement, noise, and location to adapt noise cancellation and trigger calming interventions in real time.

More to Less (M2L): Enhanced Health Recognition in the Wild with Reduced Modality of Wearable Sensors

A real-time Face Emotion Recognition (FER) system that uses a deep Convolutional Neural Network (CNN) model to detect mental stress levels during online learning environments. The system captures emotional cues from facial expressions to determine stress, enhancing digital mental health monitoring.

A comparative analysis of time-series encoding methods (GAF, MTF, RP) using CNN architectures (VGG-16, ResNet) for stress detection from wearable sensor data

Real-time burnout detection system using facial emotion recognition (FER) and temporal LSTM modeling, validated against standardized psychological surveys (MBI/PSS)

This project is designed to help users assess their stress levels and provide personalized suggestions for managing stress. The chatbot collects user data such as age, gender, sleep quality, physical activity, and health metrics, and uses a RandomForestRegressor model to predict the user's stress level.

Multimodal physiological stress detection using ML/DL with explainable AI

MindGuard — an intelligent assistant for student stress assessment and personalized wellbeing recommendations.

Detect stress and burnout in real time using facial emotion recognition and hybrid deep learning models for better mental health insights.

Real-time stress detection using facial expressions and CNN (FER2013 + OpenCV + TensorFlow)

A project that uses wearable biosignals and machine learning to adapt game narrative in real time.

Real-time stress detection using biosensors, IoT & ML

Stress detection from wearable HRV signals using a Soft-Voting Ensemble (RF, XGBoost, SVM) on the WESAD dataset. Achieved 82.97% LOSO accuracy.

Real-time AI stress tracker using mouse & keystroke dynamics. Privacy-first, local-only, and 100% offline.