C# library that handles the full process of gathering biometric data from a body-worn sensor, transforming it into handcrafted feature vectors, and delivering an inferencing result in thirty-five lines of code.

An implementation of the WESAD processing and training pipeline in Python.

An open-source toolkit for auditing wearable physiological signals: signal quality, algorithmic fairness, causal sensitivity, and downstream-task impact.

AI-powered IoT biosensor system for real-time stress detection using ESP32, physiological sensors, Flask, and a Random Forest model trained on the WESAD dataset.

A simple Python GUI to explore sensor data and classify emotional states.

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

Quantifying yogas impact: a calibrated Composite Yoga Index (Relaxation Index 0-100) from multimodal physiological data (WESAD autonomic + EEG), with leak-free, contamination-aware validation.

Real-time stress detection wearable using ESP32 + multi-sensor HRV (ECG / PPG / GSR / temp / IMU), SVM trained on WESAD, FastAPI inference service, and React dashboard. LOSO accuracy 0.891 across 16 subjects.

Multimodal physiological stress recognition on WESAD with LOSO validation and LabVIEW integration

Stress detection from wrist signals with 91.33% accuracy. Random Forest on WESAD + DEAP datasets with real-time binaural beat intervention. Python, Scikit-learn, Streamlit.

StudyBee is an intelligent multimodal learning assistant that combines RAG-based document Q&A, automatic quiz generation, adaptive difficulty control, and real-time emotion recognition (facial, speech, physiological, and text) to deliver a personalized and emotionally-aware study experience.

基于 PPG+EDA 多模态信号的轻量级可穿戴情感状态检测系统 | WESAD | 1D-CNN 三分类 | LOSO | React Dashboard

Participant-disjoint WESAD stress-monitoring reliability framework with calibration, threshold, false-alert, robustness, and subject-specific failure audits.