Real-time emotion recognition with 40-channel EEG, facial analysis & PPG fusion - PyQt6 interface with DEAP dataset, KNN/SVM classifiers

This repository offers a pipeline for classifying insomnia using EEG, EMG, EOG, and ECG signals, featuring early and late fusion, signal preprocessing, feature extraction, and machine learning models for accurate detection.

Production-grade ensemble framework combining XGBoost, PyTorch & Sklearn - 70%+ test coverage with Optuna optimization for time-series prediction

First‑year BTech Electrical Engineering project (2020–21): NI Multisim simulation of a wearable stress‑meter with sensor‑fusion analytics.

Implementation of the core Adaptive Chirplet Transform (ACT) algorithm using THRML (Thermodynamic sampling) to efficiently find the best matching atom in the continuous space

This project demonstrates how electromyographic (EMG) signals can be used to control a prosthetic hand. The software acquires raw EMG data from surface electrodes, processes it in real time using digital filters, and translates the extracted muscle activity into control commands for servo motors.

Implementation of the research paper “Heart Sounds Classification Using a CNN with 1D-Local Binary and Ternary Patterns”. Includes preprocessing, feature extraction (1D-LBP and 1D-LTP), and convolutional neural network–based classification of heart sound signals.

This repository implements a fusion algorithm based on a constant velocity model to improve the accuracy of saccade parameter measurements using electrooculography (EOG) signals. By combining regression-based and threshold-based estimations, the method enhances the detection of saccade amplitude, velocity, and duration.

Stress detection using physiological signals from the WESAD dataset. Built with Python for time series analysis, feature extraction, and machine learning. Ideal for health tech and wearable applications.