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.

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.