😴 DeepSleep2 is a compact U-Net-inspired convolutional neural network with 740,551 parameters, designed to predict non-apnea sleep arousals from full-length multi-channel polysomnographic recordings at 5-millisecond resolution. Achieves similar performance to DeepSleep with lower computational cost.

EEGLAB-compatible analysis software for manual / visual sleep stage scoring, signal processing and event marking of polysomnographic (PSG) data for MATLAB.

Wearanize+ is a multimodal sleep dataset containing overnight sleep data from 130 young, healthy participants using PSG and three wearables

Automated polysomnography for experimental animal research

Method for detecting sleep spindles using EEGlab functions and datasets

Official implementation of our paper "ENHANCING HEALTHCARE WITH EOG: A NOVEL APPROACH TO SLEEP STAGE CLASSIFICATION"

Official implementation of our paper "Transparency in Sleep Staging: Deep Learning Method for EEG Sleep Stage Classification with Model Interpretability"

Competitive apnea detector for polysomnographic data

A Python package for sleep analysis and hypnogram processing

Detecting events in sleeping tinnitus patients

ScoreREM: A user friendly Matlab-GUI for rapid eye movement (REM) sleep microstructure annotation and quantification

Deep learning-based apnea event classification using PSG data with TCNs and advanced signal processing.

Forked from https://bitbucket.org/yehezkel/edf-parser

Source code for the paper "Automatic Actigraphy and Polysomnography Sleep Scoring using Deep Learning".

Code and materials for Hainke et al. (2025), SLEEP.

Extracts information from polysomnography reports generated by Compumedics Profusion and Natus Embla RemLogic software, and then exports the data to an Excel file.

No description provided.

Detect breathing irregularities (hypopnea, obstructive apnea) in overnight sleep recordings by converting nasal airflow, thoracic movement, and SpO₂ into labeled 30-second windows. Train a 1D CNN with leave-one-participant-out validation and evaluate using accuracy, precision, recall, and confusion matrices.

Document and code that generates the Sleep Statistics defined at the Surrey Sleep Research Centre

Run CAISR (Complete AI Sleep Report) natively on Apple Silicon — no Docker needed