Jathurshan0330/Cross-Modal-Transformer

Official repository of cross-modal transformer for interpretable automatic sleep stage classification. https://arxiv.org/abs/2208.06991

35
/ 100
Emerging

This project helps clinicians and sleep researchers automatically classify sleep stages from raw sleep study data (like EEG signals) more accurately and, crucially, with clear explanations for its decisions. It takes unprocessed physiological signals from a sleep study as input and outputs a classification of sleep stages (e.g., REM, N1, N2, N3, Wake) along with visual explanations of why it made those classifications. Sleep scientists, neurologists, and clinical researchers specializing in sleep disorders would find this useful for assessing sleep health.

Use this if you need an automated tool for sleep stage classification that not only performs well but also provides transparent and interpretable insights into its decision-making process, which is essential for clinical acceptance.

Not ideal if you are looking for a plug-and-play mobile app for personal sleep tracking, as this is a research-oriented tool requiring technical expertise to set up and run.

sleep-medicine neurology biomedical-signal-processing sleep-stage-scoring clinical-diagnosis
No License No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 8 / 25

How are scores calculated?

Stars

75

Forks

4

Language

Jupyter Notebook

License

Last pushed

Feb 12, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Jathurshan0330/Cross-Modal-Transformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.