TomMakesThings/Semi-Supervised-ECG-Classifier

Undergraduate group project in which we built an ECG classifier using a TCN-CNN with 97% accuracy

19
/ 100
Experimental

This project helps medical practitioners or researchers quickly identify specific heart conditions from electrocardiogram (ECG) heartbeat data. You input raw ECG time series data, and it outputs a classification indicating different types of arrhythmia. This tool is designed for cardiologists, medical technicians, or researchers analyzing heart rhythm patterns.

No commits in the last 6 months.

Use this if you need an accurate, automated system to classify various heart arrhythmias from ECG readings to assist in diagnosis or research.

Not ideal if you require a system that explicitly uses self-supervised clustering for improved accuracy, as this particular approach did not yield significant gains here.

cardiology ECG analysis arrhythmia detection medical diagnosis heart health
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

17

Forks

1

Language

Jupyter Notebook

License

Last pushed

Oct 02, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/TomMakesThings/Semi-Supervised-ECG-Classifier"

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