MIT-BIH Atrial Fibrillation Database
Consist of 25 long-term ECG recordings of human subjects with atrial fibrillation.
Long Term AF Database
Consist of 84 long-term ECG recordings of human subjects with paroxysmal or sustained atrial fibrillation (AF). ECG signals digitized at 128 Hz with 12-bit resolution.
Test dataset for automatic multi-label ECG diagnosis of impulse or conduction abnormalities in patients with deep learning algorithm: a cohort study
828 ECGs, divide into 21 specific class rhythms. Each subject with 10 hours in duration
AF Classification from a Short Single Lead ECG Recording - The PhysioNet Computing in Cardiology Challenge 2017
8528 ECG tracks, each 2000 points