Icentia11k: An Unsupervised ECG Representation Learning Dataset for Arrhythmia Subtype Discovery
Shawn Tan and Guillaume Androz and Ahmad Chamseddine and Pierre Fecteau and Aaron Courville and Yoshua Bengio and Joseph Paul Cohen

folder icentia11k (22000 files)
file10999_batched_lbls.pkl.gz 889.54kB
file10999_batched.pkl.gz 24.05MB
file10998_batched_lbls.pkl.gz 759.26kB
file10998_batched.pkl.gz 18.93MB
file10997_batched_lbls.pkl.gz 900.90kB
file10997_batched.pkl.gz 21.77MB
file10996_batched_lbls.pkl.gz 710.42kB
file10996_batched.pkl.gz 23.57MB
file10995_batched_lbls.pkl.gz 758.58kB
file10995_batched.pkl.gz 22.86MB
file10994_batched_lbls.pkl.gz 1.74MB
file10994_batched.pkl.gz 24.54MB
file10993_batched_lbls.pkl.gz 967.55kB
file10993_batched.pkl.gz 22.69MB
file10992_batched_lbls.pkl.gz 844.82kB
file10992_batched.pkl.gz 19.45MB
file10991_batched_lbls.pkl.gz 1.03MB
file10991_batched.pkl.gz 43.23MB
file10990_batched_lbls.pkl.gz 2.18MB
file10990_batched.pkl.gz 51.35MB
file10989_batched_lbls.pkl.gz 691.36kB
file10989_batched.pkl.gz 16.38MB
file10988_batched_lbls.pkl.gz 987.64kB
file10988_batched.pkl.gz 26.76MB
file10987_batched_lbls.pkl.gz 847.66kB
file10987_batched.pkl.gz 24.15MB
file10986_batched_lbls.pkl.gz 835.89kB
file10986_batched.pkl.gz 21.14MB
file10985_batched_lbls.pkl.gz 674.90kB
file10985_batched.pkl.gz 20.12MB
file10984_batched_lbls.pkl.gz 616.36kB
file10984_batched.pkl.gz 20.44MB
file10983_batched_lbls.pkl.gz 1.12MB
file10983_batched.pkl.gz 24.04MB
file10982_batched_lbls.pkl.gz 817.35kB
file10982_batched.pkl.gz 20.88MB
file10981_batched_lbls.pkl.gz 837.91kB
file10981_batched.pkl.gz 38.83MB
file10980_batched_lbls.pkl.gz 1.19MB
file10980_batched.pkl.gz 32.36MB
file10979_batched_lbls.pkl.gz 1.76MB
file10979_batched.pkl.gz 25.73MB
file10978_batched_lbls.pkl.gz 687.49kB
file10978_batched.pkl.gz 25.37MB
file10977_batched_lbls.pkl.gz 790.54kB
file10977_batched.pkl.gz 18.21MB
file10976_batched_lbls.pkl.gz 835.86kB
file10976_batched.pkl.gz 36.05MB
file10975_batched_lbls.pkl.gz 929.27kB
Too many files! Click here to view them all.
Type: Dataset
Tags: deep learning, ECG, cardiology, ecencha, ecentia, isentia

Bibtex:
@article{,
title= {Icentia11k: An Unsupervised ECG Representation Learning Dataset for Arrhythmia Subtype Discovery},
keywords= {deep learning, ECG, cardiology, ecencha, ecentia, isentia},
author= {Shawn Tan and Guillaume Androz and Ahmad Chamseddine and Pierre Fecteau and Aaron Courville and Yoshua Bengio and Joseph Paul Cohen},
abstract= {We release the largest public ECG dataset of raw signals for representation learning containing over 11k patients and 2 billion labelled beats.
Our goal is to enable semi-supervised ECG models to be made as well as to discover unknown subtypes of arrhythmia and anomalous ECG signal events.

To this end, we propose an unsupervised representation learning task, evaluated in a semi-supervised fashion. 
We provide a set of baselines for different feature extractors that can be built upon. 
Additionally, we perform qualitative evaluations on results from PCA embeddings, where we identify some clustering of known subtypes indicating the potential for representation learning in arrhythmia sub-type discovery.

https://i.imgur.com/5PxNneL.png

License:
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0) 
http://creativecommons.org/licenses/by-nc-sa/4.0/},
terms= {},
license= {http://creativecommons.org/licenses/by-nc-sa/4.0/},
superseded= {},
url= {}
}

Hosted by users:

Send Feedback