This paper presents an innovative and generic deep learning approach to
monitor heart conditions from ECG signals.We focus our attention on both the
detection and classification of abnormal heartbeats, known as arrhythmia. We
strongly insist on generalization throughout the construction of a
deep-learning model that turns out to be effective for new unseen patient. The
novelty of our approach relies on the use of topological data analysis as basis
of our multichannel architecture, to diminish the bias due to individual
differences. We show that our structure reaches the performances of the
state-of-the-art methods regarding arrhythmia detection and classification.
Description
[1906.05795] Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks
%0 Journal Article
%1 dindin2019topological
%A Dindin, Meryll
%A Umeda, Yuhei
%A Chazal, Frederic
%D 2019
%K manifolds
%T Topological Data Analysis for Arrhythmia Detection through Modular
Neural Networks
%U http://arxiv.org/abs/1906.05795
%X This paper presents an innovative and generic deep learning approach to
monitor heart conditions from ECG signals.We focus our attention on both the
detection and classification of abnormal heartbeats, known as arrhythmia. We
strongly insist on generalization throughout the construction of a
deep-learning model that turns out to be effective for new unseen patient. The
novelty of our approach relies on the use of topological data analysis as basis
of our multichannel architecture, to diminish the bias due to individual
differences. We show that our structure reaches the performances of the
state-of-the-art methods regarding arrhythmia detection and classification.
@article{dindin2019topological,
abstract = {This paper presents an innovative and generic deep learning approach to
monitor heart conditions from ECG signals.We focus our attention on both the
detection and classification of abnormal heartbeats, known as arrhythmia. We
strongly insist on generalization throughout the construction of a
deep-learning model that turns out to be effective for new unseen patient. The
novelty of our approach relies on the use of topological data analysis as basis
of our multichannel architecture, to diminish the bias due to individual
differences. We show that our structure reaches the performances of the
state-of-the-art methods regarding arrhythmia detection and classification.},
added-at = {2019-06-15T05:58:40.000+0200},
author = {Dindin, Meryll and Umeda, Yuhei and Chazal, Frederic},
biburl = {https://www.bibsonomy.org/bibtex/22177a20d44df4f9f8fa3df168d327f17/kirk86},
description = {[1906.05795] Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks},
interhash = {ff13c900c06b32daecdee640125d1cfa},
intrahash = {2177a20d44df4f9f8fa3df168d327f17},
keywords = {manifolds},
note = {cite arxiv:1906.05795Comment: 7 pages, 4 figures},
timestamp = {2019-06-15T05:58:40.000+0200},
title = {Topological Data Analysis for Arrhythmia Detection through Modular
Neural Networks},
url = {http://arxiv.org/abs/1906.05795},
year = 2019
}