Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks

Meryll Dindin
  • Function : Author
Frédéric Chazal

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.
Fichier principal
Vignette du fichier
1906.05795.pdf (395.7 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02155849 , version 1 (14-06-2019)

Identifiers

Cite

Meryll Dindin, Yuhei Umeda, Frédéric Chazal. Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks. CanadianAI 2020 - 33rd Canadian Conference on Artificial Intelligence, May 2020, Ottawa, Canada. ⟨hal-02155849⟩
235 View
1319 Download

Altmetric

Share

Gmail Facebook X LinkedIn More