Unsupervised non-parametric change point detection in electrocardiography

Nikolay Shvetsov, Nazar Buzun, Dmitry V. Dylov

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Citations (Scopus)

Abstract

We propose a new unsupervised and non-parametric method to detect change points in electrocardiography. The detection relies on optimal transport theory combined with topological analysis and the bootstrap procedure. The algorithm is designed to detect changes in virtually any harmonic or a partially harmonic signal and is verified on ECG data streams. We successfully find abnormal or irregular cardiac cycles in the waveforms for the six of the most frequent types of clinical arrhythmias using a single algorithm. Our unsupervised approach reaches the level of performance of the supervised state-of-The-Art techniques. We provide conceptual justification for the efficiency of the method.

Original languageEnglish
Title of host publication32nd International Conference on Scientific and Statistical Database Management, SSDBM 2020, Proceedings
EditorsElaheh Pourabbas, Dimitris Sacharidis, Kurt Stockinger, Thanasis Vergoulis
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450388146
DOIs
Publication statusPublished - 7 Jul 2020
Event32nd International Conference on Scientific and Statistical Database Management, SSDBM 2020 - Virtual, Online, Austria
Duration: 7 Jul 20209 Jul 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference32nd International Conference on Scientific and Statistical Database Management, SSDBM 2020
Country/TerritoryAustria
CityVirtual, Online
Period7/07/209/07/20

Keywords

  • Anomaly detection
  • Arrhythmia detection
  • Bootstrap
  • Data streams
  • Optimal transport
  • Periodic and quasi-periodic signals
  • Topological data analysis
  • Unsupervised learning.
  • Wasserstein distance

Fingerprint

Dive into the research topics of 'Unsupervised non-parametric change point detection in electrocardiography'. Together they form a unique fingerprint.

Cite this