ECG signal processing using basis function of independent component analysis

K. L. Park, J. Lee, K. J. Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

This paper is about the study on signal processing of electrocardiogram (ECG) using basic functions extracted by independent component analysis (ICA). The study assumed ECG signals were mixed signals that combined various source signals linearly and used 12 channel signals at sampling rate of 600Hz. Using Independent Component Analysis (ICA), basis functions were extracted that could isolate and detect source signals of ECG signals - QRS complex, P wave, T wave and so on. By applying extracted basis functions to normal and abnormal waveforms, it provided the feature points necessary for diagnosis and separating normal and abnormal signals. It not only showed the method to resolve the problem that signals with specific frequencies were hardly isolated in the ECG signal processing using a wavelet transformation technique, but also indicated ICA could be a useful technique in the ECG signal analysis.

Original languageEnglish (US)
Title of host publicationProceedings of the 3rd IASTED International Conference on Biomedical Engineering 2005
EditorsM.H. Hamza
Pages425-429
Number of pages5
StatePublished - 2005
Externally publishedYes
Event3rd IASTED International Conference on Medical Engineering 2005 - Innsbruck, Austria
Duration: Feb 16 2005Feb 18 2005

Publication series

NameProceedings of the 3rd IASTED International Conference on Biomedical Engineering 2005

Conference

Conference3rd IASTED International Conference on Medical Engineering 2005
Country/TerritoryAustria
CityInnsbruck
Period2/16/052/18/05

Keywords

  • Electrocardiogram signal processing
  • Independent component analysis and basis functions

ASJC Scopus subject areas

  • General Engineering

Fingerprint

Dive into the research topics of 'ECG signal processing using basis function of independent component analysis'. Together they form a unique fingerprint.

Cite this