Feature selection algorithm for ECG signals using Range-Overlaps Method

Yun Chi Yeh, Wen June Wang, Che Wun Chiou

Research output: Contribution to journalArticlepeer-review

40 Scopus citations

Abstract

This study proposes a simple and reliable feature selection algorithm for ECG signals, termed the Range-Overlaps Method. The proposed method has the advantages of good detection results, no complex mathematic computations, fast and low memory space and low time complexity. Both cluster analysis and fuzzy logic methods are applied to evaluate the performance of the proposed method. Experimental results show that the total classification accuracy is above 93%. Thus, the proposed algorithm provides an efficient, simple and fast method for feature selection on ECG signals.

Original languageEnglish
Pages (from-to)3499-3512
Number of pages14
JournalExpert Systems with Applications
Volume37
Issue number4
DOIs
StatePublished - Apr 2010

Keywords

  • Cluster analysis
  • ECG signal
  • Feature selection
  • Fuzzy logic methods
  • MIT-BIH arrhythmia database

Fingerprint

Dive into the research topics of 'Feature selection algorithm for ECG signals using Range-Overlaps Method'. Together they form a unique fingerprint.

Cite this