ECG waveform classification using the neural network and wavelet transform

Zumray Dokur*, Tamer Olmez, Ertugrul Yazgan

*Corresponding author for this work

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

8 Citations (Scopus)

Abstract

Two feature extraction methods: Fourier analysis and wavelet analysis for ECG waveform classification are comparatively investigated. Ten different ECG waveforms from MIT/BIH database are classified using a neural network trained by genetic algorithms (NeTGA). One set of feature vectors is formed by using DFT coefficients, and the second set is formed by using wavelet transform (WT) coefficients and their autocorrelation values. Elements of the feature vectors are searched by using dynamic programming (DP) according to the divergence values. Wavelet feature set is found to result in better classification accuracy with less number of nodes. It is observed that with the feature set formed by wavelet analysis, NeTGA gives 99.4% classification performance with 26 nodes after a short training time.

Original languageEnglish
Title of host publicationAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
PublisherIEEE
Pages273
Number of pages1
ISBN (Print)0780356756
Publication statusPublished - 1999
EventProceedings of the 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Fall Meeting of the Biomedical Engineering Society (1st Joint BMES / EMBS) - Atlanta, GA, USA
Duration: 13 Oct 199916 Oct 1999

Publication series

NameAnnual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings
Volume1
ISSN (Print)0589-1019

Conference

ConferenceProceedings of the 1999 IEEE Engineering in Medicine and Biology 21st Annual Conference and the 1999 Fall Meeting of the Biomedical Engineering Society (1st Joint BMES / EMBS)
CityAtlanta, GA, USA
Period13/10/9916/10/99

Fingerprint

Dive into the research topics of 'ECG waveform classification using the neural network and wavelet transform'. Together they form a unique fingerprint.

Cite this