ECG feature extraction using optimal mother wavelet

B. Castro, D. Kogan, A. B. Geva

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

70 Scopus citations

Abstract

The main advantage related to wavelet transforms is that they are localized both in the frequency and time domains. This paper presents an algorithm, based on the wavelet transform, for feature extraction from the electrocardiograph (ECG) signal and recognition of abnormal heartbeats. A method for choosing an optimal mother wavelet from a set of orthogonal and bi-orthogonal wavelet filter bank by means of the best correlation with the ECG signal, was developed. The ECG signal is first denoised by a soft or hard threshold with limitation of 99.99 reconstructs ability and then each PQRST cycle is decomposed into a coefficients vector by the optimal wavelet function. The Coefficients, approximations of the last scale level and the details of the all levels, are used for the ECG analyzed. The coefficients of each cycle are divided into three segments, which are related to the P-wave, QRS complex and T- wave, and summed to obtained a features vector of the signal cycles.

Original languageEnglish
Title of host publication21st IEEE Convention of the Electrical and Electronic Engineers in Israel, Proceedings
PublisherInstitute of Electrical and Electronics Engineers
Pages346-350
Number of pages5
ISBN (Electronic)0780358422, 9780780358423
DOIs
StatePublished - 1 Jan 2000
Event21st IEEE Convention of the Electrical and Electronic Engineers in Israel, IEEEI 2000 - Tel-Aviv, Israel
Duration: 11 Apr 200012 Apr 2000

Publication series

Name21st IEEE Convention of the Electrical and Electronic Engineers in Israel, Proceedings

Conference

Conference21st IEEE Convention of the Electrical and Electronic Engineers in Israel, IEEEI 2000
Country/TerritoryIsrael
CityTel-Aviv
Period11/04/0012/04/00

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'ECG feature extraction using optimal mother wavelet'. Together they form a unique fingerprint.

Cite this