Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines

Chia Ping Shen, Wen-Chung Kao, Yueh Yiing Yang, Ming Chai Hsu, Yuan Ting Wu, Feipei Lai

Research output: Contribution to journalArticle

35 Citations (Scopus)

Abstract

The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92%, and the recognition rate for each class is kept above 92%.

Original languageEnglish
Pages (from-to)7845-7852
Number of pages8
JournalExpert Systems with Applications
Volume39
Issue number9
DOIs
Publication statusPublished - 2012 Jul 1

Fingerprint

Electrocardiography
Support vector machines
Feature extraction
Classifiers
Wavelet transforms
Testing

Keywords

  • Adaptive feature extraction
  • Electrocardiogram (ECG)
  • Support vector machines (SVMs)
  • k-Means clustering

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines. / Shen, Chia Ping; Kao, Wen-Chung; Yang, Yueh Yiing; Hsu, Ming Chai; Wu, Yuan Ting; Lai, Feipei.

In: Expert Systems with Applications, Vol. 39, No. 9, 01.07.2012, p. 7845-7852.

Research output: Contribution to journalArticle

Shen, Chia Ping ; Kao, Wen-Chung ; Yang, Yueh Yiing ; Hsu, Ming Chai ; Wu, Yuan Ting ; Lai, Feipei. / Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines. In: Expert Systems with Applications. 2012 ; Vol. 39, No. 9. pp. 7845-7852.
@article{08a1ecc4e822437cb5d16450c4a53b9f,
title = "Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines",
abstract = "The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92{\%}, and the recognition rate for each class is kept above 92{\%}.",
keywords = "Adaptive feature extraction, Electrocardiogram (ECG), Support vector machines (SVMs), k-Means clustering",
author = "Shen, {Chia Ping} and Wen-Chung Kao and Yang, {Yueh Yiing} and Hsu, {Ming Chai} and Wu, {Yuan Ting} and Feipei Lai",
year = "2012",
month = "7",
day = "1",
doi = "10.1016/j.eswa.2012.01.093",
language = "English",
volume = "39",
pages = "7845--7852",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "9",

}

TY - JOUR

T1 - Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines

AU - Shen, Chia Ping

AU - Kao, Wen-Chung

AU - Yang, Yueh Yiing

AU - Hsu, Ming Chai

AU - Wu, Yuan Ting

AU - Lai, Feipei

PY - 2012/7/1

Y1 - 2012/7/1

N2 - The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92%, and the recognition rate for each class is kept above 92%.

AB - The electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. Many algorithms have been proposed, however, the recognition rate is still unsatisfactory due to unreliable feature extraction in signal characteristic analysis or poor generalization capability of the classifier. In this paper, we propose a system for cardiac arrhythmia detection in ECGs with adaptive feature selection and modified support vector machines (SVMs). Wavelet transform-based coefficients and signal amplitude/interval parameters are first enumerated as candidates, but only a few specific ones are adaptively selected for the classification of each class pair. A new classifier, which integrates k-means clustering, one-against-one SVMs, and a modified majority voting mechanism, is proposed to further improve the recognition rate for extremely similar classes. The experimental results show that the proposed ECG analysis approach can obtain a higher recognition rate than the published approaches. By testing the system with more than 100,000 samples in MIT-BIH arrhythmia database, the average recognition rate is 98.92%, and the recognition rate for each class is kept above 92%.

KW - Adaptive feature extraction

KW - Electrocardiogram (ECG)

KW - Support vector machines (SVMs)

KW - k-Means clustering

UR - http://www.scopus.com/inward/record.url?scp=84862808925&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84862808925&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2012.01.093

DO - 10.1016/j.eswa.2012.01.093

M3 - Article

AN - SCOPUS:84862808925

VL - 39

SP - 7845

EP - 7852

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 9

ER -