ECG beat classification using features extracted from Teager energy functions in time and frequency domains

C. Kamath

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

It is hypothesised that a key characteristic of ECG signal is its non-linear dynamic behaviour and that the non-linear component changes more significantly between normal and arrhythmia conditions than the linear component. This study makes an attempt to analyse ECG beats from an energy point of view by accounting for the features derived from non-linear component in time and frequency domains using Teager energy operator (TEO). The key feature of TEO is that it models the energy of the source that generated the signal rather than the energy of the signal itself. Hence any deviations in the regular rhythmic activity of the heart get reflected in the Teager energy function. To show the validity of appropriate choice of features, t-tests and scatter plot are used. The t-tests show significant statistical differences and scatter plot of mean of Teager energy in time domain against mean of Teager energy in frequency domain for the ECG beats evaluated on selected Manipal Institute of Technology-Beth Israel Hospital (MIT-BIH) database, which reveals an excellent separation of the features into five different classes: normal, left bundle branch block, right bundle branch block, premature ventricular contraction and paced beats. The neural network results achieved through only two non-linear features exhibit an average accuracy that exceeds 95%, average sensitivity of about 80% and average specificity of almost 100%.

Original languageEnglish
Pages (from-to)575-581
Number of pages7
JournalIET Signal Processing
Volume5
Issue number6
DOIs
Publication statusPublished - 01-09-2011
Externally publishedYes

Fingerprint

Electrocardiography
Neural networks

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

@article{557a460fa5f74c4aa7849dae006a6458,
title = "ECG beat classification using features extracted from Teager energy functions in time and frequency domains",
abstract = "It is hypothesised that a key characteristic of ECG signal is its non-linear dynamic behaviour and that the non-linear component changes more significantly between normal and arrhythmia conditions than the linear component. This study makes an attempt to analyse ECG beats from an energy point of view by accounting for the features derived from non-linear component in time and frequency domains using Teager energy operator (TEO). The key feature of TEO is that it models the energy of the source that generated the signal rather than the energy of the signal itself. Hence any deviations in the regular rhythmic activity of the heart get reflected in the Teager energy function. To show the validity of appropriate choice of features, t-tests and scatter plot are used. The t-tests show significant statistical differences and scatter plot of mean of Teager energy in time domain against mean of Teager energy in frequency domain for the ECG beats evaluated on selected Manipal Institute of Technology-Beth Israel Hospital (MIT-BIH) database, which reveals an excellent separation of the features into five different classes: normal, left bundle branch block, right bundle branch block, premature ventricular contraction and paced beats. The neural network results achieved through only two non-linear features exhibit an average accuracy that exceeds 95{\%}, average sensitivity of about 80{\%} and average specificity of almost 100{\%}.",
author = "C. Kamath",
year = "2011",
month = "9",
day = "1",
doi = "10.1049/iet-spr.2010.0138",
language = "English",
volume = "5",
pages = "575--581",
journal = "IET Signal Processing",
issn = "1751-9675",
publisher = "Institution of Engineering and Technology",
number = "6",

}

ECG beat classification using features extracted from Teager energy functions in time and frequency domains. / Kamath, C.

In: IET Signal Processing, Vol. 5, No. 6, 01.09.2011, p. 575-581.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ECG beat classification using features extracted from Teager energy functions in time and frequency domains

AU - Kamath, C.

PY - 2011/9/1

Y1 - 2011/9/1

N2 - It is hypothesised that a key characteristic of ECG signal is its non-linear dynamic behaviour and that the non-linear component changes more significantly between normal and arrhythmia conditions than the linear component. This study makes an attempt to analyse ECG beats from an energy point of view by accounting for the features derived from non-linear component in time and frequency domains using Teager energy operator (TEO). The key feature of TEO is that it models the energy of the source that generated the signal rather than the energy of the signal itself. Hence any deviations in the regular rhythmic activity of the heart get reflected in the Teager energy function. To show the validity of appropriate choice of features, t-tests and scatter plot are used. The t-tests show significant statistical differences and scatter plot of mean of Teager energy in time domain against mean of Teager energy in frequency domain for the ECG beats evaluated on selected Manipal Institute of Technology-Beth Israel Hospital (MIT-BIH) database, which reveals an excellent separation of the features into five different classes: normal, left bundle branch block, right bundle branch block, premature ventricular contraction and paced beats. The neural network results achieved through only two non-linear features exhibit an average accuracy that exceeds 95%, average sensitivity of about 80% and average specificity of almost 100%.

AB - It is hypothesised that a key characteristic of ECG signal is its non-linear dynamic behaviour and that the non-linear component changes more significantly between normal and arrhythmia conditions than the linear component. This study makes an attempt to analyse ECG beats from an energy point of view by accounting for the features derived from non-linear component in time and frequency domains using Teager energy operator (TEO). The key feature of TEO is that it models the energy of the source that generated the signal rather than the energy of the signal itself. Hence any deviations in the regular rhythmic activity of the heart get reflected in the Teager energy function. To show the validity of appropriate choice of features, t-tests and scatter plot are used. The t-tests show significant statistical differences and scatter plot of mean of Teager energy in time domain against mean of Teager energy in frequency domain for the ECG beats evaluated on selected Manipal Institute of Technology-Beth Israel Hospital (MIT-BIH) database, which reveals an excellent separation of the features into five different classes: normal, left bundle branch block, right bundle branch block, premature ventricular contraction and paced beats. The neural network results achieved through only two non-linear features exhibit an average accuracy that exceeds 95%, average sensitivity of about 80% and average specificity of almost 100%.

UR - http://www.scopus.com/inward/record.url?scp=80052815286&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052815286&partnerID=8YFLogxK

U2 - 10.1049/iet-spr.2010.0138

DO - 10.1049/iet-spr.2010.0138

M3 - Article

VL - 5

SP - 575

EP - 581

JO - IET Signal Processing

JF - IET Signal Processing

SN - 1751-9675

IS - 6

ER -