ECG classification using morphological features derived from symbolic dynamics

Chandrakar Kamath

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The aim of this study is to estimate how far the symbolic analysis helps to characterize the nonlinear properties of Electrocardiogram (ECG) signals and thereby discriminate between normal and arrhythmia signals. Differences were found in the properties of the symbol sequence histogram of the resulting patterns and complexity measures of symbol sequences among the five different classes, namely normal, left bundle branch block (LBBB), right bundle branch block (RBBB), premature-ventricular contraction (PVC) and paced signals. The efficacy of the symbolic analysis features is also shown through classification achieved through the neural network which exhibits an average accuracy that exceeds 93.5%.

Original languageEnglish
Pages (from-to)325-336
Number of pages12
JournalInternational Journal of Biomedical Engineering and Technology
Volume9
Issue number4
DOIs
Publication statusPublished - 01-12-2012
Externally publishedYes

Fingerprint

Electrocardiography
Neural networks

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

@article{0c747e07064f4b91a29ff8b384af9611,
title = "ECG classification using morphological features derived from symbolic dynamics",
abstract = "The aim of this study is to estimate how far the symbolic analysis helps to characterize the nonlinear properties of Electrocardiogram (ECG) signals and thereby discriminate between normal and arrhythmia signals. Differences were found in the properties of the symbol sequence histogram of the resulting patterns and complexity measures of symbol sequences among the five different classes, namely normal, left bundle branch block (LBBB), right bundle branch block (RBBB), premature-ventricular contraction (PVC) and paced signals. The efficacy of the symbolic analysis features is also shown through classification achieved through the neural network which exhibits an average accuracy that exceeds 93.5{\%}.",
author = "Chandrakar Kamath",
year = "2012",
month = "12",
day = "1",
doi = "10.1504/IJBET.2012.049217",
language = "English",
volume = "9",
pages = "325--336",
journal = "International Journal of Biomedical Engineering and Technology",
issn = "1752-6418",
publisher = "Inderscience Enterprises Ltd",
number = "4",

}

ECG classification using morphological features derived from symbolic dynamics. / Kamath, Chandrakar.

In: International Journal of Biomedical Engineering and Technology, Vol. 9, No. 4, 01.12.2012, p. 325-336.

Research output: Contribution to journalArticle

TY - JOUR

T1 - ECG classification using morphological features derived from symbolic dynamics

AU - Kamath, Chandrakar

PY - 2012/12/1

Y1 - 2012/12/1

N2 - The aim of this study is to estimate how far the symbolic analysis helps to characterize the nonlinear properties of Electrocardiogram (ECG) signals and thereby discriminate between normal and arrhythmia signals. Differences were found in the properties of the symbol sequence histogram of the resulting patterns and complexity measures of symbol sequences among the five different classes, namely normal, left bundle branch block (LBBB), right bundle branch block (RBBB), premature-ventricular contraction (PVC) and paced signals. The efficacy of the symbolic analysis features is also shown through classification achieved through the neural network which exhibits an average accuracy that exceeds 93.5%.

AB - The aim of this study is to estimate how far the symbolic analysis helps to characterize the nonlinear properties of Electrocardiogram (ECG) signals and thereby discriminate between normal and arrhythmia signals. Differences were found in the properties of the symbol sequence histogram of the resulting patterns and complexity measures of symbol sequences among the five different classes, namely normal, left bundle branch block (LBBB), right bundle branch block (RBBB), premature-ventricular contraction (PVC) and paced signals. The efficacy of the symbolic analysis features is also shown through classification achieved through the neural network which exhibits an average accuracy that exceeds 93.5%.

UR - http://www.scopus.com/inward/record.url?scp=84874172021&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84874172021&partnerID=8YFLogxK

U2 - 10.1504/IJBET.2012.049217

DO - 10.1504/IJBET.2012.049217

M3 - Article

VL - 9

SP - 325

EP - 336

JO - International Journal of Biomedical Engineering and Technology

JF - International Journal of Biomedical Engineering and Technology

SN - 1752-6418

IS - 4

ER -