Decision support system for arrhythmia beats using ECG signals with DCT, DWT and EMD methods

A comparative study

Usha Desai, Roshan Joy Martis, C. Gurudas Nayak, G. Seshikala, K. Sarika, Ranjan Shetty K

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Electrocardiogram (ECG) signal is a non-invasive method, used to diagnose the patients with cardiac abnormalities. The subjective evaluation of interval and amplitude of ECG by physician can be tedious, time consuming, and susceptible to observer bias. ECG signals are generated due to the excitation of many cardiac myocytes and hence resultant signals are non-linear in nature. These subtle changes can be well represented and discriminated in transform and non-linear domains. In this paper, performance of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) methods are compared for automated diagnosis of five classes namely Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) beats. Six different approaches: (i) Principal Components (PCs) on DCT, (ii) Independent Components (ICs) on DCT, (iii) PCs on DWT, (iv) ICs on DWT, (v) PCs on EMD and (vi) ICs on EMD are employed in this work. Clinically significant features are selected using ANOVA test (p<0.0001) and fed to k-Nearest Neighbor (k-NN) classifier. We have obtained a classification accuracy of 99.77% using ICs on DWT method. Consistency of performance is evaluated using Cohen's kappa statistic. Developed approach is robust, accurate and can be employed for mass diagnosis of cardiac healthcare.

Original languageEnglish
Article number1640012
JournalJournal of Mechanics in Medicine and Biology
Volume16
Issue number1
DOIs
Publication statusPublished - 01-02-2016
Externally publishedYes

Fingerprint

Discrete cosine transforms
Discrete wavelet transforms
Decision support systems
Electrocardiography
Decomposition
Analysis of variance (ANOVA)
Classifiers
Fusion reactions
Statistics

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering

Cite this

Desai, Usha ; Martis, Roshan Joy ; Gurudas Nayak, C. ; Seshikala, G. ; Sarika, K. ; Shetty K, Ranjan. / Decision support system for arrhythmia beats using ECG signals with DCT, DWT and EMD methods : A comparative study. In: Journal of Mechanics in Medicine and Biology. 2016 ; Vol. 16, No. 1.
@article{74eb440454d04b12b0c34ffc0c4e58fe,
title = "Decision support system for arrhythmia beats using ECG signals with DCT, DWT and EMD methods: A comparative study",
abstract = "Electrocardiogram (ECG) signal is a non-invasive method, used to diagnose the patients with cardiac abnormalities. The subjective evaluation of interval and amplitude of ECG by physician can be tedious, time consuming, and susceptible to observer bias. ECG signals are generated due to the excitation of many cardiac myocytes and hence resultant signals are non-linear in nature. These subtle changes can be well represented and discriminated in transform and non-linear domains. In this paper, performance of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) methods are compared for automated diagnosis of five classes namely Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) beats. Six different approaches: (i) Principal Components (PCs) on DCT, (ii) Independent Components (ICs) on DCT, (iii) PCs on DWT, (iv) ICs on DWT, (v) PCs on EMD and (vi) ICs on EMD are employed in this work. Clinically significant features are selected using ANOVA test (p<0.0001) and fed to k-Nearest Neighbor (k-NN) classifier. We have obtained a classification accuracy of 99.77{\%} using ICs on DWT method. Consistency of performance is evaluated using Cohen's kappa statistic. Developed approach is robust, accurate and can be employed for mass diagnosis of cardiac healthcare.",
author = "Usha Desai and Martis, {Roshan Joy} and {Gurudas Nayak}, C. and G. Seshikala and K. Sarika and {Shetty K}, Ranjan",
year = "2016",
month = "2",
day = "1",
doi = "10.1142/S0219519416400121",
language = "English",
volume = "16",
journal = "Journal of Mechanics in Medicine and Biology",
issn = "0219-5194",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "1",

}

Decision support system for arrhythmia beats using ECG signals with DCT, DWT and EMD methods : A comparative study. / Desai, Usha; Martis, Roshan Joy; Gurudas Nayak, C.; Seshikala, G.; Sarika, K.; Shetty K, Ranjan.

In: Journal of Mechanics in Medicine and Biology, Vol. 16, No. 1, 1640012, 01.02.2016.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Decision support system for arrhythmia beats using ECG signals with DCT, DWT and EMD methods

T2 - A comparative study

AU - Desai, Usha

AU - Martis, Roshan Joy

AU - Gurudas Nayak, C.

AU - Seshikala, G.

AU - Sarika, K.

AU - Shetty K, Ranjan

PY - 2016/2/1

Y1 - 2016/2/1

N2 - Electrocardiogram (ECG) signal is a non-invasive method, used to diagnose the patients with cardiac abnormalities. The subjective evaluation of interval and amplitude of ECG by physician can be tedious, time consuming, and susceptible to observer bias. ECG signals are generated due to the excitation of many cardiac myocytes and hence resultant signals are non-linear in nature. These subtle changes can be well represented and discriminated in transform and non-linear domains. In this paper, performance of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) methods are compared for automated diagnosis of five classes namely Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) beats. Six different approaches: (i) Principal Components (PCs) on DCT, (ii) Independent Components (ICs) on DCT, (iii) PCs on DWT, (iv) ICs on DWT, (v) PCs on EMD and (vi) ICs on EMD are employed in this work. Clinically significant features are selected using ANOVA test (p<0.0001) and fed to k-Nearest Neighbor (k-NN) classifier. We have obtained a classification accuracy of 99.77% using ICs on DWT method. Consistency of performance is evaluated using Cohen's kappa statistic. Developed approach is robust, accurate and can be employed for mass diagnosis of cardiac healthcare.

AB - Electrocardiogram (ECG) signal is a non-invasive method, used to diagnose the patients with cardiac abnormalities. The subjective evaluation of interval and amplitude of ECG by physician can be tedious, time consuming, and susceptible to observer bias. ECG signals are generated due to the excitation of many cardiac myocytes and hence resultant signals are non-linear in nature. These subtle changes can be well represented and discriminated in transform and non-linear domains. In this paper, performance of Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) and Empirical Mode Decomposition (EMD) methods are compared for automated diagnosis of five classes namely Non-ectopic (N), Supraventricular ectopic (S), Ventricular ectopic (V), Fusion (F) and Unknown (U) beats. Six different approaches: (i) Principal Components (PCs) on DCT, (ii) Independent Components (ICs) on DCT, (iii) PCs on DWT, (iv) ICs on DWT, (v) PCs on EMD and (vi) ICs on EMD are employed in this work. Clinically significant features are selected using ANOVA test (p<0.0001) and fed to k-Nearest Neighbor (k-NN) classifier. We have obtained a classification accuracy of 99.77% using ICs on DWT method. Consistency of performance is evaluated using Cohen's kappa statistic. Developed approach is robust, accurate and can be employed for mass diagnosis of cardiac healthcare.

UR - http://www.scopus.com/inward/record.url?scp=84976251271&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976251271&partnerID=8YFLogxK

U2 - 10.1142/S0219519416400121

DO - 10.1142/S0219519416400121

M3 - Article

VL - 16

JO - Journal of Mechanics in Medicine and Biology

JF - Journal of Mechanics in Medicine and Biology

SN - 0219-5194

IS - 1

M1 - 1640012

ER -