University of Hertfordshire

Wavelet-Based Kernel Construction for Heart Disease Classification

Research output: Contribution to journalArticle

Standard

Wavelet-Based Kernel Construction for Heart Disease Classification. / Nguyen, Thanh-Nghia ; Nguyen, Thanh-Hai; Nguyen, Manh-Hung; Livatino, Salvatore.

In: AEEE Advances in Electrical and Electronic Engineering, Vol. 17, No. 3, 09.2019, p. 306-319.

Research output: Contribution to journalArticle

Harvard

APA

Vancouver

Author

Nguyen, Thanh-Nghia ; Nguyen, Thanh-Hai ; Nguyen, Manh-Hung ; Livatino, Salvatore. / Wavelet-Based Kernel Construction for Heart Disease Classification. In: AEEE Advances in Electrical and Electronic Engineering. 2019 ; Vol. 17, No. 3. pp. 306-319.

Bibtex

@article{133cb724618844d79812505ad61cae3a,
title = "Wavelet-Based Kernel Construction for Heart Disease Classification",
abstract = "Heart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is constructed based on wavelet coefficients of heartbeat signals for a classifier with high performance. In particular, a wavelet packet decomposition algorithm is applied to heartbeat signals to obtain the Approximation and Detail coefficients, which are used to calculate the parameters of the kernel. A principal component analysis algorithm with the wavelet-based kernel is employed to choose the main features of the heartbeat signals for the input of the classifier. In addition, a neural network with three hidden layers in the classifier is utilized for classifying five types of heart disease. The electrocardiogram signals in nine patients obtained from the MIT-BIH database are used to test the proposed classifier. In order to evaluate the performance of the classifier, a multi-class confusion matrix is applied to produce the performance indexes, including the Accuracy, Recall, Precision, and F1 score. The experimental results show that the proposed method gives good results for the classification of the five mentioned types of heart disease.",
keywords = "Back-propagation neural network, Electrocardiogram signals, Heart disease classification, Wavelet coefficients, Wavelet-based kernel principal component analysis",
author = "Thanh-Nghia Nguyen and Thanh-Hai Nguyen and Manh-Hung Nguyen and Salvatore Livatino",
note = "{\circledC} 2019 ADVANCES IN ELECTRICAL AND ELECTRONIC ENGINEERING",
year = "2019",
month = "9",
doi = "10.15598/aeee.v17i3.3270",
language = "English",
volume = "17",
pages = "306--319",
journal = "AEEE Advances in Electrical and Electronic Engineering",
issn = "1804-3119",
publisher = "VSB-Technical University of Ostrava",
number = "3",

}

RIS

TY - JOUR

T1 - Wavelet-Based Kernel Construction for Heart Disease Classification

AU - Nguyen, Thanh-Nghia

AU - Nguyen, Thanh-Hai

AU - Nguyen, Manh-Hung

AU - Livatino, Salvatore

N1 - © 2019 ADVANCES IN ELECTRICAL AND ELECTRONIC ENGINEERING

PY - 2019/9

Y1 - 2019/9

N2 - Heart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is constructed based on wavelet coefficients of heartbeat signals for a classifier with high performance. In particular, a wavelet packet decomposition algorithm is applied to heartbeat signals to obtain the Approximation and Detail coefficients, which are used to calculate the parameters of the kernel. A principal component analysis algorithm with the wavelet-based kernel is employed to choose the main features of the heartbeat signals for the input of the classifier. In addition, a neural network with three hidden layers in the classifier is utilized for classifying five types of heart disease. The electrocardiogram signals in nine patients obtained from the MIT-BIH database are used to test the proposed classifier. In order to evaluate the performance of the classifier, a multi-class confusion matrix is applied to produce the performance indexes, including the Accuracy, Recall, Precision, and F1 score. The experimental results show that the proposed method gives good results for the classification of the five mentioned types of heart disease.

AB - Heart disease classification plays an important role in clinical diagnoses. The performance improvement of an Electrocardiogram classifier is therefore of great relevance, but it is a challenging task too. This paper proposes a novel classification algorithm using the kernel method. A kernel is constructed based on wavelet coefficients of heartbeat signals for a classifier with high performance. In particular, a wavelet packet decomposition algorithm is applied to heartbeat signals to obtain the Approximation and Detail coefficients, which are used to calculate the parameters of the kernel. A principal component analysis algorithm with the wavelet-based kernel is employed to choose the main features of the heartbeat signals for the input of the classifier. In addition, a neural network with three hidden layers in the classifier is utilized for classifying five types of heart disease. The electrocardiogram signals in nine patients obtained from the MIT-BIH database are used to test the proposed classifier. In order to evaluate the performance of the classifier, a multi-class confusion matrix is applied to produce the performance indexes, including the Accuracy, Recall, Precision, and F1 score. The experimental results show that the proposed method gives good results for the classification of the five mentioned types of heart disease.

KW - Back-propagation neural network

KW - Electrocardiogram signals

KW - Heart disease classification

KW - Wavelet coefficients

KW - Wavelet-based kernel principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=85069507272&partnerID=8YFLogxK

U2 - 10.15598/aeee.v17i3.3270

DO - 10.15598/aeee.v17i3.3270

M3 - Article

VL - 17

SP - 306

EP - 319

JO - AEEE Advances in Electrical and Electronic Engineering

JF - AEEE Advances in Electrical and Electronic Engineering

SN - 1804-3119

IS - 3

ER -