ECG arrhythmia classification based on optimum-path forest.

Detalhes bibliográficos
Autor(a) principal: Luz, Eduardo José da Silva
Data de Publicação: 2013
Outros Autores: Nunes, Thiago Monteiro, Albuquerque, Victor Hugo Costa de, Papa, João Paulo, Gomes, David Menotti
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Institucional da UFOP
Texto Completo: http://www.repositorio.ufop.br/handle/123456789/4369
https://doi.org/10.1016/j.eswa.2012.12.063
Resumo: An important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e., cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graphbased pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e., support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e., there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis.
id UFOP_1138e0e6125033ee7378806e15d23078
oai_identifier_str oai:repositorio.ufop.br:123456789/4369
network_acronym_str UFOP
network_name_str Repositório Institucional da UFOP
repository_id_str 3233
spelling ECG arrhythmia classification based on optimum-path forest.Feature extractionOptimum path forestSupport vector machineBayesianAn important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e., cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graphbased pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e., support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e., there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis.2015-01-26T11:18:50Z2015-01-26T11:18:50Z2013info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfLUZ, E. J. da S. et al. ECG arrhythmia classification based on optimum-path forest. Expert Systems with Applications, v. 40, p. 3561-3573, jul. 2013. Disponível em: <http://www.sciencedirect.com/science/article/pii/S0957417412013048>. Acesso em: 22 jan. 2015.0957-4174http://www.repositorio.ufop.br/handle/123456789/4369https://doi.org/10.1016/j.eswa.2012.12.063O periódico Expert Systems with Applications concede permissão para depósito do artigo no Repositório Institucional da UFOP. Número da licença: 3552530332283.info:eu-repo/semantics/openAccessLuz, Eduardo José da SilvaNunes, Thiago MonteiroAlbuquerque, Victor Hugo Costa dePapa, João PauloGomes, David Menottiengreponame:Repositório Institucional da UFOPinstname:Universidade Federal de Ouro Preto (UFOP)instacron:UFOP2019-06-12T16:00:40Zoai:repositorio.ufop.br:123456789/4369Repositório InstitucionalPUBhttp://www.repositorio.ufop.br/oai/requestrepositorio@ufop.edu.bropendoar:32332019-06-12T16:00:40Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)false
dc.title.none.fl_str_mv ECG arrhythmia classification based on optimum-path forest.
title ECG arrhythmia classification based on optimum-path forest.
spellingShingle ECG arrhythmia classification based on optimum-path forest.
Luz, Eduardo José da Silva
Feature extraction
Optimum path forest
Support vector machine
Bayesian
title_short ECG arrhythmia classification based on optimum-path forest.
title_full ECG arrhythmia classification based on optimum-path forest.
title_fullStr ECG arrhythmia classification based on optimum-path forest.
title_full_unstemmed ECG arrhythmia classification based on optimum-path forest.
title_sort ECG arrhythmia classification based on optimum-path forest.
author Luz, Eduardo José da Silva
author_facet Luz, Eduardo José da Silva
Nunes, Thiago Monteiro
Albuquerque, Victor Hugo Costa de
Papa, João Paulo
Gomes, David Menotti
author_role author
author2 Nunes, Thiago Monteiro
Albuquerque, Victor Hugo Costa de
Papa, João Paulo
Gomes, David Menotti
author2_role author
author
author
author
dc.contributor.author.fl_str_mv Luz, Eduardo José da Silva
Nunes, Thiago Monteiro
Albuquerque, Victor Hugo Costa de
Papa, João Paulo
Gomes, David Menotti
dc.subject.por.fl_str_mv Feature extraction
Optimum path forest
Support vector machine
Bayesian
topic Feature extraction
Optimum path forest
Support vector machine
Bayesian
description An important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e., cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graphbased pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e., support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e., there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis.
publishDate 2013
dc.date.none.fl_str_mv 2013
2015-01-26T11:18:50Z
2015-01-26T11:18:50Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv LUZ, E. J. da S. et al. ECG arrhythmia classification based on optimum-path forest. Expert Systems with Applications, v. 40, p. 3561-3573, jul. 2013. Disponível em: <http://www.sciencedirect.com/science/article/pii/S0957417412013048>. Acesso em: 22 jan. 2015.
0957-4174
http://www.repositorio.ufop.br/handle/123456789/4369
https://doi.org/10.1016/j.eswa.2012.12.063
identifier_str_mv LUZ, E. J. da S. et al. ECG arrhythmia classification based on optimum-path forest. Expert Systems with Applications, v. 40, p. 3561-3573, jul. 2013. Disponível em: <http://www.sciencedirect.com/science/article/pii/S0957417412013048>. Acesso em: 22 jan. 2015.
0957-4174
url http://www.repositorio.ufop.br/handle/123456789/4369
https://doi.org/10.1016/j.eswa.2012.12.063
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Repositório Institucional da UFOP
instname:Universidade Federal de Ouro Preto (UFOP)
instacron:UFOP
instname_str Universidade Federal de Ouro Preto (UFOP)
instacron_str UFOP
institution UFOP
reponame_str Repositório Institucional da UFOP
collection Repositório Institucional da UFOP
repository.name.fl_str_mv Repositório Institucional da UFOP - Universidade Federal de Ouro Preto (UFOP)
repository.mail.fl_str_mv repositorio@ufop.edu.br
_version_ 1813002819209265152