Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.4025/actascitechnol.v44i1.60386 http://hdl.handle.net/11449/242089 |
Resumo: | Premature Ventricular Contractions (PVC) arrhythmias can be associated with sudden death and acute myocardial infarction, occurring in 50% of the population for Holter monitoring. PVC patterns are very hard to be recognized since their waveforms can be confused with other heartbeats, such as Right and Left Bundle Branch Blocks. This work proposes a new approach for PVC recognition, based on Gaussian Naive Bayes algorithm and AMUSE (Algorithm for Multiple Unknown Signal Extraction), which is a method for the blind source separation problem. This approach provides a set of attributes that are combined by Linear Discriminant Analysis, allowing the training of an ensemble learning. The Analytic Hierarchy Process weights each learned model according to its importance, obtained from the performance metrics. This approach has some advantages over baseline methods since it does not use a pre-processing stage and employs a simple machine learning model trained using only two parameters for each feature. Using a standard dataset for training and test phases, the proposed approach achieves 98.75% accuracy, 90.65% sensitivity, and 99.46% specificity. The best performance was 99.57% accuracy, 98.64% sensitivity, and 99.65% specificity for other datasets. In general, the proposed approach is better than 66% of the state-of-the-art methods concerning accuracy. |
id |
UNSP_7207e98cba071061f5dfe152727b2630 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/242089 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy processArrhythmia recognitiondecision making in healthensemble learningheart diseasesmachine learningPremature Ventricular Contractions (PVC) arrhythmias can be associated with sudden death and acute myocardial infarction, occurring in 50% of the population for Holter monitoring. PVC patterns are very hard to be recognized since their waveforms can be confused with other heartbeats, such as Right and Left Bundle Branch Blocks. This work proposes a new approach for PVC recognition, based on Gaussian Naive Bayes algorithm and AMUSE (Algorithm for Multiple Unknown Signal Extraction), which is a method for the blind source separation problem. This approach provides a set of attributes that are combined by Linear Discriminant Analysis, allowing the training of an ensemble learning. The Analytic Hierarchy Process weights each learned model according to its importance, obtained from the performance metrics. This approach has some advantages over baseline methods since it does not use a pre-processing stage and employs a simple machine learning model trained using only two parameters for each feature. Using a standard dataset for training and test phases, the proposed approach achieves 98.75% accuracy, 90.65% sensitivity, and 99.46% specificity. The best performance was 99.57% accuracy, 98.64% sensitivity, and 99.65% specificity for other datasets. In general, the proposed approach is better than 66% of the state-of-the-art methods concerning accuracy.Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)Departamento de Engenharia Elétrica Universidade Estadual Paulista “Júlio de Mesquita Filho”, Av. Brasil, 56, Centro, São PauloCurso de Matemática Universidade Federal de Mato Grosso do Sul, Mato Grosso do SulEngenharia Eletrônica e de Telecomunicações e Engenharia Aeronáutica Universidade Estadual Paulista “Júlio de Mesquita Filho”, São PauloDepartamento de Engenharia Elétrica Universidade Estadual Paulista “Júlio de Mesquita Filho”, Av. Brasil, 56, Centro, São PauloEngenharia Eletrônica e de Telecomunicações e Engenharia Aeronáutica Universidade Estadual Paulista “Júlio de Mesquita Filho”, São PauloCAPES: 001Universidade Estadual Paulista (UNESP)Universidade Federal de Mato Grosso do Sul (UFMS)de Oliveira, Bruno Rodrigues [UNESP]Duarte, Marco Aparecido QueirozFilho, Jozue Vieira [UNESP]2023-03-02T08:37:58Z2023-03-02T08:37:58Z2022-01-12info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.4025/actascitechnol.v44i1.60386Acta Scientiarum - Technology, v. 44.1807-86641806-2563http://hdl.handle.net/11449/24208910.4025/actascitechnol.v44i1.603862-s2.0-85135054926Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengActa Scientiarum - Technologyinfo:eu-repo/semantics/openAccess2024-07-04T19:06:25Zoai:repositorio.unesp.br:11449/242089Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T18:49:20.499155Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
title |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
spellingShingle |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process de Oliveira, Bruno Rodrigues [UNESP] Arrhythmia recognition decision making in health ensemble learning heart diseases machine learning |
title_short |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
title_full |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
title_fullStr |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
title_full_unstemmed |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
title_sort |
Premature ventricular contraction recognition using blind source separation and ensemble gaussian naive bayes weighted by analytic hierarchy process |
author |
de Oliveira, Bruno Rodrigues [UNESP] |
author_facet |
de Oliveira, Bruno Rodrigues [UNESP] Duarte, Marco Aparecido Queiroz Filho, Jozue Vieira [UNESP] |
author_role |
author |
author2 |
Duarte, Marco Aparecido Queiroz Filho, Jozue Vieira [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade Federal de Mato Grosso do Sul (UFMS) |
dc.contributor.author.fl_str_mv |
de Oliveira, Bruno Rodrigues [UNESP] Duarte, Marco Aparecido Queiroz Filho, Jozue Vieira [UNESP] |
dc.subject.por.fl_str_mv |
Arrhythmia recognition decision making in health ensemble learning heart diseases machine learning |
topic |
Arrhythmia recognition decision making in health ensemble learning heart diseases machine learning |
description |
Premature Ventricular Contractions (PVC) arrhythmias can be associated with sudden death and acute myocardial infarction, occurring in 50% of the population for Holter monitoring. PVC patterns are very hard to be recognized since their waveforms can be confused with other heartbeats, such as Right and Left Bundle Branch Blocks. This work proposes a new approach for PVC recognition, based on Gaussian Naive Bayes algorithm and AMUSE (Algorithm for Multiple Unknown Signal Extraction), which is a method for the blind source separation problem. This approach provides a set of attributes that are combined by Linear Discriminant Analysis, allowing the training of an ensemble learning. The Analytic Hierarchy Process weights each learned model according to its importance, obtained from the performance metrics. This approach has some advantages over baseline methods since it does not use a pre-processing stage and employs a simple machine learning model trained using only two parameters for each feature. Using a standard dataset for training and test phases, the proposed approach achieves 98.75% accuracy, 90.65% sensitivity, and 99.46% specificity. The best performance was 99.57% accuracy, 98.64% sensitivity, and 99.65% specificity for other datasets. In general, the proposed approach is better than 66% of the state-of-the-art methods concerning accuracy. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-01-12 2023-03-02T08:37:58Z 2023-03-02T08:37:58Z |
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 |
http://dx.doi.org/10.4025/actascitechnol.v44i1.60386 Acta Scientiarum - Technology, v. 44. 1807-8664 1806-2563 http://hdl.handle.net/11449/242089 10.4025/actascitechnol.v44i1.60386 2-s2.0-85135054926 |
url |
http://dx.doi.org/10.4025/actascitechnol.v44i1.60386 http://hdl.handle.net/11449/242089 |
identifier_str_mv |
Acta Scientiarum - Technology, v. 44. 1807-8664 1806-2563 10.4025/actascitechnol.v44i1.60386 2-s2.0-85135054926 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Acta Scientiarum - Technology |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128984484937728 |