Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control

Detalhes bibliográficos
Autor(a) principal: Boris, F. A. [UNESP]
Data de Publicação: 2022
Outros Autores: Xavier, R. T. [UNESP], Codinhoto, J. P. [UNESP], Blanco, J. E. [UNESP], Sanches, M. A.A. [UNESP], Alves, C. A. [UNESP], Carvalho, A. A. [UNESP]
Tipo de documento: Artigo de conferência
Idioma: eng
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/978-3-030-70601-2_272
http://hdl.handle.net/11449/239949
Resumo: The classification of surface electromyographic signals is an important task for the control of active upper-limb prostheses. This article aims to analyze and evaluate techniques to classify surface electromyographic signals for the control of upper limb prostheses. The electromyographic signals were obtained from a public database. Machine learning algorithms and seven features of the EMG signal were used to classify the signals. Random samples were created for the training and testing tasks in subsets with 80% and 20% of the data, respectively. Machine learning algorithms for classifying electromyographic signals were trained with different configurations, allowing evaluation between combinations of techniques and parameters. It was observed that signal feature extraction is an important process for obtaining accurate results. The best result produced an average accuracy of 95% with a Random Forest classifier and three features extracted from surface electromyography signals of two channels.
id UNSP_2e44b2845fda97663518c1a0eeccb1d0
oai_identifier_str oai:repositorio.unesp.br:11449/239949
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Electromyography Classification Techniques Analysis for Upper Limb Prostheses ControlEMG classifierMachine learningProstheses controlRandom forestUpper limbThe classification of surface electromyographic signals is an important task for the control of active upper-limb prostheses. This article aims to analyze and evaluate techniques to classify surface electromyographic signals for the control of upper limb prostheses. The electromyographic signals were obtained from a public database. Machine learning algorithms and seven features of the EMG signal were used to classify the signals. Random samples were created for the training and testing tasks in subsets with 80% and 20% of the data, respectively. Machine learning algorithms for classifying electromyographic signals were trained with different configurations, allowing evaluation between combinations of techniques and parameters. It was observed that signal feature extraction is an important process for obtaining accurate results. The best result produced an average accuracy of 95% with a Random Forest classifier and three features extracted from surface electromyography signals of two channels.School of Engineering São Paulo State University (Unesp)School of Engineering São Paulo State University (Unesp)Universidade Estadual Paulista (UNESP)Boris, F. A. [UNESP]Xavier, R. T. [UNESP]Codinhoto, J. P. [UNESP]Blanco, J. E. [UNESP]Sanches, M. A.A. [UNESP]Alves, C. A. [UNESP]Carvalho, A. A. [UNESP]2023-03-01T19:54:45Z2023-03-01T19:54:45Z2022-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject1865-1872http://dx.doi.org/10.1007/978-3-030-70601-2_272IFMBE Proceedings, v. 83, p. 1865-1872.1433-92771680-0737http://hdl.handle.net/11449/23994910.1007/978-3-030-70601-2_2722-s2.0-85128938562Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengIFMBE Proceedingsinfo:eu-repo/semantics/openAccess2023-03-01T19:54:45Zoai:repositorio.unesp.br:11449/239949Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T17:26:23.879408Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
title Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
spellingShingle Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
Boris, F. A. [UNESP]
EMG classifier
Machine learning
Prostheses control
Random forest
Upper limb
title_short Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
title_full Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
title_fullStr Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
title_full_unstemmed Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
title_sort Electromyography Classification Techniques Analysis for Upper Limb Prostheses Control
author Boris, F. A. [UNESP]
author_facet Boris, F. A. [UNESP]
Xavier, R. T. [UNESP]
Codinhoto, J. P. [UNESP]
Blanco, J. E. [UNESP]
Sanches, M. A.A. [UNESP]
Alves, C. A. [UNESP]
Carvalho, A. A. [UNESP]
author_role author
author2 Xavier, R. T. [UNESP]
Codinhoto, J. P. [UNESP]
Blanco, J. E. [UNESP]
Sanches, M. A.A. [UNESP]
Alves, C. A. [UNESP]
Carvalho, A. A. [UNESP]
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (UNESP)
dc.contributor.author.fl_str_mv Boris, F. A. [UNESP]
Xavier, R. T. [UNESP]
Codinhoto, J. P. [UNESP]
Blanco, J. E. [UNESP]
Sanches, M. A.A. [UNESP]
Alves, C. A. [UNESP]
Carvalho, A. A. [UNESP]
dc.subject.por.fl_str_mv EMG classifier
Machine learning
Prostheses control
Random forest
Upper limb
topic EMG classifier
Machine learning
Prostheses control
Random forest
Upper limb
description The classification of surface electromyographic signals is an important task for the control of active upper-limb prostheses. This article aims to analyze and evaluate techniques to classify surface electromyographic signals for the control of upper limb prostheses. The electromyographic signals were obtained from a public database. Machine learning algorithms and seven features of the EMG signal were used to classify the signals. Random samples were created for the training and testing tasks in subsets with 80% and 20% of the data, respectively. Machine learning algorithms for classifying electromyographic signals were trained with different configurations, allowing evaluation between combinations of techniques and parameters. It was observed that signal feature extraction is an important process for obtaining accurate results. The best result produced an average accuracy of 95% with a Random Forest classifier and three features extracted from surface electromyography signals of two channels.
publishDate 2022
dc.date.none.fl_str_mv 2022-01-01
2023-03-01T19:54:45Z
2023-03-01T19:54:45Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1007/978-3-030-70601-2_272
IFMBE Proceedings, v. 83, p. 1865-1872.
1433-9277
1680-0737
http://hdl.handle.net/11449/239949
10.1007/978-3-030-70601-2_272
2-s2.0-85128938562
url http://dx.doi.org/10.1007/978-3-030-70601-2_272
http://hdl.handle.net/11449/239949
identifier_str_mv IFMBE Proceedings, v. 83, p. 1865-1872.
1433-9277
1680-0737
10.1007/978-3-030-70601-2_272
2-s2.0-85128938562
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv IFMBE Proceedings
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 1865-1872
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_ 1808128811951194112