Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment
Autor(a) principal: | |
---|---|
Data de Publicação: | 2016 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/150443 |
Resumo: | Surface electromyography (sEMG) analysis is becoming increasingly popular in a broad variety of applications. Despite satisfactory classification rates are frequently obtained through supervised machine learning (ML) algorithms, there are some issues mostly related to the data acquisition which are not properly addressed in current studies. In this paper we present a method capable of mitigate the noise in the sEMG acquisition caused mainly by loose or misplaced non-invasive electrodes. To address this issue we propose a stage of pre-processing capable of being adapted on a variety of classifiers. The proposed method is capable of identify this two anomalies in the signal and provide the data to retrain the classifier, discarding the problematic channels. Once the method is retrained using only the most relevant channels it is possible to increase the accuracy rate of the ML method. The method was tested on a database containing five ablebodied subjects and four amputee subjects of both sexes. The average classification accuracy for the adaptive input selection method was 83,96 6,5% for the able-bodied subjects and 61,15 7,7% for the amputees subjects against 72,06 8,0% in ablebodied subjects and 39,77 10,6% for the amputees subjects considering the non-adaptive approach. Both systems make use of the proposed method to classify 9 distinguish upper-limb movements with different degrees of freedom. |
id |
UFRGS-2_b688e3d251d448596d5538e013cb4d3a |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/150443 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Favieiro, Gabriela WinklerCene, Vinicius HornBalbinot, Alexandre2017-01-05T02:30:29Z20162318-4531http://hdl.handle.net/10183/150443001008973Surface electromyography (sEMG) analysis is becoming increasingly popular in a broad variety of applications. Despite satisfactory classification rates are frequently obtained through supervised machine learning (ML) algorithms, there are some issues mostly related to the data acquisition which are not properly addressed in current studies. In this paper we present a method capable of mitigate the noise in the sEMG acquisition caused mainly by loose or misplaced non-invasive electrodes. To address this issue we propose a stage of pre-processing capable of being adapted on a variety of classifiers. The proposed method is capable of identify this two anomalies in the signal and provide the data to retrain the classifier, discarding the problematic channels. Once the method is retrained using only the most relevant channels it is possible to increase the accuracy rate of the ML method. The method was tested on a database containing five ablebodied subjects and four amputee subjects of both sexes. The average classification accuracy for the adaptive input selection method was 83,96 6,5% for the able-bodied subjects and 61,15 7,7% for the amputees subjects against 72,06 8,0% in ablebodied subjects and 39,77 10,6% for the amputees subjects considering the non-adaptive approach. Both systems make use of the proposed method to classify 9 distinguish upper-limb movements with different degrees of freedom.application/pdfengBrazilian journal of instrumentation and control [recurso eletrônico] = Revista brasileira de instrumentação e controle. Curitiba. Vol. 4, n. 1 (2016), p. 21-26Extremidade superiorEletromiografiaRedes neuraisElectrode assortmentUpper-limb signalNeural networkAuto-adaptive methodsSurface electromyographySelf-adaptive method for sEMG movement classification based on continuous optimal electrode assortmentinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/otherinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSORIGINAL001008973.pdf001008973.pdfTexto completo (inglês)application/pdf451921http://www.lume.ufrgs.br/bitstream/10183/150443/1/001008973.pdf93f90eae1ed99ebf3ca75d7833734037MD51TEXT001008973.pdf.txt001008973.pdf.txtExtracted Texttext/plain32457http://www.lume.ufrgs.br/bitstream/10183/150443/2/001008973.pdf.txt13fe019d035b8c43e4c14d6cbb7d57afMD52THUMBNAIL001008973.pdf.jpg001008973.pdf.jpgGenerated Thumbnailimage/jpeg2097http://www.lume.ufrgs.br/bitstream/10183/150443/3/001008973.pdf.jpgb456a8b5cfc6a882a9651e06bcff51a8MD5310183/1504432018-10-30 08:05:51.93oai:www.lume.ufrgs.br:10183/150443Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2018-10-30T11:05:51Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
title |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
spellingShingle |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment Favieiro, Gabriela Winkler Extremidade superior Eletromiografia Redes neurais Electrode assortment Upper-limb signal Neural network Auto-adaptive methods Surface electromyography |
title_short |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
title_full |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
title_fullStr |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
title_full_unstemmed |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
title_sort |
Self-adaptive method for sEMG movement classification based on continuous optimal electrode assortment |
author |
Favieiro, Gabriela Winkler |
author_facet |
Favieiro, Gabriela Winkler Cene, Vinicius Horn Balbinot, Alexandre |
author_role |
author |
author2 |
Cene, Vinicius Horn Balbinot, Alexandre |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Favieiro, Gabriela Winkler Cene, Vinicius Horn Balbinot, Alexandre |
dc.subject.por.fl_str_mv |
Extremidade superior Eletromiografia Redes neurais |
topic |
Extremidade superior Eletromiografia Redes neurais Electrode assortment Upper-limb signal Neural network Auto-adaptive methods Surface electromyography |
dc.subject.eng.fl_str_mv |
Electrode assortment Upper-limb signal Neural network Auto-adaptive methods Surface electromyography |
description |
Surface electromyography (sEMG) analysis is becoming increasingly popular in a broad variety of applications. Despite satisfactory classification rates are frequently obtained through supervised machine learning (ML) algorithms, there are some issues mostly related to the data acquisition which are not properly addressed in current studies. In this paper we present a method capable of mitigate the noise in the sEMG acquisition caused mainly by loose or misplaced non-invasive electrodes. To address this issue we propose a stage of pre-processing capable of being adapted on a variety of classifiers. The proposed method is capable of identify this two anomalies in the signal and provide the data to retrain the classifier, discarding the problematic channels. Once the method is retrained using only the most relevant channels it is possible to increase the accuracy rate of the ML method. The method was tested on a database containing five ablebodied subjects and four amputee subjects of both sexes. The average classification accuracy for the adaptive input selection method was 83,96 6,5% for the able-bodied subjects and 61,15 7,7% for the amputees subjects against 72,06 8,0% in ablebodied subjects and 39,77 10,6% for the amputees subjects considering the non-adaptive approach. Both systems make use of the proposed method to classify 9 distinguish upper-limb movements with different degrees of freedom. |
publishDate |
2016 |
dc.date.issued.fl_str_mv |
2016 |
dc.date.accessioned.fl_str_mv |
2017-01-05T02:30:29Z |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/other |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10183/150443 |
dc.identifier.issn.pt_BR.fl_str_mv |
2318-4531 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001008973 |
identifier_str_mv |
2318-4531 001008973 |
url |
http://hdl.handle.net/10183/150443 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Brazilian journal of instrumentation and control [recurso eletrônico] = Revista brasileira de instrumentação e controle. Curitiba. Vol. 4, n. 1 (2016), p. 21-26 |
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 UFRGS instname:Universidade Federal do Rio Grande do Sul (UFRGS) instacron:UFRGS |
instname_str |
Universidade Federal do Rio Grande do Sul (UFRGS) |
instacron_str |
UFRGS |
institution |
UFRGS |
reponame_str |
Repositório Institucional da UFRGS |
collection |
Repositório Institucional da UFRGS |
bitstream.url.fl_str_mv |
http://www.lume.ufrgs.br/bitstream/10183/150443/1/001008973.pdf http://www.lume.ufrgs.br/bitstream/10183/150443/2/001008973.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/150443/3/001008973.pdf.jpg |
bitstream.checksum.fl_str_mv |
93f90eae1ed99ebf3ca75d7833734037 13fe019d035b8c43e4c14d6cbb7d57af b456a8b5cfc6a882a9651e06bcff51a8 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS) |
repository.mail.fl_str_mv |
|
_version_ |
1801224912614981632 |