Deep learning for surface electromyography artifact contamination type detection
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRGS |
Texto Completo: | http://hdl.handle.net/10183/222260 |
Resumo: | The quality of surface Electromyography (sEMG) signals could be an issue if highly contaminated by Power Line Interference (PLI), Electrocardiogram signal (ECG), Movement Artifact (MOA) or White Gaussian Noise (WGN), that could lead to unsafe operation of devices that is controlled by sEMG data, such as electro-mechanical prothesis. There are some mitigation methods proposed for some specifics sEMG contaminants and to use these methods in an efficient way is important to identify the contaminant in the sEMG signal. In this work we propose the use of a Recurrent Neural Network (RNN) using Long Short-Term Memory (LSTM) units in the hidden layer with no need of features extraction with the objective to classify the signal directly from sequences of the band-pass filtered data. The method proposed use the NinaPro database with amputee and non-amputee subjects. Only non-amputee subjects are used for parameters selection and then tested on both databases. The results show that 98% of the non-contaminated sEMG data was corrected classified and more than 95% of the contaminants were identified inside the training SNR range. Also, in this work is presented a SNR sensibility control and the contamination analysis in the range from −40 dB to 40 dB in 10 dB steps. The conclusion is that is possible to classify the contamination type in sEMG signals with a RNN-LSTM with a 112.5 ms time window and to predicted with a small error the classification hit rate for each SNR level in some cases. |
id |
UFRGS-2_f300c36f3a33f21f466bfadf4387b3bb |
---|---|
oai_identifier_str |
oai:www.lume.ufrgs.br:10183/222260 |
network_acronym_str |
UFRGS-2 |
network_name_str |
Repositório Institucional da UFRGS |
repository_id_str |
|
spelling |
Machado, Juliano CostaMachado, Amauri AlmeidaBalbinot, Alexandre2021-06-16T04:36:48Z20211746-8094http://hdl.handle.net/10183/222260001126422The quality of surface Electromyography (sEMG) signals could be an issue if highly contaminated by Power Line Interference (PLI), Electrocardiogram signal (ECG), Movement Artifact (MOA) or White Gaussian Noise (WGN), that could lead to unsafe operation of devices that is controlled by sEMG data, such as electro-mechanical prothesis. There are some mitigation methods proposed for some specifics sEMG contaminants and to use these methods in an efficient way is important to identify the contaminant in the sEMG signal. In this work we propose the use of a Recurrent Neural Network (RNN) using Long Short-Term Memory (LSTM) units in the hidden layer with no need of features extraction with the objective to classify the signal directly from sequences of the band-pass filtered data. The method proposed use the NinaPro database with amputee and non-amputee subjects. Only non-amputee subjects are used for parameters selection and then tested on both databases. The results show that 98% of the non-contaminated sEMG data was corrected classified and more than 95% of the contaminants were identified inside the training SNR range. Also, in this work is presented a SNR sensibility control and the contamination analysis in the range from −40 dB to 40 dB in 10 dB steps. The conclusion is that is possible to classify the contamination type in sEMG signals with a RNN-LSTM with a 112.5 ms time window and to predicted with a small error the classification hit rate for each SNR level in some cases.application/pdfengBiomedical signal processing and control [recurso eletrônico]. [Amsterdam]. vol. 68 (July 2021), art. 102752, 11 p.EletromiografiaRedes neuraisEngenharia biomédicaSurface electromyographyContaminantsQualityRecurrent neural networkLong short-term memoryDeep learning for surface electromyography artifact contamination type detectionEstrangeiroinfo:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UFRGSinstname:Universidade Federal do Rio Grande do Sul (UFRGS)instacron:UFRGSTEXT001126422.pdf.txt001126422.pdf.txtExtracted Texttext/plain50113http://www.lume.ufrgs.br/bitstream/10183/222260/2/001126422.pdf.txta14823a19266254ad7b91b78521fe082MD52ORIGINAL001126422.pdfTexto completo (inglês)application/pdf5907278http://www.lume.ufrgs.br/bitstream/10183/222260/1/001126422.pdf35a8080ffabc4090bfc6161f3ec927caMD5110183/2222602021-06-26 04:41:58.688401oai:www.lume.ufrgs.br:10183/222260Repositório de PublicaçõesPUBhttps://lume.ufrgs.br/oai/requestopendoar:2021-06-26T07:41:58Repositório Institucional da UFRGS - Universidade Federal do Rio Grande do Sul (UFRGS)false |
dc.title.pt_BR.fl_str_mv |
Deep learning for surface electromyography artifact contamination type detection |
title |
Deep learning for surface electromyography artifact contamination type detection |
spellingShingle |
Deep learning for surface electromyography artifact contamination type detection Machado, Juliano Costa Eletromiografia Redes neurais Engenharia biomédica Surface electromyography Contaminants Quality Recurrent neural network Long short-term memory |
title_short |
Deep learning for surface electromyography artifact contamination type detection |
title_full |
Deep learning for surface electromyography artifact contamination type detection |
title_fullStr |
Deep learning for surface electromyography artifact contamination type detection |
title_full_unstemmed |
Deep learning for surface electromyography artifact contamination type detection |
title_sort |
Deep learning for surface electromyography artifact contamination type detection |
author |
Machado, Juliano Costa |
author_facet |
Machado, Juliano Costa Machado, Amauri Almeida Balbinot, Alexandre |
author_role |
author |
author2 |
Machado, Amauri Almeida Balbinot, Alexandre |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Machado, Juliano Costa Machado, Amauri Almeida Balbinot, Alexandre |
dc.subject.por.fl_str_mv |
Eletromiografia Redes neurais Engenharia biomédica |
topic |
Eletromiografia Redes neurais Engenharia biomédica Surface electromyography Contaminants Quality Recurrent neural network Long short-term memory |
dc.subject.eng.fl_str_mv |
Surface electromyography Contaminants Quality Recurrent neural network Long short-term memory |
description |
The quality of surface Electromyography (sEMG) signals could be an issue if highly contaminated by Power Line Interference (PLI), Electrocardiogram signal (ECG), Movement Artifact (MOA) or White Gaussian Noise (WGN), that could lead to unsafe operation of devices that is controlled by sEMG data, such as electro-mechanical prothesis. There are some mitigation methods proposed for some specifics sEMG contaminants and to use these methods in an efficient way is important to identify the contaminant in the sEMG signal. In this work we propose the use of a Recurrent Neural Network (RNN) using Long Short-Term Memory (LSTM) units in the hidden layer with no need of features extraction with the objective to classify the signal directly from sequences of the band-pass filtered data. The method proposed use the NinaPro database with amputee and non-amputee subjects. Only non-amputee subjects are used for parameters selection and then tested on both databases. The results show that 98% of the non-contaminated sEMG data was corrected classified and more than 95% of the contaminants were identified inside the training SNR range. Also, in this work is presented a SNR sensibility control and the contamination analysis in the range from −40 dB to 40 dB in 10 dB steps. The conclusion is that is possible to classify the contamination type in sEMG signals with a RNN-LSTM with a 112.5 ms time window and to predicted with a small error the classification hit rate for each SNR level in some cases. |
publishDate |
2021 |
dc.date.accessioned.fl_str_mv |
2021-06-16T04:36:48Z |
dc.date.issued.fl_str_mv |
2021 |
dc.type.driver.fl_str_mv |
Estrangeiro info:eu-repo/semantics/article |
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/10183/222260 |
dc.identifier.issn.pt_BR.fl_str_mv |
1746-8094 |
dc.identifier.nrb.pt_BR.fl_str_mv |
001126422 |
identifier_str_mv |
1746-8094 001126422 |
url |
http://hdl.handle.net/10183/222260 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.ispartof.pt_BR.fl_str_mv |
Biomedical signal processing and control [recurso eletrônico]. [Amsterdam]. vol. 68 (July 2021), art. 102752, 11 p. |
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/10183/222260/2/001126422.pdf.txt http://www.lume.ufrgs.br/bitstream/10183/222260/1/001126422.pdf |
bitstream.checksum.fl_str_mv |
a14823a19266254ad7b91b78521fe082 35a8080ffabc4090bfc6161f3ec927ca |
bitstream.checksumAlgorithm.fl_str_mv |
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_ |
1801225020757770240 |