Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo
Ano de defesa: | 2019 |
---|---|
Autor(a) principal: | |
Orientador(a): | |
Banca de defesa: | |
Tipo de documento: | Dissertação |
Tipo de acesso: | Acesso aberto |
Idioma: | por |
Instituição de defesa: |
Pontif?cia Universidade Cat?lica do Rio Grande do Sul
|
Programa de Pós-Graduação: |
Programa de P?s-Gradua??o em Engenharia El?trica
|
Departamento: |
Escola Polit?cnica
|
País: |
Brasil
|
Palavras-chave em Português: | |
Palavras-chave em Inglês: | |
Área do conhecimento CNPq: | |
Link de acesso: | http://tede2.pucrs.br/tede2/handle/tede/9333 |
Resumo: | Human beings often suffer from lower limb injuries which are mostly related to aging and daily-motion. This impacts health and exposes human body to undesirable surgical interventions and therapies. In this scenario, the goal of this work is twofold: (a) use artificial neural network (ANN) to identify and classify muscle usage patterns based on electromyographic (EMG) signals, and (b) use the ANN?s output decision to control a Continuous Passive Motion (CPM) machine during a patient physiotherapy session. The strategy uses surface electromyography (sEMG) combined with a supervised learning method and artificial intelligence (AI) to create a feedback signal which allows these devices to function in Continuous Active Motion (CAM) mode. Methods: This work used 300 EMG signals collected from the vastus lateralis muscle of 10 healthy individuals to develop a strength classifier system. The core?s classifier is composed of a trained (backpropagation) feedforward neural network. The EMG signals are classified into predefined force levels, which in turn are used as inputs to control a CPM machine. Thus, there is a direct correspondence between each of the predefined force levels and the CPM machine linear displacement. Results: The trained ANN classifies, at real-time, EMG signals into force levels at 81 % accuracy with computational efficiency. After receiving the predefined force levels from the ANN?s output, the delay of the mechanical control system to adjust the CPM machine is less than 100 seconds. Conclusion: The AIbased assertiveness of the proposed strategy allows us to consider extending the use of single muscle EMG signals to pave the way for controlling another biomechanical machines in a near future. |
id |
P_RS_1bc00671194c2367c84b17343452464d |
---|---|
oai_identifier_str |
oai:tede2.pucrs.br:tede/9333 |
network_acronym_str |
P_RS |
network_name_str |
Biblioteca Digital de Teses e Dissertações da PUC_RS |
repository_id_str |
|
spelling |
Vargas, Fabian Luishttp://lattes.cnpq.br/9050311050537919http://lattes.cnpq.br/6445415160156213Sponchiado, Gr?gori Stefanello2020-11-05T19:34:38Z2019-11-28http://tede2.pucrs.br/tede2/handle/tede/9333Human beings often suffer from lower limb injuries which are mostly related to aging and daily-motion. This impacts health and exposes human body to undesirable surgical interventions and therapies. In this scenario, the goal of this work is twofold: (a) use artificial neural network (ANN) to identify and classify muscle usage patterns based on electromyographic (EMG) signals, and (b) use the ANN?s output decision to control a Continuous Passive Motion (CPM) machine during a patient physiotherapy session. The strategy uses surface electromyography (sEMG) combined with a supervised learning method and artificial intelligence (AI) to create a feedback signal which allows these devices to function in Continuous Active Motion (CAM) mode. Methods: This work used 300 EMG signals collected from the vastus lateralis muscle of 10 healthy individuals to develop a strength classifier system. The core?s classifier is composed of a trained (backpropagation) feedforward neural network. The EMG signals are classified into predefined force levels, which in turn are used as inputs to control a CPM machine. Thus, there is a direct correspondence between each of the predefined force levels and the CPM machine linear displacement. Results: The trained ANN classifies, at real-time, EMG signals into force levels at 81 % accuracy with computational efficiency. After receiving the predefined force levels from the ANN?s output, the delay of the mechanical control system to adjust the CPM machine is less than 100 seconds. Conclusion: The AIbased assertiveness of the proposed strategy allows us to consider extending the use of single muscle EMG signals to pave the way for controlling another biomechanical machines in a near future.Os seres humanos sofrem frequentemente de les?es nos membros inferiores, principalmente as relacionadas aos movimentos di?rios, sendo o envelhecimento um fator de risco. Isso afeta a sa?de e submete o corpo humano a interven??es cir?rgicas e terapias indesej?veis. Nesse cen?rio, os objetivos deste trabalho s?o: (a) usar rede neural artificial (RNA) para identificar e classificar padr?es musculares com base em sinais eletromiogr?ficos (EMG) e (b) usar a decis?o de sa?da da RNA para controlar uma M?quina Movimento Passivo (CPM, do termo em ingl?s: Continuous Passive Movement) durante uma sess?o de fisioterapia do paciente. A estrat?gia usa eletromiografia de superf?cie combinada com um m?todo de aprendizado supervisionado e intelig?ncia artificial (IA) para criar um sinal de ???????? que permite que esses dispositivos funcionem no modo de Movimento Ativo Cont?nuo (CAM, do termo em ingl?s: Continuous Active Movement). M?todos: Este trabalho utilizou 300 sinais EMG coletados do m?sculo vasto lateral de 10 indiv?duos saud?veis para desenvolver um sistema classificador de for?a. O n?cleo do classificador ? composto por uma rede neural treinada (???????????????). Os sinais EMG s?o classificados em n?veis de for?a pr?-definidos, que por sua vez s?o usados como entradas para controlar uma m?quina de CPM. Assim, existe uma correspond?ncia direta entre cada um dos n?veis de for?a pr?-definidos e o deslocamento linear da m?quina CPM. Resultados: A RNA treinada classifica, em tempo real, sinais EMG em n?veis de for?a com precis?o de 81% com efici?ncia computacional. Ap?s receber os n?veis de for?a pr?-definidos da sa?da da RNA, o atraso que o sistema de controle mec?nico leva para ajustar a m?quina de CPM ? inferior a 100 segundos. Conclus?o: A assertividade baseada em IA da estrat?gia proposta nos permite considerar a extens?o do uso de sinais EMG de m?sculo ?nico para pavimentar o caminho para o controle de outras m?quinas biomec?nicas em um futuro pr?ximo.Submitted by PPG Engenharia El?trica (engenharia.pg.eletrica@pucrs.br) on 2020-08-19T19:06:45Z No. of bitstreams: 1 GR?GORI STEFANELLO SPONCHIADO_DIS.pdf: 6486542 bytes, checksum: 16eed5b739cd58deff0aacd676499c43 (MD5)Approved for entry into archive by Caroline Xavier (caroline.xavier@pucrs.br) on 2020-11-05T19:30:09Z (GMT) No. of bitstreams: 1 GR?GORI STEFANELLO SPONCHIADO_DIS.pdf: 6486542 bytes, checksum: 16eed5b739cd58deff0aacd676499c43 (MD5)Made available in DSpace on 2020-11-05T19:34:38Z (GMT). No. of bitstreams: 1 GR?GORI STEFANELLO SPONCHIADO_DIS.pdf: 6486542 bytes, checksum: 16eed5b739cd58deff0aacd676499c43 (MD5) Previous issue date: 2019-11-28application/pdfhttp://tede2.pucrs.br:80/tede2/retrieve/179329/GR%c3%89GORI%20STEFANELLO%20SPONCHIADO_DIS.pdf.jpgporPontif?cia Universidade Cat?lica do Rio Grande do SulPrograma de P?s-Gradua??o em Engenharia El?tricaPUCRSBrasilEscola Polit?cnicaAprendizado de M?quinaRedes Neurais ArtificiaisEMGCPMCAMMachine LearningArtificial Neural NetworksEMGCPMCAMENGENHARIASEstrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuoinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisTrabalho n?o apresenta restri??o para publica??o-2660504109272820295005004518971056484826825info:eu-repo/semantics/openAccessreponame:Biblioteca Digital de Teses e Dissertações da PUC_RSinstname:Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS)instacron:PUC_RSTHUMBNAILGR?GORI STEFANELLO SPONCHIADO_DIS.pdf.jpgGR?GORI STEFANELLO SPONCHIADO_DIS.pdf.jpgimage/jpeg5809http://tede2.pucrs.br/tede2/bitstream/tede/9333/4/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf.jpgb1da2ddd23825832bfd7f2906530782eMD54TEXTGR?GORI STEFANELLO SPONCHIADO_DIS.pdf.txtGR?GORI STEFANELLO SPONCHIADO_DIS.pdf.txttext/plain102661http://tede2.pucrs.br/tede2/bitstream/tede/9333/3/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf.txt9a8b8d61b8235e876d5309c765081bdfMD53ORIGINALGR?GORI STEFANELLO SPONCHIADO_DIS.pdfGR?GORI STEFANELLO SPONCHIADO_DIS.pdfapplication/pdf6486542http://tede2.pucrs.br/tede2/bitstream/tede/9333/2/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf16eed5b739cd58deff0aacd676499c43MD52LICENSElicense.txtlicense.txttext/plain; charset=utf-8590http://tede2.pucrs.br/tede2/bitstream/tede/9333/1/license.txt220e11f2d3ba5354f917c7035aadef24MD51tede/93332020-11-05 20:00:19.942oai:tede2.pucrs.br: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Biblioteca Digital de Teses e Dissertaçõeshttp://tede2.pucrs.br/tede2/PRIhttps://tede2.pucrs.br/oai/requestbiblioteca.central@pucrs.br||opendoar:2020-11-05T22:00:19Biblioteca Digital de Teses e Dissertações da PUC_RS - Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS)false |
dc.title.por.fl_str_mv |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
title |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
spellingShingle |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo Sponchiado, Gr?gori Stefanello Aprendizado de M?quina Redes Neurais Artificiais EMG CPM CAM Machine Learning Artificial Neural Networks EMG CPM CAM ENGENHARIAS |
title_short |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
title_full |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
title_fullStr |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
title_full_unstemmed |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
title_sort |
Estrat?gia de caracteriza??o de sinais eletromiogr?ficos baseada em redes neurais artificiais para sistemas de controle de m?quinas de movimento cont?nuo |
author |
Sponchiado, Gr?gori Stefanello |
author_facet |
Sponchiado, Gr?gori Stefanello |
author_role |
author |
dc.contributor.advisor1.fl_str_mv |
Vargas, Fabian Luis |
dc.contributor.advisor1Lattes.fl_str_mv |
http://lattes.cnpq.br/9050311050537919 |
dc.contributor.authorLattes.fl_str_mv |
http://lattes.cnpq.br/6445415160156213 |
dc.contributor.author.fl_str_mv |
Sponchiado, Gr?gori Stefanello |
contributor_str_mv |
Vargas, Fabian Luis |
dc.subject.por.fl_str_mv |
Aprendizado de M?quina Redes Neurais Artificiais EMG CPM CAM |
topic |
Aprendizado de M?quina Redes Neurais Artificiais EMG CPM CAM Machine Learning Artificial Neural Networks EMG CPM CAM ENGENHARIAS |
dc.subject.eng.fl_str_mv |
Machine Learning Artificial Neural Networks EMG CPM CAM |
dc.subject.cnpq.fl_str_mv |
ENGENHARIAS |
description |
Human beings often suffer from lower limb injuries which are mostly related to aging and daily-motion. This impacts health and exposes human body to undesirable surgical interventions and therapies. In this scenario, the goal of this work is twofold: (a) use artificial neural network (ANN) to identify and classify muscle usage patterns based on electromyographic (EMG) signals, and (b) use the ANN?s output decision to control a Continuous Passive Motion (CPM) machine during a patient physiotherapy session. The strategy uses surface electromyography (sEMG) combined with a supervised learning method and artificial intelligence (AI) to create a feedback signal which allows these devices to function in Continuous Active Motion (CAM) mode. Methods: This work used 300 EMG signals collected from the vastus lateralis muscle of 10 healthy individuals to develop a strength classifier system. The core?s classifier is composed of a trained (backpropagation) feedforward neural network. The EMG signals are classified into predefined force levels, which in turn are used as inputs to control a CPM machine. Thus, there is a direct correspondence between each of the predefined force levels and the CPM machine linear displacement. Results: The trained ANN classifies, at real-time, EMG signals into force levels at 81 % accuracy with computational efficiency. After receiving the predefined force levels from the ANN?s output, the delay of the mechanical control system to adjust the CPM machine is less than 100 seconds. Conclusion: The AIbased assertiveness of the proposed strategy allows us to consider extending the use of single muscle EMG signals to pave the way for controlling another biomechanical machines in a near future. |
publishDate |
2019 |
dc.date.issued.fl_str_mv |
2019-11-28 |
dc.date.accessioned.fl_str_mv |
2020-11-05T19:34:38Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/masterThesis |
format |
masterThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://tede2.pucrs.br/tede2/handle/tede/9333 |
url |
http://tede2.pucrs.br/tede2/handle/tede/9333 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.relation.program.fl_str_mv |
-266050410927282029 |
dc.relation.confidence.fl_str_mv |
500 500 |
dc.relation.cnpq.fl_str_mv |
4518971056484826825 |
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.publisher.none.fl_str_mv |
Pontif?cia Universidade Cat?lica do Rio Grande do Sul |
dc.publisher.program.fl_str_mv |
Programa de P?s-Gradua??o em Engenharia El?trica |
dc.publisher.initials.fl_str_mv |
PUCRS |
dc.publisher.country.fl_str_mv |
Brasil |
dc.publisher.department.fl_str_mv |
Escola Polit?cnica |
publisher.none.fl_str_mv |
Pontif?cia Universidade Cat?lica do Rio Grande do Sul |
dc.source.none.fl_str_mv |
reponame:Biblioteca Digital de Teses e Dissertações da PUC_RS instname:Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) instacron:PUC_RS |
instname_str |
Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) |
instacron_str |
PUC_RS |
institution |
PUC_RS |
reponame_str |
Biblioteca Digital de Teses e Dissertações da PUC_RS |
collection |
Biblioteca Digital de Teses e Dissertações da PUC_RS |
bitstream.url.fl_str_mv |
http://tede2.pucrs.br/tede2/bitstream/tede/9333/4/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf.jpg http://tede2.pucrs.br/tede2/bitstream/tede/9333/3/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf.txt http://tede2.pucrs.br/tede2/bitstream/tede/9333/2/GR%C3%89GORI+STEFANELLO+SPONCHIADO_DIS.pdf http://tede2.pucrs.br/tede2/bitstream/tede/9333/1/license.txt |
bitstream.checksum.fl_str_mv |
b1da2ddd23825832bfd7f2906530782e 9a8b8d61b8235e876d5309c765081bdf 16eed5b739cd58deff0aacd676499c43 220e11f2d3ba5354f917c7035aadef24 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Biblioteca Digital de Teses e Dissertações da PUC_RS - Pontifícia Universidade Católica do Rio Grande do Sul (PUCRS) |
repository.mail.fl_str_mv |
biblioteca.central@pucrs.br|| |
_version_ |
1796793245641998336 |