Publicação

Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network

Ver documento

Detalhes bibliográficos
Resumo:Neurological diseases may reduce Tibialis Anterior (TA) muscle recruitment capacity causing gait disorders, such as drop foot (DF). The majority of DF patients still retain excitable nerves and muscles which makes Functional Electrical Stimulation (FES) an adequate technique to restore lost mobility. Recent studies suggest the need for developing personalized and assist-as-needed control strategies for wearable FES in order to promote natural and functional movements while reducing the early onset of fatigue. This study contributes to a real-time implementation of a trajectory tracking FES control strategy for personalized DF correction. This strategy combines a feedforward Non-Linear Autoregressive Neural Network with Exogenous inputs (NARXNN) with a feedback PD controller. This control strategy advances with a user-specific TA muscle model achieved by the NARXNN’s ability to model dynamic systems relying on the foot angle and angular velocity as inputs. A closed-loop, fully wearable stimulation system was achieved using an ISTim stimulator and wearable inertial sensor for electrical stimulation and user’s kinematic gait sensing, respectively. Results showed that the NARXNN architecture with 2 hidden layers and 10 neurons provided the highest performance for modelling the kinematic behaviour of the TA muscle. The proposed trajectory tracking control revealed a low discrepancy between real and reference foot trajectories (goodness of fit = 77.87%) and time-effectiveness for correctly stimulating the TA muscle towards a natural gait and DF correction.
Autores principais:Carvalho, Simão
Outros Autores:Correia, Ana; Figueiredo, Joana; Martins, Jorge M.; Santos, Cristina
Assunto:Closed loop control Drop foot Functional Electrical Stimulation Muscle modelling Neural network Human-robot interface Hybrid control
Ano:2021
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade do Minho
Idioma:inglês
Origem:RepositóriUM - Universidade do Minho
_version_ 1867438906299908096
author Carvalho, Simão
author2 Correia, Ana
Figueiredo, Joana
Martins, Jorge M.
Santos, Cristina
author2_role author
author
author
author
author_facet Carvalho, Simão
Correia, Ana
Figueiredo, Joana
Martins, Jorge M.
Santos, Cristina
author_role author
contributor_name_str_mv RepositóriUM - Universidade do Minho
country_str PT
creators_json_txt [{\"Person.name\":\"Carvalho, Simão\"},{\"Person.name\":\"Correia, Ana\"},{\"Person.name\":\"Figueiredo, Joana\"},{\"Person.name\":\"Martins, Jorge M.\"},{\"Person.name\":\"Santos, Cristina\"}]
datacite.contributors.contributor.contributorName.fl_str_mv RepositóriUM - Universidade do Minho
datacite.creators.creator.creatorName.fl_str_mv Carvalho, Simão
Correia, Ana
Figueiredo, Joana
Martins, Jorge M.
Santos, Cristina
datacite.date.Accepted.fl_str_mv 2021-10-26T00:00:00Z
datacite.date.available.fl_str_mv 2022-03-11T11:50:10Z
datacite.date.embargoed.fl_str_mv 2022-03-11T11:50:10Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
datacite.titles.title.fl_str_mv Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
dc.contributor.none.fl_str_mv RepositóriUM - Universidade do Minho
dc.creator.none.fl_str_mv Carvalho, Simão
Correia, Ana
Figueiredo, Joana
Martins, Jorge M.
Santos, Cristina
dc.date.Accepted.fl_str_mv 2021-10-26T00:00:00Z
dc.date.available.fl_str_mv 2022-03-11T11:50:10Z
dc.date.embargoed.fl_str_mv 2022-03-11T11:50:10Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://hdl.handle.net/1822/76481
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.rights.rights.copyright.fl_str_mv openAccess
dc.subject.none.fl_str_mv Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
dc.title.fl_str_mv Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Neurological diseases may reduce Tibialis Anterior (TA) muscle recruitment capacity causing gait disorders, such as drop foot (DF). The majority of DF patients still retain excitable nerves and muscles which makes Functional Electrical Stimulation (FES) an adequate technique to restore lost mobility. Recent studies suggest the need for developing personalized and assist-as-needed control strategies for wearable FES in order to promote natural and functional movements while reducing the early onset of fatigue. This study contributes to a real-time implementation of a trajectory tracking FES control strategy for personalized DF correction. This strategy combines a feedforward Non-Linear Autoregressive Neural Network with Exogenous inputs (NARXNN) with a feedback PD controller. This control strategy advances with a user-specific TA muscle model achieved by the NARXNN’s ability to model dynamic systems relying on the foot angle and angular velocity as inputs. A closed-loop, fully wearable stimulation system was achieved using an ISTim stimulator and wearable inertial sensor for electrical stimulation and user’s kinematic gait sensing, respectively. Results showed that the NARXNN architecture with 2 hidden layers and 10 neurons provided the highest performance for modelling the kinematic behaviour of the TA muscle. The proposed trajectory tracking control revealed a low discrepancy between real and reference foot trajectories (goodness of fit = 77.87%) and time-effectiveness for correctly stimulating the TA muscle towards a natural gait and DF correction.
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://repositorium.uminho.pt/bitstreams/d8e10edc-899c-44a2-b592-4a01acb43aef/download
id rum_a38afd500e2adf5126dc697d77928e21
identifier.url.fl_str_mv https://hdl.handle.net/1822/76481
instacron_str repositorium
institution Universidade do Minho
instname_str Universidade do Minho
language eng
network_acronym_str rum
network_name_str RepositóriUM - Universidade do Minho
oai_identifier_str oai:repositorium.uminho.pt:1822/76481
organization_str_mv urn:organizationAcronym:repositorium
person_str_mv Carvalho, Simão
Correia, Ana
Figueiredo, Joana
Martins, Jorge M.
Santos, Cristina
publishDate 2021
publisher.none.fl_str_mv Multidisciplinary Digital Publishing Institute (MDPI)
reponame_str RepositóriUM - Universidade do Minho
repository_id_str urn:repositoryAcronym:rum
service_str_mv urn:repositoryAcronym:rum
spelling engMultidisciplinary Digital Publishing Institute (MDPI)porNeurological diseases may reduce Tibialis Anterior (TA) muscle recruitment capacity causing gait disorders, such as drop foot (DF). The majority of DF patients still retain excitable nerves and muscles which makes Functional Electrical Stimulation (FES) an adequate technique to restore lost mobility. Recent studies suggest the need for developing personalized and assist-as-needed control strategies for wearable FES in order to promote natural and functional movements while reducing the early onset of fatigue. This study contributes to a real-time implementation of a trajectory tracking FES control strategy for personalized DF correction. This strategy combines a feedforward Non-Linear Autoregressive Neural Network with Exogenous inputs (NARXNN) with a feedback PD controller. This control strategy advances with a user-specific TA muscle model achieved by the NARXNN’s ability to model dynamic systems relying on the foot angle and angular velocity as inputs. A closed-loop, fully wearable stimulation system was achieved using an ISTim stimulator and wearable inertial sensor for electrical stimulation and user’s kinematic gait sensing, respectively. Results showed that the NARXNN architecture with 2 hidden layers and 10 neurons provided the highest performance for modelling the kinematic behaviour of the TA muscle. The proposed trajectory tracking control revealed a low discrepancy between real and reference foot trajectories (goodness of fit = 77.87%) and time-effectiveness for correctly stimulating the TA muscle towards a natural gait and DF correction.application/pdfporFunctional electrical stimulation system for drop foot correction using a dynamic NARX neural networkCarvalho, SimãoCorreia, AnaFigueiredo, JoanaMartins, Jorge M.Santos, CristinaHostingInstitutionOrganizationalRepositóriUM - Universidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptCITATIONCarvalho, S.; Correia, A.; Figueiredo, J.; Martins, J.M.; Santos, C.P. Functional Electrical Stimulation System for Drop Foot Correction Using a Dynamic NARX Neural Network. Machines 2021, 9, 253. https://doi.org/10.3390/machines9110253ARTICLENUMBER253ISSNIsPartOf2075-1702DOIIsPartOf10.3390/machines91102532022-03-11T11:50:10Z2021-10-262021-11-25T16:00:17Z2021-10-26T00:00:00ZHandlehttps://hdl.handle.net/1822/76481http://purl.org/coar/access_right/c_abf2open accessClosed loop controlDrop footFunctional Electrical StimulationMuscle modellingNeural networkHuman-robot interfaceHybrid control3392706 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal article2021-10-26http://creativecommons.org/licenses/by/4.0/openAccesshttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/d8e10edc-899c-44a2-b592-4a01acb43aef/download
spellingShingle Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
Carvalho, Simão
Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
status SINGLETON
subject.fl_str_mv Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
title Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
title_full Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
title_fullStr Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
title_full_unstemmed Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
title_short Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
title_sort Functional electrical stimulation system for drop foot correction using a dynamic NARX neural network
topic Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
topic_facet Closed loop control
Drop foot
Functional Electrical Stimulation
Muscle modelling
Neural network
Human-robot interface
Hybrid control
url https://hdl.handle.net/1822/76481
visible 1