Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models

Real-time decoding of locomotion initiation processes using surface electroencephalogram (sEMG) is an emergent topic with significant theoretical and practical implications in e.g. human interaction with intelligent assistive robots. An open yet important question is how machine learning using dynam...

Full description

Saved in:
Bibliographic Details
Main Authors: Jin, Huiwen, Lin, Zhiping, Chen, Yongming, Zhang, Haihong, Wang, Chuanchu, Ng, Soon Huat, Tang, Christina Ka Yin, Ang, Kai Keng
Format: Conference Proceeding
Language:English
Subjects:
Bayes methods
Brain modeling
Dynamics
Electromyography
Hidden Markov models
Legged locomotion
locomotion initiation
Predictive models
rehabilitation
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1901
container_issue
container_start_page 1896
container_title
container_volume
creator Jin, Huiwen
Lin, Zhiping
Chen, Yongming
Zhang, Haihong
Wang, Chuanchu
Ng, Soon Huat
Tang, Christina Ka Yin
Ang, Kai Keng
description Real-time decoding of locomotion initiation processes using surface electroencephalogram (sEMG) is an emergent topic with significant theoretical and practical implications in e.g. human interaction with intelligent assistive robots. An open yet important question is how machine learning using dynamic Bayesian networks can learn the early, prior-to-motion transient EMG activities - not only in the moving leg but also in the stance leg. To address this question, this preliminary study designs and evaluates a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM) in the context of predicting 3 classes of human lower-limb movements, namely, left, middle, and right kicks. Using these unsupervised learning models on EMG recordings from the stance leg only, Bayesian classification achieved an average prediction accuracy of 86.80% in three out of five test subjects. We also analyzed the hidden-state-transition patterns during the motion initiation process. This study demonstrated the feasibility of using unsupervised dynamic Bayesian learning models to capture the predictive dynamic EMG activities in the stance leg during locomotion initiation.
doi_str_mv 10.1109/ICIEA58696.2023.10241881
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_10241881</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10241881</ieee_id><sourcerecordid>10241881</sourcerecordid><originalsourceid>FETCH-LOGICAL-i119t-554fb0a940cbe56a9a3e358c5a72fb27487246971d72a4916485364d07ccc86b3</originalsourceid><addsrcrecordid>eNo1kMtOAjEYhauJiQR5Axd9gcHeL0tCECYZ4gbXpNMpWB06pO2grHx1B9TVOX_Od_7FAQBiNMUY6adyXi5mXAktpgQROsWIMKwUvgETLbWiHFFMCMK3YEQwVwUhWt6DSUrvCA2RlIriEfiunInBhz3cRBOSdyHDRetsjt3h3O2jOb55C2c2-5PP3iXY9PFCV92ni0XrDzVcd9l3AZZhAMzV9umCLE2fkjcBrv1X7qODK980bjhN_OhOQ61xbXoAdzvTJjf50zF4fV5s5quielmW81lVeIx1LjhnuxoZzZCtHRdGG-ooV5YbSXY1kUxJwoSWuJHEMI0FU5wK1iBprVWipmPw-PvXO-e2x-gPJp63_5vRH9gcYy8</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models</title><source>IEEE Xplore All Conference Series</source><creator>Jin, Huiwen ; Lin, Zhiping ; Chen, Yongming ; Zhang, Haihong ; Wang, Chuanchu ; Ng, Soon Huat ; Tang, Christina Ka Yin ; Ang, Kai Keng</creator><creatorcontrib>Jin, Huiwen ; Lin, Zhiping ; Chen, Yongming ; Zhang, Haihong ; Wang, Chuanchu ; Ng, Soon Huat ; Tang, Christina Ka Yin ; Ang, Kai Keng</creatorcontrib><description>Real-time decoding of locomotion initiation processes using surface electroencephalogram (sEMG) is an emergent topic with significant theoretical and practical implications in e.g. human interaction with intelligent assistive robots. An open yet important question is how machine learning using dynamic Bayesian networks can learn the early, prior-to-motion transient EMG activities - not only in the moving leg but also in the stance leg. To address this question, this preliminary study designs and evaluates a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM) in the context of predicting 3 classes of human lower-limb movements, namely, left, middle, and right kicks. Using these unsupervised learning models on EMG recordings from the stance leg only, Bayesian classification achieved an average prediction accuracy of 86.80% in three out of five test subjects. We also analyzed the hidden-state-transition patterns during the motion initiation process. This study demonstrated the feasibility of using unsupervised dynamic Bayesian learning models to capture the predictive dynamic EMG activities in the stance leg during locomotion initiation.</description><identifier>EISSN: 2158-2297</identifier><identifier>EISBN: 9798350312201</identifier><identifier>DOI: 10.1109/ICIEA58696.2023.10241881</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bayes methods ; Brain modeling ; Dynamics ; Electromyography ; Hidden Markov models ; Legged locomotion ; locomotion initiation ; Predictive models ; rehabilitation</subject><ispartof>2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA), 2023, p.1896-1901</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10241881$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>310,311,786,790,795,796,27958,54906,55283</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10241881$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jin, Huiwen</creatorcontrib><creatorcontrib>Lin, Zhiping</creatorcontrib><creatorcontrib>Chen, Yongming</creatorcontrib><creatorcontrib>Zhang, Haihong</creatorcontrib><creatorcontrib>Wang, Chuanchu</creatorcontrib><creatorcontrib>Ng, Soon Huat</creatorcontrib><creatorcontrib>Tang, Christina Ka Yin</creatorcontrib><creatorcontrib>Ang, Kai Keng</creatorcontrib><title>Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models</title><title>2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA)</title><addtitle>ICIEA</addtitle><description>Real-time decoding of locomotion initiation processes using surface electroencephalogram (sEMG) is an emergent topic with significant theoretical and practical implications in e.g. human interaction with intelligent assistive robots. An open yet important question is how machine learning using dynamic Bayesian networks can learn the early, prior-to-motion transient EMG activities - not only in the moving leg but also in the stance leg. To address this question, this preliminary study designs and evaluates a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM) in the context of predicting 3 classes of human lower-limb movements, namely, left, middle, and right kicks. Using these unsupervised learning models on EMG recordings from the stance leg only, Bayesian classification achieved an average prediction accuracy of 86.80% in three out of five test subjects. We also analyzed the hidden-state-transition patterns during the motion initiation process. This study demonstrated the feasibility of using unsupervised dynamic Bayesian learning models to capture the predictive dynamic EMG activities in the stance leg during locomotion initiation.</description><subject>Bayes methods</subject><subject>Brain modeling</subject><subject>Dynamics</subject><subject>Electromyography</subject><subject>Hidden Markov models</subject><subject>Legged locomotion</subject><subject>locomotion initiation</subject><subject>Predictive models</subject><subject>rehabilitation</subject><issn>2158-2297</issn><isbn>9798350312201</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2023</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNo1kMtOAjEYhauJiQR5Axd9gcHeL0tCECYZ4gbXpNMpWB06pO2grHx1B9TVOX_Od_7FAQBiNMUY6adyXi5mXAktpgQROsWIMKwUvgETLbWiHFFMCMK3YEQwVwUhWt6DSUrvCA2RlIriEfiunInBhz3cRBOSdyHDRetsjt3h3O2jOb55C2c2-5PP3iXY9PFCV92ni0XrDzVcd9l3AZZhAMzV9umCLE2fkjcBrv1X7qODK980bjhN_OhOQ61xbXoAdzvTJjf50zF4fV5s5quielmW81lVeIx1LjhnuxoZzZCtHRdGG-ooV5YbSXY1kUxJwoSWuJHEMI0FU5wK1iBprVWipmPw-PvXO-e2x-gPJp63_5vRH9gcYy8</recordid><startdate>20230818</startdate><enddate>20230818</enddate><creator>Jin, Huiwen</creator><creator>Lin, Zhiping</creator><creator>Chen, Yongming</creator><creator>Zhang, Haihong</creator><creator>Wang, Chuanchu</creator><creator>Ng, Soon Huat</creator><creator>Tang, Christina Ka Yin</creator><creator>Ang, Kai Keng</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>20230818</creationdate><title>Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models</title><author>Jin, Huiwen ; Lin, Zhiping ; Chen, Yongming ; Zhang, Haihong ; Wang, Chuanchu ; Ng, Soon Huat ; Tang, Christina Ka Yin ; Ang, Kai Keng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i119t-554fb0a940cbe56a9a3e358c5a72fb27487246971d72a4916485364d07ccc86b3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Bayes methods</topic><topic>Brain modeling</topic><topic>Dynamics</topic><topic>Electromyography</topic><topic>Hidden Markov models</topic><topic>Legged locomotion</topic><topic>locomotion initiation</topic><topic>Predictive models</topic><topic>rehabilitation</topic><toplevel>online_resources</toplevel><creatorcontrib>Jin, Huiwen</creatorcontrib><creatorcontrib>Lin, Zhiping</creatorcontrib><creatorcontrib>Chen, Yongming</creatorcontrib><creatorcontrib>Zhang, Haihong</creatorcontrib><creatorcontrib>Wang, Chuanchu</creatorcontrib><creatorcontrib>Ng, Soon Huat</creatorcontrib><creatorcontrib>Tang, Christina Ka Yin</creatorcontrib><creatorcontrib>Ang, Kai Keng</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jin, Huiwen</au><au>Lin, Zhiping</au><au>Chen, Yongming</au><au>Zhang, Haihong</au><au>Wang, Chuanchu</au><au>Ng, Soon Huat</au><au>Tang, Christina Ka Yin</au><au>Ang, Kai Keng</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models</atitle><btitle>2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA)</btitle><stitle>ICIEA</stitle><date>2023-08-18</date><risdate>2023</risdate><spage>1896</spage><epage>1901</epage><pages>1896-1901</pages><eissn>2158-2297</eissn><eisbn>9798350312201</eisbn><abstract>Real-time decoding of locomotion initiation processes using surface electroencephalogram (sEMG) is an emergent topic with significant theoretical and practical implications in e.g. human interaction with intelligent assistive robots. An open yet important question is how machine learning using dynamic Bayesian networks can learn the early, prior-to-motion transient EMG activities - not only in the moving leg but also in the stance leg. To address this question, this preliminary study designs and evaluates a Gaussian Mixture Model - Hidden Markov Model (GMM-HMM) in the context of predicting 3 classes of human lower-limb movements, namely, left, middle, and right kicks. Using these unsupervised learning models on EMG recordings from the stance leg only, Bayesian classification achieved an average prediction accuracy of 86.80% in three out of five test subjects. We also analyzed the hidden-state-transition patterns during the motion initiation process. This study demonstrated the feasibility of using unsupervised dynamic Bayesian learning models to capture the predictive dynamic EMG activities in the stance leg during locomotion initiation.</abstract><pub>IEEE</pub><doi>10.1109/ICIEA58696.2023.10241881</doi><tpages>6</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2158-2297
ispartof 2023 IEEE 18th Conference on Industrial Electronics and Applications (ICIEA), 2023, p.1896-1901
issn 2158-2297
language eng
recordid cdi_ieee_primary_10241881
source IEEE Xplore All Conference Series
subjects Bayes methods
Brain modeling
Dynamics
Electromyography
Hidden Markov models
Legged locomotion
locomotion initiation
Predictive models
rehabilitation
title Learning Transient Electromyographic Activities during Lower-limb Motion Initiation using Gaussian Mixture Hidden Markov Models
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T18%3A15%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Learning%20Transient%20Electromyographic%20Activities%20during%20Lower-limb%20Motion%20Initiation%20using%20Gaussian%20Mixture%20Hidden%20Markov%20Models&rft.btitle=2023%20IEEE%2018th%20Conference%20on%20Industrial%20Electronics%20and%20Applications%20(ICIEA)&rft.au=Jin,%20Huiwen&rft.date=2023-08-18&rft.spage=1896&rft.epage=1901&rft.pages=1896-1901&rft.eissn=2158-2297&rft_id=info:doi/10.1109/ICIEA58696.2023.10241881&rft.eisbn=9798350312201&rft_dat=%3Cieee_CHZPO%3E10241881%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i119t-554fb0a940cbe56a9a3e358c5a72fb27487246971d72a4916485364d07ccc86b3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10241881&rfr_iscdi=true