An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis

Abstract The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task....

Full description

Saved in:
Bibliographic Details
Published in:Journal of electromyography and kinesiology 2016-02, Vol.26, p.36-43
Main Authors: Shourijeh, Mohammad S, Flaxman, Teresa E, Benoit, Daniel L
Format: Article
Language:English
Subjects:
Adult
Algorithms
Electromyography
Electromyography - methods
Electromyography - standards
Humans
Knee
Male
Muscle synergy
Muscle, Skeletal - physiology
Non-negative matrix factorization
Physical Medicine and Rehabilitation
Repeatability
Reproducibility of Results
Robustness
Weight-Bearing - physiology
Young Adult
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133
cites cdi_FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133
container_end_page 43
container_issue
container_start_page 36
container_title Journal of electromyography and kinesiology
container_volume 26
creator Shourijeh, Mohammad S
Flaxman, Teresa E
Benoit, Daniel L
description Abstract The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (>0.99; 0.99–1.0) compared to NMF (>0.26; range 0.26–0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.
doi_str_mv 10.1016/j.jelekin.2015.12.001
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_1811908390</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>1_s2_0_S1050641115002345</els_id><sourcerecordid>1765579113</sourcerecordid><originalsourceid>FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133</originalsourceid><addsrcrecordid>eNqFUk1v1DAQtRCIlsJPAOXIJcETx_m4gKoKaKVKHICz5diTxaljL3ayavj1ON0tBy49zYfee6OZN4S8BVoAhfrDWIxo8c64oqTACygLSuEZOYe2YTlvAJ6nnHKa1xXAGXkV45gADW3pS3JW1g3nULNzcn_pMrnfBy_Vr2zwITNTKg7G7bKAe5Sz7I0185pJp1PHmsfaD5nzLne4k7M5YDbJOZj7bJBq9sH8SU3vHgSnJSqLWVwdht2mI-0aTXxNXgzSRnxzihfk55fPP66u89tvX2-uLm9zxUs2521Pq4rWqtGsqzVXnGGvVdVWA7aMNt3Q6hJUIzsNVJV8YLQvu45Vemi7XgNjF-T9UTet9XvBOIvJRIXWSod-iQJagI62rKNPQ5ua86aDB1V-hKrgYww4iH0wkwyrACo2f8QoTv6IzR8BpUjnT7x3pxFLP6H-x3o0JAE-HQGYbnIwGERUBp1CbQKqWWhvnhzx8T8FZY0zSto7XDGOfgnJgrSNiIkgvm9Psv0IcEpLVnH2F2Kvuq4</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1765579113</pqid></control><display><type>article</type><title>An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis</title><source>ScienceDirect Journals</source><creator>Shourijeh, Mohammad S ; Flaxman, Teresa E ; Benoit, Daniel L</creator><creatorcontrib>Shourijeh, Mohammad S ; Flaxman, Teresa E ; Benoit, Daniel L</creatorcontrib><description>Abstract The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (&gt;0.99; 0.99–1.0) compared to NMF (&gt;0.26; range 0.26–0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.</description><identifier>ISSN: 1050-6411</identifier><identifier>EISSN: 1873-5711</identifier><identifier>DOI: 10.1016/j.jelekin.2015.12.001</identifier><identifier>PMID: 26755163</identifier><language>eng</language><publisher>England: Elsevier Ltd</publisher><subject>Adult ; Algorithms ; Electromyography ; Electromyography - methods ; Electromyography - standards ; Humans ; Knee ; Male ; Muscle synergy ; Muscle, Skeletal - physiology ; Non-negative matrix factorization ; Physical Medicine and Rehabilitation ; Repeatability ; Reproducibility of Results ; Robustness ; Weight-Bearing - physiology ; Young Adult</subject><ispartof>Journal of electromyography and kinesiology, 2016-02, Vol.26, p.36-43</ispartof><rights>Elsevier Ltd</rights><rights>2015 Elsevier Ltd</rights><rights>Copyright © 2015 Elsevier Ltd. All rights reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133</citedby><cites>FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27922,27923</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/26755163$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Shourijeh, Mohammad S</creatorcontrib><creatorcontrib>Flaxman, Teresa E</creatorcontrib><creatorcontrib>Benoit, Daniel L</creatorcontrib><title>An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis</title><title>Journal of electromyography and kinesiology</title><addtitle>J Electromyogr Kinesiol</addtitle><description>Abstract The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (&gt;0.99; 0.99–1.0) compared to NMF (&gt;0.26; range 0.26–0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.</description><subject>Adult</subject><subject>Algorithms</subject><subject>Electromyography</subject><subject>Electromyography - methods</subject><subject>Electromyography - standards</subject><subject>Humans</subject><subject>Knee</subject><subject>Male</subject><subject>Muscle synergy</subject><subject>Muscle, Skeletal - physiology</subject><subject>Non-negative matrix factorization</subject><subject>Physical Medicine and Rehabilitation</subject><subject>Repeatability</subject><subject>Reproducibility of Results</subject><subject>Robustness</subject><subject>Weight-Bearing - physiology</subject><subject>Young Adult</subject><issn>1050-6411</issn><issn>1873-5711</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNqFUk1v1DAQtRCIlsJPAOXIJcETx_m4gKoKaKVKHICz5diTxaljL3ayavj1ON0tBy49zYfee6OZN4S8BVoAhfrDWIxo8c64oqTACygLSuEZOYe2YTlvAJ6nnHKa1xXAGXkV45gADW3pS3JW1g3nULNzcn_pMrnfBy_Vr2zwITNTKg7G7bKAe5Sz7I0185pJp1PHmsfaD5nzLne4k7M5YDbJOZj7bJBq9sH8SU3vHgSnJSqLWVwdht2mI-0aTXxNXgzSRnxzihfk55fPP66u89tvX2-uLm9zxUs2521Pq4rWqtGsqzVXnGGvVdVWA7aMNt3Q6hJUIzsNVJV8YLQvu45Vemi7XgNjF-T9UTet9XvBOIvJRIXWSod-iQJagI62rKNPQ5ua86aDB1V-hKrgYww4iH0wkwyrACo2f8QoTv6IzR8BpUjnT7x3pxFLP6H-x3o0JAE-HQGYbnIwGERUBp1CbQKqWWhvnhzx8T8FZY0zSto7XDGOfgnJgrSNiIkgvm9Psv0IcEpLVnH2F2Kvuq4</recordid><startdate>20160201</startdate><enddate>20160201</enddate><creator>Shourijeh, Mohammad S</creator><creator>Flaxman, Teresa E</creator><creator>Benoit, Daniel L</creator><general>Elsevier Ltd</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7X8</scope><scope>7TS</scope></search><sort><creationdate>20160201</creationdate><title>An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis</title><author>Shourijeh, Mohammad S ; Flaxman, Teresa E ; Benoit, Daniel L</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Adult</topic><topic>Algorithms</topic><topic>Electromyography</topic><topic>Electromyography - methods</topic><topic>Electromyography - standards</topic><topic>Humans</topic><topic>Knee</topic><topic>Male</topic><topic>Muscle synergy</topic><topic>Muscle, Skeletal - physiology</topic><topic>Non-negative matrix factorization</topic><topic>Physical Medicine and Rehabilitation</topic><topic>Repeatability</topic><topic>Reproducibility of Results</topic><topic>Robustness</topic><topic>Weight-Bearing - physiology</topic><topic>Young Adult</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Shourijeh, Mohammad S</creatorcontrib><creatorcontrib>Flaxman, Teresa E</creatorcontrib><creatorcontrib>Benoit, Daniel L</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>Physical Education Index</collection><jtitle>Journal of electromyography and kinesiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Shourijeh, Mohammad S</au><au>Flaxman, Teresa E</au><au>Benoit, Daniel L</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis</atitle><jtitle>Journal of electromyography and kinesiology</jtitle><addtitle>J Electromyogr Kinesiol</addtitle><date>2016-02-01</date><risdate>2016</risdate><volume>26</volume><spage>36</spage><epage>43</epage><pages>36-43</pages><issn>1050-6411</issn><eissn>1873-5711</eissn><abstract>Abstract The aim of this study was to evaluate non-negative matrix factorization (NMF) and concatenated NMF (CNMF) to analyze and reliably extract muscle synergies. NMF and CNMF were used to extract knee joint muscle synergies from surface EMGs collected during a weight bearing, force matching task. Repeatability and between subject similarity were evaluated for each method using intra-class correlation coefficients (ICCs). High repeatability was found for CNMF (&gt;0.99; 0.99–1.0) compared to NMF (&gt;0.26; range 0.26–0.98). Reasonable consistency across subjects was improved using the CNMF over the NMF approach. CNMF was found to be a more reliable approach than NMF and suitable for between subject comparison of muscle synergies.</abstract><cop>England</cop><pub>Elsevier Ltd</pub><pmid>26755163</pmid><doi>10.1016/j.jelekin.2015.12.001</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1050-6411
ispartof Journal of electromyography and kinesiology, 2016-02, Vol.26, p.36-43
issn 1050-6411
1873-5711
language eng
recordid cdi_proquest_miscellaneous_1811908390
source ScienceDirect Journals
subjects Adult
Algorithms
Electromyography
Electromyography - methods
Electromyography - standards
Humans
Knee
Male
Muscle synergy
Muscle, Skeletal - physiology
Non-negative matrix factorization
Physical Medicine and Rehabilitation
Repeatability
Reproducibility of Results
Robustness
Weight-Bearing - physiology
Young Adult
title An approach for improving repeatability and reliability of non-negative matrix factorization for muscle synergy analysis
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T16%3A37%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20approach%20for%20improving%20repeatability%20and%20reliability%20of%20non-negative%20matrix%20factorization%20for%20muscle%20synergy%20analysis&rft.jtitle=Journal%20of%20electromyography%20and%20kinesiology&rft.au=Shourijeh,%20Mohammad%20S&rft.date=2016-02-01&rft.volume=26&rft.spage=36&rft.epage=43&rft.pages=36-43&rft.issn=1050-6411&rft.eissn=1873-5711&rft_id=info:doi/10.1016/j.jelekin.2015.12.001&rft_dat=%3Cproquest_cross%3E1765579113%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c523t-8b04406c7d396d5c53ebdc484fe83079f8d21c7a9d10c25f30b29934df89bd133%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1765579113&rft_id=info:pmid/26755163&rfr_iscdi=true