Show simple item record

dc.contributor.authorRasines, Irati
dc.contributor.authorPrada, Miguel
dc.contributor.authorBobrov, Viacheslav
dc.contributor.authorAgrawal, Dhruv
dc.contributor.authorMartinez, Leire
dc.contributor.authorIriondo, Pedro
dc.contributor.authorRemazeilles, Anthony
dc.contributor.authorMcIntyre, Joseph
dc.date.accessioned2022-03-21T22:18:42Z
dc.date.available2022-03-21T22:18:42Z
dc.date.issued2021-11-25
dc.identifier.citationRasines, Irati, Miguel Prada, Viacheslav Bobrov, Dhruv Agrawal, Leire Martinez, Pedro Iriondo, Anthony Remazeilles, and Joseph McIntyre. “Regulating Grip Forces through EMG-Controlled Protheses for Transradial Amputees.” Applied Sciences 11, no. 23 (November 25, 2021): 11199. doi:10.3390/app112311199.en
dc.identifier.urihttp://hdl.handle.net/11556/1310
dc.description.abstractThis study aims to evaluate different combinations of features and algorithms to be used in the control of a prosthetic hand wherein both the configuration of the fingers and the gripping forces can be controlled. This requires identifying machine learning algorithms and feature sets to detect both intended force variation and hand gestures in EMG signals recorded from upper-limb amputees. However, despite the decades of research into pattern recognition techniques, each new problem requires researchers to find a suitable classification algorithm, as there is no such thing as a universal ’best’ solution. Consideration of different techniques and data representation represents a fundamental practice in order to achieve maximally effective results. To this end, we employ a publicly-available database recorded from amputees to evaluate different combinations of features and classifiers. Analysis of data from 9 different individuals shows that both for classic features and for time-dependent power spectrum descriptors (TD-PSD) the proposed logarithmically scaled version of the current window plus previous window achieves the highest classification accuracy. Using linear discriminant analysis (LDA) as a classifier and applying a majority-voting strategy to stabilize the individual window classification, we obtain 88% accuracy with classic features and 89% with TD-PSD features.en
dc.description.sponsorshipThis paper is supported by European Union’s Horizon 2020 research and innovation programme under the Grant Agreement no 779967, project RobotUnion.en
dc.language.isoengen
dc.publisherMultidisciplinary Digital Publishing Institute (MDPI)en
dc.rightsAttribution 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.titleRegulating Grip Forces through EMG-Controlled Protheses for Transradial Amputeesen
dc.typearticleen
dc.identifier.doi10.3390/app112311199en
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/779967/EU/Stimulate ScaleUps to develop novel and challenging TEchnology and systems applicable to new Markets for ROBOtic soLUTIONs/RobotUnionen
dc.rights.accessRightsopenAccessen
dc.subject.keywordsClassificationen
dc.subject.keywordsForce level variationen
dc.subject.keywordsMyoelectric controlen
dc.subject.keywordsPattern recognitionen
dc.subject.keywordsRobustnessen
dc.subject.keywordsSurface electromyogram (sEMG)en
dc.subject.keywordsTransradial amputeesen
dc.identifier.essn2076-3417en
dc.issue.number23en
dc.journal.titleApplied Sciencesen
dc.page.initial11199en
dc.volume.number11en


Files in this item

Thumbnail

    Show simple item record

    Attribution 4.0 InternationalExcept where otherwise noted, this item's license is described as Attribution 4.0 International