{"title":"EMG-Torque Estimation at Future Times","authors":"Kishor Koirala, Meera Dasog, Pu Liu, E. Clancy","doi":"10.1109/NEBEC.2013.88","DOIUrl":null,"url":null,"abstract":"This paper investigates the ability of surface electromyogram (EMG) to estimate joint torque at future times, up to 1 s. EMG was recorded from the biceps and triceps muscles of 54 subjects during constant-posture, force-varying contractions and related to the torque produced about the elbow. EMG to joint torque was predicted up to 80 ms into the future without any changes in the minimum least square error of 5.48% of maximum voluntary contraction for the best estimation model investigated: whitened, multiple-channel EMG used with a nonlinear model. Error progressively increased for prediction times above 80 ms.","PeriodicalId":153112,"journal":{"name":"2013 39th Annual Northeast Bioengineering Conference","volume":"436 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 39th Annual Northeast Bioengineering Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NEBEC.2013.88","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
This paper investigates the ability of surface electromyogram (EMG) to estimate joint torque at future times, up to 1 s. EMG was recorded from the biceps and triceps muscles of 54 subjects during constant-posture, force-varying contractions and related to the torque produced about the elbow. EMG to joint torque was predicted up to 80 ms into the future without any changes in the minimum least square error of 5.48% of maximum voluntary contraction for the best estimation model investigated: whitened, multiple-channel EMG used with a nonlinear model. Error progressively increased for prediction times above 80 ms.