{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:50:23Z","timestamp":1791355823001,"version":"4.3.1"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Rehabil. Sci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Surface electromyography (sEMG) is the dominant non-invasive route to volitional prosthetic control, but a closed-world classifier issues a command for every input, including inputs corresponding to no trained gesture. This study evaluated a low-cost, three-gesture sEMG control pipeline combining a Random Forest classifier with rejection on the maximum Random-Forest class probability and temporal majority voting, and measured the resulting rejection behaviour rather than assuming it.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Three data sources were analysed: modelled synthetic sEMG; Ninapro DB5 (10 subjects, 16 channels at 200\u2009Hz, documented three-channel subset); and live three-channel sEMG from 13 healthy limb-intact adults recorded over three sessions with MyoWare sensors spaced equally around the forearm flexor group. Each of the 117 recordings lasted 120\u2009s, comprising a 60\u2009s continuous phase and four 10\u2009s sustained contractions separated by 5\u2009s of rest, yielding 21,294 windows of which 4,212 were rest. Channel interleaving gave an effective 333.3\u2009Hz per channel. All datasets were segmented in physical time (0.6\u2009s window, 0.2\u2009s overlap) without resampling, and four time-domain features (MAV, RMS, WL, ZC) were classified by a 100-tree Random Forest. Evaluation used repetition-level, cross-session and leave-one-participant-out (LOPO) splits, with calibration and threshold selection confined to a participant-disjoint partition. Models were trained and tested within each domain, so the three accuracies index benchmark difficulty rather than transfer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      LOPO accuracy was 80.2% (synthetic), 74.5% (DB5) and 80.2% (live). The pooled window-level split used originally overestimated live accuracy by 7.7 percentage points. Expected calibration error was 0.147 uncalibrated and 0.038 after Platt scaling. Open-set AUROC was 0.842 against rest, 0.784 under electrode displacement and 0.741 for held-out movements, and 7.4% of windows were confidently incorrect. The complete pipeline reduced false actuation from 19.80% to 5.00% and command switching from 0.16 to 0.02\u2009\n                      <jats:inline-formula>\n                        <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" id=\"IM1\">\n                          <mml:msup>\n                            <mml:mrow>\n                              <mml:mi mathvariant=\"normal\">s<\/mml:mi>\n                            <\/mml:mrow>\n                            <mml:mrow>\n                              <mml:mo>\u2212<\/mml:mo>\n                              <mml:mn>1<\/mml:mn>\n                            <\/mml:mrow>\n                          <\/mml:msup>\n                        <\/mml:math>\n                      <\/jats:inline-formula>\n                      , while rejecting 18.40% of windows and raising median latency from 0.60 to 1.95\u2009s. The prototype completed 12 of 15 benchtop trials.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The results support a benchtop engineering proof of concept with quantified rejection and latency behaviour, not clinical safety or deployment readiness.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fresc.2026.1864998","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:58:51Z","timestamp":1791352731000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Confidence-gated temporal voting for EMG-based prosthetic arm control: a low-cost end-to-end pipeline with quantified rejection behaviour"],"prefix":"10.3389","volume":"7","author":[{"given":"Anagha","family":"Shinde","sequence":"first","affiliation":[{"name":"School of Engineering and Science, MIT ADT Campus, MIT Art, Design and Technology University","place":["Pune, Maharashtra, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Virendra","family":"Shete","sequence":"additional","affiliation":[{"name":"School of Engineering and Science, MIT ADT Campus, MIT Art, Design and Technology University","place":["Pune, Maharashtra, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ninad","family":"Mehendale","sequence":"additional","affiliation":[{"name":"K. J. Somaiya School of Engineering, Somaiya Vidyavihar University","place":["Mumbai, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"140053","DOI":"10.1038\/sdata.2014.53","article-title":"Electromyography data for non-invasive naturally-controlled robotic hand prostheses","volume":"1","author":"Atzori","year":"2014","journal-title":"Sci Data"},{"key":"B2","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1682\/JRRD.2010.09.0177","article-title":"Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use","volume":"48","author":"Scheme","year":"2011","journal-title":"J Rehabil Res Dev"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1152\/jn.01018.2009","article-title":"Relationship between firing rate and recruitment threshold of motoneurons in voluntary isometric contractions","volume":"104","author":"De Luca","year":"2010","journal-title":"J Neurophysiol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.bspc.2014.08.017","article-title":"Combined surface and intramuscular EMG for improved real-time myoelectric control performance","volume":"17","author":"Kamavuako","year":"2015","journal-title":"Biomed Signal Process Control"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1563","DOI":"10.1109\/TBME.2013.2238939","article-title":"Confidence-based rejection for improved pattern recognition myoelectric control","volume":"60","author":"Scheme","year":"2013","journal-title":"IEEE Trans Biomed Eng"},{"key":"B6","doi-asserted-by":"publisher","first-page":"862193","DOI":"10.3389\/fnbot.2022.862193","article-title":"Rejecting novel motions in high-density myoelectric pattern recognition using hybrid neural networks","volume":"16","author":"Wu","year":"2022","journal-title":"Front Neurorobot"},{"key":"B7","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1109\/TBME.2003.813539","article-title":"A robust, real-time control scheme for multifunction myoelectric control","volume":"50","author":"Englehart","year":"2003","journal-title":"IEEE Trans Biomed Eng"},{"key":"B8","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/TIT.1970.1054406","article-title":"On optimum recognition error and reject tradeoff","volume":"16","author":"Chow","year":"1970","journal-title":"IEEE Trans Inf Theory"},{"key":"B9","doi-asserted-by":"publisher","first-page":"2002","DOI":"10.1109\/JBHI.2018.2878907","article-title":"Effects of confidence-based rejection on usability and error in pattern recognition-based myoelectric control","volume":"23","author":"Robertson","year":"2019","journal-title":"IEEE J Biomed Health Inform"},{"key":"B10","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/THMS.2021.3123186","article-title":"CNN confidence estimation for rejection-based hand gesture classification in myoelectric control","volume":"52","author":"Bao","year":"2022","journal-title":"IEEE Trans Hum Mach Syst"},{"key":"B11","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/TNSRE.2022.3141593","article-title":"Reliability analysis for finger movement recognition with raw electromyographic signal by evidential convolutional networks","volume":"30","author":"Lin","year":"2022","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B12","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/10.204774","article-title":"A new strategy for multifunction myoelectric control","volume":"40","author":"Hudgins","year":"1993","journal-title":"IEEE Trans Biomed Eng"},{"key":"B13","doi-asserted-by":"publisher","first-page":"17004","DOI":"10.1109\/ACCESS.2022.3166885","article-title":"Machine learning and signal processing based analysis of sEMG signals for daily action classification","volume":"10","author":"Sadiq","year":"2022","journal-title":"IEEE Access"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e0186132","DOI":"10.1371\/journal.pone.0186132","article-title":"Comparison of six electromyography acquisition setups on hand movement classification tasks","volume":"12","author":"Pizzolato","year":"2017","journal-title":"PLoS One"},{"key":"B15","doi-asserted-by":"publisher","first-page":"463","DOI":"10.3390\/bioengineering13040463","article-title":"Optimized signal acquisition and advanced AI for robust 1D EMG classification: a comparative study of machine learning, deep learning, and reinforcement learning","volume":"13","author":"Shinde","year":"2026","journal-title":"Bioengineering"},{"key":"B16","author":"Yazawa","year":""},{"key":"B17","author":"Niculescu-Mizil","year":""},{"key":"B18","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1109\/TMRB.2024.3377530","article-title":"Explorations of autonomous prosthetic grasping via proximity vision and deep learning","volume":"6","author":"Mastinu","year":"2024","journal-title":"IEEE Trans Med Rob Bion"},{"key":"B19","doi-asserted-by":"publisher","first-page":"2396","DOI":"10.1109\/TNSRE.2022.3194582","article-title":"Evoked tactile feedback and control scheme on functional utility of prosthetic hand","volume":"30","author":"Vargas","year":"2022","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1134827","DOI":"10.3389\/fnhum.2023.1134827","article-title":"A survey of EEG and machine learning-based methods for neural rehabilitation","volume":"17","author":"Singh","year":"2023","journal-title":"Front Hum Neurosci"},{"key":"B21","doi-asserted-by":"publisher","first-page":"4329","DOI":"10.1109\/TNSRE.2023.3327907","article-title":"Neural correlation of EEG and eye movement in natural grasping intention estimation","volume":"31","author":"Lin","year":"2023","journal-title":"IEEE Trans Neural Syst Rehabil Eng"},{"key":"B22","doi-asserted-by":"publisher","first-page":"7420","DOI":"10.1016\/j.eswa.2012.01.102","article-title":"Feature reduction and selection for EMG signal classification","volume":"39","author":"Phinyomark","year":"2012","journal-title":"Expert Syst Appl"},{"key":"B23","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B24","author":"Shinde","year":""},{"key":"B25","author":"Shinde","year":""},{"key":"B26","author":"Shinde","year":""}],"container-title":["Frontiers in Rehabilitation Sciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fresc.2026.1864998\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T05:58:52Z","timestamp":1791352732000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fresc.2026.1864998\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":26,"alternative-id":["10.3389\/fresc.2026.1864998"],"URL":"https:\/\/doi.org\/10.3389\/fresc.2026.1864998","relation":{},"ISSN":["2673-6861"],"issn-type":[{"value":"2673-6861","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1864998"}}