{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:08:35Z","timestamp":1783436915595,"version":"3.54.6"},"reference-count":45,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T00:00:00Z","timestamp":1722211200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Imperial-META Wearable Neural Interfaces Research Centre"},{"DOI":"10.13039\/100019827","name":"Meta","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100019827","id-type":"DOI","asserted-by":"crossref"}]},{"name":"EPSRC Centre for Doctoral Training in Neurotechnology for Life and Health","award":["EP\/L016737\/1"],"award-info":[{"award-number":["EP\/L016737\/1"]}]},{"name":"ERC Natural BionicS","award":["810346"],"award-info":[{"award-number":["810346"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["J. Neural Eng."],"published-print":{"date-parts":[[2024,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>\n                  <jats:italic>Objective<\/jats:italic>. Developing neural decoders robust to non-stationary conditions is essential to ensure their long-term accuracy and stability. This is particularly important when decoding the neural drive to muscles during dynamic contractions, which pose significant challenges for stationary decoders. <jats:italic>Approach<\/jats:italic>. We propose a novel adaptive electromyography (EMG) decomposition algorithm that builds on blind source separation methods by leveraging the Kullback\u2013Leibler divergence and kurtosis of the signals as metrics for online learning. The proposed approach provides a theoretical framework to tune the adaptation hyperparameters and compensate for non-stationarities in the mixing matrix, such as due to dynamic contractions, and to identify the underlying motor neuron (MN) discharges. The adaptation is performed in real-time (\u223c22 ms of computational time per 100\u2009ms batches). <jats:italic>Main results<\/jats:italic>. The hyperparameters of the proposed adaptation captured anatomical differences between recording locations (forearm vs wrist) and generalised across subjects. Once optimised, the proposed adaptation algorithm significantly improved all decomposition performance metrics with respect to the absence of adaptation in a wide range of motion of the wrist (80<jats:sup>\u2218<\/jats:sup>). The rate of agreement, sensitivity, and precision were <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mtext>\u2a7e<\/mml:mtext>\n                           <mml:mn>90<\/mml:mn>\n                           <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                        <\/mml:mrow>\n                     <\/mml:math>\n                  <\/jats:inline-formula> in <jats:inline-formula>\n                     <jats:tex-math\/>\n                     <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                           <mml:mtext>\u2a7e<\/mml:mtext>\n                           <mml:mn>80<\/mml:mn>\n                           <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                        <\/mml:mrow>\n                     <\/mml:math>\n                  <\/jats:inline-formula> of the cases in both simulated and experimentally recorded data, according to a two-source validation approach. <jats:italic>Significance<\/jats:italic>. The findings demonstrate the suitability of the proposed online learning metrics and hyperparameter optimisation to compensate the induced modulation and accurately decode MN discharges in dynamic conditions. Moreover, the study proposes an experimental validation method for EMG decomposition in dynamic tasks.<\/jats:p>","DOI":"10.1088\/1741-2552\/ad5ebf","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T22:28:35Z","timestamp":1720045715000},"page":"046023","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters"],"prefix":"10.1088","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7361-4618","authenticated-orcid":true,"given":"Irene","family":"Mendez Guerra","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3115-4577","authenticated-orcid":true,"given":"Deren Y","family":"Barsakcioglu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7883-2697","authenticated-orcid":true,"given":"Dario","family":"Farina","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2024,7,29]]},"reference":[{"key":"jnead5ebfbib1","doi-asserted-by":"publisher","first-page":"4487","DOI":"10.1109\/TSP.2007.896108","article-title":"Multichannel blind source separation using convolution kernel compensation","volume":"55","author":"Holobar","year":"2007","journal-title":"IEEE Trans. Signal Process."},{"key":"jnead5ebfbib2","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/13\/2\/026027","article-title":"Multi-channel intramuscular and surface EMG decomposition by convolutive blind source separation","volume":"13","author":"Negro","year":"2016","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib3","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TNSRE.2015.2412038","article-title":"A novel framework based on FastICA for high density surface EMG decomposition","volume":"24","author":"Chen","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jnead5ebfbib4","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1109\/TBME.2020.3006508","article-title":"Deep learning for robust decomposition of high-density surface EMG signals","volume":"68","author":"Clarke","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib5","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abeead","article-title":"A convolutional neural network to identify motor units from high-density surface electromyography signals in real time","volume":"18","author":"Wen","year":"2021","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib6","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1109\/JPROC.2015.2498665","article-title":"Characterization of human motor units from surface EMG decomposition","volume":"104","author":"Farina","year":"2016","journal-title":"Proc. IEEE"},{"key":"jnead5ebfbib7","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1109\/TBME.2020.3001942","article-title":"Control of spinal motoneurons by feedback from a non-invasive real-time interface","volume":"68","author":"Barsakcioglu","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib8","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/0168-5597(93)90018-K","article-title":"Far-field potential production by quadrupole generators in cylindrical volume conductors","volume":"88","author":"Dumitru","year":"1993","journal-title":"Electroencephalogr. Clin. Neurophysiol. Evoked Potentials"},{"key":"jnead5ebfbib9","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1097\/00004691-199709000-00009","article-title":"Near- and far-fields: source characteristics and the conducting medium in neurophysiology","volume":"14","author":"Stegeman","year":"1997","journal-title":"J. Clin. Neurophysiol."},{"key":"jnead5ebfbib10","doi-asserted-by":"publisher","first-page":"981","DOI":"10.1002\/mus.880141009","article-title":"Far-field potentials in muscle","volume":"14","author":"Dumitru","year":"1991","journal-title":"Muscle Nerve"},{"key":"jnead5ebfbib11","doi-asserted-by":"publisher","first-page":"477","DOI":"10.1007\/BF02350988","article-title":"Influence of muscle fibre shortening on estimates of conduction velocity and spectral frequencies from surface electromyographic signals","volume":"42","author":"Schulte","year":"2004","journal-title":"Med. Biol. Eng. Comput."},{"key":"jnead5ebfbib12","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/TNSRE.2018.2885283","article-title":"Motor unit identification from high-density surface electromyograms in repeated dynamic muscle contractions","volume":"27","author":"Glaser","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jnead5ebfbib13","doi-asserted-by":"publisher","first-page":"103533","DOI":"10.1109\/ACCESS.2021.3099015","article-title":"On the prediction of motor unit filter changes in blind source separation of high-density surface electromyograms during dynamic muscle contractions","volume":"9","author":"Kramberger","year":"2021","journal-title":"IEEE Access"},{"key":"jnead5ebfbib14","doi-asserted-by":"publisher","first-page":"123901","DOI":"10.1109\/ACCESS.2021.3107283","article-title":"Robust identification of motor unit discharges from high-density surface EMG in dynamic muscle contractions of the tibialis anterior","volume":"9","author":"Yokoyama","year":"2021","journal-title":"IEEE Access"},{"key":"jnead5ebfbib15","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1152\/japplphysiol.00043.2021","article-title":"Neural control of matched motor units during muscle shortening and lengthening at increasing velocities","volume":"130","author":"Oliveira","year":"2021","journal-title":"J. Appl. Physiol."},{"key":"jnead5ebfbib16","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1109\/TNSRE.2013.2247631","article-title":"Real-time motor unit identification from high-density surface EMG","volume":"21","author":"Glaser","year":"2013","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jnead5ebfbib17","doi-asserted-by":"publisher","first-page":"3501","DOI":"10.1109\/TBME.2020.2989311","article-title":"Adaptive real-time identification of motor unit discharges from non-stationary high-density surface electromyographic signals","volume":"67","author":"Chen","year":"2020","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib18","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ad33b0","article-title":"Adaptive HD-sEMG decomposition: towards robust real-time decoding of neural drive","volume":"21","author":"Yeung","year":"2024","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib19","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1371\/journal.pcbi.1012257","article-title":"NeuroMotion: open-source platform with neuromechanical and deep network models to generate surface EMG signals during voluntary movement","volume":"20","author":"Ma","year":"2024","journal-title":"PLoS Comput. Biol."},{"key":"jnead5ebfbib20","doi-asserted-by":"publisher","first-page":"1600","DOI":"10.1038\/s41467-023-37238-w","article-title":"A myoelectric digital twin for fast and realistic modelling in deep learning","volume":"14","author":"Maksymenko","year":"2023","journal-title":"Nat. Commun."},{"key":"jnead5ebfbib21","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1109\/TBME.2022.3217722","article-title":"A musculoskeletal model of the hand and wrist capable of simulating functional tasks","volume":"70","author":"McFarland","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib22","article-title":"Conditional generative models for simulation of EMG during naturalistic movements","author":"Ma","year":"2023"},{"key":"jnead5ebfbib23","doi-asserted-by":"publisher","first-page":"1404","DOI":"10.1152\/japplphysiol.00135.2018","article-title":"Central nervous system modulates the neuromechanical delay in a broad range for the control of muscle force","volume":"125","author":"Del Vecchio","year":"2018","journal-title":"J. Appl. Physiol."},{"key":"jnead5ebfbib24","doi-asserted-by":"publisher","first-page":"2470","DOI":"10.1152\/jn.1993.70.6.2470","article-title":"Models of recruitment and rate coding organization in motor-unit pools","volume":"70","author":"Fuglevand","year":"1993","journal-title":"J. Neurophysiol."},{"key":"jnead5ebfbib25","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1109\/TBME.2006.870256","article-title":"A finite element model for describing the effect of muscle shortening on surface EMG","volume":"53","author":"Mesin","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib26","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1113\/jphysiol.1987.sp016756","article-title":"Muscle fibre conduction velocity in motor units of the human anterior tibial muscle: a new size principle parameter","volume":"391","author":"Andreassen","year":"1987","journal-title":"J. Physiol."},{"key":"jnead5ebfbib27","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1109\/10.827303","article-title":"Noninvasive estimation of motor unit conduction velocity distribution using linear electrode arrays","volume":"47","author":"Farina","year":"2000","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"jnead5ebfbib28","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1152\/japplphysiol.01282.2005","article-title":"Amplitude cancellation reduces the size of motor unit potentials averaged from the surface EMG","volume":"100","author":"Keenan","year":"2006","journal-title":"J. Appl. Physiol."},{"key":"jnead5ebfbib29","doi-asserted-by":"publisher","first-page":"70013500101","DOI":"10.5014\/ajot.2016.015487","article-title":"Range of motion requirements for upper-limb activities of daily living","volume":"70","author":"Gates","year":"2016","journal-title":"Am. J. Occup. Ther."},{"key":"jnead5ebfbib30","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1016\/j.jht.2020.05.001","article-title":"Remote self-measurement of wrist range of motion performed on normal wrists by a minimally trained individual using the iPhone level application only demonstrated good reliability in measuring wrist flexion and extension","volume":"34","author":"Alford","year":"2021","journal-title":"J. Hand Ther."},{"key":"jnead5ebfbib31","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ac5f1a","article-title":"Far-field electric potentials provide access to the output from the spinal cord from wrist-mounted sensors","volume":"19","author":"Mendez Guerra","year":"2022","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib32","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1162\/neco.1997.9.7.1483","article-title":"A fast fixed-point algorithm for independent component analysis","volume":"9","author":"Hyv\u00e4rinen","year":"1997","journal-title":"Neural Comput."},{"key":"jnead5ebfbib33","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/11\/1\/016008","article-title":"Accurate identification of motor unit discharge patterns from high-density surface EMG and validation with a novel signal-based performance metric","volume":"11","author":"Holobar","year":"2014","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib34","first-page":"pp 4791","article-title":"Analysis of motor unit activities during multiple motor tasks by real-time EMG decomposition: perspective for myoelectric control","author":"Chen","year":"2020"},{"key":"jnead5ebfbib35","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1109\/78.553476","article-title":"Equivariant adaptive source separation","volume":"44","author":"Cardoso","year":"1996","journal-title":"IEEE Trans. Signal Process."},{"key":"jnead5ebfbib36","first-page":"pp 165","author":"Hyv\u00e4rinen","year":"2001"},{"key":"jnead5ebfbib37","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1152\/physrev.1983.63.2.387","article-title":"Motor unit and muscle activity in voluntary motor control","volume":"63","author":"Freund","year":"1983","journal-title":"Physiol. Rev."},{"key":"jnead5ebfbib38","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TNSRE.2010.2041593","article-title":"Experimental analysis of accuracy in the identification of motor unit spike trains from high-density surface EMG","volume":"18","author":"Holobar","year":"2010","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"jnead5ebfbib39","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1152\/jn.90219.2008","article-title":"Detecting the unique representation of motor-unit action potentials in the surface electromyogram","volume":"100","author":"Farina","year":"2008","journal-title":"J. Neurophysiol."},{"key":"jnead5ebfbib40","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1002\/mus.10256","article-title":"Surface EMG crosstalk between knee extensor muscles: experimental and model results","volume":"26","author":"Farina","year":"2002","journal-title":"Muscle Nerve"},{"key":"jnead5ebfbib41","doi-asserted-by":"publisher","first-page":"1479","DOI":"10.1113\/JP273662","article-title":"Tracking motor units longitudinally across experimental sessions with high-density surface electromyography","volume":"595","author":"Martinez-Valdes","year":"2017","journal-title":"J. Physiol."},{"key":"jnead5ebfbib42","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ab4d05","article-title":"Interfacing the neural output of the spinal cord: robust and reliable longitudinal identification of motor neurons in humans","volume":"17","author":"Del Vecchio","year":"2019","journal-title":"J. Neural Eng."},{"key":"jnead5ebfbib43","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1152\/japplphysiol.00271.2023","article-title":"Motor unit tracking using blind source separation filters and waveform cross-correlations: reliability under physiological and pharmacological conditions","volume":"135","author":"Goodlich","year":"2023","journal-title":"J. Appl. Physiol."},{"key":"jnead5ebfbib44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jelekin.2020.102426","article-title":"Tutorial: analysis of motor unit discharge characteristics from high-density surface EMG signals","volume":"53","author":"Del Vecchio","year":"2020","journal-title":"J. Electromyogr. Kinesiol."},{"key":"jnead5ebfbib45","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/ac35ac","article-title":"Skilled independent control of individual motor units via a non-invasive neuromuscular\u2013machine interface","volume":"18","author":"Formento","year":"2021","journal-title":"J. Neural Eng."}],"container-title":["Journal of Neural Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,29]],"date-time":"2024-07-29T12:24:12Z","timestamp":1722255852000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ad5ebf"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,29]]},"references-count":45,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2024,7,29]]},"published-print":{"date-parts":[[2024,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/1741-2552\/ad5ebf","relation":{},"ISSN":["1741-2560","1741-2552"],"issn-type":[{"value":"1741-2560","type":"print"},{"value":"1741-2552","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,29]]},"assertion":[{"value":"Adaptive EMG decomposition in dynamic conditions based on online learning metrics with tunable hyperparameters","name":"article_title","label":"Article Title"},{"value":"Journal of Neural Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-02-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-03","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-07-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}