Real-Time Motor Unit Tracking From sEMG Signals With Adaptive ICA on a Parallel Ultra-Low Power Processor
Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric co...
Saved in:
| Published in | IEEE transactions on biomedical circuits and systems Vol. 18; no. 4; pp. 771 - 782 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.08.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1932-4545 1940-9990 1940-9990 |
| DOI | 10.1109/TBCAS.2024.3410840 |
Cover
Loading…
| Abstract | Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58 <inline-formula id="ilm1"><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 14.91% and macro-F1 score of 85.86 <inline-formula id="ilm2"><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal. |
|---|---|
| AbstractList | Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58±14.91% and macro-F1 score of 85.86±14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal.Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58±14.91% and macro-F1 score of 85.86±14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal. Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58 <inline-formula id="ilm1"><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 14.91% and macro-F1 score of 85.86 <inline-formula id="ilm2"><tex-math notation="LaTeX">\pm</tex-math></inline-formula> 14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal. Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are able to identify motor unit (MU) discharges involved in muscle contractions. However, BSS approaches are currently restricted to isometric contractions, limiting their applicability in real-world scenarios. We present a strategy to track MUs across different dynamic hand gestures using adaptive independent component analysis (ICA): first, a pool of MUs is identified during isometric contractions, and the decomposition parameters are stored; during dynamic gestures, the decomposition parameters are updated online in an unsupervised fashion, yielding the refined MUs; then, a Pan-Tompkins-inspired algorithm detects the spikes in each MUs; finally, the identified spikes are fed to a classifier to recognize the gesture. We validate our approach on a 4-subject, 7-gesture + rest dataset collected with our custom 16-channel dry sEMG armband, achieving an average balanced accuracy of 85.58±14.91% and macro-F1 score of 85.86±14.48%. We deploy our solution onto GAP9, a parallel ultra-low-power microcontroller specialized for computation-intensive linear algebra applications at the edge, obtaining an energy consumption of 4.72 mJ @ 240 MHz and a latency of 121.3 ms for each 200 ms-long window of sEMG signal. |
| Author | Kartsch, Victor Zanghieri, Marcello Rapa, Pierangelo Maria Frey, Sebastian Benatti, Simone Benini, Luca Orlandi, Mattia |
| Author_xml | – sequence: 1 givenname: Mattia orcidid: 0000-0002-8553-3273 surname: Orlandi fullname: Orlandi, Mattia email: mattia.orlandi@unibo.it organization: Department of Electrical, Electronic, and Information Engineering, University of Bologna, Bologna, Italy – sequence: 2 givenname: Pierangelo Maria orcidid: 0000-0003-4596-0374 surname: Rapa fullname: Rapa, Pierangelo Maria email: pierangelomaria.rapa@unibo.it, pierangelomaria.rapa@unimore.it organization: Department of Electrical, Electronic, and Information Engineering, University of Bologna, Bologna, Italy – sequence: 3 givenname: Marcello orcidid: 0000-0002-4303-8389 surname: Zanghieri fullname: Zanghieri, Marcello email: marcello.zanghieri2@unibo.it organization: Department of Electrical, Electronic, and Information Engineering, University of Bologna, Bologna, Italy – sequence: 4 givenname: Sebastian orcidid: 0009-0000-6948-4363 surname: Frey fullname: Frey, Sebastian email: sebastian.frey@iis.ee.ethz.ch organization: Integrated Systems Laboratory, Department of Information Technology and Electrical Engineering, ETH Zürich, Zürich, Switzerland – sequence: 5 givenname: Victor orcidid: 0000-0003-3325-6347 surname: Kartsch fullname: Kartsch, Victor email: victor.kartsch@iis.ee.ethz.ch organization: Integrated Systems Laboratory, Department of Information Technology and Electrical Engineering, ETH Zürich, Zürich, Switzerland – sequence: 6 givenname: Luca orcidid: 0000-0001-8068-3806 surname: Benini fullname: Benini, Luca email: luca.benini@unibo.it, lbenini@iis.ee.ethz.ch organization: Department of Electrical, Electronic, and Information Engineering, University of Bologna, Bologna, Italy – sequence: 7 givenname: Simone orcidid: 0000-0002-5700-5342 surname: Benatti fullname: Benatti, Simone email: simone.benatti@unibo.it, simone.benatti@unimore.it organization: Department of Electrical, Electronic, and Information Engineering, University of Bologna, Bologna, Italy |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/38848226$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkU1PwkAQhjcGI4L-AWPMHr0U97PdHpEomkAkAvHYbNsprrZd3C0S_71F0HiaOTzvm8w8PdSpbQ0IXVAyoJTEN4vb0XA-YISJAReUKEGO0CmNBQniOCad3c5ZIKSQXdTz_o0QGbKYnaAuV0ooxsJTZJ5Bl8HCVICntrEOL2vT4IXT2bupV_je2Qr7u-kYz82q1qXHL6Z5xcNcrxvzCfhxNMS2xhrPtNNlCSVelo3TwcRu8cxuweGZsxl4b90ZOi7aAjg_zD5a3t8tRg_B5Gnc1kyCjEWyCSQHwqhWMtUFD4tc8JBCe14kSZjnMuK0UEzSlKUaWMQUgyjNYx4VmmgpVcb76Hrfu3b2YwO-SSrjMyhLXYPd-ISTUMaK0vY5fXR1QDdpBXmydqbS7iv5fU8LsD2QOeu9g-IPoSTZOUh-HCQ7B8nBQRu63IcMAPwLSMmoiPg3leSAJA |
| CODEN | ITBCCW |
| Cites_doi | 10.1109/TBCAS.2023.3314053 10.1109/sas51076.2021.9530007 10.1109/thms.2021.3086003 10.1109/TNSRE.2017.2759664 10.1109/TBME.2020.2989311 10.1523/eneuro.0064-23.2023 10.1109/TBCAS.2019.2914476 10.1109/72.761722 10.1109/ISCAS.2012.6271896 10.1109/TBCAS.2019.2955641 10.1016/j.bspc.2023.105178 10.1109/tbcas.2019.2959160 10.3389/fncom.2019.00014 10.1007/s11263-007-0075-7 10.1109/tbcas.2019.2955641 10.1109/TBCAS.2019.2925454 10.1109/tsp.2020.2985299 10.1109/BioCAS58349.2023.10388538 10.1109/TNSRE.2018.2885283 10.1109/tbcas.2019.2953998 10.3390/bdcc2030021 10.1088/1741-2560/13/2/026027 10.1109/tbme.1985.325532 10.1007/978-3-540-74494-8_77 10.1007/s11265-015-1070-9 10.1109/coins51742.2021.9524188 10.1007/s00422-008-0278-1 10.1109/ICABME53305.2021.9604876 10.1109/TSP.2007.896108 10.1023/a:1010933404324 10.1098/rsta.2019.0155 10.1109/tbcas.2020.2974154 10.1109/TNSRE.2015.2508759 10.1109/COINS57856.2023.10189286 10.1109/TNSRE.2015.2412038 10.1109/lsp.2005.863638 10.1109/MSP.2013.2251072 10.1016/j.jelekin.2020.102426 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TBCAS.2024.3410840 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 1940-9990 |
| EndPage | 782 |
| ExternalDocumentID | 38848226 10_1109_TBCAS_2024_3410840 10552147 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: ETH Zürich's Future Computing Laboratory – fundername: EU Horizon Europe project IntelliMan grantid: 101070136 – fundername: Huawei Technologies |
| GroupedDBID | --- 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION RIG NPM 7X8 |
| ID | FETCH-LOGICAL-c275t-53e021a85baf36fd4361e3417506dd5731f8251b2bae27282e7bd937fa0a558c3 |
| IEDL.DBID | RIE |
| ISSN | 1932-4545 1940-9990 |
| IngestDate | Fri Jul 11 04:33:53 EDT 2025 Thu Jan 02 22:29:08 EST 2025 Tue Jul 01 05:12:39 EDT 2025 Wed Aug 27 02:04:21 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c275t-53e021a85baf36fd4361e3417506dd5731f8251b2bae27282e7bd937fa0a558c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0003-4596-0374 0000-0002-5700-5342 0000-0002-4303-8389 0009-0000-6948-4363 0000-0003-3325-6347 0000-0001-8068-3806 0000-0002-8553-3273 |
| PMID | 38848226 |
| PQID | 3065981119 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | pubmed_primary_38848226 proquest_miscellaneous_3065981119 ieee_primary_10552147 crossref_primary_10_1109_TBCAS_2024_3410840 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2024-08-01 |
| PublicationDateYYYYMMDD | 2024-08-01 |
| PublicationDate_xml | – month: 08 year: 2024 text: 2024-08-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transactions on biomedical circuits and systems |
| PublicationTitleAbbrev | TBCAS |
| PublicationTitleAlternate | IEEE Trans Biomed Circuits Syst |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | ref13 ref35 ref12 ref15 ref37 ref14 ref36 ref31 ref30 ref11 ref33 ref10 ref32 ref2 ref1 ref17 ref39 ref16 ref38 ref19 ref18 Hyvärinen (ref25) 2001 ref24 ref23 (ref29) 2022 Amari (ref34) 1995; 8 ref26 ref20 ref42 ref41 ref22 ref21 ref28 ref27 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 |
| References_xml | – volume-title: Independent Component Analysis (Adaptive and LearningSystems for Signal Processing, Communications, and Control) year: 2001 ident: ref25 – ident: ref11 doi: 10.1109/TBCAS.2023.3314053 – ident: ref39 doi: 10.1109/sas51076.2021.9530007 – ident: ref3 doi: 10.1109/thms.2021.3086003 – ident: ref19 doi: 10.1109/TNSRE.2017.2759664 – ident: ref22 doi: 10.1109/TBME.2020.2989311 – ident: ref32 doi: 10.1523/eneuro.0064-23.2023 – ident: ref23 doi: 10.1109/TBCAS.2019.2914476 – ident: ref17 doi: 10.1109/72.761722 – ident: ref26 doi: 10.1109/ISCAS.2012.6271896 – ident: ref40 doi: 10.1109/TBCAS.2019.2955641 – ident: ref20 doi: 10.1016/j.bspc.2023.105178 – ident: ref7 doi: 10.1109/tbcas.2019.2959160 – ident: ref15 doi: 10.3389/fncom.2019.00014 – ident: ref33 doi: 10.1007/s11263-007-0075-7 – ident: ref8 doi: 10.1109/tbcas.2019.2955641 – ident: ref24 doi: 10.1109/TBCAS.2019.2925454 – ident: ref6 doi: 10.1109/tsp.2020.2985299 – ident: ref10 doi: 10.1109/BioCAS58349.2023.10388538 – ident: ref21 doi: 10.1109/TNSRE.2018.2885283 – ident: ref5 doi: 10.1109/tbcas.2019.2953998 – ident: ref9 doi: 10.1109/TBCAS.2023.3314053 – ident: ref1 doi: 10.3390/bdcc2030021 – ident: ref16 doi: 10.1088/1741-2560/13/2/026027 – ident: ref35 doi: 10.1109/tbme.1985.325532 – ident: ref14 doi: 10.1007/978-3-540-74494-8_77 – ident: ref36 doi: 10.1007/s11265-015-1070-9 – ident: ref41 doi: 10.1109/coins51742.2021.9524188 – ident: ref2 doi: 10.1007/s00422-008-0278-1 – ident: ref12 doi: 10.1109/ICABME53305.2021.9604876 – ident: ref13 doi: 10.1109/TSP.2007.896108 – ident: ref38 doi: 10.1023/a:1010933404324 – ident: ref37 doi: 10.1098/rsta.2019.0155 – ident: ref4 doi: 10.1109/tbcas.2020.2974154 – ident: ref27 doi: 10.1109/TNSRE.2015.2508759 – ident: ref28 doi: 10.1109/COINS57856.2023.10189286 – ident: ref18 doi: 10.1109/TNSRE.2015.2412038 – ident: ref31 doi: 10.1109/lsp.2005.863638 – year: 2022 ident: ref29 article-title: Inference: tiny. v1.0 Results – ident: ref42 doi: 10.1109/MSP.2013.2251072 – volume: 8 volume-title: Proc. Adv. Neural Inf. Process. Syst. year: 1995 ident: ref34 article-title: A new learning algorithm for blind signal separation – ident: ref30 doi: 10.1016/j.jelekin.2020.102426 |
| SSID | ssj0056292 |
| Score | 2.3845656 |
| Snippet | Spike extraction by blind source separation (BSS) algorithms can successfully extract physiologically meaningful information from the sEMG signal, as they are... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 771 |
| SubjectTerms | Blind source separation Electrodes Electromyography Graphical user interfaces human-machine interfaces Independent component analysis low-power Machine learning Motors Muscles on-device learning online learning PULP Real-time systems surface EMG |
| Title | Real-Time Motor Unit Tracking From sEMG Signals With Adaptive ICA on a Parallel Ultra-Low Power Processor |
| URI | https://ieeexplore.ieee.org/document/10552147 https://www.ncbi.nlm.nih.gov/pubmed/38848226 https://www.proquest.com/docview/3065981119 |
| Volume | 18 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV3dT9RAEJ8IDwYeFBH0FM2Q8GZ69Lq3_Xg8L5xIOEKAi7w1-1W5gC0pvZj41zuzbQ2akPjWh37ubGd-v52d-QEcRCYa6VRb-tMSG5DDC4PUpTaQWkfSRrGShoni_Cw-XoxPruV1V6zua2Gcc37zmRvyoc_l28qseKnskMUcWVdnDdaIubXFWr3bpTjuFZAZkHAjb9lXyITZ4dXn6eSSuGA0HpLTDonTbMBzkaZjio7xXwHJK6w8DTZ90Jm9hLP-ddu9JrfDVaOH5tc_nRz_-3u24EUHP3HSzpdX8MyV27D5qCnha1heEHYMuDQE5xUxcmRYihTTDK-q46yufuDD0fwLXi6_c_Nl_LZsbnBi1T17Tvw6nWBVosJzVbNOyx0u7ppaBafVTzxnSTbsahOqegcWs6Or6XHQCTIEJkpkE0jhCBKoVGpViLiwYxGPHI0ooY7YWpmIUcGVsDrSykUJkTmXaEv4p1ChkjI1YhfWy6p0bwHjTMUZcUvBAuwjo5XlhKspQhOKROlkAJ96q-T3bd-N3POVMMu9OXM2Z96ZcwA7PLqPzmwHdgD7vSVz-m04F6JKV60ecsH55JQcfTaAN62J_1zdz4x3T9z1PWzww9ttgHuw3tQr94GgSaM_-in5G0S52pY |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9NAEB6VVoJygAJtCa8uEjfk1PF6_TiGqCFtk6iiiejN2pfbqMWuXEdI_Hpm1jYqSJW4-WBb653dmW88-80H8CnQwUAlyuBOi42HDs_3EpsYTygVCBNEUmhKFGfzaLIMTy7ERUtWd1wYa607fGb7dOlq-abUa_pVdkhijqSr8wi2MPCHaUPX6hwvRnKngUyQhFp5i44j46eHiy-j4Tlmg0HYR7ftY1azDY95koQYH6O_QpLTWHkYbrqwM34O827AzWmT6_66Vn39659ejv_9RTvwrAWgbNismBewYYuX8PReW8JXsPqG6NEjcgiblZiTMwKmDKOapv_qbFyVP9jd0ewrO19dUvtl9n1VX7GhkbfkO9nxaMjKgkl2JitSarlhy5u6kt60_MnOSJSNteyEstqF5fhoMZp4rSSDp4NY1J7gFkGBTISSOY9yE_JoYHFGEXdExoiYD3LiwqpASRvEmM7ZWBlEQLn0pRCJ5nuwWZSFfQ0sSmWUYnbJSYJ9oJU0VHLVua99HksV9-BzZ5Xstum8kbmMxU8zZ86MzJm15uzBLs3uvTubie3Bx86SGW4cqobIwpbru4xTRTlBV5_2YL8x8Z-nu5Xx5oG3HsCTyWI2zabH89O3sE0DaQ4FvoPNulrb9whUavXBLc_f7QTd5g |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Real-Time+Motor+Unit+Tracking+From+sEMG+Signals+With+Adaptive+ICA+on+a+Parallel+Ultra-Low+Power+Processor&rft.jtitle=IEEE+transactions+on+biomedical+circuits+and+systems&rft.au=Orlandi%2C+Mattia&rft.au=Rapa%2C+Pierangelo+Maria&rft.au=Zanghieri%2C+Marcello&rft.au=Frey%2C+Sebastian&rft.date=2024-08-01&rft.issn=1932-4545&rft.eissn=1940-9990&rft.volume=18&rft.issue=4&rft.spage=771&rft.epage=782&rft_id=info:doi/10.1109%2FTBCAS.2024.3410840&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TBCAS_2024_3410840 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1932-4545&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1932-4545&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1932-4545&client=summon |