kth.sePublications KTH
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Influence of Input Features and EMG Type on Ankle Joint Torque Prediction With Support Vector Regression
KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Vehicle Engineering and Solid Mechanics. KTH MoveAbil Lab.ORCID iD: 0000-0001-9652-4594
KTH, School of Engineering Sciences (SCI), Engineering Mechanics. KTH MoveAbil Lab.
KTH, School of Engineering Sciences (SCI), Engineering Mechanics, Vehicle Engineering and Solid Mechanics. KTH MoveAbil Lab.ORCID iD: 0000-0002-2232-5258
2023 (English)In: IEEE transactions on neural systems and rehabilitation engineering, ISSN 1534-4320, E-ISSN 1558-0210, Vol. 31, p. 4286-4294Article in journal (Refereed) Published
Abstract [en]

Reliable and accurate EMG-driven prediction of joint torques are instrumental in the control of wearable robotic systems. This study investigates how different EMG input features affect the machine learning algorithm-based prediction of ankle joint torque in isometric and dynamic conditions. High-density electromyography (HD-EMG) of five lower leg muscles were recorded during isometric contractions and dynamic tasks. Four datasets (HD-EMG, HD-EMG with reduced dimensionality, features extracted from HD-EMG with Convolutional Neural Network, and bipolar EMG) were created and used alone or in combination with joint kinematic information for the prediction of ankle joint torque using Support Vector Regression. The performance was evaluated under intra-session, inter-subject, and inter-session cases. All HD-EMG-derived datasets led to significantly more accurate isometric ankle torque prediction than the bipolar EMG datasets. The highest torque prediction accuracy for the dynamic tasks was achieved using bipolar EMG or HD-EMG with reduced dimensionality in combination with kinematic features. The findings of this study contribute to the knowledge allowing an informed selection of appropriate features for EMG-driven torque prediction.

Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2023. Vol. 31, p. 4286-4294
Keywords [en]
Dynamic contraction, electromyography, joint torque, machine learning, support vector regression
National Category
Bioinformatics (Computational Biology)
Identifiers
URN: urn:nbn:se:kth:diva-340658DOI: 10.1109/TNSRE.2023.3323364ISI: 001098745800001PubMedID: 37815967Scopus ID: 2-s2.0-85174836404OAI: oai:DiVA.org:kth-340658DiVA, id: diva2:1818402
Note

QC 20231211

Available from: 2023-12-11 Created: 2023-12-11 Last updated: 2025-05-06Bibliographically approved
In thesis
1. Neuromechanical Assessment ofIntact and Impaired Muscle Control: High-density EMG-informed approach
Open this publication in new window or tab >>Neuromechanical Assessment ofIntact and Impaired Muscle Control: High-density EMG-informed approach
2025 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Neuromuscular impairments in ankle dorsi-/plantarflexor muscles presentrehabilitation challenges after spinal cord injury (SCI) and stroke. Reliabletorque prediction and characterization of muscle impairments are essential forguiding rehabilitation and monitoring recovery. This thesis aims to assess howhigh-density EMG (HDEMG) improves torque estimation by integrating spatialand neurophysiological data (Studies I & II) and examine motor unit (MU)behavior and corticomuscular connectivity in SCI and stroke (Studies III & IV).Proposed methodologies combine HDEMG with advanced signal processingtechniques. Specifically, Study I uses machine learning (ML) to predict torquefrom bipolar EMG, HDEMG, and extracted features. Study II incorporates acomputational cumulative spike train-driven motoneuron pool model into aneuromusculoskeletal framework to generate neural drive signals. Study IIIuses HDEMG decomposition to analyze MU firing behavior in SCI. Study IVinvestigates MU/EMG–EEG corticomuscular coherence (CMC) to assesscorticospinal disruptions in stroke.Findings from Studies I & II show ML methods predict torque well in staticconditions but face challenges in dynamic movement due to absence ofkinematic constraints. Neuromusculoskeletal modeling provides betterrepresentation of neural and mechanical function by incorporating MU firingproperties. Studies III & IV offer insights into MU-level changes inneuromuscular disorders. Specifically, Study III identifies SCI-related EMG andMU behavior alterations, reflecting compensatory motor control strategies.Study IV introduces MU-level CMC analysis in stroke, revealing that motorneuron parameters do not significantly determine CMC strength, and thefundamental pattern of beta-band coupling over motor areas remainsidentifiable across all subject groups and CMC modalities.Overall, this thesis demonstrates that HDEMG enhances torque estimation andneuromuscular assessment. By integrating spatial EMG features and MU-levelanalyses, it deepens understanding of pathological motor control andneurophysiology, with implications for rehabilitation, assistive devices, andneuromuscular modeling.

Abstract [sv]

Neuromuskulära funktionsnedsättningar i dorsal-/plantarflexor i fotledenutgör stora rehabiliteringsutmaningar efter ryggmärgsskada (RMS) och stroke.Att karakterisera muskel-funktionsnedsättningar är avgörande för att följa uppåterhämtning. Tillförlitlig vridmomentestimering är väsentlig för planering avrehabiliteringsstrategier. Denna avhandling syftar till att (i) bedöma hurhögdensitets elektromyografi (HDEMG) förbättrar vridmomentestimeringgenom att integrera rumsliga och neurofysiologiska data (Studie I & II) och (ii)undersöka muskelaktivering och motorenhetsbeteende (ME) hos individer medRMS och stroke (Studie III & IV).Metodologierna kombinerar HDEMG med avancerad signalbehandling. StudieI använder maskininlärning (ML) för att estimera vridmoment från EMG,HDEMG och EMG-baserade egenskaper. Studie II använder enberäkningsmodell för motoneuronpooler, driven av kumulativt spikmönster(CST), in i ett neuromuskuloskeletalt ramverk för att generera nervsignalstyrka.Studie III använder HDEMG-dekomposition för att analysera ME-avfyrning vidRMS. Studie IV undersöker ME/EMG-EEG corticomuskulär koherens (CMC)för att upptäcka corticospinala störningar hos individer efter stroke.Resultaten från Studie I och II visar att ML-metoder estimerar vridmomenttillförlitligt under statiska förhållanden men har svårigheter vid dynamiskarörelser på grund av saknande kinematisk information. Neuromuskuloskeletalmodellering avbildar bättre motorisk och mekanisk funktion genom attintegrera ME-avfyrningsegenskaper. Studie III och IV ger insikter i förändringarpå ME-nivå vid neuromuskulära sjukdomar. Studie III identifierar EMG- ochME-förändringar relaterade till RMS. Studie IV visar attmotorneuronparameterar inte påverkar CMC-styrka och att det grundläggandebeta-bandmönstret är identifierbart i alla CMC-modaliteter.Sammanfattningsvis visar denna avhandling att HDEMG förbättrarvridmomentestimering och neuromuskulär bedömning. Genom att integrerarumsliga EMG-egenskaper och ME-analyser fördjupas förståelsen förmotorstyrning och neurofysiologi, med implicita konsekvenser förrehabilitering, hjälpmedel och modellering.

Place, publisher, year, edition, pages
Stockholm: KTH Royal Institute of Technology, 2025. p. 72
Series
TRITA-SCI-FOU ; 2025:20
Keywords
Neuromuscular modeling, torque estimation, machine learning, motor unit, stroke, spinal cord injury, Neuromuskulär modellering, vridmomentestimering, maskininlärning, motorenhet, stroke, ryggmärgsskada.
National Category
Neurosciences Physiology and Anatomy Other Medical Engineering
Research subject
Engineering Mechanics
Identifiers
urn:nbn:se:kth:diva-363130 (URN)978-91-8106-248-9 (ISBN)
Public defence
2025-05-23, Kollegiesallen, Room 4301, Brinellvägen 6, Stockholm, 09:00 (English)
Opponent
Supervisors
Note

QC 250506

Available from: 2025-05-06 Created: 2025-05-06 Last updated: 2025-05-14Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Kizyte, AstaWang, Ruoli

Search in DiVA

By author/editor
Kizyte, AstaLei, YuchenWang, Ruoli
By organisation
Vehicle Engineering and Solid MechanicsEngineering Mechanics
In the same journal
IEEE transactions on neural systems and rehabilitation engineering
Bioinformatics (Computational Biology)

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 76 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf