Academic Journal
Προβολή σε EDS

Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.
Συγγραφείς: Zhao H; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China., Liu Y; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China., Li X; School of Computer Science and Technology, Anhui University, Hefei, Anhui 230601, P. R. China., Chen X; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China., Zhang X; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China.
Πηγή: International journal of neural systems [Int J Neural Syst] 2025 Apr; Vol. 35 (4), pp. 2550014. Date of Electronic Publication: 2025 Feb 04.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: World Scientific Pub. Co Country of Publication: Singapore NLM ID: 9100527 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1793-6462 (Electronic) Linking ISSN: 01290657 NLM ISO Abbreviation: Int J Neural Syst Subsets: MEDLINE
Imprint Name(s): Original Publication: Singapore ; Teaneck, N.J. : World Scientific Pub. Co., c1989-
Ιατρικοί όροι (MeSH): Electromyography*/methods , Fingers*/physiology , Pattern Recognition, Automated*/methods , Muscle, Skeletal*/physiology , Pattern Recognition, Physiological*/physiology, Movement/physiology ; Humans ; Male ; Adult ; Female ; Young Adult ; Deep Learning
Περίληψη: Cross-user variability is a well-known challenge that leads to severe performance degradation and impacts the robustness of practical myoelectric control systems. To address this issue, a novel method for myoelectric recognition of finger movement patterns is proposed by incorporating a neural decoding approach with unsupervised domain adaption (UDA) learning. In our method, the neural decoding approach is implemented by extracting microscopic features characterizing individual motor unit (MU) activities obtained from a two-stage online surface electromyogram (SEMG) decomposition. A specific deep learning model is designed and initially trained using labeled data from a set of existing users. The model can update adaptively when recognizing the movement patterns of a new user. The final movement pattern was determined by a fuzzy weighted decision strategy. SEMG signals were collected from the finger extensor muscles of 15 subjects to detect seven dexterous finger-movement patterns. The proposed method achieved a movement pattern recognition accuracy of ([Formula: see text])% over seven movements under cross-user testing scenarios, much higher than that of the conventional methods using global SEMG features. Our study presents a novel robust myoelectric pattern recognition approach at a fine-grained MU level, with wide applications in neural interface and prosthesis control.
Contributed Indexing: Keywords: Myoelectric pattern recognition; cross-user; motor unit; online SEMG decomposition
Entry Date(s): Date Created: 20250205 Date Completed: 20250506 Latest Revision: 20250526
Update Code: 20260130
DOI: 10.1142/S0129065725500145
PMID: 39907499
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 39907499
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Zhao+H%22">Zhao H</searchLink>; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China.<br /><searchLink fieldCode="AU" term="%22Liu+Y%22">Liu Y</searchLink>; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China.<br /><searchLink fieldCode="AU" term="%22Li+X%22">Li X</searchLink>; School of Computer Science and Technology, Anhui University, Hefei, Anhui 230601, P. R. China.<br /><searchLink fieldCode="AU" term="%22Chen+X%22">Chen X</searchLink>; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China.<br /><searchLink fieldCode="AU" term="%22Zhang+X%22">Zhang X</searchLink>; School of Microelectronics, University of Science and Technology of China, Hefei, Anhui 230002, P. R. China.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%229100527%22">International journal of neural systems</searchLink> [Int J Neural Syst] 2025 Apr; Vol. 35 (4), pp. 2550014. <i>Date of Electronic Publication: </i>2025 Feb 04.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22World+Scientific+Pub%2E+Co%22">World Scientific Pub. Co </searchLink><i>Country of Publication: </i>Singapore <i>NLM ID: </i>9100527 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1793-6462 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2201290657%22">01290657 </searchLink><i>NLM ISO Abbreviation: </i>Int J Neural Syst <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: Singapore ; Teaneck, N.J. : World Scientific Pub. Co., c1989-
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Electromyography%22">Electromyography*</searchLink>/<searchLink fieldCode="MM" term="%22Electromyography+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Fingers%22">Fingers*</searchLink>/<searchLink fieldCode="MM" term="%22Fingers+physiology%22">physiology</searchLink> <br /><searchLink fieldCode="MM" term="%22Pattern+Recognition%2C+Automated%22">Pattern Recognition, Automated*</searchLink>/<searchLink fieldCode="MM" term="%22Pattern+Recognition%2C+Automated+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Muscle%2C+Skeletal%22">Muscle, Skeletal*</searchLink>/<searchLink fieldCode="MM" term="%22Muscle%2C+Skeletal+physiology%22">physiology</searchLink> <br /><searchLink fieldCode="MM" term="%22Pattern+Recognition%2C+Physiological%22">Pattern Recognition, Physiological*</searchLink>/<searchLink fieldCode="MM" term="%22Pattern+Recognition%2C+Physiological+physiology%22">physiology</searchLink><br /><searchLink fieldCode="MH" term="%22Movement%22">Movement</searchLink>/<searchLink fieldCode="MH" term="%22Movement+physiology%22">physiology</searchLink> ; <searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Male%22">Male</searchLink> ; <searchLink fieldCode="MH" term="%22Adult%22">Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Young+Adult%22">Young Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Deep+Learning%22">Deep Learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Cross-user variability is a well-known challenge that leads to severe performance degradation and impacts the robustness of practical myoelectric control systems. To address this issue, a novel method for myoelectric recognition of finger movement patterns is proposed by incorporating a neural decoding approach with unsupervised domain adaption (UDA) learning. In our method, the neural decoding approach is implemented by extracting microscopic features characterizing individual motor unit (MU) activities obtained from a two-stage online surface electromyogram (SEMG) decomposition. A specific deep learning model is designed and initially trained using labeled data from a set of existing users. The model can update adaptively when recognizing the movement patterns of a new user. The final movement pattern was determined by a fuzzy weighted decision strategy. SEMG signals were collected from the finger extensor muscles of 15 subjects to detect seven dexterous finger-movement patterns. The proposed method achieved a movement pattern recognition accuracy of ([Formula: see text])% over seven movements under cross-user testing scenarios, much higher than that of the conventional methods using global SEMG features. Our study presents a novel robust myoelectric pattern recognition approach at a fine-grained MU level, with wide applications in neural interface and prosthesis control.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>Myoelectric pattern recognition; cross-user; motor unit; online SEMG decomposition
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20250205 <i>Date Completed: </i>20250506 <i>Latest Revision: </i>20250526
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260130
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1142/S0129065725500145
– Name: AN
  Label: PMID
  Group: ID
  Data: 39907499
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=39907499
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1142/S0129065725500145
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 2550014
    Subjects:
      – SubjectFull: Movement physiology
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: Adult
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Young Adult
        Type: general
      – SubjectFull: Deep Learning
        Type: general
      – SubjectFull: Electromyography methods
        Type: general
      – SubjectFull: Fingers physiology
        Type: general
      – SubjectFull: Pattern Recognition, Automated methods
        Type: general
      – SubjectFull: Muscle, Skeletal physiology
        Type: general
      – SubjectFull: Pattern Recognition, Physiological physiology
        Type: general
    Titles:
      – TitleFull: Online and Cross-User Finger Movement Pattern Recognition by Decoding Neural Drive Information from Surface Electromyogram.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhao H
      – PersonEntity:
          Name:
            NameFull: Liu Y
      – PersonEntity:
          Name:
            NameFull: Li X
      – PersonEntity:
          Name:
            NameFull: Chen X
      – PersonEntity:
          Name:
            NameFull: Zhang X
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: 2025 Apr
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-electronic
              Value: 1793-6462
          Numbering:
            – Type: volume
              Value: 35
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: International journal of neural systems
              Type: main
ResultId 1