Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier
The design of prosthetic controllers by means of neurophysiological signals still poses a crucial challenge to bioengineers. State of the art of electromyographic (EMG) continuous pattern recognition controllers rely on the questionable assumption that repeated muscular contractions produce repeatab...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9937197/ |
| _version_ | 1797805127879360512 |
|---|---|
| author | Daniele D'Accolti Katarina Dejanovic Leonardo Cappello Enzo Mastinu Max Ortiz-Catalan Christian Cipriani |
| author_facet | Daniele D'Accolti Katarina Dejanovic Leonardo Cappello Enzo Mastinu Max Ortiz-Catalan Christian Cipriani |
| author_sort | Daniele D'Accolti |
| collection | DOAJ |
| description | The design of prosthetic controllers by means of neurophysiological signals still poses a crucial challenge to bioengineers. State of the art of electromyographic (EMG) continuous pattern recognition controllers rely on the questionable assumption that repeated muscular contractions produce repeatable patterns of steady-state EMG signals. Conversely, we propose an algorithm that decodes wrist and hand movements by processing the signals that immediately follow the onset of contraction (i.e., the <inline-formula> <tex-math notation="LaTeX">$\textit {transient}$ </tex-math></inline-formula> EMG). We collected EMG data from the forearms of 14 non-amputee and 5 transradial amputee participants while they performed wrist flexion/extension, pronation/supination, and four hand grasps (power, lateral, bi-digital, open). We firstly identified the combination of wrist and hand movements that yielded the best control performance for the same participant (intra-subject classification). Then, we assessed the ability of our algorithm to classify participant data that were not included in the training set (cross-subject classification). Our controller achieved a median accuracy of ~96% with non-amputees, while it achieved heterogeneous outcomes with amputees, with a median accuracy of ~89%. Importantly, for each amputee, it produced at least one <inline-formula> <tex-math notation="LaTeX">$\textit {acceptable}$ </tex-math></inline-formula> combination of wrist-hand movements (i.e., with accuracy >85%). Regarding the cross-subject classifier, while our algorithm obtained promising results with non-amputees (accuracy up to ~80%), they were not as good with amputees (accuracy up to ~35%), possibly suggesting further assessments with domain-adaptation strategies. In general, our offline outcomes, together with a preliminary online assessment, support the hypothesis that the transient EMG decoding could represent a viable pattern recognition strategy, encouraging further online assessments. |
| first_indexed | 2024-03-13T05:46:38Z |
| format | Article |
| id | doaj.art-f877cb68cd3e439e8cecfa63c7838add |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:46:38Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-f877cb68cd3e439e8cecfa63c7838add2023-06-13T20:09:30ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102023-01-013120821710.1109/TNSRE.2022.32184309937197Decoding of Multiple Wrist and Hand Movements Using a Transient EMG ClassifierDaniele D'Accolti0https://orcid.org/0000-0001-8155-5160Katarina Dejanovic1https://orcid.org/0000-0003-0278-3208Leonardo Cappello2Enzo Mastinu3https://orcid.org/0000-0001-8361-9586Max Ortiz-Catalan4https://orcid.org/0000-0002-6084-3865Christian Cipriani5https://orcid.org/0000-0003-2108-0700BioRobotics Institute and the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, ItalyBioRobotics Institute and the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, ItalyBioRobotics Institute and the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, ItalyBioRobotics Institute and the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, ItalyCenter for Bionics and Pain Research, Mölndal, SwedenBioRobotics Institute and the Department of Excellence in Robotics and AI, Scuola Superiore Sant’Anna, Pisa, ItalyThe design of prosthetic controllers by means of neurophysiological signals still poses a crucial challenge to bioengineers. State of the art of electromyographic (EMG) continuous pattern recognition controllers rely on the questionable assumption that repeated muscular contractions produce repeatable patterns of steady-state EMG signals. Conversely, we propose an algorithm that decodes wrist and hand movements by processing the signals that immediately follow the onset of contraction (i.e., the <inline-formula> <tex-math notation="LaTeX">$\textit {transient}$ </tex-math></inline-formula> EMG). We collected EMG data from the forearms of 14 non-amputee and 5 transradial amputee participants while they performed wrist flexion/extension, pronation/supination, and four hand grasps (power, lateral, bi-digital, open). We firstly identified the combination of wrist and hand movements that yielded the best control performance for the same participant (intra-subject classification). Then, we assessed the ability of our algorithm to classify participant data that were not included in the training set (cross-subject classification). Our controller achieved a median accuracy of ~96% with non-amputees, while it achieved heterogeneous outcomes with amputees, with a median accuracy of ~89%. Importantly, for each amputee, it produced at least one <inline-formula> <tex-math notation="LaTeX">$\textit {acceptable}$ </tex-math></inline-formula> combination of wrist-hand movements (i.e., with accuracy >85%). Regarding the cross-subject classifier, while our algorithm obtained promising results with non-amputees (accuracy up to ~80%), they were not as good with amputees (accuracy up to ~35%), possibly suggesting further assessments with domain-adaptation strategies. In general, our offline outcomes, together with a preliminary online assessment, support the hypothesis that the transient EMG decoding could represent a viable pattern recognition strategy, encouraging further online assessments.https://ieeexplore.ieee.org/document/9937197/Myoelectric controlpattern recognitiontransient EMGhand wrist prostheticscross-subject classifier |
| spellingShingle | Daniele D'Accolti Katarina Dejanovic Leonardo Cappello Enzo Mastinu Max Ortiz-Catalan Christian Cipriani Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier IEEE Transactions on Neural Systems and Rehabilitation Engineering Myoelectric control pattern recognition transient EMG hand wrist prosthetics cross-subject classifier |
| title | Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier |
| title_full | Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier |
| title_fullStr | Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier |
| title_full_unstemmed | Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier |
| title_short | Decoding of Multiple Wrist and Hand Movements Using a Transient EMG Classifier |
| title_sort | decoding of multiple wrist and hand movements using a transient emg classifier |
| topic | Myoelectric control pattern recognition transient EMG hand wrist prosthetics cross-subject classifier |
| url | https://ieeexplore.ieee.org/document/9937197/ |
| work_keys_str_mv | AT danieledaccolti decodingofmultiplewristandhandmovementsusingatransientemgclassifier AT katarinadejanovic decodingofmultiplewristandhandmovementsusingatransientemgclassifier AT leonardocappello decodingofmultiplewristandhandmovementsusingatransientemgclassifier AT enzomastinu decodingofmultiplewristandhandmovementsusingatransientemgclassifier AT maxortizcatalan decodingofmultiplewristandhandmovementsusingatransientemgclassifier AT christiancipriani decodingofmultiplewristandhandmovementsusingatransientemgclassifier |