Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control
Despite decades of research, commercially available powered myoelectric prostheses continue to use sequential, classification-based control. While regression-based approaches can improve the dexterity offered through simultaneous, independent, and proportional control, current training protocols lac...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10988608/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850132063975374848 |
|---|---|
| author | Christian Morrell Evan Campbell Ethan Eddy Erik Scheme |
| author_facet | Christian Morrell Evan Campbell Ethan Eddy Erik Scheme |
| author_sort | Christian Morrell |
| collection | DOAJ |
| description | Despite decades of research, commercially available powered myoelectric prostheses continue to use sequential, classification-based control. While regression-based approaches can improve the dexterity offered through simultaneous, independent, and proportional control, current training protocols lack consistency across studies and fail to capture realistic user behaviours, resulting in robustness issues. To address these challenges, this work employs context-informed incremental learning (CIIL) in an unconstrained, velocity-based environment for regression-based myoelectric control. Two new adaptive models, one inspired by previous works (O-CIIL) and one modified to factor in user compliance and behaviours (T-CIIL), were compared with two models trained using traditional screen-guided training. Sixteen participants completed an online Fitts’ Law target acquisition task. Both adaptive approaches significantly outperformed (<inline-formula> <tex-math notation="LaTeX">${p}\lt {0}.{05}$ </tex-math></inline-formula>) the non-adaptive models across a variety of metrics. Additionally, T-CIIL outperformed O-CIIL in alleviating drift and action interference, key issues that have plagued existing regression-based myoelectric control systems. These findings are supported by two novel metrics, namely action interference and simultaneity gain, which show that adding simultaneity often increases instability in the form of undesired and uncontrollable simultaneous motions. These findings demonstrate the viability of CIIL in an unconstrained, velocity-controlled environment for regression-based myoelectric control, and highlight the importance of capturing user behaviours when training regression-based myoelectric control systems. Source code is available on <uri>https://github.com/cbmorrell/adaptive-regression</uri> |
| format | Article |
| id | doaj-art-04baba9ca44d42fd809e50bea2eef38e |
| institution | OA Journals |
| issn | 1534-4320 1558-0210 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj-art-04baba9ca44d42fd809e50bea2eef38e2025-08-20T02:32:16ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1534-43201558-02102025-01-01331841185210.1109/TNSRE.2025.356724510988608Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric ControlChristian Morrell0https://orcid.org/0000-0002-7650-6310Evan Campbell1https://orcid.org/0000-0001-5399-4318Ethan Eddy2https://orcid.org/0000-0002-8392-3729Erik Scheme3https://orcid.org/0000-0002-4421-1016Institute of Biomedical Engineering, University of New Brunswick, Fredericton, NB, CanadaInstitute of Biomedical Engineering, University of New Brunswick, Fredericton, NB, CanadaInstitute of Biomedical Engineering, University of New Brunswick, Fredericton, NB, CanadaInstitute of Biomedical Engineering, University of New Brunswick, Fredericton, NB, CanadaDespite decades of research, commercially available powered myoelectric prostheses continue to use sequential, classification-based control. While regression-based approaches can improve the dexterity offered through simultaneous, independent, and proportional control, current training protocols lack consistency across studies and fail to capture realistic user behaviours, resulting in robustness issues. To address these challenges, this work employs context-informed incremental learning (CIIL) in an unconstrained, velocity-based environment for regression-based myoelectric control. Two new adaptive models, one inspired by previous works (O-CIIL) and one modified to factor in user compliance and behaviours (T-CIIL), were compared with two models trained using traditional screen-guided training. Sixteen participants completed an online Fitts’ Law target acquisition task. Both adaptive approaches significantly outperformed (<inline-formula> <tex-math notation="LaTeX">${p}\lt {0}.{05}$ </tex-math></inline-formula>) the non-adaptive models across a variety of metrics. Additionally, T-CIIL outperformed O-CIIL in alleviating drift and action interference, key issues that have plagued existing regression-based myoelectric control systems. These findings are supported by two novel metrics, namely action interference and simultaneity gain, which show that adding simultaneity often increases instability in the form of undesired and uncontrollable simultaneous motions. These findings demonstrate the viability of CIIL in an unconstrained, velocity-controlled environment for regression-based myoelectric control, and highlight the importance of capturing user behaviours when training regression-based myoelectric control systems. Source code is available on <uri>https://github.com/cbmorrell/adaptive-regression</uri>https://ieeexplore.ieee.org/document/10988608/Electromyographysimultaneous controlregressionuser-in-the-loopadaptationaction interference |
| spellingShingle | Christian Morrell Evan Campbell Ethan Eddy Erik Scheme Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control IEEE Transactions on Neural Systems and Rehabilitation Engineering Electromyography simultaneous control regression user-in-the-loop adaptation action interference |
| title | Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control |
| title_full | Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control |
| title_fullStr | Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control |
| title_full_unstemmed | Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control |
| title_short | Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control |
| title_sort | context informed incremental learning improves throughput and reduces drift in regression based myoelectric control |
| topic | Electromyography simultaneous control regression user-in-the-loop adaptation action interference |
| url | https://ieeexplore.ieee.org/document/10988608/ |
| work_keys_str_mv | AT christianmorrell contextinformedincrementallearningimprovesthroughputandreducesdriftinregressionbasedmyoelectriccontrol AT evancampbell contextinformedincrementallearningimprovesthroughputandreducesdriftinregressionbasedmyoelectriccontrol AT ethaneddy contextinformedincrementallearningimprovesthroughputandreducesdriftinregressionbasedmyoelectriccontrol AT erikscheme contextinformedincrementallearningimprovesthroughputandreducesdriftinregressionbasedmyoelectriccontrol |