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...

Full description

Saved in:
Bibliographic Details
Main Authors: Christian Morrell, Evan Campbell, Ethan Eddy, Erik Scheme
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&#x2019; 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&#x2019; 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