Cargando…
Recalibration of myoelectric control with active learning
INTRODUCTION: Improving the robustness of myoelectric control to work over many months without the need for recalibration could reduce prosthesis abandonment. Current approaches rely on post-hoc error detection to verify the certainty of a decoder's prediction using predefined threshold value....
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9797496/ https://www.ncbi.nlm.nih.gov/pubmed/36590085 http://dx.doi.org/10.3389/fnbot.2022.1061201 |
_version_ | 1784860692820525056 |
---|---|
author | Szymaniak, Katarzyna Krasoulis, Agamemnon Nazarpour, Kianoush |
author_facet | Szymaniak, Katarzyna Krasoulis, Agamemnon Nazarpour, Kianoush |
author_sort | Szymaniak, Katarzyna |
collection | PubMed |
description | INTRODUCTION: Improving the robustness of myoelectric control to work over many months without the need for recalibration could reduce prosthesis abandonment. Current approaches rely on post-hoc error detection to verify the certainty of a decoder's prediction using predefined threshold value. Since the decoder is fixed, the performance decline over time is inevitable. Other approaches such as supervised recalibration and unsupervised self-recalibration entail limitations in scaling up and computational resources. The objective of this paper is to study active learning as a scalable, human-in-the-loop framework, to improve the robustness of myoelectric control. METHOD: Active learning and linear discriminate analysis methods were used to create an iterative learning process, to modify decision boundaries based on changes in the data. We simulated a real-time scenario. We exploited least confidence, smallest margin and entropy reduction sampling strategies in single and batch-mode sample selection. Optimal batch-mode sampling was considered using ranked batch-mode active learning. RESULTS: With only 3.2 min of data carefully selected by the active learner, the decoder outperforms random sampling by 4–5 and ~2% for able-bodied and people with limb difference, respectively. We observed active learning strategies to systematically and significantly enhance the decoders adaptation while optimizing the amount of training data on a class-specific basis. Smallest margin and least confidence uncertainty were shown to be the most supreme. DISCUSSION: We introduce for the first time active learning framework for long term adaptation in myoelectric control. This study simulates closed-loop environment in an offline manner and proposes a pipeline for future real-time deployment. |
format | Online Article Text |
id | pubmed-9797496 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-97974962022-12-30 Recalibration of myoelectric control with active learning Szymaniak, Katarzyna Krasoulis, Agamemnon Nazarpour, Kianoush Front Neurorobot Neuroscience INTRODUCTION: Improving the robustness of myoelectric control to work over many months without the need for recalibration could reduce prosthesis abandonment. Current approaches rely on post-hoc error detection to verify the certainty of a decoder's prediction using predefined threshold value. Since the decoder is fixed, the performance decline over time is inevitable. Other approaches such as supervised recalibration and unsupervised self-recalibration entail limitations in scaling up and computational resources. The objective of this paper is to study active learning as a scalable, human-in-the-loop framework, to improve the robustness of myoelectric control. METHOD: Active learning and linear discriminate analysis methods were used to create an iterative learning process, to modify decision boundaries based on changes in the data. We simulated a real-time scenario. We exploited least confidence, smallest margin and entropy reduction sampling strategies in single and batch-mode sample selection. Optimal batch-mode sampling was considered using ranked batch-mode active learning. RESULTS: With only 3.2 min of data carefully selected by the active learner, the decoder outperforms random sampling by 4–5 and ~2% for able-bodied and people with limb difference, respectively. We observed active learning strategies to systematically and significantly enhance the decoders adaptation while optimizing the amount of training data on a class-specific basis. Smallest margin and least confidence uncertainty were shown to be the most supreme. DISCUSSION: We introduce for the first time active learning framework for long term adaptation in myoelectric control. This study simulates closed-loop environment in an offline manner and proposes a pipeline for future real-time deployment. Frontiers Media S.A. 2022-12-15 /pmc/articles/PMC9797496/ /pubmed/36590085 http://dx.doi.org/10.3389/fnbot.2022.1061201 Text en Copyright © 2022 Szymaniak, Krasoulis and Nazarpour. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Szymaniak, Katarzyna Krasoulis, Agamemnon Nazarpour, Kianoush Recalibration of myoelectric control with active learning |
title | Recalibration of myoelectric control with active learning |
title_full | Recalibration of myoelectric control with active learning |
title_fullStr | Recalibration of myoelectric control with active learning |
title_full_unstemmed | Recalibration of myoelectric control with active learning |
title_short | Recalibration of myoelectric control with active learning |
title_sort | recalibration of myoelectric control with active learning |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9797496/ https://www.ncbi.nlm.nih.gov/pubmed/36590085 http://dx.doi.org/10.3389/fnbot.2022.1061201 |
work_keys_str_mv | AT szymaniakkatarzyna recalibrationofmyoelectriccontrolwithactivelearning AT krasoulisagamemnon recalibrationofmyoelectriccontrolwithactivelearning AT nazarpourkianoush recalibrationofmyoelectriccontrolwithactivelearning |