Cargando…

Deep Cross-User Models Reduce the Training Burden in Myoelectric Control

The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has be...

Descripción completa

Detalles Bibliográficos
Autores principales: Campbell, Evan, Phinyomark, Angkoon, Scheme, Erik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8181426/
https://www.ncbi.nlm.nih.gov/pubmed/34108858
http://dx.doi.org/10.3389/fnins.2021.657958
_version_ 1783704093761470464
author Campbell, Evan
Phinyomark, Angkoon
Scheme, Erik
author_facet Campbell, Evan
Phinyomark, Angkoon
Scheme, Erik
author_sort Campbell, Evan
collection PubMed
description The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has been shown to be critical for robust machine learning models. This added training burden is prohibitive for most regular use cases, so cross-user models have been proposed that could leverage inter-repetition variability supplied by other users. Existing cross-user models have not yet achieved performance levels sufficient for commercialization and require users to closely adhere to a training protocol that is impractical without expert guidance. In this work, we extend a previously reported adaptive domain adversarial neural network (ADANN) to a cross-subject framework that requires very little training data from the end-user. We compare its performance to single-repetition within-user training and the previous state-of-the-art cross-subject technique, canonical correlation analysis (CCA). ADANN significantly outperformed CCA for both intact-limb (86.8–96.2%) and amputee (64.1–84.2%) populations. Moreover, the ADANN adaptation computation time was substantially lower than the time otherwise devoted to conducting a full within-subject training protocol. This study shows that cross-user models, enabled by deep-learned adaptations, may be a viable option for improved generalized pattern recognition-based myoelectric control.
format Online
Article
Text
id pubmed-8181426
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-81814262021-06-08 Deep Cross-User Models Reduce the Training Burden in Myoelectric Control Campbell, Evan Phinyomark, Angkoon Scheme, Erik Front Neurosci Neuroscience The effort, focus, and time to collect data and train EMG pattern recognition systems is one of the largest barriers to their widespread adoption in commercial applications. In addition to multiple repetitions of motions, including exemplars of confounding factors during the training protocol has been shown to be critical for robust machine learning models. This added training burden is prohibitive for most regular use cases, so cross-user models have been proposed that could leverage inter-repetition variability supplied by other users. Existing cross-user models have not yet achieved performance levels sufficient for commercialization and require users to closely adhere to a training protocol that is impractical without expert guidance. In this work, we extend a previously reported adaptive domain adversarial neural network (ADANN) to a cross-subject framework that requires very little training data from the end-user. We compare its performance to single-repetition within-user training and the previous state-of-the-art cross-subject technique, canonical correlation analysis (CCA). ADANN significantly outperformed CCA for both intact-limb (86.8–96.2%) and amputee (64.1–84.2%) populations. Moreover, the ADANN adaptation computation time was substantially lower than the time otherwise devoted to conducting a full within-subject training protocol. This study shows that cross-user models, enabled by deep-learned adaptations, may be a viable option for improved generalized pattern recognition-based myoelectric control. Frontiers Media S.A. 2021-05-24 /pmc/articles/PMC8181426/ /pubmed/34108858 http://dx.doi.org/10.3389/fnins.2021.657958 Text en Copyright © 2021 Campbell, Phinyomark and Scheme. 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
Campbell, Evan
Phinyomark, Angkoon
Scheme, Erik
Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title_full Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title_fullStr Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title_full_unstemmed Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title_short Deep Cross-User Models Reduce the Training Burden in Myoelectric Control
title_sort deep cross-user models reduce the training burden in myoelectric control
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8181426/
https://www.ncbi.nlm.nih.gov/pubmed/34108858
http://dx.doi.org/10.3389/fnins.2021.657958
work_keys_str_mv AT campbellevan deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol
AT phinyomarkangkoon deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol
AT schemeerik deepcrossusermodelsreducethetrainingburdeninmyoelectriccontrol