Cargando…

Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features

Existing research on myoelectric control systems primarily focuses on extracting discriminative characteristics of the electromyographic (EMG) signal by designing handcrafted features. Recently, however, deep learning techniques have been applied to the challenging task of EMG-based gesture recognit...

Descripción completa

Detalles Bibliográficos
Autores principales: Côté-Allard, Ulysse, Campbell, Evan, Phinyomark, Angkoon, Laviolette, François, Gosselin, Benoit, Scheme, Erik
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7063031/
https://www.ncbi.nlm.nih.gov/pubmed/32195238
http://dx.doi.org/10.3389/fbioe.2020.00158
_version_ 1783504629558935552
author Côté-Allard, Ulysse
Campbell, Evan
Phinyomark, Angkoon
Laviolette, François
Gosselin, Benoit
Scheme, Erik
author_facet Côté-Allard, Ulysse
Campbell, Evan
Phinyomark, Angkoon
Laviolette, François
Gosselin, Benoit
Scheme, Erik
author_sort Côté-Allard, Ulysse
collection PubMed
description Existing research on myoelectric control systems primarily focuses on extracting discriminative characteristics of the electromyographic (EMG) signal by designing handcrafted features. Recently, however, deep learning techniques have been applied to the challenging task of EMG-based gesture recognition. The adoption of these techniques slowly shifts the focus from feature engineering to feature learning. Nevertheless, the black-box nature of deep learning makes it hard to understand the type of information learned by the network and how it relates to handcrafted features. Additionally, due to the high variability in EMG recordings between participants, deep features tend to generalize poorly across subjects using standard training methods. Consequently, this work introduces a new multi-domain learning algorithm, named ADANN (Adaptive Domain Adversarial Neural Network), which significantly enhances (p = 0.00004) inter-subject classification accuracy by an average of 19.40% compared to standard training. Using ADANN-generated features, this work provides the first topological data analysis of EMG-based gesture recognition for the characterization of the information encoded within a deep network, using handcrafted features as landmarks. This analysis reveals that handcrafted features and the learned features (in the earlier layers) both try to discriminate between all gestures, but do not encode the same information to do so. In the later layers, the learned features are inclined to instead adopt a one-vs.-all strategy for a given class. Furthermore, by using convolutional network visualization techniques, it is revealed that learned features actually tend to ignore the most activated channel during contraction, which is in stark contrast with the prevalence of handcrafted features designed to capture amplitude information. Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features.
format Online
Article
Text
id pubmed-7063031
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-70630312020-03-19 Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features Côté-Allard, Ulysse Campbell, Evan Phinyomark, Angkoon Laviolette, François Gosselin, Benoit Scheme, Erik Front Bioeng Biotechnol Bioengineering and Biotechnology Existing research on myoelectric control systems primarily focuses on extracting discriminative characteristics of the electromyographic (EMG) signal by designing handcrafted features. Recently, however, deep learning techniques have been applied to the challenging task of EMG-based gesture recognition. The adoption of these techniques slowly shifts the focus from feature engineering to feature learning. Nevertheless, the black-box nature of deep learning makes it hard to understand the type of information learned by the network and how it relates to handcrafted features. Additionally, due to the high variability in EMG recordings between participants, deep features tend to generalize poorly across subjects using standard training methods. Consequently, this work introduces a new multi-domain learning algorithm, named ADANN (Adaptive Domain Adversarial Neural Network), which significantly enhances (p = 0.00004) inter-subject classification accuracy by an average of 19.40% compared to standard training. Using ADANN-generated features, this work provides the first topological data analysis of EMG-based gesture recognition for the characterization of the information encoded within a deep network, using handcrafted features as landmarks. This analysis reveals that handcrafted features and the learned features (in the earlier layers) both try to discriminate between all gestures, but do not encode the same information to do so. In the later layers, the learned features are inclined to instead adopt a one-vs.-all strategy for a given class. Furthermore, by using convolutional network visualization techniques, it is revealed that learned features actually tend to ignore the most activated channel during contraction, which is in stark contrast with the prevalence of handcrafted features designed to capture amplitude information. Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features. Frontiers Media S.A. 2020-03-03 /pmc/articles/PMC7063031/ /pubmed/32195238 http://dx.doi.org/10.3389/fbioe.2020.00158 Text en Copyright © 2020 Côté-Allard, Campbell, Phinyomark, Laviolette, Gosselin and Scheme. http://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 Bioengineering and Biotechnology
Côté-Allard, Ulysse
Campbell, Evan
Phinyomark, Angkoon
Laviolette, François
Gosselin, Benoit
Scheme, Erik
Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title_full Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title_fullStr Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title_full_unstemmed Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title_short Interpreting Deep Learning Features for Myoelectric Control: A Comparison With Handcrafted Features
title_sort interpreting deep learning features for myoelectric control: a comparison with handcrafted features
topic Bioengineering and Biotechnology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7063031/
https://www.ncbi.nlm.nih.gov/pubmed/32195238
http://dx.doi.org/10.3389/fbioe.2020.00158
work_keys_str_mv AT coteallardulysse interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures
AT campbellevan interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures
AT phinyomarkangkoon interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures
AT laviolettefrancois interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures
AT gosselinbenoit interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures
AT schemeerik interpretingdeeplearningfeaturesformyoelectriccontrolacomparisonwithhandcraftedfeatures