Cargando…

Real-time, simultaneous myoelectric control using a convolutional neural network

The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a...

Descripción completa

Detalles Bibliográficos
Autores principales: Ameri, Ali, Akhaee, Mohammad Ali, Scheme, Erik, Englehart, Kevin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6136764/
https://www.ncbi.nlm.nih.gov/pubmed/30212573
http://dx.doi.org/10.1371/journal.pone.0203835
_version_ 1783355065206046720
author Ameri, Ali
Akhaee, Mohammad Ali
Scheme, Erik
Englehart, Kevin
author_facet Ameri, Ali
Akhaee, Mohammad Ali
Scheme, Erik
Englehart, Kevin
author_sort Ameri, Ali
collection PubMed
description The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts’ law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration.
format Online
Article
Text
id pubmed-6136764
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-61367642018-09-27 Real-time, simultaneous myoelectric control using a convolutional neural network Ameri, Ali Akhaee, Mohammad Ali Scheme, Erik Englehart, Kevin PLoS One Research Article The evolution of deep learning techniques has been transformative as they have allowed complex mappings to be trained between control inputs and outputs without the need for feature engineering. In this work, a myoelectric control system based on convolutional neural networks (CNN) is proposed as a possible alternative to traditional approaches that rely on specifically designed features. This CNN-based system is validated using a real-time Fitts’ law style target acquisition test requiring single and combined wrist motions. The performance of the proposed system is then compared to that of a standard support vector machine (SVM) based myoelectric system using a set of time-domain features. Despite the prevalence and demonstrated performance of these well-known features, no significant difference (p>0.05) was found between the two methods for any of the computed control metrics. This demonstrates the potential for automated learning approaches to extract complex and rich information from stochastic biological signals. This first evaluation of the usability of a CNN in a real-time myoelectric control environment provides a basis for further exploration. Public Library of Science 2018-09-13 /pmc/articles/PMC6136764/ /pubmed/30212573 http://dx.doi.org/10.1371/journal.pone.0203835 Text en © 2018 Ameri et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Ameri, Ali
Akhaee, Mohammad Ali
Scheme, Erik
Englehart, Kevin
Real-time, simultaneous myoelectric control using a convolutional neural network
title Real-time, simultaneous myoelectric control using a convolutional neural network
title_full Real-time, simultaneous myoelectric control using a convolutional neural network
title_fullStr Real-time, simultaneous myoelectric control using a convolutional neural network
title_full_unstemmed Real-time, simultaneous myoelectric control using a convolutional neural network
title_short Real-time, simultaneous myoelectric control using a convolutional neural network
title_sort real-time, simultaneous myoelectric control using a convolutional neural network
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6136764/
https://www.ncbi.nlm.nih.gov/pubmed/30212573
http://dx.doi.org/10.1371/journal.pone.0203835
work_keys_str_mv AT ameriali realtimesimultaneousmyoelectriccontrolusingaconvolutionalneuralnetwork
AT akhaeemohammadali realtimesimultaneousmyoelectriccontrolusingaconvolutionalneuralnetwork
AT schemeerik realtimesimultaneousmyoelectriccontrolusingaconvolutionalneuralnetwork
AT englehartkevin realtimesimultaneousmyoelectriccontrolusingaconvolutionalneuralnetwork