Prediction of muscle activity during loaded movements of the upper limb

Persistent Link:
http://hdl.handle.net/10150/610323
Title:
Prediction of muscle activity during loaded movements of the upper limb
Author:
Tibold, R.; Fuglevand, A. J.
Affiliation:
Departments of Physiology and Neuroscience, University of Arizona
Issue Date:
2015
Publisher:
BioMed Central
Citation:
Tibold and Fuglevand Journal of NeuroEngineering and Rehabilitation 2015, 12:6 http://www.jneuroengrehab.com/content/12/1/6
Journal:
Journal of NeuroEngineering and Rehabilitation
Rights:
© 2015 Tibold and Fuglevand; licensee BioMed Central. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0),
Collection Information:
This item is part of the UA Faculty Publications collection. For more information this item or other items in the UA Campus Repository, contact the University of Arizona Libraries at repository@u.library.arizona.edu.
Abstract:
BACKGROUND: Accurate prediction of electromyographic (EMG) signals associated with a variety of motor behaviors could, in theory, serve as activity templates needed to evoke movements in paralyzed individuals using functional electrical stimulation. Such predictions should encompass complex multi-joint movements and include interactions with objects in the environment. METHODS: Here we tested the ability of different artificial neural networks (ANNs) to predict EMG activities of 12 arm muscles while human subjects made free movements of the arm or grasped and moved objects of different weights and dimensions. Inputs to the trained ANNs included hand position, hand orientation, and thumb grip force. RESULTS: The ability of ANNs to predict EMG was equally as good for tasks involving interactions with external loads as for unloaded movements. The ANN that yielded the best predictions was a feed-forward network consisting of a single hidden layer of 30 neural elements. For this network, the average coefficient of determination (R2 value) between predicted and actual EMG signals across all nine subjects and 12 muscles during movements that involved episodes of moving objects was 0.43. CONCLUSION: This reasonable accuracy suggests that ANNs could be used to provide an initial estimate of the complex patterns of muscle stimulation needed to produce a wide array of movements, including those involving object interaction, in paralyzed individuals.
EISSN:
1743-0003
PubMed ID:
25592397
PubMed Central ID:
PMC4326445
DOI:
10.1186/1743-0003-12-6 [doi]
Keywords:
Functional electrical stimulation; Electromyography; Artificial neural networks; Kinematics; Grip force; Upper limb
Version:
Final published version
Additional Links:
http://jneuroengrehab.biomedcentral.com/articles/10.1186/1743-0003-12-6

Full metadata record

DC FieldValue Language
dc.contributor.authorTibold, R.en
dc.contributor.authorFuglevand, A. J.en
dc.date.accessioned2016-05-20T09:04:12Z-
dc.date.available2016-05-20T09:04:12Z-
dc.date.issued2015en
dc.identifier.citationTibold and Fuglevand Journal of NeuroEngineering and Rehabilitation 2015, 12:6 http://www.jneuroengrehab.com/content/12/1/6en
dc.identifier.pmid25592397en
dc.identifier.doi10.1186/1743-0003-12-6 [doi]en
dc.identifier.urihttp://hdl.handle.net/10150/610323-
dc.description.abstractBACKGROUND: Accurate prediction of electromyographic (EMG) signals associated with a variety of motor behaviors could, in theory, serve as activity templates needed to evoke movements in paralyzed individuals using functional electrical stimulation. Such predictions should encompass complex multi-joint movements and include interactions with objects in the environment. METHODS: Here we tested the ability of different artificial neural networks (ANNs) to predict EMG activities of 12 arm muscles while human subjects made free movements of the arm or grasped and moved objects of different weights and dimensions. Inputs to the trained ANNs included hand position, hand orientation, and thumb grip force. RESULTS: The ability of ANNs to predict EMG was equally as good for tasks involving interactions with external loads as for unloaded movements. The ANN that yielded the best predictions was a feed-forward network consisting of a single hidden layer of 30 neural elements. For this network, the average coefficient of determination (R2 value) between predicted and actual EMG signals across all nine subjects and 12 muscles during movements that involved episodes of moving objects was 0.43. CONCLUSION: This reasonable accuracy suggests that ANNs could be used to provide an initial estimate of the complex patterns of muscle stimulation needed to produce a wide array of movements, including those involving object interaction, in paralyzed individuals.en
dc.language.isoenen
dc.publisherBioMed Centralen
dc.relation.urlhttp://jneuroengrehab.biomedcentral.com/articles/10.1186/1743-0003-12-6en
dc.rights© 2015 Tibold and Fuglevand; licensee BioMed Central. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0),en
dc.subjectFunctional electrical stimulationen
dc.subjectElectromyographyen
dc.subjectArtificial neural networksen
dc.subjectKinematicsen
dc.subjectGrip forceen
dc.subjectUpper limben
dc.titlePrediction of muscle activity during loaded movements of the upper limben
dc.typeArticleen
dc.identifier.eissn1743-0003en
dc.contributor.departmentDepartments of Physiology and Neuroscience, University of Arizonaen
dc.identifier.journalJournal of NeuroEngineering and Rehabilitationen
dc.identifier.pmcidPMC4326445en
dc.description.collectioninformationThis item is part of the UA Faculty Publications collection. For more information this item or other items in the UA Campus Repository, contact the University of Arizona Libraries at repository@u.library.arizona.edu.en
dc.eprint.versionFinal published versionen

Related articles on PubMed

All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.