Sparse Gaussian process regression in real-time myoelectric control

Jung, MC; Chai, R; Zheng, J; Nguyen, H

Sparse Gaussian process regression in real-time myoelectric control

Jung, MC Chai, R

Zheng, J Nguyen, H

Permalink

Publisher:: Inderscience Publishers
Publication Type:: Journal Article
Citation:: International Journal of Modelling, Identification and Control, 2021, 39, (1), pp. 51-60
Issue Date:: 2021-01-01

Closed Access

	Filename	Description	Size
	ijmic.2021.123372.pdf	Published version	1.95 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Jung, MC
dc.contributor.author	Chai, R https://orcid.org/0000-0002-1922-7024
dc.contributor.author	Zheng, J
dc.contributor.author	Nguyen, H
dc.date.accessioned	2022-09-19T23:19:03Z
dc.date.available	2022-09-19T23:19:03Z
dc.date.issued	2021-01-01
dc.identifier.citation	International Journal of Modelling, Identification and Control, 2021, 39, (1), pp. 51-60
dc.identifier.issn	1746-6172
dc.identifier.issn	1746-6180
dc.identifier.uri	http://hdl.handle.net/10453/161904
dc.description.abstract	In myoelectric control, nonlinear regression models, Gaussian process (GP) in specific, have shown promising accuracy in estimation, but no study has been conducted to evaluate the real-time performance of GP regression. In this work, the real-time performance of sparse GP regression is evaluated with 17 able-bodied subjects. Unlike the existing training methods, in which training protocols are strictly pre-determined, a novel training method is proposed. The subjects' real-time performance adjusts training time and the number of training samples. While the majority of subjects showed similar learning rates, there was a significant difference between a few subjects (p < 0.05). As a result of real-time performance, the subjects completed 97% of the average tasks and achieved 80% path efficiency comparable to existing methods.
dc.language	en
dc.publisher	Inderscience Publishers
dc.relation.ispartof	International Journal of Modelling, Identification and Control
dc.relation.isbasedon	10.1504/IJMIC.2021.123372
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0805 Distributed Computing
dc.subject.classification	Industrial Engineering & Automation
dc.title	Sparse Gaussian process regression in real-time myoelectric control
dc.type	Journal Article
utslib.citation.volume	39
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0805 Distributed Computing
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Biomedical Engineering
pubs.organisational-group	/University of Technology Sydney/Centre for Health Technologies (CHT)
utslib.copyright.status	closed_access	*
dc.date.updated	2022-09-19T23:19:02Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	39
utslib.citation.issue	1

Abstract:

In myoelectric control, nonlinear regression models, Gaussian process (GP) in specific, have shown promising accuracy in estimation, but no study has been conducted to evaluate the real-time performance of GP regression. In this work, the real-time performance of sparse GP regression is evaluated with 17 able-bodied subjects. Unlike the existing training methods, in which training protocols are strictly pre-determined, a novel training method is proposed. The subjects' real-time performance adjusts training time and the number of training samples. While the majority of subjects showed similar learning rates, there was a significant difference between a few subjects (p < 0.05). As a result of real-time performance, the subjects completed 97% of the average tasks and achieved 80% path efficiency comparable to existing methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/161904