Show simple item record

dc.contributor.authorTan, Jay-Shian
dc.contributor.authorBeheshti, Behrouz Khabbaz
dc.contributor.authorBinnie, Tara
dc.contributor.authorDavey, Paul
dc.contributor.authorCaneiro, JP
dc.contributor.authorKent, Peter
dc.contributor.authorSmith, Anne
dc.contributor.authorO’Sullivan, Peter
dc.contributor.authorCampbell, Amity
dc.date.accessioned2021-11-18T00:12:00Z
dc.date.available2021-11-18T00:12:00Z
dc.date.issued2021
dc.identifier.citationTan, J.S. and Beheshti, B.K. and Binnie, T. and Davey, P. and Caneiro, J.P. and Kent, P. and Smith, A. et al. 2021. Human activity recognition for people with knee osteoarthritis—A proof‐of‐concept. Sensors. 21 (10): Article No. 3381.
dc.identifier.urihttp://hdl.handle.net/20.500.11937/86491
dc.identifier.doi10.3390/s21103381
dc.description.abstract

Clinicians lack objective means for monitoring if their knee osteoarthritis patients are improving outside of the clinic (e.g., at home). Previous human activity recognition (HAR) models using wearable sensor data have only used data from healthy people and such models are typically imprecise for people who have medical conditions affecting movement. HAR models designed for people with knee osteoarthritis have classified rehabilitation exercises but not the clinically relevant activities of transitioning from a chair, negotiating stairs and walking, which are commonly monitored for improvement during therapy for this condition. Therefore, it is unknown if a HAR model trained on data from people who have knee osteoarthritis can be accurate in classifying these three clinically relevant activities. Therefore, we collected inertial measurement unit (IMU) data from 18 participants with knee osteoarthritis and trained convolutional neural network models to identify chair, stairs and walking activities, and phases. The model accuracy was 85% at the first level of classification (activity), 89–97% at the second (direction of movement) and 60–67% at the third level (phase). This study is the first proof‐of‐concept that an accurate HAR system can be developed using IMU data from people with knee osteoarthritis to classify activities and phases of activities.

dc.languageEnglish
dc.publisherMDPI
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectScience & Technology
dc.subjectPhysical Sciences
dc.subjectTechnology
dc.subjectChemistry, Analytical
dc.subjectEngineering, Electrical & Electronic
dc.subjectInstruments & Instrumentation
dc.subjectChemistry
dc.subjectEngineering
dc.subjectknee osteoarthritis
dc.subjectmachine learning
dc.subjecthuman activity recognition
dc.subjectinertial measurement units
dc.subjectphysical activity monitoring
dc.subjectOLDER-ADULTS
dc.subjectSYSTEM
dc.subjectSENSORS
dc.subjectGAIT
dc.subjectHIP
dc.subjectVARIABILITY
dc.subjectSEVERITY
dc.subjectWALKING
dc.subjectBURDEN
dc.subjectMOTION
dc.titleHuman activity recognition for people with knee osteoarthritis—A proof‐of‐concept
dc.typeJournal Article
dcterms.source.volume21
dcterms.source.number10
dcterms.source.issn1424-8220
dcterms.source.titleSensors
dc.date.updated2021-11-18T00:12:00Z
curtin.note

© 2021 The Authors. Published by MDPI Publishing.

curtin.departmentCurtin School of Nursing
curtin.departmentCurtin School of Allied Health
curtin.accessStatusOpen access
curtin.facultyFaculty of Health Sciences
curtin.contributor.orcidCaneiro, JP [0000-0001-5555-4412]
curtin.contributor.orcidKent, Peter [0000-0002-2429-9233]
curtin.contributor.orcidSmith, Anne [0000-0002-4667-7389]
curtin.contributor.orcidDavey, Paul [0000-0002-2119-8066]
curtin.contributor.orcidTan, Jay-Shian [0000-0002-9728-3128]
curtin.contributor.orcidBeheshti, Behrouz Khabbaz [0000-0003-1826-6184]
curtin.identifier.article-numberARTN 3381
dcterms.source.eissn1424-8220
curtin.contributor.scopusauthoridCaneiro, JP [24398641900]
curtin.contributor.scopusauthoridKent, Peter [55579115800] [57195098269]
curtin.contributor.scopusauthoridSmith, Anne [7406756140]
curtin.contributor.scopusauthoridCampbell, Amity [35794905700]
curtin.contributor.scopusauthoridDavey, Paul [35263712600]


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

http://creativecommons.org/licenses/by/4.0/
Except where otherwise noted, this item's license is described as http://creativecommons.org/licenses/by/4.0/