Machine learning models for weight-bearing activity type recognition based on accelerometry in postmenopausal women

Vista sencilla de ítem
dc.contributor.authorHuggins, Cameron
dc.contributor.authorClarke, Rebecca
dc.contributor.authorAbásolo Baz, Daniel
dc.contributor.authorGil Rey, Erreka
dc.contributor.authorTobias, Jonathan H.
dc.contributor.authorDeere, Kevin
dc.contributor.authorAllison, Sarah Jane
dc.date.accessioned2025-09-04T10:22:09Z
dc.date.available2025-09-04T10:22:09Z
dc.date.issued2022-11-25
dc.date.updated2025-09-04T10:22:09Z
dc.description.abstractHip-worn triaxial accelerometers are widely used to assess physical activity in terms of energy expenditure. Methods for classification in terms of different types of activity of relevance to the skeleton in populations at risk of osteoporosis are not currently available. This publication aims to assess the accuracy of four machine learning models on binary (standing and walking) and tertiary (standing, walking, and jogging) classification tasks in postmenopausal women. Eighty women performed a shuttle test on an indoor track, of which thirty performed the same test on an indoor treadmill. The raw accelerometer data were pre-processed, converted into eighteen different features and then combined into nine unique feature sets. The four machine learning models were evaluated using three different validation methods. Using the leave-one-out validation method, the highest average accuracy for the binary classification model, 99.61%, was produced by a k-NN Manhattan classifier using a basic statistical feature set. For the tertiary classification model, the highest average accuracy, 94.04%, was produced by a k-NN Manhattan classifier using a feature set that included all 18 features. The methods and classifiers within this study can be applied to accelerometer data to more accurately characterize weight-bearing activity which are important to skeletal health.en
dc.identifier.citationHuggins, C. J., Clarke, R., Abasolo, D., Gil-Rey, E., Tobias, J. H., Deere, K., & Allison, S. J. (2022). Machine learning models for weight-bearing activity type recognition based on accelerometry in postmenopausal women. Sensors, 22(23). https://doi.org/10.3390/S22239176
dc.identifier.doi10.3390/S22239176
dc.identifier.issn1424-8220
dc.identifier.urihttps://hdl.handle.net/20.500.14454/3499
dc.language.isoeng
dc.publisherMDPI
dc.rights© 2022 by the authors
dc.subject.otherAccelerometry
dc.subject.otherActivity type recognition
dc.subject.otherClassification
dc.subject.otherMachine learning
dc.subject.otherSignal processing
dc.titleMachine learning models for weight-bearing activity type recognition based on accelerometry in postmenopausal womenen
dc.typejournal article
dcterms.accessRightsopen access
oaire.citation.issue23
oaire.citation.titleSensors
oaire.citation.volume22
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
huggins_machine_2022.pdf
Tamaño:
966.64 KB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Artículos