A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees

There are currently limited data on how prosthetic devices are used to support lower-limb prosthesis users in their free-living environment. Possessing the ability to monitor a patient’s physical behaviour while using these devices would enhance our understanding of the impact of different prostheti...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Benjamin Griffiths, Laura Diment, Malcolm H. Granat
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	classification physical behaviour monitoring machine learning accelerometer activity monitor lower-limb amputee Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/e885a95537f245ab9c7253249af87ba6
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e885a95537f245ab9c7253249af87ba6
record_format	dspace
spelling	oai:doaj.org-article:e885a95537f245ab9c7253249af87ba62021-11-25T18:56:36ZA Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees10.3390/s212274581424-8220https://doaj.org/article/e885a95537f245ab9c7253249af87ba62021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7458https://doaj.org/toc/1424-8220There are currently limited data on how prosthetic devices are used to support lower-limb prosthesis users in their free-living environment. Possessing the ability to monitor a patient’s physical behaviour while using these devices would enhance our understanding of the impact of different prosthetic products. The current approaches for monitoring human physical behaviour use a single thigh or wrist-worn accelerometer, but in a lower-limb amputee population, we have the unique opportunity to embed a device within the prosthesis, eliminating compliance issues. This study aimed to develop a model capable of accurately classifying postures (sitting, standing, stepping, and lying) by using data from a single shank-worn accelerometer. Free-living posture data were collected from 14 anatomically intact participants and one amputee over three days. A thigh worn activity monitor collected labelled posture data, while a shank worn accelerometer collected 3-axis acceleration data. Postures and the corresponding shank accelerations were extracted in window lengths of 5–180 s and used to train several machine learning classifiers which were assessed by using stratified cross-validation. A random forest classifier with a 15 s window length provided the highest classification accuracy of 93% weighted average F-score and between 88 and 98% classification accuracy across all four posture classes, which is the best performance achieved to date with a shank-worn device. The results of this study show that data from a single shank-worn accelerometer with a machine learning classification model can be used to accurately identify postures that make up an individual’s daily physical behaviour. This opens up the possibility of embedding an accelerometer-based activity monitor into the shank component of a prosthesis to capture physical behaviour information in both above and below-knee amputees. The models and software used in this study have been made open source in order to overcome the current restrictions of applying activity monitoring methods to lower-limb prosthesis users.Benjamin GriffithsLaura DimentMalcolm H. GranatMDPI AGarticleclassificationphysical behaviour monitoringmachine learningaccelerometeractivity monitorlower-limb amputeeChemical technologyTP1-1185ENSensors, Vol 21, Iss 7458, p 7458 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	classification physical behaviour monitoring machine learning accelerometer activity monitor lower-limb amputee Chemical technology TP1-1185
spellingShingle	classification physical behaviour monitoring machine learning accelerometer activity monitor lower-limb amputee Chemical technology TP1-1185 Benjamin Griffiths Laura Diment Malcolm H. Granat A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
description	There are currently limited data on how prosthetic devices are used to support lower-limb prosthesis users in their free-living environment. Possessing the ability to monitor a patient’s physical behaviour while using these devices would enhance our understanding of the impact of different prosthetic products. The current approaches for monitoring human physical behaviour use a single thigh or wrist-worn accelerometer, but in a lower-limb amputee population, we have the unique opportunity to embed a device within the prosthesis, eliminating compliance issues. This study aimed to develop a model capable of accurately classifying postures (sitting, standing, stepping, and lying) by using data from a single shank-worn accelerometer. Free-living posture data were collected from 14 anatomically intact participants and one amputee over three days. A thigh worn activity monitor collected labelled posture data, while a shank worn accelerometer collected 3-axis acceleration data. Postures and the corresponding shank accelerations were extracted in window lengths of 5–180 s and used to train several machine learning classifiers which were assessed by using stratified cross-validation. A random forest classifier with a 15 s window length provided the highest classification accuracy of 93% weighted average F-score and between 88 and 98% classification accuracy across all four posture classes, which is the best performance achieved to date with a shank-worn device. The results of this study show that data from a single shank-worn accelerometer with a machine learning classification model can be used to accurately identify postures that make up an individual’s daily physical behaviour. This opens up the possibility of embedding an accelerometer-based activity monitor into the shank component of a prosthesis to capture physical behaviour information in both above and below-knee amputees. The models and software used in this study have been made open source in order to overcome the current restrictions of applying activity monitoring methods to lower-limb prosthesis users.
format	article
author	Benjamin Griffiths Laura Diment Malcolm H. Granat
author_facet	Benjamin Griffiths Laura Diment Malcolm H. Granat
author_sort	Benjamin Griffiths
title	A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
title_short	A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
title_full	A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
title_fullStr	A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
title_full_unstemmed	A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees
title_sort	machine learning classification model for monitoring the daily physical behaviour of lower-limb amputees
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/e885a95537f245ab9c7253249af87ba6
work_keys_str_mv	AT benjamingriffiths amachinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees AT lauradiment amachinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees AT malcolmhgranat amachinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees AT benjamingriffiths machinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees AT lauradiment machinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees AT malcolmhgranat machinelearningclassificationmodelformonitoringthedailyphysicalbehaviouroflowerlimbamputees
_version_	1718410561749778432

A Machine Learning Classification Model for Monitoring the Daily Physical Behaviour of Lower-Limb Amputees

Ejemplares similares