Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults

Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jalal Alizadeh, Martin Bogdan, Joseph Classen, Christopher Fricke
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	fall detection machine learning SVM kNN random forest older adults Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/c4e4e3d0806b491ab499c4561bc1442a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c4e4e3d0806b491ab499c4561bc1442a
record_format	dspace
spelling	oai:doaj.org-article:c4e4e3d0806b491ab499c4561bc1442a2021-11-11T19:09:33ZSupport Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults10.3390/s212171661424-8220https://doaj.org/article/c4e4e3d0806b491ab499c4561bc1442a2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7166https://doaj.org/toc/1424-8220Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A promising technique might be based on the classification of movements based on accelerometer signals by machine-learning algorithms, but the generalizability of classifiers trained on laboratory data to real-world datasets is a common issue. Here, three machine-learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were trained to detect fall events. We used a dataset containing intentional falls (SisFall) to train the classifier and validated the approach on a different dataset which included real-world accidental fall events of elderly people (FARSEEING). The results suggested that the linear SVM was the most suitable classifier in this cross-dataset validation approach and reliably distinguished a fall event from normal everyday activity at an accuracy of 93% and similarly high sensitivity and specificity. Thus, classifiers based on linear SVM might be useful for automatic fall detection in real-world applications.Jalal AlizadehMartin BogdanJoseph ClassenChristopher FrickeMDPI AGarticlefall detectionmachine learningSVMkNNrandom forestolder adultsChemical technologyTP1-1185ENSensors, Vol 21, Iss 7166, p 7166 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	fall detection machine learning SVM kNN random forest older adults Chemical technology TP1-1185
spellingShingle	fall detection machine learning SVM kNN random forest older adults Chemical technology TP1-1185 Jalal Alizadeh Martin Bogdan Joseph Classen Christopher Fricke Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
description	Falls are a major cause of morbidity and mortality in neurological disorders. Technical means of detecting falls are of high interest as they enable rapid notification of caregivers and emergency services. Such approaches must reliably differentiate between normal daily activities and fall events. A promising technique might be based on the classification of movements based on accelerometer signals by machine-learning algorithms, but the generalizability of classifiers trained on laboratory data to real-world datasets is a common issue. Here, three machine-learning algorithms including Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Random Forest (RF) were trained to detect fall events. We used a dataset containing intentional falls (SisFall) to train the classifier and validated the approach on a different dataset which included real-world accidental fall events of elderly people (FARSEEING). The results suggested that the linear SVM was the most suitable classifier in this cross-dataset validation approach and reliably distinguished a fall event from normal everyday activity at an accuracy of 93% and similarly high sensitivity and specificity. Thus, classifiers based on linear SVM might be useful for automatic fall detection in real-world applications.
format	article
author	Jalal Alizadeh Martin Bogdan Joseph Classen Christopher Fricke
author_facet	Jalal Alizadeh Martin Bogdan Joseph Classen Christopher Fricke
author_sort	Jalal Alizadeh
title	Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
title_short	Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
title_full	Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
title_fullStr	Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
title_full_unstemmed	Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults
title_sort	support vector machine classifiers show high generalizability in automatic fall detection in older adults
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/c4e4e3d0806b491ab499c4561bc1442a
work_keys_str_mv	AT jalalalizadeh supportvectormachineclassifiersshowhighgeneralizabilityinautomaticfalldetectioninolderadults AT martinbogdan supportvectormachineclassifiersshowhighgeneralizabilityinautomaticfalldetectioninolderadults AT josephclassen supportvectormachineclassifiersshowhighgeneralizabilityinautomaticfalldetectioninolderadults AT christopherfricke supportvectormachineclassifiersshowhighgeneralizabilityinautomaticfalldetectioninolderadults
_version_	1718431609828409344

Support Vector Machine Classifiers Show High Generalizability in Automatic Fall Detection in Older Adults

Ejemplares similares