Feature selection to classify lameness using a smartphone-based inertial measurement unit.

<h4>Background and objectives</h4>Gait can be severely affected by pain, muscle weakness, and aging resulting in lameness. Despite the high incidence of lameness, there are no studies on the features that are useful for classifying lameness patterns. Therefore, we aimed to identify featu...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Satoshi Arita, Daisuke Nishiyama, Takaya Taniguchi, Daisuke Fukui, Manabu Yamanaka, Hiroshi Yamada
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/00ef249ff85744289e2607200a58c43b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:00ef249ff85744289e2607200a58c43b
record_format	dspace
spelling	oai:doaj.org-article:00ef249ff85744289e2607200a58c43b2021-12-02T20:13:52ZFeature selection to classify lameness using a smartphone-based inertial measurement unit.1932-620310.1371/journal.pone.0258067https://doaj.org/article/00ef249ff85744289e2607200a58c43b2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0258067https://doaj.org/toc/1932-6203<h4>Background and objectives</h4>Gait can be severely affected by pain, muscle weakness, and aging resulting in lameness. Despite the high incidence of lameness, there are no studies on the features that are useful for classifying lameness patterns. Therefore, we aimed to identify features of high importance for classifying population differences in lameness patterns using an inertial measurement unit mounted above the sacral region.<h4>Methods</h4>Features computed exhaustively for multidimensional time series consisting of three-axis angular velocities and three-axis acceleration were carefully selected using the Benjamini-Yekutieli procedure, and multiclass classification was performed using LightGBM (Microsoft Corp., Redmond, WA, USA). We calculated the relative importance of the features that contributed to the classification task in machine learning.<h4>Results</h4>The most important feature was found to be the absolute value of the Fourier coefficients of the second frequency calculated by the one-dimensional discrete Fourier transform for real input. This was determined by the fast Fourier transformation algorithm using data of a single gait cycle of the yaw angular velocity of the pelvic region.<h4>Conclusions</h4>Using an inertial measurement unit worn over the sacral region, we determined a set of features of high importance for classifying differences in lameness patterns based on different factors. This completely new set of indicators can be used to advance the understanding of lameness.Satoshi AritaDaisuke NishiyamaTakaya TaniguchiDaisuke FukuiManabu YamanakaHiroshi YamadaPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 9, p e0258067 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Satoshi Arita Daisuke Nishiyama Takaya Taniguchi Daisuke Fukui Manabu Yamanaka Hiroshi Yamada Feature selection to classify lameness using a smartphone-based inertial measurement unit.
description	<h4>Background and objectives</h4>Gait can be severely affected by pain, muscle weakness, and aging resulting in lameness. Despite the high incidence of lameness, there are no studies on the features that are useful for classifying lameness patterns. Therefore, we aimed to identify features of high importance for classifying population differences in lameness patterns using an inertial measurement unit mounted above the sacral region.<h4>Methods</h4>Features computed exhaustively for multidimensional time series consisting of three-axis angular velocities and three-axis acceleration were carefully selected using the Benjamini-Yekutieli procedure, and multiclass classification was performed using LightGBM (Microsoft Corp., Redmond, WA, USA). We calculated the relative importance of the features that contributed to the classification task in machine learning.<h4>Results</h4>The most important feature was found to be the absolute value of the Fourier coefficients of the second frequency calculated by the one-dimensional discrete Fourier transform for real input. This was determined by the fast Fourier transformation algorithm using data of a single gait cycle of the yaw angular velocity of the pelvic region.<h4>Conclusions</h4>Using an inertial measurement unit worn over the sacral region, we determined a set of features of high importance for classifying differences in lameness patterns based on different factors. This completely new set of indicators can be used to advance the understanding of lameness.
format	article
author	Satoshi Arita Daisuke Nishiyama Takaya Taniguchi Daisuke Fukui Manabu Yamanaka Hiroshi Yamada
author_facet	Satoshi Arita Daisuke Nishiyama Takaya Taniguchi Daisuke Fukui Manabu Yamanaka Hiroshi Yamada
author_sort	Satoshi Arita
title	Feature selection to classify lameness using a smartphone-based inertial measurement unit.
title_short	Feature selection to classify lameness using a smartphone-based inertial measurement unit.
title_full	Feature selection to classify lameness using a smartphone-based inertial measurement unit.
title_fullStr	Feature selection to classify lameness using a smartphone-based inertial measurement unit.
title_full_unstemmed	Feature selection to classify lameness using a smartphone-based inertial measurement unit.
title_sort	feature selection to classify lameness using a smartphone-based inertial measurement unit.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/00ef249ff85744289e2607200a58c43b
work_keys_str_mv	AT satoshiarita featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit AT daisukenishiyama featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit AT takayataniguchi featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit AT daisukefukui featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit AT manabuyamanaka featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit AT hiroshiyamada featureselectiontoclassifylamenessusingasmartphonebasedinertialmeasurementunit
_version_	1718374684771221504

Feature selection to classify lameness using a smartphone-based inertial measurement unit.

Ejemplares similares