Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices

Parkinson’s disease (PD) is a common neurodegenerative disease, one of the symptoms of which is a gait disorder, which decreases gait speed and cadence. Recently, augmented feedback training has been considered to achieve effective physical rehabilitation. Therefore, we have devised a numerical mode...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Hyeonjong Kim, Ji-Won Kim, Junghyuk Ko
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	Parkinson’s disease gait disorder augmented feedback training gait detection gait classification wearable device Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/4ac7e8990ea3486aad9994836171272c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4ac7e8990ea3486aad9994836171272c
record_format	dspace
spelling	oai:doaj.org-article:4ac7e8990ea3486aad9994836171272c2021-11-25T18:58:23ZGait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices10.3390/s212276761424-8220https://doaj.org/article/4ac7e8990ea3486aad9994836171272c2021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7676https://doaj.org/toc/1424-8220Parkinson’s disease (PD) is a common neurodegenerative disease, one of the symptoms of which is a gait disorder, which decreases gait speed and cadence. Recently, augmented feedback training has been considered to achieve effective physical rehabilitation. Therefore, we have devised a numerical modeling process and algorithm for gait detection and classification (GDC) that actively utilizes augmented feedback training. The numerical model converted each joint angle into a magnitude of acceleration (MoA) and a Z-axis angular velocity (ZAV) parameter. Subsequently, we confirmed the validity of both the GDC numerical modeling and algorithm. As a result, a higher gait detection and classification rate (GDCR) could be observed at a higher gait speed and lower acceleration threshold (AT) and gyroscopic threshold (GT). However, the pattern of the GDCR was ambiguous if the patient was affected by a gait disorder compared to a normal user. To utilize the relationships between the GDCR, AT, GT, and gait speed, we controlled the GDCR by using AT and GT as inputs, which we found to be a reasonable methodology. Moreover, the GDC algorithm could distinguish between normal people and people who suffered from gait disorders. Consequently, the GDC method could be used for rehabilitation and gait evaluation.Hyeonjong KimJi-Won KimJunghyuk KoMDPI AGarticleParkinson’s diseasegait disorderaugmented feedback traininggait detectiongait classificationwearable deviceChemical technologyTP1-1185ENSensors, Vol 21, Iss 7676, p 7676 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Parkinson’s disease gait disorder augmented feedback training gait detection gait classification wearable device Chemical technology TP1-1185
spellingShingle	Parkinson’s disease gait disorder augmented feedback training gait detection gait classification wearable device Chemical technology TP1-1185 Hyeonjong Kim Ji-Won Kim Junghyuk Ko Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
description	Parkinson’s disease (PD) is a common neurodegenerative disease, one of the symptoms of which is a gait disorder, which decreases gait speed and cadence. Recently, augmented feedback training has been considered to achieve effective physical rehabilitation. Therefore, we have devised a numerical modeling process and algorithm for gait detection and classification (GDC) that actively utilizes augmented feedback training. The numerical model converted each joint angle into a magnitude of acceleration (MoA) and a Z-axis angular velocity (ZAV) parameter. Subsequently, we confirmed the validity of both the GDC numerical modeling and algorithm. As a result, a higher gait detection and classification rate (GDCR) could be observed at a higher gait speed and lower acceleration threshold (AT) and gyroscopic threshold (GT). However, the pattern of the GDCR was ambiguous if the patient was affected by a gait disorder compared to a normal user. To utilize the relationships between the GDCR, AT, GT, and gait speed, we controlled the GDCR by using AT and GT as inputs, which we found to be a reasonable methodology. Moreover, the GDC algorithm could distinguish between normal people and people who suffered from gait disorders. Consequently, the GDC method could be used for rehabilitation and gait evaluation.
format	article
author	Hyeonjong Kim Ji-Won Kim Junghyuk Ko
author_facet	Hyeonjong Kim Ji-Won Kim Junghyuk Ko
author_sort	Hyeonjong Kim
title	Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
title_short	Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
title_full	Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
title_fullStr	Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
title_full_unstemmed	Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices
title_sort	gait disorder detection and classification method using inertia measurement unit for augmented feedback training in wearable devices
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4ac7e8990ea3486aad9994836171272c
work_keys_str_mv	AT hyeonjongkim gaitdisorderdetectionandclassificationmethodusinginertiameasurementunitforaugmentedfeedbacktraininginwearabledevices AT jiwonkim gaitdisorderdetectionandclassificationmethodusinginertiameasurementunitforaugmentedfeedbacktraininginwearabledevices AT junghyukko gaitdisorderdetectionandclassificationmethodusinginertiameasurementunitforaugmentedfeedbacktraininginwearabledevices
_version_	1718410460591554560

Gait Disorder Detection and Classification Method Using Inertia Measurement Unit for Augmented Feedback Training in Wearable Devices

Ejemplares similares