Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors

Abstract Long term monitoring of locomotor behaviour in humans using body-worn sensors can provide insight into the dynamical structure of locomotion, which can be used for quantitative, predictive and classification analyses in a biomedical context. A frequently used approach to study daily life lo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Sayantan Ghosh, Tim Fleiner, Eleftheria Giannouli, Uwe Jaekel, Sabato Mellone, Peter Häussermann, Wiebren Zijlstra
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2018
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c485485c3d9c40e9825551ddfa6d234b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c485485c3d9c40e9825551ddfa6d234b
record_format	dspace
spelling	oai:doaj.org-article:c485485c3d9c40e9825551ddfa6d234b2021-12-02T15:08:35ZStatistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors10.1038/s41598-018-25523-42045-2322https://doaj.org/article/c485485c3d9c40e9825551ddfa6d234b2018-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-018-25523-4https://doaj.org/toc/2045-2322Abstract Long term monitoring of locomotor behaviour in humans using body-worn sensors can provide insight into the dynamical structure of locomotion, which can be used for quantitative, predictive and classification analyses in a biomedical context. A frequently used approach to study daily life locomotor behaviour in different population groups involves categorisation of locomotion into various states as a basis for subsequent analyses of differences in locomotor behaviour. In this work, we use such a categorisation to develop two feature sets, namely state probability and transition rates between states, and use supervised classification techniques to demonstrate differences in locomotor behaviour. We use this to study the influence of various states in differentiating between older adults with and without dementia. We further assess the contribution of each state and transition and identify the states most influential in maximising the classification accuracy between the two groups. The methods developed here are general and can be applied to areas dealing with categorical time series.Sayantan GhoshTim FleinerEleftheria GiannouliUwe JaekelSabato MellonePeter HäussermannWiebren ZijlstraNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 8, Iss 1, Pp 1-10 (2018)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Sayantan Ghosh Tim Fleiner Eleftheria Giannouli Uwe Jaekel Sabato Mellone Peter Häussermann Wiebren Zijlstra Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
description	Abstract Long term monitoring of locomotor behaviour in humans using body-worn sensors can provide insight into the dynamical structure of locomotion, which can be used for quantitative, predictive and classification analyses in a biomedical context. A frequently used approach to study daily life locomotor behaviour in different population groups involves categorisation of locomotion into various states as a basis for subsequent analyses of differences in locomotor behaviour. In this work, we use such a categorisation to develop two feature sets, namely state probability and transition rates between states, and use supervised classification techniques to demonstrate differences in locomotor behaviour. We use this to study the influence of various states in differentiating between older adults with and without dementia. We further assess the contribution of each state and transition and identify the states most influential in maximising the classification accuracy between the two groups. The methods developed here are general and can be applied to areas dealing with categorical time series.
format	article
author	Sayantan Ghosh Tim Fleiner Eleftheria Giannouli Uwe Jaekel Sabato Mellone Peter Häussermann Wiebren Zijlstra
author_facet	Sayantan Ghosh Tim Fleiner Eleftheria Giannouli Uwe Jaekel Sabato Mellone Peter Häussermann Wiebren Zijlstra
author_sort	Sayantan Ghosh
title	Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
title_short	Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
title_full	Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
title_fullStr	Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
title_full_unstemmed	Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
title_sort	statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors
publisher	Nature Portfolio
publishDate	2018
url	https://doaj.org/article/c485485c3d9c40e9825551ddfa6d234b
work_keys_str_mv	AT sayantanghosh statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT timfleiner statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT eleftheriagiannouli statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT uwejaekel statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT sabatomellone statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT peterhaussermann statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors AT wiebrenzijlstra statisticallearningofmobilitypatternsfromlongtermmonitoringoflocomotorbehaviourwithbodywornsensors
_version_	1718388085689942016

Statistical learning of mobility patterns from long-term monitoring of locomotor behaviour with body-worn sensors

Ejemplares similares