Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach

The increasing ubiquity of smartphone data, with greater spatial and temporal coverage than achieved by traditional study designs, have the potential to provide insight into habitual physical activity patterns. This study implements and evaluates the utility of both K-means clustering and agglomerat...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Francesca Pontin, Nik Lomax, Graham Clarke, Michelle A. Morris
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	physical activity unsupervised machine learning smartphone secondary data cluster analysis data science Medicine R
Acceso en línea:	https://doaj.org/article/8c123dc6713846f096840954df911a49
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8c123dc6713846f096840954df911a49
record_format	dspace
spelling	oai:doaj.org-article:8c123dc6713846f096840954df911a492021-11-11T16:36:13ZCharacterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach10.3390/ijerph1821114761660-46011661-7827https://doaj.org/article/8c123dc6713846f096840954df911a492021-10-01T00:00:00Zhttps://www.mdpi.com/1660-4601/18/21/11476https://doaj.org/toc/1661-7827https://doaj.org/toc/1660-4601The increasing ubiquity of smartphone data, with greater spatial and temporal coverage than achieved by traditional study designs, have the potential to provide insight into habitual physical activity patterns. This study implements and evaluates the utility of both K-means clustering and agglomerative hierarchical clustering methods in identifying weekly and yearlong physical activity behaviour trends. Characterising the demographics and choice of activity type within the identified clusters of behaviour. Across all seven clusters of seasonal activity behaviour identified, daylight saving was shown to play a key role in influencing behaviour, with increased activity in summer months. Investigation into weekly behaviours identified six clusters with varied roles, of weekday versus weekend, on the likelihood of meeting physical activity guidelines. Preferred type of physical activity likewise varied between clusters, with gender and age strongly associated with cluster membership. Key relationships are identified between weekly clusters and seasonal activity behaviour clusters, demonstrating how short-term behaviours contribute to longer-term activity patterns. Utilising unsupervised machine learning, this study demonstrates how the volume and richness of secondary app data can allow us to move away from aggregate measures of physical activity to better understand temporal variations in habitual physical activity behaviour.Francesca PontinNik LomaxGraham ClarkeMichelle A. MorrisMDPI AGarticlephysical activityunsupervised machine learningsmartphonesecondary datacluster analysisdata scienceMedicineRENInternational Journal of Environmental Research and Public Health, Vol 18, Iss 11476, p 11476 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	physical activity unsupervised machine learning smartphone secondary data cluster analysis data science Medicine R
spellingShingle	physical activity unsupervised machine learning smartphone secondary data cluster analysis data science Medicine R Francesca Pontin Nik Lomax Graham Clarke Michelle A. Morris Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
description	The increasing ubiquity of smartphone data, with greater spatial and temporal coverage than achieved by traditional study designs, have the potential to provide insight into habitual physical activity patterns. This study implements and evaluates the utility of both K-means clustering and agglomerative hierarchical clustering methods in identifying weekly and yearlong physical activity behaviour trends. Characterising the demographics and choice of activity type within the identified clusters of behaviour. Across all seven clusters of seasonal activity behaviour identified, daylight saving was shown to play a key role in influencing behaviour, with increased activity in summer months. Investigation into weekly behaviours identified six clusters with varied roles, of weekday versus weekend, on the likelihood of meeting physical activity guidelines. Preferred type of physical activity likewise varied between clusters, with gender and age strongly associated with cluster membership. Key relationships are identified between weekly clusters and seasonal activity behaviour clusters, demonstrating how short-term behaviours contribute to longer-term activity patterns. Utilising unsupervised machine learning, this study demonstrates how the volume and richness of secondary app data can allow us to move away from aggregate measures of physical activity to better understand temporal variations in habitual physical activity behaviour.
format	article
author	Francesca Pontin Nik Lomax Graham Clarke Michelle A. Morris
author_facet	Francesca Pontin Nik Lomax Graham Clarke Michelle A. Morris
author_sort	Francesca Pontin
title	Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
title_short	Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
title_full	Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
title_fullStr	Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
title_full_unstemmed	Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach
title_sort	characterisation of temporal patterns in step count behaviour from smartphone app data: an unsupervised machine learning approach
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8c123dc6713846f096840954df911a49
work_keys_str_mv	AT francescapontin characterisationoftemporalpatternsinstepcountbehaviourfromsmartphoneappdataanunsupervisedmachinelearningapproach AT niklomax characterisationoftemporalpatternsinstepcountbehaviourfromsmartphoneappdataanunsupervisedmachinelearningapproach AT grahamclarke characterisationoftemporalpatternsinstepcountbehaviourfromsmartphoneappdataanunsupervisedmachinelearningapproach AT michelleamorris characterisationoftemporalpatternsinstepcountbehaviourfromsmartphoneappdataanunsupervisedmachinelearningapproach
_version_	1718432309027274752

Characterisation of Temporal Patterns in Step Count Behaviour from Smartphone App Data: An Unsupervised Machine Learning Approach

Ejemplares similares