Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The impact of calorific screening thresholds and weight status when validating UK supermarket transaction records in dietary evaluation: FIO-STRIDE.

International journal of obesity (2005)·2026
Same author

Pilot mental health sensitisation programme for community leaders in Uganda: impact evaluation.

BJPsych international·2026
Same author

Measuring the accessibility of veterinary care for companion animals in England and Wales.

Animal welfare (South Mimms, England)·2026
Same author

Protocol for a quasi-experimental analysis: using retail sales data to evaluate impacts of the high fat, sugar and salt (HFSS) product placement restrictions legislation in England.

BMJ public health·2025
Same author

Mapping Advertising Assets Project: a cross-sectional analysis of food-related outdoor advertising and the relationship with deprivation in Leeds, UK.

Public health nutrition·2025
Same author

An inclusive economy dataset for wards in Great Britain using administrative and synthetic data sources.

Scientific data·2025

Related Experiment Video

Updated: Oct 13, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K

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

Francesca Pontin1,2, Nik Lomax1,2, Graham Clarke2

  • 1Leeds Institute for Data Analytics, University of Leeds, Leeds LS2 9ET, UK.

International Journal of Environmental Research and Public Health
|November 13, 2021
PubMed
Summary

Smartphone data reveals distinct physical activity patterns. Machine learning identified seasonal and weekly trends, influenced by daylight saving time, demographics, and activity choices.

Keywords:
big datacluster analysisdata sciencephysical activitysecondary dataself-recorded health datasmartphoneunsupervised machine learning

More Related Videos

Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.7K
Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
05:51

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

713

Related Experiment Videos

Last Updated: Oct 13, 2025

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment
06:49

Evaluation of a Smartphone-based Human Activity Recognition System in a Daily Living Environment

Published on: December 11, 2015

9.0K
Trajectory Data Analyses for Pedestrian Space-time Activity Study
16:14

Trajectory Data Analyses for Pedestrian Space-time Activity Study

Published on: February 25, 2013

13.7K
Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
05:51

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

713

Area of Science:

  • Digital Health
  • Behavioral Science
  • Data Science

Background:

  • Smartphone data offers unprecedented spatial and temporal coverage for studying physical activity.
  • Traditional study designs often lack the granularity to capture habitual physical activity patterns effectively.
  • Unsupervised machine learning can analyze large datasets to uncover complex behavioral trends.

Purpose of the Study:

  • To implement and evaluate clustering methods for identifying physical activity behavior trends.
  • To characterize demographics and activity types within identified behavioral clusters.
  • To understand the relationship between weekly and yearlong physical activity patterns.

Main Methods:

  • K-means clustering and agglomerative hierarchical clustering were applied to smartphone data.
  • Analysis focused on identifying seasonal (yearlong) and weekly physical activity behavior trends.
  • Demographic factors (age, gender) and activity types were characterized within behavioral clusters.

Main Results:

  • Seven clusters of seasonal activity behavior were identified, with daylight saving time influencing activity levels and summer months showing increased engagement.
  • Six clusters of weekly behaviors were identified, highlighting variations in meeting physical activity guidelines between weekdays and weekends.
  • Significant associations were found between gender, age, and cluster membership, as well as preferred physical activity types.

Conclusions:

  • Unsupervised machine learning effectively utilizes rich secondary app data to analyze habitual physical activity.
  • This approach moves beyond aggregate measures to reveal temporal variations in physical activity behavior.
  • Understanding these temporal dynamics is crucial for developing targeted health interventions.