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

Effect of Branched-Chain Amino Acid Supplementation Alone or Combined With Tryptophan or Methionine on Appetite Control and Related Health Outcomes in Older Adults: Protocol for a Randomized Controlled Trial.

JMIR research protocols·2026
Same author

Health literacy of adolescents' responses to a workshop focusing on food, nutrition, climate change and digital technology solutions in Oceania: a multi-site pilot study in Vanuatu.

BMC public health·2025
Same author

Self-reported and accelerometry measures of sleep components in adolescents living in Pacific Island countries and territories: Exploring the role of sociocultural background.

Child: care, health and development·2024
Same author

A mixed-methods study exploring women's perceptions and recommendations for a pregnancy app with monitoring tools.

NPJ digital medicine·2023
Same author

Mining Sensor Data to Assess Changes in Physical Activity Behaviors in Health Interventions: Systematic Review.

JMIR medical informatics·2023
Same author

Pregnancy Apps for Self-Monitoring: Scoping Review of the Most Popular Global Apps Available in Australia.

International journal of environmental research and public health·2023

Related Experiment Video

Updated: Aug 22, 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

Unsupervised Early Detection of Physical Activity Behaviour Changes from Wearable Accelerometer Data.

Claudio Diaz1, Corinne Caillaud2,3, Kalina Yacef1

  • 1School of Computer Science, The University of Sydney, Sydney, NSW 2006, Australia.

Sensors (Basel, Switzerland)
|November 11, 2022
PubMed
Summary

The U-BEHAVED algorithm detects physical activity behavior changes from wearable sensors. It identifies new habits with 80% accuracy, enabling timely interventions for promoting healthy lifestyles.

Keywords:
accelerometeractivity trackerbehaviour changesphysical activityunsupervised learning

More Related Videos

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Assessment of Physical Activity Intensity with Accelerometers and Oxygen Consumption
08:45

Assessment of Physical Activity Intensity with Accelerometers and Oxygen Consumption

Published on: June 20, 2025

151

Related Experiment Videos

Last Updated: Aug 22, 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
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.8K
Assessment of Physical Activity Intensity with Accelerometers and Oxygen Consumption
08:45

Assessment of Physical Activity Intensity with Accelerometers and Oxygen Consumption

Published on: June 20, 2025

151

Area of Science:

  • Behavioral Science
  • Digital Health
  • Wearable Technology

Background:

  • Wearable accelerometers offer high-resolution physical activity data.
  • Detecting behavior changes is crucial for promoting healthy habits and interventions.
  • Timely feedback and personalized programs enhance adherence and effectiveness.

Purpose of the Study:

  • To present and illustrate U-BEHAVED, an unsupervised algorithm for detecting physical activity behavior changes.
  • To assess if detected changes represent potentially habitual patterns.
  • To validate the algorithm's performance in a real-world dataset.

Main Methods:

  • U-BEHAVED algorithm uses rolling time windows to compare current and recent physical activity (step data).
  • It identifies significant behavior changes and classifies sustained changes as potential new habits.
  • Validation performed on a dataset of 12,798 users from 79 individuals using activity trackers.

Main Results:

  • The algorithm detected 80% of behavior changes (400-1600 steps/hour) in users with low/high variability.
  • This corresponds to 4-16 minutes of moderate-to-vigorous physical activity.
  • New habit detection achieved 80% accuracy with thresholds of 500 or 1600 steps/hour.

Conclusions:

  • U-BEHAVED effectively detects physical activity behavior changes and potential habit formation.
  • The algorithm's findings can inform personalized interventions for promoting physical activity.
  • This technology supports strategies for teaching healthy behaviors and improving intervention outcomes.