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 Experiment Video

Updated: Aug 4, 2025

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

12.6K

Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly

Christopher B Thornton1, Niina Kolehmainen1,2, Kianoush Nazarpour3

  • 1Population Health Sciences Institute, Faculty of Medical Sciences, Newcastle University, United Kingdom.

PLOS Digital Health
|April 5, 2023
PubMed
Summary
This summary is machine-generated.

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

SPIRIT-Children and Adolescents (SPIRIT-C) 2026 extension statement: enhancing the reporting and usefulness of paediatric randomised trial protocols.

The Lancet. Child & adolescent health·2026
Same author

CONSORT-Children and Adolescents (CONSORT-C) 2026 extension statement: enhancing the reporting and impact of paediatric randomised trials.

The Lancet. Child & adolescent health·2026
Same author

Case Report: Low-frequency tibial nerve stimulation: demonstrating a novel therapeutic option for Fowler's syndrome through a pilot case series.

Frontiers in urology·2026
Same author

Self-Care in Children and Young People With and Without Developmental Disabilities-A Systematic Review.

Child: care, health and development·2026
Same author

Planning and delivering co-creation workshops: practical lessons from digital health device design.

Frontiers in digital health·2026
Same author

Physiology of everyday sleep and physical activity: An exploratory mixed-methods study of multi-sensor wearables for infants and toddlers.

Behavior research methods·2026

A new machine learning method for analyzing accelerometer data in children provides more accurate physical activity measurements than traditional methods. This data-driven approach improves inclusivity for diverse populations in research.

Area of Science:

  • Pediatric research
  • Biomedical engineering
  • Machine learning applications

Background:

  • Accelerometers are common for measuring children's physical activity.
  • Traditional methods use population-specific cut points, limiting generalizability and increasing costs.
  • These limitations hinder research across diverse populations and over time.

Purpose of the Study:

  • To apply an unsupervised machine learning approach to segment and cluster raw accelerometer data.
  • To compare the effectiveness of this data-driven method against the traditional cut points approach.
  • To assess the correlation of physical activity measurements with developmental abilities in children.

Main Methods:

  • Utilized a hidden semi-Markov model, an unsupervised machine learning technique.

More Related Videos

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

99
Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

6.8K

Related Experiment Videos

Last Updated: Aug 4, 2025

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers
07:24

A Method for Quantifying Upper Limb Performance in Daily Life Using Accelerometers

Published on: April 21, 2017

12.6K
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

99
Home-Based Monitor for Gait and Activity Analysis
07:24

Home-Based Monitor for Gait and Activity Analysis

Published on: August 8, 2019

6.8K
  • Analyzed accelerometer data from 279 children (9-38 months) with diverse developmental abilities (PEDI-CAT).
  • Benchmarked results against literature-validated cut points for the same device and similar population.

    • Main Results:

    • The unsupervised approach showed stronger correlations with PEDI-CAT measures for mobility (R2: 0.51 vs 0.39), social-cognitive capacity (R2: 0.32 vs 0.20), and daily activity (R2: 0.35 vs 0.24).
    • It also correlated better with age (R2: 0.15 vs 0.1).
    • The data-driven method demonstrated improved sensitivity and appropriateness compared to cut points.

    Conclusions:

    • Unsupervised machine learning offers a more sensitive, appropriate, and cost-effective method for quantifying physical activity in children.
    • This approach enhances research inclusivity for diverse and evolving populations.
    • It provides a novel perspective for processing accelerometer data without relying on external population parameters.