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

Inflammatory, metabolic, and vascular pathways linking cardiorespiratory fitness to cognition: Results from the IGNITE study.

Brain, behavior, & immunity - health·2026
Same author

Are older adult research participants representative of the general population? Results from 19 clinical studies at one academic research center.

Contemporary clinical trials·2026
Same author

This time with feeling: recommendations for full-bodied reporting of research on dance.

Frontiers in cognition·2026
Same author

Does today's workload predict tomorrow's stress, fatigue, and other strain states? Exploring directionality in daily dynamics.

Ergonomics·2026
Same author

A mobile intervention to reduce pain and improve health-III: protocol for a remotely delivered randomized controlled trial of physical activity for pain management in older adults with obesity and knee or hip osteoarthritis.

Frontiers in digital health·2026
Same author

Effectiveness of a behavioral weight management intervention by race, ethnicity, income, and education: a meta-analysis.

Communications medicine·2026

Related Experiment Video

Updated: May 12, 2026

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

Machine Learning-Based Stepping Filter Improves Estimates of Moderate-to-Vigorous-Intensity Physical Activity from

Josh Cherian1, Emily C Hector2, Shyh-Huei Chen3

  • 1Department of Biomedical Engineering, Wake Forest University School of Medicine, Winston-Salem, NC, USA.

Digital Biomarkers
|May 11, 2026
PubMed
Summary

A new stepping classification algorithm significantly reduced overestimations of moderate-to-vigorous-intensity physical activity (MVPA) from wrist-worn accelerometers in older adults. This method improves accuracy by filtering out non-stepping movements before analysis.

Keywords:
AccelerometryAgingMeasurementPhysical activity

More Related Videos

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

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

Related Experiment Videos

Last Updated: May 12, 2026

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

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

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

Area of Science:

  • Gerontology
  • Biomedical Engineering
  • Physical Activity Research

Background:

  • Wearable accelerometers are commonly used to measure physical activity (PA) but can overestimate moderate-to-vigorous-intensity physical activity (MVPA) due to non-stepping movements.
  • Older adults exhibit varying functional levels, making accurate PA assessment crucial for health monitoring and interventions.

Purpose of the Study:

  • To evaluate if a simple stepping classification algorithm can reduce non-stepping acceleration from wrist-worn ActiGraph data.
  • To improve the accuracy of quantifying time spent in MVPA by filtering out non-stepping behaviors before applying standard acceleration cut points.

Main Methods:

  • Older adults (72.51 ± 6.93 years) wore both ActiGraph (wrist) and ActivPAL (thigh) monitors during various tasks over 2 days.
  • A stepping classifier was trained for each device to identify and remove non-stepping behaviors.
  • MVPA was calculated before and after applying the classifier-based filter.

Main Results:

  • Initially, ActiGraph reported ~3.5 times more MVPA than ActivPAL (48.47 vs. 14.00 min).
  • After applying the filter, ActiGraph MVPA reduced by 60% (to 20.57 min), and ActivPAL MVPA reduced by 14% (to 11.80 min).
  • The difference between devices decreased significantly, with ActiGraph recording only 1.74 times more MVPA than ActivPAL.

Conclusions:

  • Filtering non-stepping behaviors from accelerometer data can significantly reduce inflated MVPA estimates.
  • This approach enhances the reliability of PA measurement in older adults using wrist-worn devices.
  • Development of robust, population-specific step classification algorithms is recommended for future PA research.