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

Change in walking cadence as a digital outcome measure of clinically meaningful improvement in gait speed and 6-minute walk test distance after a mobility intervention in older adults.

PloS one·2026
Same author

Sport-Related Head Exposure Characteristics and Health Outcomes in Former Collegiate Athletes: A CARE Consortium Study.

Neurology·2026
Same author

Risk calculation circuit abnormalities plus psychosocial risk variables predict problematic substance use in youth with externalizing disorders.

Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology·2026
Same author

Inconsistent Effects of Experience on Running Biomechanics May be Influenced by Study Heterogeneity and Classification Criteria: a Systematic Review and Proposal of a Revised Taxonomy.

Sports medicine - open·2025
Same author

Running stiffness and spatiotemporal parameters are similar between non-runners and runners with different experience levels.

Sports biomechanics·2025
Same author

Smartphone-based measures as real-world indicators of functional status in advanced cancer patients.

medRxiv : the preprint server for health sciences·2025
Same journal

Continuous tracking of aortic aneurysm diameter with peripheral pulse waves: a computational framework combining sequential Markov chain Monte Carlo with Kalman filtering.

Physiological measurement·2026
Same journal

The 2026 global roadmap for textile-integrated wearable technologies in health.

Physiological measurement·2026
Same journal

Augmenting single-lead ECG interpretation through QRS waveform decomposition and rotation.

Physiological measurement·2026
Same journal

Dynamic Beat-to-Beat Blood Pressure Estimation using a Multi-modal Wearable Deep Learning Approach.

Physiological measurement·2026
Same journal

Dual warm-start fusion versus attention-based fusion in low-label ECG-PCG classification: a controlled ablation study.

Physiological measurement·2026
Same journal

Inter-patient multi-label ECG classification via low-rank adaptation fine-tuned large language models with dynamic graph convolutional network.

Physiological measurement·2026
See all related articles

Related Experiment Video

Updated: Oct 10, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K

CARL: a running recognition algorithm for free-living accelerometer data.

John J Davis1, Marcin Straczkiewicz2, Jaroslaw Harezlak3

  • 1Department of Kinesiology, School of Public Health, Indiana University Bloomington, Bloomington, IN United States of America.

Physiological Measurement
|December 9, 2021
PubMed
Summary
This summary is machine-generated.

A new algorithm, the continuous amplitude running logistic (CARL) classifier, accurately identifies running from wearable accelerometer data. This tool enhances physical activity analysis in research and sports biomechanics.

Keywords:
human activity recognitionmachine learningwearable sensorswearable technology

More Related Videos

Tracking Cells in GFP-transgenic Zebrafish Using the Photoconvertible PSmOrange System
07:59

Tracking Cells in GFP-transgenic Zebrafish Using the Photoconvertible PSmOrange System

Published on: February 5, 2016

8.7K
A Familial Hypercholesterolemia Human Liver Chimeric Mouse Model Using Induced Pluripotent Stem Cell-derived Hepatocytes
10:56

A Familial Hypercholesterolemia Human Liver Chimeric Mouse Model Using Induced Pluripotent Stem Cell-derived Hepatocytes

Published on: September 15, 2018

8.3K

Related Experiment Videos

Last Updated: Oct 10, 2025

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla
08:51

Magnetic Resonance Imaging of Multiple Sclerosis at 7.0 Tesla

Published on: February 19, 2021

9.3K
Tracking Cells in GFP-transgenic Zebrafish Using the Photoconvertible PSmOrange System
07:59

Tracking Cells in GFP-transgenic Zebrafish Using the Photoconvertible PSmOrange System

Published on: February 5, 2016

8.7K
A Familial Hypercholesterolemia Human Liver Chimeric Mouse Model Using Induced Pluripotent Stem Cell-derived Hepatocytes
10:56

A Familial Hypercholesterolemia Human Liver Chimeric Mouse Model Using Induced Pluripotent Stem Cell-derived Hepatocytes

Published on: September 15, 2018

8.3K

Area of Science:

  • Biomedical Engineering
  • Sports Science
  • Epidemiology

Background:

  • Wearable accelerometers are valuable for physical activity epidemiology and sports biomechanics.
  • Accurately identifying specific activities like running from raw accelerometer data is challenging.

Purpose of the Study:

  • To develop and validate an algorithm for identifying running bouts in free-living accelerometer data.
  • To assess algorithm performance across various wearable device locations (wrist, torso) and datasets.

Main Methods:

  • Developed the continuous amplitude running logistic (CARL) classifier based on amplitude and frequency characteristics of running.
  • Trained the CARL classifier on data from 31 adults (waist and wrist accelerometers).
  • Validated the classifier on independent free-living data (30 subjects) and 166 subjects from prior studies using diverse devices and locations.

Main Results:

  • The CARL classifier achieved high accuracy (F1 score) in free-living data: 0.984 (waist) and 0.994 (wrist).
  • Performance on previously published datasets showed F1 scores ranging from 0.861 (chest) to 0.916 (waist).
  • Misclassifications were mainly observed during activities with similar motion profiles, like rope jumping and elliptical training.

Conclusions:

  • The CARL classifier accurately identifies running bouts as short as three seconds in free-living accelerometry data.
  • The algorithm demonstrates robust performance across different devices, wear locations, and datasets.
  • An open-source implementation is available, facilitating its use in research and sports applications.