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

Ear-Worn Inertial Sensors Can Predict Gait Metrics and Reconstruct Vertical Ground Reaction Force Curves During Running.

Journal of applied biomechanics·2026
Same author

Prediction of on-field rugby scrummaging contact forces from videos using artificial neural networks.

PloS one·2026
Same author

Estimation of lower limb joint moments using consumer realistic wearable sensor locations and deep learning - finding the balance between accuracy and consumer viability.

Sports biomechanics·2025
Same author

Physical activity and joint health: Implications for knee osteoarthritis disease pathophysiology and mechanics.

Experimental physiology·2024
Same author

Consumer-priced wearable sensors combined with deep learning can be used to accurately predict ground reaction forces during various treadmill running conditions.

PeerJ·2024
Same author

Clustering analysis across different speeds reveals two distinct running techniques with no differences in running economy.

Sports biomechanics·2024

Related Experiment Video

Updated: Oct 6, 2025

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

743

A support vector machine algorithm can successfully classify running ability when trained with wearable sensor data

Joshua Autton Carter1, Adrian Rodriguez Rivadulla1, Ezio Preatoni1

  • 1Department for Health, University of Bath, Bath, UK.

Sports Biomechanics
|January 20, 2022
PubMed
Summary

This study developed a machine learning model using wearable sensors to automatically distinguish between novice and experienced runners. The model achieved high accuracy, even with a single sensor, offering potential for personalized running feedback.

Keywords:
Running biomechanicsgait analysisinertial measurement unitmachine 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

10.9K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.4K

Related Experiment Videos

Last Updated: Oct 6, 2025

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography
04:06

Author Spotlight: Enhancing Remote Rehabilitation with Virtual Reality and Electromyography

Published on: January 12, 2024

743
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification
07:47

Design and Evaluation of Smart Glasses for Food Intake and Physical Activity Classification

Published on: February 14, 2018

11.4K

Area of Science:

  • Biomechanics
  • Machine Learning
  • Sports Science

Background:

  • Understanding running technique differences is crucial for performance enhancement and injury prevention.
  • Automated analysis of running technique can provide objective feedback.

Purpose of the Study:

  • To develop and validate a support vector machine classifier for differentiating running technique.
  • To utilize wearable sensor data for automatic classification of runners by experience level.

Main Methods:

  • Collected 3D linear accelerations and angular velocities from six wearable sensors.
  • Employed cross-validation to test classification accuracy with various sensor combinations and running speeds.
  • Utilized a support vector machine (SVM) classifier.

Main Results:

  • Achieved classification accuracies ranging from 71.3% to 98.4%.
  • Single sensor locations, particularly the upper arm, demonstrated high classification accuracy (average 96.4%).
  • Identified significant differences in upper body biomechanics between novice and experienced runners.

Conclusions:

  • The developed SVM classifier effectively differentiates running techniques using wearable sensor data.
  • The methodology and identified biomechanical differences can inform personalized coaching for novice runners.
  • Wearable sensor technology offers a viable solution for objective running technique analysis.