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: Jul 11, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

A hidden Markov model-based stride segmentation technique applied to equine inertial sensor trunk movement data.

Thilo Pfau1, Marta Ferrari, Kevin Parsons

  • 1Structure and Motion Laboratory, Department of Veterinary Basic Sciences, The Royal Veterinary College, University of London, Hawkshead Lane, North Mymms, Hatfield AL9 7TA, UK. tpfau@rc.ac.uk

Journal of Biomechanics
|September 28, 2007
PubMed
Summary

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

Differences in Stride Characteristics Between Lead and Wheel Horses in Competitive Chuckwagon Racing.

Animals : an open access journal from MDPI·2026
Same author

Screening practices for diabetic peripheral neuropathy in pediatric type 1 diabetes: a nationwide survey by the ISPED Diabetes Study Group.

Acta diabetologica·2026
Same author

Measuring Chuckwagon Racehorse Movement Asymmetry Before and After Racing Using Wearable GNSS-IMUs: A Preliminary Study.

Animals : an open access journal from MDPI·2026
Same author

Warming temperatures increase close encounters between two top predator species via changes in spatial behaviour.

Movement ecology·2026
Same author

The influence of dirt track hardness on equine limb acceleration and impact attenuation.

BMC veterinary research·2026
Same author

Hoof and movement asymmetry in Thoroughbred racehorses with predominantly single direction training.

American journal of veterinary research·2026

Hidden Markov models (HMMs) automate the analysis of large inertial sensor datasets from galloping horses. This method accurately identifies over 91% of strides, enabling efficient data processing for research and clinical applications.

Area of Science:

  • Biomechanics
  • Animal locomotion
  • Data science

Background:

  • Inertial sensors enable large-scale data collection in human and animal movement studies.
  • Automated data processing is crucial for managing large datasets from ambulatory measurements.
  • Hidden Markov models (HMMs) are effective for classifying non-stationary data.

Purpose of the Study:

  • To apply HMMs for automated identification and segmentation of gallop strides from inertial sensor data in Thoroughbred racehorses.
  • To evaluate the performance of HMM-based stride segmentation using manually annotated data.

Main Methods:

  • Collected data from trunk-mounted six degrees of freedom inertial sensors on galloping horses.
  • Utilized HMMs to classify and segment gallop strides from mixed gait sequences.

More Related Videos

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

Related Experiment Videos

Last Updated: Jul 11, 2026

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats
06:52

Deep-Learning Based Multi-Joint Synchronous Tracking for Objective Quantification of Hindlimb Locomotor Kinematics in Rats

Published on: April 3, 2026

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb
08:24

Sit-to-stand-and-walk from 120% Knee Height: A Novel Approach to Assess Dynamic Postural Control Independent of Lead-limb

Published on: August 30, 2016

  • Subdivided data into training, cross-validation, and independent test sets for robust evaluation.

    • Main Results:

    • HMMs accurately detected 91% of gallop strides within +/- 40 ms of manual segmentation on the test set.
    • The automated system achieved high stride detection accuracy without missing strides.
    • Consistent performance was observed across cross-validation and test sets with limited training data.

    Conclusions:

    • HMMs provide an effective and easily implementable solution for automated stride segmentation in equine locomotion analysis.
    • Automated processing of inertial sensor data is essential for efficient analysis and decision-making in ambulatory research.
    • This approach supports leveraging large datasets for increased statistical power in movement studies.