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: Jun 26, 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

Gait event detection using a multilayer neural network.

Adam Miller1

  • 1Motion Analysis Center, Mary Free Bed Rehabilitation Hospital, 360 Lafayette SE, Suite 340, Grand Rapids, MI 49503-4680, United States. Adam.Miller@maryfreebed.com

Gait & Posture
|January 13, 2009
PubMed
Summary

This study introduces an artificial neural network to automatically detect gait events in patients with pathologic gait. The method accurately identifies foot-contact and foot-off events, improving upon manual analysis.

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

MAGNETOcardiography Parameters to Predict Sudden Cardiac Death (MAGNETO-SCD) or Ventricular Events From Implantable Cardioverter Defibrillators.

JACC. Clinical electrophysiology·2026
Same author

Current views on sustainability in urology: findings from the North Central Section of American Urological Association membership survey.

Frontiers in urology·2026
Same author

Discovery of Novel Magnetocardiography Parameters Predicting Future ICD Therapies: Insights From the Magneto-SCD Study.

Circulation. Arrhythmia and electrophysiology·2026
Same author

A Prickly Problem: Genome Skimming Reveals Varying Levels of Phylogenetic Diversity in the Freshwater Crayfish <i>Euastacus armatus</i> Complex (Parastacidae) With Implications for Taxonomy and Conservation.

Ecology and evolution·2026
Same author

The effect of intravenous calcium administration on haemodynamics in perioperative cardiothoracic surgery and intensive care: A narrative review.

Critical care and resuscitation : journal of the Australasian Academy of Critical Care Medicine·2026
Same author

Real-World Outcomes of Primary Versus Interval Debulking Surgery in a Multicenter Cohort of Advanced Ovarian Cancer Patients Treated with Bevacizumab.

Cancers·2026

Area of Science:

  • Biomechanics
  • Computational Neuroscience
  • Medical Technology

Background:

  • Manual detection of gait events from motion capture data is time-consuming.
  • Automated methods for analyzing pathologic gait are lacking.
  • Artificial neural networks (ANNs) are suitable for classification tasks like gait event detection.

Purpose of the Study:

  • To present a multilayer artificial neural network for classifying gait events.
  • To utilize sagittal plane coordinates from heel and toe markers for event detection.
  • To compare ANN-based event detection with force plate measurements in pathologic gait.

Main Methods:

  • Developed a multilayer artificial neural network for gait event classification.
  • Used sagittal plane kinematic data (heel and toe markers).

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

Related Experiment Videos

Last Updated: Jun 26, 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

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

  • Compared ANN results to force plate data in 40 pathologic gait subjects (barefoot and shod/braced).

    • Main Results:

    • The ANN detected foot-contact events 7.1 ms (barefoot) and 0.8 ms (shod/braced) earlier than the force plate.
    • The ANN detected foot-off events 8.8 ms (barefoot) and 3.3 ms (shod/braced) earlier than the force plate.
    • Agreement between methods was within 1-2 frames at 120 Hz data collection rate.

    Conclusions:

    • The artificial neural network provides an accurate and autonomous method for detecting gait events in pathologic gait.
    • This automated approach significantly reduces the labor involved in gait analysis.
    • The findings suggest a promising tool for clinical gait assessment and research.