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 Videos

Simple artificial neural network models can generate basic muscle activity patterns for human locomotion at different

S D Prentice1, A E Patla, D A Stacey

  • 1Department of Kinesiology, University of Waterloo, Canada.

Experimental Brain Research
|December 31, 1998
PubMed
Summary

A neural network model accurately replicates human locomotion muscle activity using only gait cycle timing. This computational model advances understanding of central pattern generators (CPGs) in movement control.

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

Global Burden of Animal Diseases informatics strategy, data quality and model interoperability.

Revue scientifique et technique (International Office of Epizootics)·2024
Same author

Informatics progress of the Global Burden of Animal Diseases programme towards data for One Health.

Revue scientifique et technique (International Office of Epizootics)·2023
Same author

Age-related changes in balance control system: initiation of stepping.

Clinical biomechanics (Bristol, Avon)·2013
Same author

Adaptation of gait termination on a slippery surface in Parkinson's disease.

Gait & posture·2012
Same author

Gaze fixation patterns for negotiating complex ground terrain.

Neuroscience·2006
Same author

An evaluation of sensorimotor integration during locomotion toward a target in Parkinson's disease.

Neuroscience·2005

Area of Science:

  • Neuroscience
  • Biomechanics
  • Computational Biology

Background:

  • Central pattern generators (CPGs) are neural circuits controlling rhythmic behaviors like locomotion.
  • Understanding CPG function is crucial for developing advanced prosthetics and rehabilitation strategies.
  • Previous models often require complex inputs or fail to capture detailed muscle activation patterns.

Purpose of the Study:

  • To develop a neural network model simulating the shaping function of a CPG for human locomotion.
  • To investigate if simple gait cycle timing inputs can generate realistic muscle activation patterns.
  • To assess the model's ability to represent both amplitude and timing of electromyographic (EMG) signals.

Main Methods:

  • A neural network was trained using back-propagation.

Related Experiment Videos

  • Input data consisted of sine and cosine waveforms representing stride rate.
  • Electromyographic (EMG) and cadence data from a human subject walking on a treadmill were used for training and validation.
  • The model predicted activation patterns for eight lower limb and trunk muscles.

    • Main Results:

    • The neural network model successfully generated muscle activation patterns closely matching experimental EMG data.
    • The model accurately represented both the timing and amplitude characteristics of muscle activity.
    • The model demonstrated effectiveness across a range of walking speeds.
    • A relatively small number of hidden units were sufficient for accurate modeling.

    Conclusions:

    • Simple gait cycle timing is a powerful determinant of muscle activation patterns in human locomotion.
    • This neural network model provides a robust and efficient representation of CPG function.
    • The findings suggest potential for modeling sensory feedback influences on muscle control.
    • The model offers a valuable tool for research in human movement and neural control.