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

Gait control system for functional electrical stimulation using neural networks.

K Y Tong1, M H Granat

  • 1Bioengineering Unit, University of Strathclyde, Wolfson Centre, Glasgow, UK.

Medical & Biological Engineering & Computing
|July 9, 1999
PubMed
Summary
This summary is machine-generated.

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

Priorities when designing a service-focused delivery model for mobility devices: a systematic review.

Disability and rehabilitation. Assistive technology·2024
Same author

Characteristics of a protocol to collect objective physical activity/sedentary behaviour data in a large study: Seniors USP (understanding sedentary patterns).

Journal for the measurement of physical behaviour·2018
Same author

Upper limb activity in myoelectric prosthesis users is biased towards the intact limb and appears unrelated to goal-directed task performance.

Scientific reports·2018
Same author

Comparison of single- and dual-monitor approaches to differentiate sitting from lying in free-living conditions.

Scandinavian journal of medicine & science in sports·2018
Same author

Time spent in sedentary posture is associated with waist circumference and cardiovascular risk.

International journal of obesity (2005)·2017
Same author

Seasonal variation in the distribution of daily stepping in 11-13 year old school children.

International journal of exercise science·2015

Continuous neural networks using multiple sensors can improve functional electrical stimulation (FES) for spinal cord injury (SCI) patients. This approach offers better control and fewer oscillations compared to traditional methods.

Area of Science:

  • Biomedical Engineering
  • Neuroscience
  • Rehabilitation Technology

Background:

  • Functional electrical stimulation (FES) is crucial for restoring walking in spinal cord injured (SCI) individuals.
  • Hand switches are currently the preferred method for controlling FES timing, relying on user expertise.
  • Existing neural network approaches for FES control use limited sensors and binary outputs, leading to potential oscillations.

Purpose of the Study:

  • To develop and evaluate a more effective FES controller using a continuous function, three-layer neural network.
  • To investigate the use of a larger number of sensors, including 'virtual' sensors, for improved FES control.
  • To compare the performance of continuous neural networks against binary networks for FES applications.

Main Methods:

Related Experiment Videos

  • A three-layer neural network with five hidden nodes was employed.
  • Sensor sets included ten force sensors and 13 'virtual' kinematic sensors.
  • Continuous and binary neural networks were constructed and compared using 32 synchronized sensors.

    • Main Results:

    • A three-sensor set demonstrated optimal performance, achieving 90% accuracy with force sensors and 93% with virtual kinematic sensors.
    • Continuous neural networks exhibited significantly fewer oscillations compared to binary networks.
    • The developed FES control system showed improved accuracy over traditional heel switches (77-81%).

    Conclusions:

    • Continuous function neural networks are effective in cloning user expertise for FES control.
    • Utilizing a larger set of sensors, including virtual ones, enhances FES system performance.
    • Continuous neural networks offer a promising solution for generating robust and oscillation-free FES controllers for SCI individuals.