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 event detection for FES using accelerometers and supervised machine learning.

R Williamson1, B J Andrews

  • 1Second Sight, LLC, Valencia, CA 91355, USA.

IEEE Transactions on Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society
|September 23, 2000
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

The effect of FES-rowing training on cardiac structure and function: pilot studies in people with spinal cord injury.

Spinal cord·2016
Same author

Can FES-rowing mediate bone mineral density in SCI: a pilot study.

Spinal cord·2014
Same author

FES-rowing in tetraplegia: a preliminary report.

Spinal cord·2014
Same author

The emergence of retinopathy of prematurity in Guatemala.

Journal of pediatric ophthalmology and strabismus·2011
Same author

Activation of lower back muscles via FES for pressure sores prevention in paraplegia: a case study.

Journal of medical engineering & technology·2010
Same author

Transcutaneous posterior tibial nerve stimulation for treatment of detrusor hyperreflexia in spinal cord injury.

The Journal of urology·2003

This study developed rule-based gait phase detectors using Rough Sets (RS) and Adaptive Logic Networks (ALNs) for real-time walking analysis. The RS detector achieved high accuracy and was more efficient, making it suitable for microcontrollers.

Area of Science:

  • Biomechanics
  • Signal Processing
  • Machine Learning

Background:

  • Real-time gait phase detection is crucial for analyzing normal walking.
  • Previous methods relied on handcrafted algorithms, limiting efficiency.

Purpose of the Study:

  • To develop and compare rule-based gait phase detectors using Rough Sets (RS) and Adaptive Logic Networks (ALNs).
  • To evaluate detector accuracy and efficiency for real-time gait analysis.

Main Methods:

  • Utilized a single cluster of shank-mounted accelerometers.
  • Synthesized gait phase detectors using RS and ALN rule induction algorithms.
  • Compared performance against a handcrafted stance/swing detector.

Main Results:

Related Experiment Videos

  • RS and ALN detectors achieved high stance/swing detection accuracy (94-97% and 87-94%, respectively).
  • A post-detector filter improved RS and ALN accuracy to 98%.
  • RS and ALN detected five gait phases with 82-91% accuracy.
  • RS-based detectors were 10x faster and used 1/10th memory of ALN-based detectors.

Conclusions:

  • Rule-based detectors, particularly RS, offer accurate and efficient real-time gait phase detection.
  • The RS-based detector is suitable for microcontroller implementation due to its speed and low memory requirements.
  • These findings advance wearable technology for gait analysis and rehabilitation.