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

A fuzzy clustering neural network architecture for multifunction upper-limb prosthesis.

Bekir Karlik1, M Osman Tokhi, Musa Alci

  • 1Department of Computer Engineering, College of Information Technology, University of Bahrain, Kingdom of Bahrain.

IEEE Transactions on Bio-Medical Engineering
|November 19, 2003
PubMed
Summary

New fuzzy clustering neural networks (FCNNs) offer improved classification of surface myoelectric signals for controlling prosthetic limbs. This advancement enhances user learning and real-time prosthetic control efficiency.

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

Artificial Neural Network Approach to Competency-Based Training Using a Virtual Reality Neurosurgical Simulation.

Operative neurosurgery (Hagerstown, Md.)·2022
Same author

Quantitation of Tissue Resection Using a Brain Tumor Model and 7-T Magnetic Resonance Imaging Technology.

World neurosurgery·2021
Same author

Artificial Neural Networks to Assess Virtual Reality Anterior Cervical Discectomy Performance.

Operative neurosurgery (Hagerstown, Md.)·2019
Same author

Machine Learning Identification of Surgical and Operative Factors Associated With Surgical Expertise in Virtual Reality Simulation.

JAMA network open·2019
Same author

Artificial Intelligence in Medical Education: Best Practices Using Machine Learning to Assess Surgical Expertise in Virtual Reality Simulation.

Journal of surgical education·2019
Same author

A new bats echolocation-based algorithm for single objective optimisation.

Evolutionary intelligence·2016

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence
  • Neuroscience

Background:

  • Surface myoelectric signal classification is crucial for advanced prosthetic control.
  • Existing neural network (NN) architectures face challenges in accuracy and computational efficiency.
  • Multifunction prostheses require sophisticated signal processing for intuitive user control.

Purpose of the Study:

  • To introduce and evaluate novel fuzzy clustering neural network (FCNN) architectures for myoelectric signal classification.
  • To compare the classification accuracy of FCNNs against traditional NN algorithms like multilayered perceptron and conic section function NNs.
  • To assess the potential of FCNNs in improving the control of multifunction upper-limb prostheses.

Main Methods:

  • Development of new fuzzy clustering neural network (FCNN) architectures.

Related Experiment Videos

  • Comparative analysis of classification accuracy using back-propagation multilayered perceptron NN, conic section function NN, and FCNNs.
  • Testing on myoelectric signals corresponding to six upper-limb movements: elbow flexion/extension, wrist pronation/supination, grasp, and resting.

    • Main Results:

    • Fuzzy clustering neural networks (FCNNs) demonstrated superior generalization capabilities compared to other evaluated NN algorithms.
    • The FCNN approach facilitated faster and more effective user learning for prosthetic control.
    • The proposed FCNN method shows significant potential for highly efficient real-time applications.

    Conclusions:

    • Fuzzy clustering neural networks represent a promising advancement in myoelectric signal classification for prosthetic control.
    • FCNNs offer enhanced performance in terms of accuracy and user adaptability.
    • The efficiency of FCNNs makes them suitable for real-time prosthetic limb applications.