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

RBF networks for source localization in quantitative electrophysiology.

A K Tun1, N T Lye, Z Guanglan

  • 1School of Electrical and Electronics Engineering, Nanyang Technological University, Singapore.

Critical Reviews in Biomedical Engineering
|December 7, 2000
PubMed
Summary

Radial Basis Function (RBF) networks offer an efficient alternative to traditional methods for solving inverse problems in quantitative electrophysiology. These networks, including the Minimal Resource Allocation Network (MRAN), provide accurate brain source localization without iterative computations.

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

Characterizing the NREM/REM sleep specific obstructive sleep apnea severity using snore sounds.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2017
Same author

Variations of snoring properties with macro sleep stages in a population of Obstructive Sleep Apnea patients.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013
Same author

Neural network based algorithm for automatic identification of cough sounds.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013
Same author

Cough sound analysis - a new tool for diagnosing pneumonia.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013
Same author

Automated algorithm for Wet/Dry cough sounds classification.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013
Same author

High frequency analysis of cough sounds in pediatric patients with respiratory diseases.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2013

Area of Science:

  • Neuroscience
  • Computational Electrophysiology
  • Artificial Intelligence

Background:

  • Quantitative electrophysiology often involves solving complex inverse problems.
  • Backpropagation neural networks have emerged as a potential solution.
  • Existing methods may require iterative computations or extensive resources.

Purpose of the Study:

  • To evaluate Radial Basis Function (RBF) networks for brain source localization.
  • To compare the performance of RBF networks against Levenberg-Marquardt (LM) algorithms.
  • To introduce and assess an improved RBF network, the Minimal Resource Allocation Network (MRAN).

Main Methods:

  • Implementation of a classic RBF network with a fixed number of hidden layer neurons.
  • Utilization of the Minimal Resource Allocation Network (MRAN) for dynamic network configuration.

Related Experiment Videos

  • Systematic performance comparison between RBF networks and LM algorithms for source localization.

    • Main Results:

    • RBF networks demonstrate efficacy in solving inverse problems in quantitative electrophysiology.
    • The MRAN shows capability for dynamic structural configuration, creating compact topologies.
    • Performance metrics indicate competitive or superior results compared to LM algorithms in specific contexts.

    Conclusions:

    • RBF networks, particularly MRAN, present a viable and efficient approach for brain source localization.
    • The dynamic configuration of MRAN allows for optimized network structures tailored to data.
    • These findings suggest a promising direction for computational electrophysiology and neuroimaging analysis.