Jove
Visualize
Contact Us

Related Experiment Videos

Evolutionary design of a fuzzy classifier from data.

Xiaoguang Chang1, John H Lilly

  • 1Department of Electrical and Computer Engineering, University of Louisville, Louisville, KY 40292, USA.

IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
|October 7, 2004
PubMed
Summary

This study introduces a novel evolutionary approach for creating compact fuzzy classification systems directly from data. The method automatically generates rules and membership functions without prior assumptions, demonstrating effectiveness on benchmark datasets.

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

A modern look at simplicity bias in image classification tasks.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Mitochondrial genome in Hypsizygus marmoreus and its evolution in Dikarya.

BMC genomics·2019
Same author

System for demonstrating arbitrary multi-spot beam steering from spatial light modulators.

Optics express·2009
Same author

A two-input sliding-mode controller for a planar arm actuated by four pneumatic muscle groups.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2004
Same author

Adaptive tracking for pneumatic muscle actuators in bicep and tricep configurations.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2003
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

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Data Mining

Background:

  • Automated fuzzy system design often requires predefined structural assumptions.
  • Existing methods may impose constraints on rule base size or data distribution.
  • There is a need for methods that derive fuzzy systems directly from data without prior knowledge.

Purpose of the Study:

  • To propose a new evolutionary approach for deriving compact fuzzy classification systems from data.
  • To develop a method that does not require a priori knowledge or assumptions about data distribution.
  • To automatically create and optimize fuzzy rules and membership functions within an evolutionary process.

Main Methods:

  • A novel evolutionary algorithm is employed for fuzzy system design.

Related Experiment Videos

  • The Variable Input Spread Inference Training (VISIT) algorithm is used to encode fuzzy systems.
  • Genetic operations are utilized to search for optimal fuzzy systems.
  • A fuzzy expert system serves as the fitness function to evaluate accuracy and compactness.

    • Main Results:

    • The proposed method successfully derives compact fuzzy classification systems.
    • The approach eliminates the need for initial assumptions on rule base size or data distribution.
    • Evaluations on benchmark datasets (iris, wine, breast cancer, diabetes) show the method's effectiveness.
    • Comparisons with existing literature highlight the advantages of the proposed technique.

    Conclusions:

    • The developed evolutionary approach effectively designs compact fuzzy classification systems from data.
    • This method offers a flexible alternative to existing techniques by removing structural constraints.
    • The approach demonstrates strong performance on various benchmark classification tasks.