Skip to the content

A new fuzzy set merging technique using inclusion-based fuzzy clustering

Nefti-Meziani, S, Kaymak, U and Oussalah, M 2008, 'A new fuzzy set merging technique using inclusion-based fuzzy clustering' , Fuzzy Systems, IEEE Transactions on, 16 (1) , pp. 145-161.

[img]
Preview
PDF (Publisher version)
Download (1MB) | Preview

Abstract

This paper proposes a new method of merging parameterized fuzzy sets based on clustering in the parameters space, taking into account the degree of inclusion of each fuzzy set in the cluster prototypes. The merger method is applied to fuzzy rule base simplification by automatically replacing the fuzzy sets corresponding to a given cluster with that pertaining to cluster prototype. The feasibility and the performance of the proposed method are studied using an application in mobile robot navigation. The results indicate that the proposed merging and rule base simplification approach leads to good navigation performance in the application considered and to fuzzy models that are interpretable by experts. In this paper, we concentrate mainly on fuzzy systems with Gaussian membership functions, but the general approach can also be applied to other parameterized fuzzy sets.

Item Type: Article
Uncontrolled Keywords: Fuzzy set theory, mobile robots, path planning, pattern clustering, fuzzy rule base simplification, fuzzy set merging technique, inclusion-based fuzzy clustering, mobile robot navigation, fuzzy clustering, fuzzy modeling, fuzzy sets, inclusion, merging
Themes: Subjects / Themes > Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Subjects outside of the University Themes
Schools: Colleges and Schools > College of Science & Technology
Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering
Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering > CASE Control & Systems Engineering Research Centre
Journal or Publication Title: Fuzzy Systems, IEEE Transactions on
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Refereed: Yes
ISSN: 10636706
Related URLs:
Depositing User: H Kenna
Date Deposited: 09 Jan 2009 09:52
Last Modified: 20 Aug 2013 15:51
URI: http://usir.eprints.org/id/eprint/980

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year