Species-based hybrid of electromagnetism-like mechanism and back-propagation algorithms for an interval type-2 fuzzy system design

Ching Hung Lee*, Feng Yu Chang, Chung Ta Lee

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

In this paper, we propose a species-based hybrid of electromagnetism-like mechanism and back-propagation algorithms (SEMBP) for an interval type-2 fuzzy neural system with asymmetric membership functions (aIT2FNS). The proposed SEMBP combines the advantages of EM and BP algorithms to obtain the faster convergence and lower computational complexity. In addition, SEMBP uses the uniform method to have the initial solution agents scatter over the feasible solution region evenly and the notion of species which can locate multiple optima to provide bigger possibility of finding the global optimum. The proposed aIT2FNS system uses type-2 asymmetric fuzzy membership functions and the TSK type consequence part. Finally, the chaotic system identification problem is presented to show the performance and effectiveness of the proposed aIT2FNS with SEMBP algorithm.

Original languageEnglish
Title of host publicationProceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
Pages140-145
Number of pages6
StatePublished - 2010
EventInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010 - Kowloon, Hong Kong
Duration: 17 Mar 201019 Mar 2010

Publication series

NameProceedings of the International MultiConference of Engineers and Computer Scientists 2010, IMECS 2010

Conference

ConferenceInternational MultiConference of Engineers and Computer Scientists 2010, IMECS 2010
CountryHong Kong
CityKowloon
Period17/03/1019/03/10

Keywords

  • Asymmetric
  • Fuzzy logic system
  • Takagi-Sugeno-Kang
  • Type-2 fuzzy neural system
  • Uniform initialization

Fingerprint Dive into the research topics of 'Species-based hybrid of electromagnetism-like mechanism and back-propagation algorithms for an interval type-2 fuzzy system design'. Together they form a unique fingerprint.

Cite this