A new two-phase approach to fuzzy modeling for nonlinear function approximation

Wooyong Chung, Euntai Kim

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Nonlinear modeling of complex irregular systems constitutes the essential part of many control and decision-making systems and fuzzy logic is one of the most effective algorithms to build such a nonlinear model. In this paper, a new approach to fuzzy modeling is proposed. The model considered herein is the well-known Sugeno-type fuzzy system. The fuzzy modeling algorithm suggested in this paper is composed of two phases: coarse tuning and fine tuning. In the first phase (coarse tuning), a successive clustering algorithm with the fuzzy validity measure (SCFVM) is proposed to find the number of the fuzzy rules and an initial fuzzy model. In the second phase (fine tuning), a moving genetic algorithm with partial encoding (MGAPE) is developed and used for optimized tuning of membership functions of the fuzzy model. Two computer simulation examples are provided to evaluate the performance of the proposed modeling approach and compare it with other modeling approaches.

Original languageEnglish
Pages (from-to)2473-2483
Number of pages11
JournalIEICE Transactions on Information and Systems
VolumeE89-D
Issue number9
DOIs
Publication statusPublished - 2006 Jan 1

Fingerprint

Tuning
Fuzzy rules
Fuzzy systems
Membership functions
Clustering algorithms
Fuzzy logic
Large scale systems
Genetic algorithms
Decision making
Computer simulation

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering
  • Artificial Intelligence

Cite this

@article{ed39b6aff7514b24ac5ae3c1f47eb72e,
title = "A new two-phase approach to fuzzy modeling for nonlinear function approximation",
abstract = "Nonlinear modeling of complex irregular systems constitutes the essential part of many control and decision-making systems and fuzzy logic is one of the most effective algorithms to build such a nonlinear model. In this paper, a new approach to fuzzy modeling is proposed. The model considered herein is the well-known Sugeno-type fuzzy system. The fuzzy modeling algorithm suggested in this paper is composed of two phases: coarse tuning and fine tuning. In the first phase (coarse tuning), a successive clustering algorithm with the fuzzy validity measure (SCFVM) is proposed to find the number of the fuzzy rules and an initial fuzzy model. In the second phase (fine tuning), a moving genetic algorithm with partial encoding (MGAPE) is developed and used for optimized tuning of membership functions of the fuzzy model. Two computer simulation examples are provided to evaluate the performance of the proposed modeling approach and compare it with other modeling approaches.",
author = "Wooyong Chung and Euntai Kim",
year = "2006",
month = "1",
day = "1",
doi = "10.1093/ietisy/e89-d.9.2473",
language = "English",
volume = "E89-D",
pages = "2473--2483",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

A new two-phase approach to fuzzy modeling for nonlinear function approximation. / Chung, Wooyong; Kim, Euntai.

In: IEICE Transactions on Information and Systems, Vol. E89-D, No. 9, 01.01.2006, p. 2473-2483.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A new two-phase approach to fuzzy modeling for nonlinear function approximation

AU - Chung, Wooyong

AU - Kim, Euntai

PY - 2006/1/1

Y1 - 2006/1/1

N2 - Nonlinear modeling of complex irregular systems constitutes the essential part of many control and decision-making systems and fuzzy logic is one of the most effective algorithms to build such a nonlinear model. In this paper, a new approach to fuzzy modeling is proposed. The model considered herein is the well-known Sugeno-type fuzzy system. The fuzzy modeling algorithm suggested in this paper is composed of two phases: coarse tuning and fine tuning. In the first phase (coarse tuning), a successive clustering algorithm with the fuzzy validity measure (SCFVM) is proposed to find the number of the fuzzy rules and an initial fuzzy model. In the second phase (fine tuning), a moving genetic algorithm with partial encoding (MGAPE) is developed and used for optimized tuning of membership functions of the fuzzy model. Two computer simulation examples are provided to evaluate the performance of the proposed modeling approach and compare it with other modeling approaches.

AB - Nonlinear modeling of complex irregular systems constitutes the essential part of many control and decision-making systems and fuzzy logic is one of the most effective algorithms to build such a nonlinear model. In this paper, a new approach to fuzzy modeling is proposed. The model considered herein is the well-known Sugeno-type fuzzy system. The fuzzy modeling algorithm suggested in this paper is composed of two phases: coarse tuning and fine tuning. In the first phase (coarse tuning), a successive clustering algorithm with the fuzzy validity measure (SCFVM) is proposed to find the number of the fuzzy rules and an initial fuzzy model. In the second phase (fine tuning), a moving genetic algorithm with partial encoding (MGAPE) is developed and used for optimized tuning of membership functions of the fuzzy model. Two computer simulation examples are provided to evaluate the performance of the proposed modeling approach and compare it with other modeling approaches.

UR - http://www.scopus.com/inward/record.url?scp=33748759256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748759256&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e89-d.9.2473

DO - 10.1093/ietisy/e89-d.9.2473

M3 - Article

AN - SCOPUS:33748759256

VL - E89-D

SP - 2473

EP - 2483

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 9

ER -