A Design for a Self-Organising Fuzzy Neural Network Based on the Genetic Algortihm

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A novel hybrid algorithm based on the genetic algorithm, named self-organizing fuzzy neural network based on genetic algorithm (SOFNNGA), is proposed to design a fuzzy neural network to implement Takagi- Sugeno (TS) type fuzzy models in this paper. A new adding method based on geometric growing criterion and the å-completeness of fuzzy rules is used to generate the initial structure firstly. Then a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least squares estimation is used to adjust all parameters, which has two steps: first, adjusting the parameter matrix, and second, centers and widths of all membership functions are modified. A simulation for a benchmark problem is presented to illustrate the performance of the proposed algorithm.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages1967-1972
Number of pages6
Publication statusPublished - Oct 2003
Event2003 IEEE Int. Conf. Systems Man and Cybernetics - Washington, DC, USA
Duration: 1 Oct 2003 → …

Conference

Conference2003 IEEE Int. Conf. Systems Man and Cybernetics
Period1/10/03 → …

Fingerprint

Fuzzy neural networks
Genetic algorithms
Fuzzy rules
Membership functions
Backpropagation

Cite this

@inproceedings{f902908f4ed043f3960883ff875939f0,
title = "A Design for a Self-Organising Fuzzy Neural Network Based on the Genetic Algortihm",
abstract = "A novel hybrid algorithm based on the genetic algorithm, named self-organizing fuzzy neural network based on genetic algorithm (SOFNNGA), is proposed to design a fuzzy neural network to implement Takagi- Sugeno (TS) type fuzzy models in this paper. A new adding method based on geometric growing criterion and the {\aa}-completeness of fuzzy rules is used to generate the initial structure firstly. Then a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least squares estimation is used to adjust all parameters, which has two steps: first, adjusting the parameter matrix, and second, centers and widths of all membership functions are modified. A simulation for a benchmark problem is presented to illustrate the performance of the proposed algorithm.",
author = "G Leng and TM McGinnity and G Prasad",
year = "2003",
month = "10",
language = "English",
pages = "1967--1972",
booktitle = "Unknown Host Publication",

}

Leng, G, McGinnity, TM & Prasad, G 2003, A Design for a Self-Organising Fuzzy Neural Network Based on the Genetic Algortihm. in Unknown Host Publication. pp. 1967-1972, 2003 IEEE Int. Conf. Systems Man and Cybernetics, 1/10/03.

A Design for a Self-Organising Fuzzy Neural Network Based on the Genetic Algortihm. / Leng, G; McGinnity, TM; Prasad, G.

Unknown Host Publication. 2003. p. 1967-1972.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - A Design for a Self-Organising Fuzzy Neural Network Based on the Genetic Algortihm

AU - Leng, G

AU - McGinnity, TM

AU - Prasad, G

PY - 2003/10

Y1 - 2003/10

N2 - A novel hybrid algorithm based on the genetic algorithm, named self-organizing fuzzy neural network based on genetic algorithm (SOFNNGA), is proposed to design a fuzzy neural network to implement Takagi- Sugeno (TS) type fuzzy models in this paper. A new adding method based on geometric growing criterion and the å-completeness of fuzzy rules is used to generate the initial structure firstly. Then a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least squares estimation is used to adjust all parameters, which has two steps: first, adjusting the parameter matrix, and second, centers and widths of all membership functions are modified. A simulation for a benchmark problem is presented to illustrate the performance of the proposed algorithm.

AB - A novel hybrid algorithm based on the genetic algorithm, named self-organizing fuzzy neural network based on genetic algorithm (SOFNNGA), is proposed to design a fuzzy neural network to implement Takagi- Sugeno (TS) type fuzzy models in this paper. A new adding method based on geometric growing criterion and the å-completeness of fuzzy rules is used to generate the initial structure firstly. Then a hybrid algorithm based on genetic algorithms, backpropagation, and recursive least squares estimation is used to adjust all parameters, which has two steps: first, adjusting the parameter matrix, and second, centers and widths of all membership functions are modified. A simulation for a benchmark problem is presented to illustrate the performance of the proposed algorithm.

M3 - Conference contribution

SP - 1967

EP - 1972

BT - Unknown Host Publication

ER -