A dynamic hierarchical fuzzy neural network for a general continuous function

Wei-Yen Wang, I. Hsum Li, Shu Chang Li, Men Shen Tsai, Shun Feng Su

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

A serious problem limiting the applicability of the fuzzy neural networks is the "curse of dimensional-ity", especially for general continuous functions. A way to deal with this problem is to construct a dy-namic hierarchical fuzzy neural network. In this pa-per, we propose a two-stage genetic algorithm to in-telligently construct the dynamic hierarchical fuzzy neural network (HFNN) based on the merged-FNN for general continuous functions. First, we use a ge-netic algorithm which is popular for flowshop sched-uling problems (GA-FSP) to construct the HFNN. Then, a reduced-form genetic algorithm (RGA) op-timizes the HFNN constructed by GA-FSP. For a real-world application, the presented method is used to approximate the Taiwanese stock market.

Original languageEnglish
Pages (from-to)130-136
Number of pages7
JournalInternational Journal of Fuzzy Systems
Volume11
Issue number2
Publication statusPublished - 2009 Jun 1

Fingerprint

Fuzzy neural networks
Fuzzy Neural Network
Continuous Function
Genetic algorithms
Genetic Algorithm
Flow Shop
Stock Market
Real-world Applications
Limiting
Gas

Keywords

  • Fuzzy neural networks
  • Genetic algorithms
  • Hierarchical structures

ASJC Scopus subject areas

  • Software
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this

A dynamic hierarchical fuzzy neural network for a general continuous function. / Wang, Wei-Yen; Li, I. Hsum; Li, Shu Chang; Tsai, Men Shen; Su, Shun Feng.

In: International Journal of Fuzzy Systems, Vol. 11, No. 2, 01.06.2009, p. 130-136.

Research output: Contribution to journalArticle

Wang, Wei-Yen ; Li, I. Hsum ; Li, Shu Chang ; Tsai, Men Shen ; Su, Shun Feng. / A dynamic hierarchical fuzzy neural network for a general continuous function. In: International Journal of Fuzzy Systems. 2009 ; Vol. 11, No. 2. pp. 130-136.
@article{d8c86515721946faba674a4591fdb9c4,
title = "A dynamic hierarchical fuzzy neural network for a general continuous function",
abstract = "A serious problem limiting the applicability of the fuzzy neural networks is the {"}curse of dimensional-ity{"}, especially for general continuous functions. A way to deal with this problem is to construct a dy-namic hierarchical fuzzy neural network. In this pa-per, we propose a two-stage genetic algorithm to in-telligently construct the dynamic hierarchical fuzzy neural network (HFNN) based on the merged-FNN for general continuous functions. First, we use a ge-netic algorithm which is popular for flowshop sched-uling problems (GA-FSP) to construct the HFNN. Then, a reduced-form genetic algorithm (RGA) op-timizes the HFNN constructed by GA-FSP. For a real-world application, the presented method is used to approximate the Taiwanese stock market.",
keywords = "Fuzzy neural networks, Genetic algorithms, Hierarchical structures",
author = "Wei-Yen Wang and Li, {I. Hsum} and Li, {Shu Chang} and Tsai, {Men Shen} and Su, {Shun Feng}",
year = "2009",
month = "6",
day = "1",
language = "English",
volume = "11",
pages = "130--136",
journal = "International Journal of Fuzzy Systems",
issn = "1562-2479",
publisher = "Chinese Fuzzy Systems Association",
number = "2",

}

TY - JOUR

T1 - A dynamic hierarchical fuzzy neural network for a general continuous function

AU - Wang, Wei-Yen

AU - Li, I. Hsum

AU - Li, Shu Chang

AU - Tsai, Men Shen

AU - Su, Shun Feng

PY - 2009/6/1

Y1 - 2009/6/1

N2 - A serious problem limiting the applicability of the fuzzy neural networks is the "curse of dimensional-ity", especially for general continuous functions. A way to deal with this problem is to construct a dy-namic hierarchical fuzzy neural network. In this pa-per, we propose a two-stage genetic algorithm to in-telligently construct the dynamic hierarchical fuzzy neural network (HFNN) based on the merged-FNN for general continuous functions. First, we use a ge-netic algorithm which is popular for flowshop sched-uling problems (GA-FSP) to construct the HFNN. Then, a reduced-form genetic algorithm (RGA) op-timizes the HFNN constructed by GA-FSP. For a real-world application, the presented method is used to approximate the Taiwanese stock market.

AB - A serious problem limiting the applicability of the fuzzy neural networks is the "curse of dimensional-ity", especially for general continuous functions. A way to deal with this problem is to construct a dy-namic hierarchical fuzzy neural network. In this pa-per, we propose a two-stage genetic algorithm to in-telligently construct the dynamic hierarchical fuzzy neural network (HFNN) based on the merged-FNN for general continuous functions. First, we use a ge-netic algorithm which is popular for flowshop sched-uling problems (GA-FSP) to construct the HFNN. Then, a reduced-form genetic algorithm (RGA) op-timizes the HFNN constructed by GA-FSP. For a real-world application, the presented method is used to approximate the Taiwanese stock market.

KW - Fuzzy neural networks

KW - Genetic algorithms

KW - Hierarchical structures

UR - http://www.scopus.com/inward/record.url?scp=70349426015&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349426015&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:70349426015

VL - 11

SP - 130

EP - 136

JO - International Journal of Fuzzy Systems

JF - International Journal of Fuzzy Systems

SN - 1562-2479

IS - 2

ER -