Fusion of neural networks with fuzzy logic and genetic algorithm

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

Combining multiple estimators has appeared as one of hot research topics in several areas including artificial neural networks. This paper presents three methods to work out the problem based on so-called softcomputing techniques, toward a unified framework of hybrid softcomputing techniques. The first method based on fuzzy logic nonlinearly combines objective evidences, in the form of network outputs, with subjective evaluation of the reliability of the individual neural networks. The second method based on genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs. Finally, we have proposed a hybrid synergistic method of fuzzy logic and genetic algorithm to optimally combine neural networks. The experimental results with the recognition problem of totally unconstrained handwritten digits show that the performance could be improved significantly with the proposed softcomputing techniques.

Original languageEnglish
Pages (from-to)363-372
Number of pages10
JournalIntegrated Computer-Aided Engineering
Volume9
Issue number4
Publication statusPublished - 2002 Jan 1

Fingerprint

Soft Computing
Fuzzy Logic
Fuzzy logic
Fusion
Fusion reactions
Genetic algorithms
Genetic Algorithm
Neural Networks
Neural networks
Subjective Evaluation
Output
Hybrid Method
Digit
Artificial Neural Network
Estimator
Experimental Results

All Science Journal Classification (ASJC) codes

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

Cite this

@article{2d4568add3bb454eba38e225f95d4c16,
title = "Fusion of neural networks with fuzzy logic and genetic algorithm",
abstract = "Combining multiple estimators has appeared as one of hot research topics in several areas including artificial neural networks. This paper presents three methods to work out the problem based on so-called softcomputing techniques, toward a unified framework of hybrid softcomputing techniques. The first method based on fuzzy logic nonlinearly combines objective evidences, in the form of network outputs, with subjective evaluation of the reliability of the individual neural networks. The second method based on genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs. Finally, we have proposed a hybrid synergistic method of fuzzy logic and genetic algorithm to optimally combine neural networks. The experimental results with the recognition problem of totally unconstrained handwritten digits show that the performance could be improved significantly with the proposed softcomputing techniques.",
author = "Cho, {Sung Bae}",
year = "2002",
month = "1",
day = "1",
language = "English",
volume = "9",
pages = "363--372",
journal = "Integrated Computer-Aided Engineering",
issn = "1069-2509",
publisher = "IOS Press",
number = "4",

}

Fusion of neural networks with fuzzy logic and genetic algorithm. / Cho, Sung Bae.

In: Integrated Computer-Aided Engineering, Vol. 9, No. 4, 01.01.2002, p. 363-372.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fusion of neural networks with fuzzy logic and genetic algorithm

AU - Cho, Sung Bae

PY - 2002/1/1

Y1 - 2002/1/1

N2 - Combining multiple estimators has appeared as one of hot research topics in several areas including artificial neural networks. This paper presents three methods to work out the problem based on so-called softcomputing techniques, toward a unified framework of hybrid softcomputing techniques. The first method based on fuzzy logic nonlinearly combines objective evidences, in the form of network outputs, with subjective evaluation of the reliability of the individual neural networks. The second method based on genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs. Finally, we have proposed a hybrid synergistic method of fuzzy logic and genetic algorithm to optimally combine neural networks. The experimental results with the recognition problem of totally unconstrained handwritten digits show that the performance could be improved significantly with the proposed softcomputing techniques.

AB - Combining multiple estimators has appeared as one of hot research topics in several areas including artificial neural networks. This paper presents three methods to work out the problem based on so-called softcomputing techniques, toward a unified framework of hybrid softcomputing techniques. The first method based on fuzzy logic nonlinearly combines objective evidences, in the form of network outputs, with subjective evaluation of the reliability of the individual neural networks. The second method based on genetic algorithm gives us an effective vehicle to determine the optimal weight parameters that are multiplied by the network outputs. Finally, we have proposed a hybrid synergistic method of fuzzy logic and genetic algorithm to optimally combine neural networks. The experimental results with the recognition problem of totally unconstrained handwritten digits show that the performance could be improved significantly with the proposed softcomputing techniques.

UR - http://www.scopus.com/inward/record.url?scp=0036452280&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036452280&partnerID=8YFLogxK

M3 - Article

VL - 9

SP - 363

EP - 372

JO - Integrated Computer-Aided Engineering

JF - Integrated Computer-Aided Engineering

SN - 1069-2509

IS - 4

ER -