Multiple network architecture combined by fuzzy integral

Sung-Bae Cho, Jin H. Kim

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

3 Citations (Scopus)

Abstract

Recently, in the area of artificial neural network, the concept of combining multiple networks has been proposed as a new direction for the development of highly reliable neural network systems. In this paper we propose a method for multinetwork combination based on the fuzzy integral. This technique nonlinearly combines objective evidence. in the form of a fuzzy membership function, with subjective evaluation of the worth of the individual neural networks with respect to the decision. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Pages1373-1376
Number of pages4
Volume2
ISBN (Print)0780314212
Publication statusPublished - 1993 Dec 1
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3) - Nagoya, Jpn
Duration: 1993 Oct 251993 Oct 29

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3)
CityNagoya, Jpn
Period93/10/2593/10/29

Fingerprint

Network architecture
Neural networks
Membership functions

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Cho, S-B., & Kim, J. H. (1993). Multiple network architecture combined by fuzzy integral. In Anon (Ed.), Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1373-1376). Publ by IEEE.
Cho, Sung-Bae ; Kim, Jin H. / Multiple network architecture combined by fuzzy integral. Proceedings of the International Joint Conference on Neural Networks. editor / Anon. Vol. 2 Publ by IEEE, 1993. pp. 1373-1376
@inproceedings{af3bf0ddd7cd44d1b0a8a73b287a40dc,
title = "Multiple network architecture combined by fuzzy integral",
abstract = "Recently, in the area of artificial neural network, the concept of combining multiple networks has been proposed as a new direction for the development of highly reliable neural network systems. In this paper we propose a method for multinetwork combination based on the fuzzy integral. This technique nonlinearly combines objective evidence. in the form of a fuzzy membership function, with subjective evaluation of the worth of the individual neural networks with respect to the decision. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.",
author = "Sung-Bae Cho and Kim, {Jin H.}",
year = "1993",
month = "12",
day = "1",
language = "English",
isbn = "0780314212",
volume = "2",
pages = "1373--1376",
editor = "Anon",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

Cho, S-B & Kim, JH 1993, Multiple network architecture combined by fuzzy integral. in Anon (ed.), Proceedings of the International Joint Conference on Neural Networks. vol. 2, Publ by IEEE, pp. 1373-1376, Proceedings of 1993 International Joint Conference on Neural Networks. Part 2 (of 3), Nagoya, Jpn, 93/10/25.

Multiple network architecture combined by fuzzy integral. / Cho, Sung-Bae; Kim, Jin H.

Proceedings of the International Joint Conference on Neural Networks. ed. / Anon. Vol. 2 Publ by IEEE, 1993. p. 1373-1376.

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

TY - GEN

T1 - Multiple network architecture combined by fuzzy integral

AU - Cho, Sung-Bae

AU - Kim, Jin H.

PY - 1993/12/1

Y1 - 1993/12/1

N2 - Recently, in the area of artificial neural network, the concept of combining multiple networks has been proposed as a new direction for the development of highly reliable neural network systems. In this paper we propose a method for multinetwork combination based on the fuzzy integral. This technique nonlinearly combines objective evidence. in the form of a fuzzy membership function, with subjective evaluation of the worth of the individual neural networks with respect to the decision. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.

AB - Recently, in the area of artificial neural network, the concept of combining multiple networks has been proposed as a new direction for the development of highly reliable neural network systems. In this paper we propose a method for multinetwork combination based on the fuzzy integral. This technique nonlinearly combines objective evidence. in the form of a fuzzy membership function, with subjective evaluation of the worth of the individual neural networks with respect to the decision. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.

UR - http://www.scopus.com/inward/record.url?scp=0027815097&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027815097&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027815097

SN - 0780314212

VL - 2

SP - 1373

EP - 1376

BT - Proceedings of the International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -

Cho S-B, Kim JH. Multiple network architecture combined by fuzzy integral. In Anon, editor, Proceedings of the International Joint Conference on Neural Networks. Vol. 2. Publ by IEEE. 1993. p. 1373-1376