Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification

Sung Bae Cho, Jin H. Kim

Research output: Contribution to journalArticlepeer-review

286 Citations (Scopus)

Abstract

Recently, in the area of artificial neural networks, 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 confirm the superiority of the presented method to the other voting techniques.

Original languageEnglish
Pages (from-to)380-384
Number of pages5
JournalIEEE Transactions on Systems, Man and Cybernetics
Volume25
Issue number2
DOIs
Publication statusPublished - 1995 Feb

Bibliographical note

Funding Information:
Manuscript received April 16, 1993; revised December 22, 1993 and March 14, 1994. This work was supported in part by a grant from the Korean Science and Engineering Foundation (KOSEF) and by the IEEE Computer Society. The authors are with the Center for Artificial Intelligence Research and Computer Science Department, Korea Advanced Institute of Science and Technology, 373-1 Koosung-dong, Yoosung-ku, Taejeon 305-70 I, Republic of Korea. S.-B. Cho is currently with ATR Human Information Processing Research Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-02, Japan. His permanent address is the Department of Computer Science, Yonsei University, 134 Shinchon-dong, Sudaemoon-ku, Seoul 120-749, Republic of Korea. IEEE Log Number 9405708.

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Combining Multiple Neural Networks by Fuzzy Integral for Robust Classification'. Together they form a unique fingerprint.

Cite this