|Table of Contents|

A Study on Identification Methods of λ-Fuzzy Measures(PDF)

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2001年01期
Page:
44-47
Research Field:
Publishing date:

Info

Title:
A Study on Identification Methods of λ-Fuzzy Measures
Author(s):
SunHuaijiang YangJingyu
Department of Computer Science and Technology,NUST,Nanjing 210094
Keywords:
artificial intelligence pattern recognit ion meas
PACS:
TP18
DOI:
-
Abstract:
Fuzzy measures g iven by human ex pert s usually contain uncertaint ies, and do not sat isfy required mathemat ical properties. The problem of ident ifying lambda-fuzzy measures is studied w hen the uncertaint ies are expressed by intervals and fuzzy numbers. Four error funct ions are proposed. The minima of error functions correspond to opt imal ident ified results. When there is not any uncertainty, obtained results are equal to those from exist ing methods. Numerical experimental result s indicate that the proposed ident if icat ion algorithms are ef ficient .

References:

1 Tahani H, Keller J M. Informatio n fusion in computer vision using the fuzzy integr al. IEEE Trans SMC, 1990, 20( 3) : 733~ 741
2 Leszczynski K, Penczek P, Grochulski W. Sug eno. s fuzzy measure and fuzzy cluster ing . Fuzzy Sets and Systems, 1985, 15( 2) : 147~ 158
3 Wier zchon S T. An alg orithm for identificat ion of fuzzy measure. Fuzzy Sets and Systems, 1983,9( 1) : 69~ 78
4 Lee K M, Leekw ang H. Ident ification of K-fuzzy measure by g enetic alg orithms. Fuzzy Sets and Systems, 1995, 75( 3) : 301~ 309

Memo

Memo:
-
Last Update: 2013-03-25