このエントリーをはてなブックマークに追加
ID 28458
file
A1206.pdf 747 KB
creator
Karatsu, Naoya
Nagata, Yuichi
Ono, Isao
Kobayashi, Shigenobu
NDC
Technology. Engineering
abstract
When attempting to optimize a function where exists several big-valley structures, conventional GAs often fail to find the global optimum. Innately Split Model (ISM) is a framework of GAs, which is designed to avoid this phenomenon called UV -Phenomenon. However, ISM doesn't care about previouslysearched areas by the past populations. Thus, it is possible that populations of ISM waste evaluation cost for redundant searches reaching previously-found optima. In this paper, we introduce Extended ISM (EISM) that uses search information of past populations as trap to suppress overlapping searches. To show performance of EISM, we apply it to some test functions, and analyze the behavior.
journal title
5th International Workshop on Computational Intelligence & Applications Proceedings : IWCIA 2009
start page
284
end page
289
date of issued
2009-11
publisher
IEEE SMC Hiroshima Chapter
issn
1883-3977
language
eng
nii type
Conference Paper
HU type
Conference Papers
DCMI type
text
format
application/pdf
text version
publisher
rights
(c) Copyright by IEEE SMC Hiroshima Chapter.
relation url
department
Graduate School of Engineering