A Study on cSSE that Improves Generation Alternation Model of SSE

Accession number;07A0176815
Title;A Study on cSSE that Improves Generation Alternation Model of SSE
Author; MARUYAMA TAKASHI (Graduate School of Medicine, Nagoya Univ., JPN) KITA EISUKE (Graduate School of Medicine, Nagoya Univ., JPN)
Journal Title;IPSJ Transactions on Database
Journal Code:Z0778A
ISSN:0387-5806
VOL.48;NO.SIG2(TOM16);PAGE.78-90(2007)
Figure&Table&Reference;FIG.15, TBL.7, REF.21
Pub. Country;Japan
Language;Japanese
Abstract;The Stochastic Schemata Exploiter (SSE) is one of the evolutionary optimization algorithms for solving the combinatorial optimization problems. The SSE can improve the global search ability by maintaining the diversity of the population. In this paper, we present the Cross generational elitist selection SSE (cSSE) algorithms which improves the generation alternation model of the SSE. The SSE and the cSSE are compared with the GA with the Minimal Generation Gap (MGG) and the Bayesian Optimization Algorithm (BOA) in 0/1 combinatorial optimization problem in order to discuss their convergence property. As a result, we indicate that cSSE has an excellent convergence property and the global search ability. (author abst.)