Fuzzy Adaptive Search Method for Parallel Genetic Algorithm with Island Combination Process
スポンサーリンク
概要
- 論文の詳細を見る
Genetic algorithms (GAs) pose several problems. Probably, the most important oneis that the search ability of ordinary GAs is not always optimal in the early and finalstages of the search because of fixed GA parameters. To solve this problem, we proposedthe fuzzy adaptive search method for genetic algorithms (FASGA) that is ableto tune the genetic parameters according to the search stage by the fuzzy reasoning.In this paper, a fuzzy adaptive search method for parallel genetic algorithms(FASPGA) is proposed, in which the high-speed search ability of fuzzy adaptivetuning by FASGA is combined with the high-quality solution finding capacity ofparallel genetic algorithms. The proposed method offers improved search performance,and produces high-quality solutions. Moreover, we also propose FASPGAwith an operation of combining dynamically sub-populations (C-FASPGA) whichcombines two elite islands in the final stage of the evolution to find a better solutionas early as possible. Simulations are performed to confirm the efficiency of the proposedmethod, which is shown to be superior to both ordinary and parallel geneticalgorithms.
- Elsevier Ltdの論文
Elsevier Ltd | 論文
- Inelastic collision processes of low energy protons in liquid water
- Evolution of the maturation rate collapses competitive coexistence
- Experimental evidence of the one-third magnetization plateau in the diamond chain compound Cu3(CO3)2(OH)2
- Stabilization and modulation of the output power of submillimeter wave gyrotron
- High-field ESR study on anomalous magnetization in CsFeCl3