GA has been successfully introduced to solve various optimizations problems. One of the characteristics of GA is that once it has converged, most of its population members will be copies of the best individual, causing GA to loose population diversity. This characteristic is a setback when we consider non-stationary problems in which the fitness functions vary with time. In this paper we propose Migrational-GA that stores the past environmental solutions and retrieved them rapidly when that environment is reactivated, through probabilistic operation.
|ホスト出版物のタイトル||Proceedings of the IEEE International Conference on Systems, Man and Cybernetics|
|出版ステータス||Published - 2001|
|イベント||2001 IEEE International Conference on Systems, Man and Cybernetics - Tucson, AZ, United States|
継続期間: 2001 10 7 → 2001 10 10
|Other||2001 IEEE International Conference on Systems, Man and Cybernetics|
|Period||01/10/7 → 01/10/10|
ASJC Scopus subject areas