基于一种新的优胜劣汰遗传算法的最小缩减计算

Find Minimal Reduces Using a Novel Survival of the Fittest Genetic Algorithm

粗合集合理论现在已成为数据库知识分类的一种强有力的工具。而这种技术的核心问题是寻找一种最小缩减,即与原信息集合有相同的区分数据能力的最小的信息子集。提出了一种新的基于优胜劣汰遗传算法的最小缩减算法,在该算法中避免了传统遗传算法中的近亲繁殖和交叉、变异概率的盲目性,实验证明其具有较好的收敛性。

Rough sets theory is emerging as a powerful tool as inducing knowledge classification knowledge from database.Central to this technique is the problem of searching for a reduct which is a minimal subset of information that has the same ability to classify data as when the full set of information is used.In this paper,we present a new method of finding minimal reducts using a novel survival of the fittest genetic algorithm.The algorithm can avoid close breeding and the deficiency of selection of crossover and mutation probability in traditional genetic algorithm.The experimental results show that it is well convergent.