基于变长编码遗传算法的最小缩减计算

MINIMAL REDUCT COMPUTING BASED ON VARIABLE LENGTHCODING GENETIC ALGORITHM

在数据库知识发现的过程中 ,属性选取是其中的一个重要步骤 ,它通过去除冗余属性 ,达到提高数据挖掘效能的目的 .本文利用粗糙集合中的理论作为背景知识 ,讨论了使用遗传算法寻找最小缩减的方法 ,并提出采用个体变长编码的方法来解决最小缩减的计算问题 ,设计出相应的交叉、变异算子 。

Attribute selection is one of the most importance steps in the process of KDD. It can improve the efficiency of data mining greatly through removing the useless data. With Rough Set theory as the background knowledge, this paper discusses how to use genetic algorithm to solve the problem of computing the minimal reduct, brings forward a new method based on variable length coding genetic algorithm, and then designs the corresponding crossover and mutation operators. This method has been proved efficient through experiment.