遗传算法在数量型关联规则提取中的应用

关系数据库中数量属性的关联规则挖掘问题是关联规则挖掘中经常要遇到的问题。该文利用遗传算法解决FCM模糊聚类问题主要是为了避免FCM算法的局部极小问题。利用聚类的结果可以使数量型属性关联规则转换成类别型属性,类别型属性再转化为布尔型属性,这样,即可以使用许多已有关联规则挖掘方法挖掘出有意义的规则。

The Application of Gene Algorithm on Mining Quantitative Association Rules

The problem that we often encounter is mining association rules on the quantitative attributes in RDB(Rela-tion Data Base).This paper proposes the gene algorithm to solve the clustering problem which can be solved by FCM so as to decrease the local optimization.The quantitative attributes can be converted to be categorical attributes,and then the categorical attributes are converted to be bool attributes,so that many association algorithms can be used to mine significant association rules.