基于属性桶的约简算法

Reduction Algorithm Based on Attribute Buckets

基于粗糙集理论的属性约简算法是机器学习和数据挖掘领域的研究热点之一。粗糙集理论是一种新型的处理模糊和不确定信息的数学工具,在保证分类能力不变的前提下,通过知识的约简导出概念的分类规则。文中提出了一种基于属性桶的约简算法,其约简过程类似基于属性频度函数的约简算法。该算法首先构造一组与决策表决策属性个数相同的属性桶,不同的属性桶划分了不同长度的区分矩阵项,避免了约简前的排序过程。通过构造属性桶时对核属性进行特殊处理,在一定程度上简化了属性约简过程。

Reduction algorithm based on rough set theory is one of the main subjects in the field of machine learning and data mining. The rough set theory is a new mathematics tool which is used to process fuzzy and indetermination problem. This theory which＇s advantages lle in not requiring prior information when carries out the clessicification is to derive classification rules of eoncepfion by knowledge reduction without changing the classification capacity of the information system. Presents a reduction algorithm based on attribute buckets which reduction progress is more similar than attribute reduction algorithm based on attributes frequency. At first, this algorithm oonstruct a set of attribute b^kets which have the same number of attribute in the decision table. Becattse the items of diseernable matrixes with different length will put in the different attribute buckets,the sort process of attribute reduction can be avoided. By particularly manipulating the core of attributes when oonstructing the attribute buckets, the algorithm can simplify the process of attribute reduction to a certain extent.