基于决策类的分块差别矩阵及属性集求核算法

A Core Algorithm of Attribute Sets Based on the Decision Classification Block Difference Matrix

通过对基于差别矩阵的属性集求核算法研究,提出一种基于决策类的分块差别矩阵及相关属性集求核算法.该算法无论域划分过程,删除决策表信息系统中相容对象和对分块差别矩阵中元素之间关系的讨论,避免对象间的不必要比较.及时存储不相容对象作为遍历分块差别矩阵寻找核属性的判定条件,避免核属性的求解错误.实例分析与实验验证,说明了该算法的有效性.

Through the research on the algorithm for solving the kernel attribute based on the discernibility matrix,A block difference matrix and related attribute set calculation method based on decision class is proposed.Regardless of the domain division process,the algorithm deletes the compatible objects in the decision table information system and the.discussion of the relationship between the elements in the block difference matrix,so as to avoid unnecessary comparison between objects.The incompatible objects stored in time are used as the judgment conditions-for traversing the block difference matrix to find the core attributes,The example analysis and experimental verification show the effectiveness of the algorithm.