改进的差别矩阵及其求核方法

Improvement of Discernibility Matrix and the Computation of a Core

粗糙集方法提供了一种新的处理不精确、不完全与不相容知识的数学工具.属性约简是粗糙集理论的重要研究内容之一,而现有的很多属性约简算法都是从信息系统(或决策表)的核开始.针对HU利用差别矩阵求解粗糙集中的核方法的错误,叶东毅提出了新的差别矩阵及其求核方法,但计算代价高.为此,给出了改进的差别矩阵定义和求核方法,该方法纠正HU方法的错误,且可有效地降低计算代价.

Rough set theory is a new mathematical tool to deal with imprecise, incomplete and inconsistent data. Attributes reduction is one of important parts researched in rough set theory. The attributes core of a decision table is the start point to many existing algorithms of attributes reduction. In order to correct the error of HU'method based on discernibility matrix for computing the core of a decision table, Ye Dong-yi proposes new discernibility matrix and the computation of a core, but the complexity is too high. Therefore a improved discernibility matrix definition together with a method for computing the core is introduced, which corrects the error of HU'method and is with low complexity.