区分对象对集的不完备决策表属性约简

Attribute reduction algorithm based on discernibility object pair set in incomplete decision table

通过利用粗糙集中差别矩阵的思想,引入不完备决策表的区分对象对集的概念。并给出不完备决策表基于区分对象对集的属性约简定义。同时,也证明了利用该定义得到的不完备决策表的属性约简与基于正区域的属性约简是等价的。相比较基于正区域的不完备决策表属性约简算法,基于区分对象对集的属性约简算法时间复杂度是降低的。最后,用一个实例说明了该算法的合理性。

This paper brings up a definition of discernibility object pair set in incomplete decision table by using the idea of discernibility matrix in rough set.Then the corresponding definition of attribute reduction in incomplete decision table is given.At the same time it is proved that the attribute reduction based on discernibility object pair set is equivalent to the one based on positive region.And the time complexity of attribute reduction algorithm based on it is cut down compared with the attribute reduction of postive region.Finally,an example is used to illustrate the rationality of the new algorithm.