作　　者： (路娟）; (李德玉）;

机构地区： 山西大学计算机与信息技术学院,太原030006 中北大学理学院,太原030051

出　　处： 《计算机科学》 2017年第9期28-33,共6页

摘　　要： 属性约简是粗糙集理论的重要应用之一,其目的是在保持分类能力不变的前提下去掉冗余的属性,从而简化信息系统。由于经典粗糙集等价关系的要求过于严格,为了更好地解决实际问题,将粗糙集与二型模糊集结合,得到二型模糊粗糙集。利用论域和特征空间的积空间上的两个一型模糊集来构造论域的一个二型模糊划分,将模糊粗糙集属性约简的模型推广到二型模糊粗糙集框架中,得到了一个二型模糊粗糙属性约简的模型,并举例说明了用此模型进行属性约简的方法。 Attribute reduction is an important application of rough set theory,which aims to delete redundant attributes and simplify the information system while maintaining the classifying ability of the system. But traditional rough set theory is based on an equivalent relation,which seems to be a very restrictive condition that may limit the application of the rough set model. To overcome this shortcoming, type-2 fuzzy rough set is obtained by combining rough set with type-2 fuzzy set. Two type^l fuzzy sets, defined on the universe and the product space of feature spaces respectively, are used to construct a type-2 fuzzy partition of the universe and a model for fuzzy rough attribute reduction is expanded to the framework of type-2 fuzzy rough sets,and then a model for type^2 fuzzy rough attribute reduction is obtained. An example is given to show the application of this model.

关 键 词： 二型模糊集 粗糙集 二型模糊粗糙集 表示定理 属性约简