信息系统中知识的距离及基于知识距离的属性约简算法

Knowledge Distance in Information Systems and Attribute Reduction Algorithm Based on It

从粒度计算的观点出发,给出了信息系统中知识距离的定义,指出利用知识距离可以度量信息系统中知识的粗糙性,分析了其相关性质.提出了一种基于知识距离的启发式属性约简算法,算法不需求核,对无核的特殊信息系统计算约简更加有效.

Referring the concept of the symmetric difference of sets, from the viewpoint of the granular computing, knowledge distance in information systems is defined in the paper, and its properties are studied too. Moreover, the knowledge distance is used to measure the roughness of knowledge. An attribute reduction algorithm based on knowledge distance is proposed, and it is especially effective to information system without core.