基于模糊粗糙集的粒度计算

Granular Computation Based on Fuzzy Rough Sets

粒度计算是一种新的智能计算的理论和方法,目前受到很多学者的关注。但是,具体可行的粒表示模型和不同粒的推理方法研究相对较少。本文将模糊粗糙集纳入粒度计算这种新的理论框架,对于处理复杂信息系统,求解复杂问题无疑具有重要的意义。首先利用笛卡尔积,构建了模糊关系下的信息粒;然后给出不同粒度下模糊粗糙算子的表示方法,进而形成一个分层递阶结构;最后考虑了对于模糊信息系统粒度粗细的选择问题,并给出一个实例,从而为粒度计算提供一个具体而实用的框架。

Granular computing emerges as a new theory of intelligence computing and has received much attention at present. However, there are few researches on feasible granule representation models and reasoning methods in different granular levels. Undoubtedly,it is significant to put fuzzy rough set in the framework of granular computing for processing complex information system and solving complex problems. At first, cartesian product provided us with a method for constructing information granularity in fuzzy relation. Then the paper presented fuzzy rough operator that in different granularities. Moreover, a hierarchy model was formed. Finally, the problem of how to choose the coarser degree of granularity in fuzzy information system was also taken into account,and an example put forward maked it clear that the whole process of constructing granularity. The research we have done suggests that a concrete and useful framework for granular computing is provided.