基于粒度的知识粗糙性研究  

On the Roughness of Knowledge Based on Granularity

作　　者：王刚[1] 王浩[1] 

机构地区：[1]合肥工业大学计算机与信息学院

出　　处：《计算机技术与发展》2008年第1期67-69,共3页Computer Technology and Development

基　　金：安徽省高等学校省级自然科学研究基金(KJ2007B382ZC)

摘　　要：粒度计算是粗糙集理论研究的一种强有力的工具。在粗糙集理论中,提出知识是有粒度的并定义了知识粗糙度的概念。众所周知,知识获取是专家系统开发的"瓶颈"问题。文中主要从知识粒度、分辨度以及重要度等方面入手,着重研究了知识粗糙性的粒度原理与知识粗糙性的关系,提出了一种基于属性重要度的粗糙性知识获取算法,并通过理论与实验,证明该算法是正确的,行之有效的。Granular computing is emerging as a powerful tool for rough set theory. The theory of rough - set points out that knowledge has granularity and defines the concept of roughness of knowledge. It＇s well known that the difficulties of system- developing lie in the acquisition of knowledge. From the granularity, recognizability and importance of knowledge, studies the relationship between the roughness of knowledge and its priciple of granularity,puts forward a method of acquiring knowledge based on the importance of attributes,and proves the feasibility of this merthod through theory and experiments.

关 键 词：粗糙集 粒度 分辨度 约简 重要度 规则 

分 类 号：TP182[自动化与计算机技术—控制理论与控制工程]