基于粗集和模糊集的启发式规则约简算法研究  

Study of a Heuristic Rule Reduction Algorithm Based on Rough Set and Fuzzy Set

作　　者：赵惠文[1] 朱根标[1] 张凤鸣[1] 

机构地区：[1]空军工程大学工程学院

出　　处：《空军工程大学学报（自然科学版）》2005年第5期88-90,94,共4页Journal of Air Force Engineering University(Natural Science Edition)

摘　　要：提出了一种新型的决策规则约简方法。基于均匀划分和正态分布隶属度函数,对决策表的连续属性进行模糊化,用欧氏距离贴近度来构建相似矩阵,并提出了一种论域的模糊划分算法;依据粗糙集隶属度进行属性约简的基础上,给出了一种决策规则约简算法,从而达到发掘知识并简化知识的目的。A method of reduction of decision rulers is proposed based on rough set and fuzzy set. The continuous attributes in the decision table are justified using the proper fuzzy membership functions and division method. The fuzzy similar matrix of the attributes is constructed by means of the fuzzy degree of nearness and the indiscernibility relation in classical rough set is generalized to the fuzzy similarity relation. And a decision rule reduction algorithm is presented based on fuzzy -rough set model.

关 键 词：模糊集 粗糙集 模糊相似关系 属性约简 规则约简 

分 类 号：O159[理学—数学]