基于模糊集的连续域决策表属性约简算法  

Attribute Reduction Algorithm of Continuous Domain Decision Table Based on Fuzzy Set

作　　者：周瑞琼[1] 朱颢东[2] 吴洪丽[1,2] 

机构地区：[1]海南师范大学信息科学技术学院,海口571158 [2]中国科学院成都计算机应用研究所,成都610041

出　　处：《计算机工程》2010年第23期44-46,共3页Computer Engineering

基　　金：海南省自然科学基金资助项目(807050)

摘　　要：把模糊集和粗糙集结合起来,对连续域决策表属性约简算法进行研究。使用三角隶属度函数将连续属性值转化为模糊值。定义两模糊对象间的相似度、模糊对象的相似类以及连续属性在对象集上划分所形成的相似类集组成的特征向量。给出连续型属性的数字特征向量,以此为基础建立连续型属性间的相似矩阵。提出一个新的属性约简算法,并用一个实例加以验证。Combining fuzzy set with rough set,attribute reduction algorithm of continuous domain decision table is studied.Continuous attribute values are transformed into fuzzy values with triangular membership function.Similarity degree of two fuzzy objects and similarity class of each fuzzy object are defined.Characteristic vector of continuous attribute which is made up of similarity class of each fuzzy object is provided.Digital characteristic vector of continuous attribute is presented and similar matrix of continuous attributes is proposed.A new attribute reduction algorithm is provided.Also,the algorithm is verified through an illustrative example.

关 键 词：模糊集 粗糙集 三角隶属度函数 相似矩阵 属性约简 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]