基于云变换和特性关系下粗糙集的决策树构造  

Decision Tree Construction Based on Cloud Transform and Rough Set Theory under Characteristic Relation

作　　者：宋晶[1] 戚建淮[1] 

机构地区：[1]西南交通大学信息化研究院,四川成都610031

出　　处：《西南交通大学学报》2010年第2期312-316,共5页Journal of Southwest Jiaotong University

摘　　要：为了从不完备信息系统中挖掘分类知识,提出了一种基于云变换和特性关系下粗糙集的决策树构造算法(DTCCRSCR).其核心思想是,利用云变换离散化连续型数据,选择特性关系下加权平均粗糙度最小的属性作为当前的分裂节点.实验表明,由DTCCRSCR构造的决策树不仅结构简单,分类准确率较高,而且分类规则也容易理解.A new algorithm,DTCCRSCR（decision tree construction based on cloud transform and rough set theory under characteristic relation）,was proposed for mining classification knowledge from incomplete information systems.It utilizes cloud transform to discretize continuous data,and then the attribute with the smallest weighted mean roughness under the characteristic relation is selected as the current splitting node.Experimental results show that decision trees constructed by the DTCCRSCR have a simpler structure,a higher classification accuracy and more understandable rules than those based on the C5.0 algorithm.

关 键 词：云变换 粗糙集 决策树 加权平均粗糙度 特性关系 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]