摘要
粗糙集方法是一种有效的处理分类问题的方法,但是它在面对高维数据时,很难依靠属性约简提取出泛化能力较高的规则。这是由于粗糙集约简本身在一定程度上忽略了对象个体对信息系统的影响。为避免此问题,通过描述各个对象与其补集间的差别,提取了各个对象所包含的分类信息。在此基础上,设计了一种新的基于粗糙集的规则提取算法。通过实验分析,验证了本算法比传统算法具有更好的泛化能力。
Rough set method is an effective method of classification,but with high-dimensional data,it is difficult to rely on reduction to extract the rules which have high generalization capability,because the reduction of rough set itself fails to notice the effect of the object on the information system to a certain degree.This paper describes the differences between different objects and extracts the classified information of every object.Then a new rules extraction method is designed based on rough set.And the algorithm is proved to have better generalization capability than the traditional one.
出处
《广西师范大学学报（自然科学版）》
CAS
北大核心
2011年第3期94-100,共7页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金资助项目(71031006
60970014)
关键词
粗糙集
属性约简
决策表
等价类
等价描述矩阵
rough set
attribute reduction
decision datasets
equivalence class
equivalence describe matrix
