基于概念格同构下的属性约简及其算法研究  

ON ATTRIBUTE REDUCTION AND ITS ALGORITHM BASED ON CONCEPT LATTICE ISOMORPHISM

作　　者：刘建明[1,2] 刘保相[1] 

机构地区：[1]河北联合大学理学院,河北唐山063000 [2]唐山师范学院数学与信息科学系,河北唐山063000

出　　处：《计算机应用与软件》2014年第5期34-36,140,共4页Computer Applications and Software

基　　金：河北省自然科学基金项目(A2011209046;A2011209030);河北省高等学校科学技术研究指导项目(Z2012046)

摘　　要：通过研究概念格和同构理论,发现不同的概念格之间存在同构关系,并引入算子E=A-D和G=E-D**,给出一系列概念格同构的判定定理。基于概念格同构这一理论,对形式背景的属性约简及最小属性约简集的算法进行初步研究,为应用概念格进行数据挖掘提供新的理论依据。Through the study of concept lattice and isomorphism theory,we find that between different concept lattices there are the isomorphic relationships,and introduce the operator E = A- D and G = E- D＊＊,present a series of discriminant theorem of concept lattice isomorphism; Based on this concept lattice isomorphism theory,we make initial study on the attribute reduction and the minimal attribute reduction set algorithm of formal context,which provide a new theoretical basis for applying the concept lattice to data mining.

关 键 词：概念格同构 形式背景 属性约简 最小属性约简集 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]