基于近似属性约简的信息表浓缩和规则提取  

Data enrichment and rule extraction based on approximate attribute reduction in the context of rough sets

作　　者：叶东毅[1] 

机构地区：[1]福州大学信息学院计算机系,福建福州350002

出　　处：《福建工程学院学报》2003年第1期15-17,共3页Journal of Fujian University of Technology

基　　金：教育部重点科研项目 ( 0 0 185 JA0 0 144 )

摘　　要：首先介绍粗糙集属性约简的概念并指出属性约简算法的优缺点 ,在此基础上 ,提出了 ε - 近似属性约简的概念和相应的计算方法 ,它可以比单纯的属性约简更有效地对冗余信息表进行浓缩并获得简洁的近似决策规则 ,并以一个具体的实例对此进行了分析和比较。In this paper, the concept of attribute reduction and its functionality in the theory of rough sets is analyzed first. Then a concept of ε-approximate attribute reduction is introduced and an algorithm for findingan ε-approximate reduct is presented. It turns out that using the ε-approximate attribute reduction instead of the traditional attribute reduction may help to enhance the efficiency of data enrichment and at the same time to extract simpler and more concise approximate decision rules from a given information table. At the end of the paper, a practical example is given to show the advantages of the ε-approximate attribute reduction.

关 键 词：粗糙集 近似属性约简 信息表 数据浓缩 规则提取 近似决策规则 数据挖掘 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论] TP18[自动化与计算机技术—计算机科学与技术]