一种基于粗集的决策表属性值约简改进算法  

An improved algorithm for value reduction of attributes in decision tables based on rough set theory

作　　者：史君华[1] 胡学钢[2] 

机构地区：[1]合肥师范学院计算机科学与技术系,安徽合肥230061 [2]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2008年第1期36-39,共4页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(050420207)

摘　　要：属性约简和值约简是粗糙集理论中的重要内容。文章提出一种适用于决策表的属性值约简改进算法AVRIMC,对分辨矩阵中的每一行,直接利用吸收率和求得的值核信息,优化该行后续元素的构造;最后用UCI数据集进行实验,并与文献中算法相比较,结果表明本算法在保持正确性的基础上,时间性能有一定程度的改进。Attribute reduction and value reduction are two main contents in rough set theory. An improved value reduction algorithm suitable for decision tables, AVRIMC,is presented in this paper. For every row in the discernibility matrix, it utilizes the absorptivity and value core properties as optimization conditions to construct the latter items of this row. Experiment results show that this method is superior to the algorithm in related literature in time consumption.

关 键 词：数据挖掘 粗糙集合 决策表 分辨矩阵 值约简 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]