Rough Set规则自动生成的关键算法改进  

The Improvement of Key Algorithms for Automatic Rule Generation in Rough Set Theory

作　　者：赵荣泳[1] 张浩[2] 李翠玲[3] 樊留群[1] 王骏[4] 

机构地区：[1]同济大学CIMS研究中心,上海200092 [2]上海电力学院,上海200090 [3]上海海事大学电气系,上海200135 [4]上海大众汽车有限公司,上海201805

出　　处：《计算机工程与应用》2005年第13期32-35,共4页Computer Engineering and Applications

基　　金：中德政府合作项目(编号:20002DFG00027)支持

摘　　要：基于RoughSet理论,研究从Skrowon分辨矩阵到规则自动生成过程中的关键算法的改进问题。提出由分辨矩阵到合取项矩阵的计算方法,建立了从属性约简的合取项矩阵到析取项矩阵转换的数学模型,基于数学模型,提出直接搜索的转换方法。同时,提出了属性值约简的改进方法,使得改进后的算法从总体上节省了运算空间,降低了算法的时间复杂性,提高了规则生成的效率。最后通过UCI数据库的实例验证了改进算法的有效性。The automatic rule generation algorithms from Skrowon discernibility matrix are studied and improved respectively based on Rough Set Theory.The tansformation method form discernibility matrix to conjunction matrix is presented.And the mathimetic model of the transformation from conjunction matrix to disjunction matrix is esteblished for the attribute reduct.Based on the model,direct search method is presented.Also,the attribute value reduction algorithm is impoved.By this means,the whole rule ganeration can save the computing space and CPU occupation time,enhance the efficiency of decision rules generation.Finally,by the factual process for UCI database,the validity of two improved algorithms are proved.

关 键 词：粗糙集 属性约简 析取范式 模型 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]