基于差别矩阵的高效属性约简算法  

A Efficient Algorithm for Attribute Reduction Based on Discernibility Matrix

作　　者：张娟[1] 蒋瑜[2] 聂华北[1] 李永礼[3] 

机构地区：[1]东莞理工学院城市学院计算机与信息科学系,东莞523106 [2]成都信息工程学院软件工程学院,成都610225 [3]兰州大学信息科学与工程学院,兰州741000

出　　处：《武汉理工大学学报》2010年第23期145-149,共5页Journal of Wuhan University of Technology

摘　　要：针对现有粗糙集属性约简算法的不足,提出了一种基于差别矩阵的属性约简新算法。算法的构造借助于差别矩阵,结合集合运算,采用迭代的思想,利用完备优化算子,最后得到决策表的一个完备约简,有效地降低了约简算法的时间复杂度。仿真实验结果显示,其产生的约简与现有算法产生的最优约简一致,进一步表明了新算法的高效性与完备性。With regard to the defect of algorithms for reduction in rough set theory,a new efficient algorithm for attribute reduction based on discernibility matrix is introduced.The algorithm is constructed using the difference matrix,combined with the operation of the sets and applied iterative methods,then further to use the complete optimization operator to get a complete decision table reduction.It effectively reduces the reduction algorithm of time complexity.Experimental result indicates the reduction got by new algorithm is the same to the approach of other algorithms,this conclusion illuminates the new algorithm is efficient and complete.

关 键 词：粗糙集 差别矩阵 属性约简 完备算法 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]