基于简化差别矩阵的增量式属性约简  

Incremental Attribute Reduction Based on Simplified Discernibility Matrix

作　　者：葛浩[1,2] 李龙澍[1,3] 杨传健[4] 

机构地区：[1]安徽大学计算智能与信号处理教育部重点实验室,安徽合肥230039 [2]滁州学院机械与电子工程学院,安徽滁州239012 [3]安徽大学计算机科学与技术学院,安徽合肥230039 [4]滁州学院计算机与信息工程学院,安徽滁州239012

出　　处：《四川大学学报（工程科学版）》2013年第1期116-124,共9页Journal of Sichuan University (Engineering Science Edition)

基　　金：安徽省自然科学基金资助项目(090412054);安徽高校省级自然科学研究项目(KJ2012A212);安徽省高等学校省级优秀青年人才基金资助项目(2011SQRL123);滁州学院科学研究项目(2011KJ003Z)

摘　　要：新对象添加到决策表后,已有的属性约简将会发生改变,需要对其动态更新。为此,首先给出简化决策表和简化差别矩阵的定义,并证明了基于简化差别矩阵的属性约简与正区域的属性约简是等价的;然后,分析增量对象的不同情况,将增量属性约简映射到简化决策表上来实现,由此设计基于简化差别矩阵的增量式属性约简算法,并对算法进行改进;最后,利用实例和实验验证了所提出算法的正确性和高效性。In order to update the attribute reduction of decision table dynamically, the definitions of the simplified decision table and attribute reduction based on simplified discernibility matrix were proposed. It was proved that attribute reduction acquired from the definition is equivalence to attribute reduction based on positive region. Then the different cases of added object were analyzed, and incremental attribute reduction was mapped to the simplifying decision table to achieve. Finally, the attribute reduction algorithm based on simplified discernibility matrix was designed and the algorithm was further improved. The example and experiment results showed that the algorithms are effective and effieient.

关 键 词：粗糙集 属性约简 差别集 差别矩阵 增量式算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]