一种高效的增量式属性约简算法  

Effective increment algorithm for attribute reduction

作　　者：冯少荣[1] 张东站[1] 

机构地区：[1]厦门大学计算机科学系,福建厦门361005

出　　处：《控制与决策》2011年第4期495-500,共6页Control and Decision

基　　金：国家自然科学基金项目(50604012)

摘　　要：针对粗糙集中求属性核和属性约简存在的问题,首先给出了改进的差别矩阵定义,进而提出一种基于改进差别矩阵的核增量式更新算法,用于解决对象动态增加情况下核的更新问题;同时,为了降低现有增量式属性约简算法的时间、空间复杂度,提出一种不存储差别矩阵的高效属性约简算法,用于处理对象动态增加情况下属性约简的更新问题.理论分析及实验结果均表明了所提出算法的有效性和可行性.Aiming at some shortcomings of existing on computing attribute core and attribute reduction in rough sets,an improved discernibility matrix definition is introduced.By using this foundation,based on improved discernibility matrix,an incremental updating algorithm for computing core is proposed,which is mainly used to solve core updating when objects are dynamically increased and deleted.In order to decrease time and space complexity on the existence incremental attribute reduction algorithm,an effective algorithm for attribute reduction is proposed,which does not storage discernibility matrix.This algorithm is mainly used to process attribute reduction updating when objects are dynamically increased.Theoretical analysis and experimental results show the feasibility and effectiveness of the proposed algorithm.

关 键 词：粗糙集 增量 属性约简 差别矩阵 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]