不完备区间值信息系统的粗糙集约简算法  

Attribute reduction algorithm based on rough set in incomplete interval-valued information system

作　　者：曾玲[1] 何普彦[1] 付敏[1] 

机构地区：[1]桂林电子科技大学数学与计算科学学院,广西桂林541004

出　　处：《南京理工大学学报》2013年第4期524-529,共6页Journal of Nanjing University of Science and Technology

基　　金：国家自然科学基金(61163041)

摘　　要：探讨不完备区间值信息系统的属性约简问题。定义了一种相似联系度容差关系,基于此关系建立了拓展粗糙集模型。然后通过定义双参数分配约简和同异反可辨识矩阵,给出了基于同异反可辨识矩阵的双参数分配约简算法。所建模型可根据不同的用户需求和数据集的分布特点对参数进行动态调整,更符合实际。最后给出了数值例子,并分析了不同参数值对约简结果的影响。This paper discusses the attribute reduction in incomplete interval-valued information system.A tolerance relation based on similarity connection degree is defined and the extension of a rough set model based on this relation is proposed.By defining the two-parameter assignment reduction and identical-discrepancy-contrary discernibility matrix,a two-parameter assignment reduction algorithm based on the identical-discrepancy-contrary discernibility matrix is proposed.According to the requirements of different users and the distribution characteristics of the data set,the parameters can be dynamically adjusted to be more realistic.A numerical example is given and the effect of different parameters for reduction is investigated.

关 键 词：粗糙集 不完备区间值信息系统 相似联系度容差关系 双参数分配约简 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]