一种多阈值邻域粗糙集的属性约简算法  

An Attribute Reduct Algorithm for Multi-threshold Neighborhood Rough Set

作　　者：娄畅[1] 刘遵仁[1] 郭功振 

机构地区：[1]青岛大学信息工程学院,青岛266071

出　　处：《青岛大学学报（自然科学版）》2014年第4期44-48,共5页Journal of Qingdao University(Natural Science Edition)

摘　　要：δ-邻域计算是邻域粗糙集模型中操作最为频繁和复杂的。针对邻域计算,提出了利用多阈值替代单一阈值,并根据样本空间的分布,提出块集概念,证明了每个样本的邻域只存在于与之相邻的块集中。在此基础上,提出基于块集的多阈值邻域粗糙集的属性约简算法,降低了计算邻域的时间复杂性,并利用多个UCI标准数据集对该算法进行验证,结果表明,该算法行之有效。It is a frequent and complex operation to calculate the g-neighborhood elements of each record in neighborhood rough set model. Aiming at the Neighborhood calculation problem, the concept of multiple thresholds to displace the traditional uniform threshold approach is proposed. The concept of Block Sets is also proposed according to the distribution of sample records in the space, which proves the Block-Setneighborhood theory. The Block-Set-neighborhood theory shows that 3-neighborhood elements of a record are contained only by its own block set and adjacent block sets. Based on the concepts, an attribute reduct algorithm for multi-threshold neighborhood rough set is proposed. Then the algorithm is proved to be an efficient way to reduce the time complexity to calculate the 8-neighborhood elements of each record by the test results of several data sets from UCI.

关 键 词：粗糙集 邻域 多阈值 属性约简 块集 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]