基于邻域样本稳定性的三支聚类方法  

Three-way Clustering Based on Neighborhood Sample’s Stability

作　　者：李洪梅[1] 姜冬勤 王平心 LI Hongmei;JIANG Dongqin;WANG Pingxin(School of Computer,Jiangsu University of Science and Technology,Zhenjiang 212003,China;School of Science,Jiangsu University of Science and Technology,Zhenjiang 212003,China)

机构地区：[1]江苏科技大学计算机学院,江苏镇江212003 [2]江苏科技大学理学院,江苏镇江212003

出　　处：《山西大学学报（自然科学版）》2020年第4期874-879,共6页Journal of Shanxi University(Natural Science Edition)

基　　金：国家自然科学基金(61503160,61572242);江苏省高校自然科学基金(15KJB110004)。

摘　　要：文章将样本稳定性和三支聚类结合,给出了一种基于邻域样本稳定性的三支聚类算法。首先使用任意两个样本的邻域中的公共元素个数定义两个样本的共现概率,并在此基础上定义每个样本的稳定性,然后基于阈值将这些样本元素分为稳定样本集和不稳定样本集。对稳定集中的样本,采用传统方法挖掘其类簇结构。对于不稳定集中的样本,通过比较样本到稳定集中聚类中心的距离将它们分到相应类的边界域中。通过以上策略可以得到三支聚类的核心域和边界域。在UCI数据集上的实验结果显示,该方法能够更好地显示出聚类的结构。A three-way clustering algorithm is proposed by integrating sample’s stability into the idea of three-way clustering.In the proposed algorithm,the number of common samples in two sample’s neighborhood are used to define the frequencies of two samples and the sample’s stability is calculated based on the defined frequencies.The universe are divided into stable set and unstable set based on sample’s stability.The samples in the stable set are assigned into the core region of each cluster by using traditional clustering algorithm.The samples in the unstable set are assigned into the fringe region of corresponding cluster according to distances between the elements and the centers of the cluster core region.Therefore,a three-way clustering is naturally formed.The experimental results on UCI datasets show that this method can improve the structure of the clustering results.

关 键 词：邻域 样本稳定性 二支聚类 三支聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]