基于约束三角剖分的k-means聚类  

k-MEANS CLUSERING BASED ON CONSTRAINED TRIANGULATION

作　　者：王俊杰[1,2] 刘丽[1,2] 

机构地区：[1]山东师范大学信息科学与工程学院,济南250014 [2]山东省分布式计算机软件新技术重点实验室,济南250014

出　　处：《山东师范大学学报（自然科学版）》2013年第4期49-52,共4页Journal of Shandong Normal University(Natural Science)

基　　金：国家自然科学基金资助项目（61170145）;教育部博士点基金项目（20113704110001）;山东省自然科学基金资助项目（ZR2010FM021）;泰山学者基金资助项目.

摘　　要：提出基于约束三角剖分的k-means聚类算法.笔者首先按照约束三角剖分规则对数据点集进行三角网格化,删除大于给定阈值的长边形成k个连通子图,每个连通子图作为一个子类；然后对删除长边的孤立数据点在其邻域内进行局部划分,将其归到最接近的子类中.实验结果表明本文算法无需事先输入聚类数目,可以发现任意非凸形状簇.A new method named k -means clustering algorithm based on constrained triangulation is proposed. Firstly,the set of data points is triangled mesh according to constrained triangulation rule, deleted the long edges greater than the given threshold, forming k connected subgraphs and each connected subgraph is a subclass. The isolated points deleted the long side are clustered in the neighborhood, classified into the closest a subclass. The experimental results show that this algorithm does not need to input the number of clusters in advance, can discover arbitrary non -convex shape clusters.

关 键 词：K-MEANS聚类 约束三角剖分 连通子图 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]