基于区域最近邻生长的层次聚类算法  

Hierarchical Clustering Algorithm Based on Regional Nearest Neighbor Growth

作　　者：杨栋[1] 詹海亮[2] 苏锦旗[2] 

机构地区：[1]西京学院,西安710123 [2]西北工业大学,西安710072

出　　处：《化工自动化及仪表》2010年第5期9-12,共4页Control and Instruments in Chemical Industry

基　　金：陕西省自然科学基金资助项目(2005F45);陕西省科技攻关计划项目(2005K04-G13)

摘　　要：对于非球形和其它特殊形状的非凸数据集的聚类,基于划分的聚类算法很难取得理想的聚类结果。层次聚类算法根据数据的特征将距离近的数据进行合并,对于球形数据集和其它具有特殊形状的数据集有很好的聚类效果。在分析现有层次聚类算法的基础上,根据层次聚类的合并思想和最近邻距离的计算提出了基于区域最近邻生长的层次聚类算法。For non-spherical shapes and other special non-convex data sets clustering,clustering algorithm based on division of clustering was difficult to achieve the desired results.Hierarchical clustering algorithm based on the data would be characterized by data from the recent merger of data sets for spherical and other data sets with special shapes,and it had a good clustering efficiency.The existing hierarchical clustering algorithm based on the hierarchical clustering of the combined ideas was analyzed and the nearest neighbor distance calculation was presented based on the growth of the region nearest-neighbor hierarchical clustering algorithm.

关 键 词：聚类算法 层次聚类算法 区域最近邻生长 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]