PAC:一种结合了分割和凝聚技术的聚类方法  

PAC:A New Clustering Method Combining Partitional and Agglomerative Techniques

作　　者：陈继明[1] 周源远[1] 宋顺林[1] 

机构地区：[1]江苏大学计算机科学与通信工程学院,镇江212013

出　　处：《计算机工程》2005年第17期12-14,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60273040)

摘　　要：文档的自动聚类技术被普遍认为是一种行之有效的网上信息资源管理方法。目前主要存在两种类型的聚类方法:分割型和凝聚型,它们在计算复杂度和聚类效果上各有千秋。该文提出了一种结合了这两种聚类技术的聚类法:PAC。实验结果表明,PAC具有较低的计算复杂度,且聚类结果优于传统的分割型和凝聚型方法。The automatic clustering of documents has been widely regarded as an effective method for managing the internet information and resources. Now there are two kinds of clustering techniques： partitional and agglomerative. Each one has its advantages on the computational complexity and clustering efficiency. This paper presents a new clustering method PAC combining partitional and agglomerative techniques. Experiments show that the new PAC method gets a superior performance over traditional methods both in computational complexity and in clustering efficiency.

关 键 词：聚类 分割 凝聚 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]