一种基于超图模式的高维空间数据聚类方法  

A METHOD FOR CLUSTERING DATA IN HIGH DIMENSIONAL SPACE BASED ON HYPERGRAPH MODEL

作　　者：张蓉[1] 彭宏[2] 

机构地区：[1]广东商学院信息系,广州510320 [2]华南理工大学计算机系,广州510640

出　　处：《模式识别与人工智能》2002年第2期223-227,共5页Pattern Recognition and Artificial Intelligence

基　　金：广东省科委基金(No.2000-J-006-01)

摘　　要：本文把一个求解高维空间数据聚类问题转换为一个超图分割寻优问题,提出一种基于超图模式的高维空间数据聚类方法.该方法不需要减少高维空间数据项的维数,直接用超图模式描述原始数据之间的关系,并能通过选择适当的支持度阈值,有效去除噪声点,保证数据聚类的质量.In this paper, the problem of solving the data clustering in high dimensional space is formulated as a hypergraph optimal partition problem, and a method is proposed for clustering data in high dimensional space based on hypergraph model. It does not require dimensionality reduction, and it uses the hypergraph model to represent relations among the original data items. By finding an appropriate support threshold, noise data can be filtered out from the clusters very effectively and the quality of the cluseters can be controled.

关 键 词：超图模式 高维空间 数据聚类 关联规则 模拟退火算法 数据挖掘 数据库 

分 类 号：TP311.13[自动化与计算机技术—计算机软件与理论]