基于属性分布相似度的超图高维聚类算法研究  

A New Clustering Method in High-Dimension Based on SAD Hypergraph Models

作　　者：陈建斌[1,2] 宋翰涛[1] 

机构地区：[1]北京理工大学,北京100081 [2]华北工学院

出　　处：《计算机工程与应用》2004年第34期195-198,共4页Computer Engineering and Applications

摘　　要：在许多聚类应用中,数据对象是具有高维、稀疏、二元的特征。传统聚类算法无法有效地处理此类数据。该文提出一种基于超图模型的高维聚类算法,通过定义对象属性分布特征向量和对象间属性分布相似度,建立超图模型,并应用超图分割法进行聚类。聚类结果通过簇内奇异特征值进行评价。实验结果和算法分析表明,该算法可以有效地进行聚类知识挖掘。The data sets have features such as high-dimensional,sparseness and binary value in many clustering applications.Most of the traditional algorithms fail to produce meaningful clusters in such data sets.In this paper,we propose a new method for clustering data in a high dimensional space based on a hypergraph model.The hypergraph model maps the relationship present in the original data in high dimensional space into a hypergraph.A hyperedge represents the similarity of attribute value distribution between two points.A hypergraph partitioning algorithm is used to find a partitioning of the vertices such that the corresponding data items in each partition are highly related and the weight of the hyperedges cut by the partitioning is minimized.The quality of the clustering result can be evaluated applying the intra-cluster singularity value.Our analysis demonstrates that this approach is applicable and effective in wide ranging scheme.

关 键 词：高维聚类 超图模型 数据挖掘 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]