摘要
聚类指的是把数据库里的对象分组成有意义的子集,使得一个聚类内的成员尽可能相似,而不同聚类间的成员差异尽可能大。空闻对象的主要特性受其邻接对象的影响,并且随着距离的增加或减少,影响作用也相应地增加或减少。论文针对相邻空间对象的特性总是相似或相关联的特点,以邻接关系为基础对空间聚类算法进行了分析与研究。
Clustering is the task of grouping the objects of a database into meaningful subclasses (that is,clusters)so that the members of a cluster are as similar as possible whereas the members of different clustering differ as much as possible from each other.Spatial objects are often influenced by their neighbors.And the influence typically decreases or increases more or less continuously with increasing or decreasing distance.Due to the attributes of the neighbors are always similar or associated to each other,spatial trend detection based on spatial neighborhood relations is analyzed to extract useful knowledge in this paper.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第34期184-186,共3页
Computer Engineering and Applications
基金
国家十五重大科技计划项目(编号:2002BA107B)
建设部科技攻关项目建科001-4-70
重庆大学基础及应用基础研究支持项目
关键词
空间聚类分析
空间邻接关系
空间邻接图
邻接路径
spatial trend detection,spatial neighborhood relations,Spatial Neighborhood Graphs,neighborhood paths
