首页 | 本学科首页   官方微博 | 高级检索  
     

基于SVM的空间数据库的层次聚类分析
引用本文:李侃,高春晓,刘玉树. 基于SVM的空间数据库的层次聚类分析[J]. 北京理工大学学报, 2002, 22(4): 485-488. DOI: 10.3969/j.issn.1001-0645.2002.04.022
作者姓名:李侃  高春晓  刘玉树
作者单位:北京理工大学,计算机科学与工程系,北京,100081
摘    要:支持向量机用于两类问题的识别研究.本算法引入了SVM,构造二叉树对多类问题进行层次聚类分析.该算法采用SVM对两类问题进行识别,通过合并逐步由底向上构造二叉树,最终二叉树的数目即为聚类数.它适合任意形状的聚类问题,而且可以确定最优聚类的结果,并适于高维数据的分析.

关 键 词:支持向量机  数据挖掘  空间数据库  聚类  层次算法
文章编号:1001-0645(2002)04-0485-04
收稿时间:2001-10-24
修稿时间:2001-10-24

Support Vector Machine Based Hierarchical Clustering of Spatial Databases
LI Kan,GAO Chun xiao and LIU Yu shu. Support Vector Machine Based Hierarchical Clustering of Spatial Databases[J]. Journal of Beijing Institute of Technology(Natural Science Edition), 2002, 22(4): 485-488. DOI: 10.3969/j.issn.1001-0645.2002.04.022
Authors:LI Kan  GAO Chun xiao  LIU Yu shu
Affiliation:Dept. of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China;Dept. of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China;Dept. of Computer Science and Engineering, Beijing Institute of Technology, Beijing100081, China
Abstract:Support vector machine (SVM) is applied to recognize two separable classes. The algorithm builds up a binary tree to tackle multi class recognition by SVM based hierarchical clustering. SVM is used to recognize two classes and builds up a binary tree in a bottom to up version to analyze the multi class recognition. The number of binary trees is ultimately the number of clustering. It can be applied to clustering problems of arbitrary shapes, achieving the best result, and adapted to fit for the analysis of high dimensional data.
Keywords:support vector machine (SVM)  data mining (DM)  spatial databases (SD)  clustering  hierarchical algorithm  
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《北京理工大学学报》浏览原始摘要信息
点击此处可从《北京理工大学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号