| 最小方差在聚类分析中的两个使用背景 |
| |
| 引用本文： | 文小琴.最小方差在聚类分析中的两个使用背景[J].佳木斯大学学报,2005,23(1):129-130. |
| |
| 作者姓名： | 文小琴 |
| |
| 作者单位： | 涪陵师范学院数学系,重庆,408003 |
| |
| 摘 要： | 聚类分析是对大型数据进行分类，使得相似性好的数据同类，相似性差的数据异类．划分法是最基本的聚类方法，它以方差作为准则函数，试着找出使得方差最小的k个划分．本文证明了最小方差是点集的递增函数，k的递减函数。
|
| 关 键 词： | 聚类分析 划分法 方差 |
| 文章编号： | 1008-1402(2005)01-0129-02 |
| 修稿时间： | 2004年9月11日 |
TWO BACKGROUNDS OF MINIMUM SQUARED- ERROR IN CLUSTER ANALYSIS |
| |
| WEN Xiao-qin.TWO BACKGROUNDS OF MINIMUM SQUARED- ERROR IN CLUSTER ANALYSIS[J].Journal of Jiamusi University(Natural Science Edition),2005,23(1):129-130. |
| |
| Authors: | WEN Xiao-qin |
| |
| Abstract: | cluster analysis is the process of grouping the data into classes so that objects within a cluster have high similarity in comparison to one another, but are not similar to objects in other clusters. The most commonly used method to group the data is partitioning method. It tries to determine k partitions that minimize the squared-error criterion. This article proved that minimum squared-error is an increasing function of set and decreasing function of k. |
| |
| Keywords: | cluster analysis partitioning method squared-error |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
