| 基于改进微粒群算法的K-MEANS聚类和孤立点查找 |
| |
| 引用本文： | 肖会敏,刘臣,杨晓兵. 基于改进微粒群算法的K-MEANS聚类和孤立点查找[J]. 河南科学, 2007, 25(1): 107-111 |
| |
| 作者姓名： | 肖会敏 刘臣 杨晓兵 |
| |
| 作者单位： | 河南财经学院,信息学院,郑州,450002;河南财经学院,信息学院,郑州,450002;河南财经学院,信息学院,郑州,450002 |
| |
| 摘 要： | K均值算法的聚类个数K需指定,聚类结果与数据输入顺序相关,而且易受孤立点影响.针对这些缺陷,首先以实验的方式证明了找到最优的初始质心是K-MEANS算法有效的条件,对局部版的微粒群优化算法(PSO)进行了改进,利用其局部搜索的功能查找到K均值算法的最优初始质心和存在的孤立点,克服了K均值算法的这些缺陷。
|
| 关 键 词： | 微粒群算法 K均值算法 聚类 孤立点查找 |
| 文章编号： | 1004-3918（2007）01-0107-05 |
| 修稿时间： | 2006-08-03 |
K-Means Clustering and Outlier Detection Based on PSO |
| |
| XIAO Hui-min,LIU Chen,YANG Xiao-bing. K-Means Clustering and Outlier Detection Based on PSO[J]. Henan Science, 2007, 25(1): 107-111 |
| |
| Authors: | XIAO Hui-min LIU Chen YANG Xiao-bing |
| |
| Affiliation: | School of Information, Henan University of Finance and Economics, Zhengzhou 450002, China |
| |
| Abstract: | K-means algorithm has some deficiencies.The number K must be pointed and its effectiveness liable to be effected by isolated data and the input sequence of data.To solve these deficiencies,data experiments were done to find the precondition of K-means effectiveness,which is finding the best initial core.Then a new algorithm that base on PSO is composed to find the initial core and the outlier.Through these,the disadvantages of K-means were solved. |
| |
| Keywords: | PSO K-means clustering outlier detection |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
