| 一种新的混合聚类分析算法* |
| |
| 引用本文： | 何登旭,曲良东.一种新的混合聚类分析算法*[J].计算机应用研究,2009,26(3):879-880. |
| |
| 作者姓名： | 何登旭 曲良东 |
| |
| 作者单位： | 广西民族大学,数学与计算机科学学院,南宁,530006 |
| |
| 基金项目： | 国家民委科学基金资助项目(05GX06); 广西自然科学基金资助项目(桂科自0728054) |
| |
| 摘 要： | 结合人工鱼群算法的全局寻优优点提出了一种基于人工鱼群算法的K-平均混合聚类分析算法。实验结果表明，该算法能克服K-平均聚类算法易陷入局部极小的不足，有较好的全局性，且聚类正确率明显高于K-平均算法，聚类效果更好。
|
| 关 键 词： | 人工鱼群算法 K-平均 全局优化 |
Novel hybrid algorithm for clustering analysis |
| |
| HE Deng-xu,QU Liang-dong.Novel hybrid algorithm for clustering analysis[J].Application Research of Computers,2009,26(3):879-880. |
| |
| Authors: | HE Deng-xu QU Liang-dong |
| |
| Affiliation: | (College of Mathematics & Computer Science, Guangxi University for Nationalities, Nanning 530006, China) |
| |
| Abstract: | This paper proposed a novel hybrid algorithm for clustering analysis based on artificial fish-school algorithm and K-means. The experimental results show that the algorithm can overcome K-means clustering algorithm easily into the local minimum, have a better global optimization.The cluster accuracy is higher than K-means clustering algorithm obviously, and the cluster effect is better. |
| |
| Keywords: | artificial fish-school algorithm K-means global optimization |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机应用研究》浏览原始摘要信息 |
|
点击此处可从《计算机应用研究》下载全文 |
