| 一种有效的并行高维聚类算法 |
| |
| 引用本文： | 冯永,吴开贵,熊忠阳,吴中福.一种有效的并行高维聚类算法[J].计算机科学,2005,32(3):216-218. |
| |
| 作者姓名： | 冯永 吴开贵 熊忠阳 吴中福 |
| |
| 作者单位： | 重庆大学计算机学院,重庆,400030 |
| |
| 基金项目： | 重庆市科技计划项目应用基础项目(7968) |
| |
| 摘 要： | 针对CLQUE算法聚类结果精确性不高的缺点,提出利用小波变换来生成自适应网格的方法对CLIQUE算法进行改进,将改进算法并行化以增强聚类维数升高时算法的可伸缩性,并将其应用于药品的销售预测。实验表明本算法聚类结果的精确性高,可伸缩性好,并且有效地降低了计算复杂度。
|
| 关 键 词： | 聚类 CLIQUE算法 小波变换 自适应网格 并行 |
An Efficient Parallel Clustering Algorithm of High Dimension |
| |
| FENG Yong,WU Kai-Gui,XIONG Zhong-Yang,WU Zhong-fu.An Efficient Parallel Clustering Algorithm of High Dimension[J].Computer Science,2005,32(3):216-218. |
| |
| Authors: | FENG Yong WU Kai-Gui XIONG Zhong-Yang WU Zhong-fu |
| |
| Affiliation: | FENG Yong,WU Kai-Gui,XIONG Zhong-Yang,WU Zhong-Fu College of Computer Science,Chongqing University,Chongqing 400030 |
| |
| Abstract: | The classical CLIQUE algorithm is lost to a satisfying accuracy. So, a technique which generates adaptive grid by wavelet transform is put forward to improve it. The scalability of the improved algorithm is enhanced by par- allelization with the clustering dimensions increased. In the last, the algorithm is applied to drug sale estimation. The experimental demonstrate that the improved algorithm is more accurate, more scalable, and more efficient in decrease of computation complexity. |
| |
| Keywords: | Clustering The CLIQUE algorithm Wavelet-transform Adaptive grid Parallel |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
