| 一种适合于大数据集处理的混合EM算法 |
| |
| 引用本文： | 张德喜,黄浩.一种适合于大数据集处理的混合EM算法[J].计算机应用,2006,26(8):1884-1887. |
| |
| 作者姓名： | 张德喜 黄浩 |
| |
| 作者单位： | 1. 许昌学院,计算机科学与技术学院,河南,许昌,461000
2. 北京理工大学,计算机科学技术学院,北京,100029 |
| |
| 基金项目： | 中国科学院资助项目;国家自然科学基金;河南省高校青年骨干教师资助项目 |
| |
| 摘 要： | EM算法的计算强度较大，且当数据集较大时，计算效率较低。为此，提出了基于部分E步的混合EM算法，降低了算法的计算强度，提高了算法对数据集大小的适应能力，并且保持了EM算法的收敛特性。最后通过将算法应用于大的数据集，验证了该算法能减少计算强度。
|
| 关 键 词： | EM算法 增量EM算法 懒惰EM算法 混合EM算法 |
| 文章编号： | 1001-9081（2006）08-1884-04 |
| 收稿时间： | 2006-01-19 |
| 修稿时间： | 2006-01-192006-04-06 |
Mixed EM algorithm for large data sets |
| |
| ZHANG De-xi,HUANG Hao.Mixed EM algorithm for large data sets[J].journal of Computer Applications,2006,26(8):1884-1887. |
| |
| Authors: | ZHANG De-xi HUANG Hao |
| |
| Affiliation: | 1. College of Computer Science and Technology, Xuchang University, Xuchang Henan 461000, China; 2. School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100029, China |
| |
| Abstract: | EM algorithm often needs great computational costs. And its computing is inefficient when the data sets are large. A mixed EM algorithm based on partial E-steps method was presented which can reduce the intensity of computation, make it adapted to the scale of data sets better and have the standard convergence guarantee of EM. It is verified that the mixed EM algorithm can reduce computational costs evidently through its application to large data sets. |
| |
| Keywords: | EM algorithm incremental EM algorithm lazy EM algorithm mixed EM 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《计算机应用》浏览原始摘要信息 |
|
点击此处可从《计算机应用》下载全文 |
