| 最小二乘支持向量机的在线学习算法研究 |
| |
| 引用本文： | 李威,孙海青,宋伟强.最小二乘支持向量机的在线学习算法研究[J].航天控制,2011,29(5). |
| |
| 作者姓名： | 李威 孙海青 宋伟强 |
| |
| 作者单位： | 1. 空军工程大学导弹学院,陕西 三原,713800
2. 95865部队装备部,北京,102218 |
| |
| 摘 要： | 针对最小二乘支持向量机在线逼近过程中求解矩阵维数逐渐扩大的问题,提出了一种最小二乘支持向量机的在线学习算法。借助滚动窗口的思想,建立一个随时间滑动的建模数据区间,在线逼近中通过接受新数据删除旧数据来保持数据区间长度不变,同时数据不断更新,从而实现模型的在线学习。仿真结果表明了这种学习算法的有效性。
|
| 关 键 词： | 最小二乘支持向量机 在线学习 算法 |
Study on the On-line Learning Algorithm for Least Squares Support Vector Machine |
| |
| LI Wei,SUN Haiqing,SONG Weiqiang.Study on the On-line Learning Algorithm for Least Squares Support Vector Machine[J].Aerospace Control,2011,29(5). |
| |
| Authors: | LI Wei SUN Haiqing SONG Weiqiang |
| |
| Institution: | LI Wei1 SUN Haiqing2 SONG Weiqiang2 1.The Missile Institute,Air Force Engineering University,Sanyuan,Shanxi 713800,China 2.Unit 95865 equipment department,Beijing 102218,China |
| |
| Abstract: | An on-line learning algorithm for least squares support vector machine(LS-SVM) is proposed to resolve the problem of matrix dimension expending in the on-line approximation of nonlinear function.Based on the theory of sliding window,a data region which is sliding with time is built.The data region keeps the length invariant and data updating by means of receiving the new data and omitting the old data,and the on-line learning of the model is realized in this way.The simulation result shows the feasibility o... |
| |
| Keywords: | Least squares support vector machine On-line learning Algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
