| 一种改进的在线最小二乘支持向量机回归算法 |
| |
| 引用本文： | 郭振凯,宋召青,毛剑琴. 一种改进的在线最小二乘支持向量机回归算法[J]. 控制与决策, 2009, 24(1): 145-148 |
| |
| 作者姓名： | 郭振凯 宋召青 毛剑琴 |
| |
| 作者单位： | 北京航空航天大学第七研究室,北京,100083;海军航空工程学院控制工程系,山东烟台,264001 |
| |
| 基金项目： | 国家自然科学基金，国家重点基础研究发展计划(973计划)，教育部高等学校博士学科点专项科研基金，北京市重点学科建设项目 |
| |
| 摘 要： | 针对一般最小二乘支持向量机处理大规模数据集会出现训练速度幔、计算量大、不易在线训练的缺点,将修正后的遗忘因子矩形窗方法与支持向量机相结合,提出一种基于改进的遗忘因子矩形窗算法的在线最小二乘支持向量机回归算法,既突出了当前窗口数据的作用,又考虑了历史数据的影响.所提出的算法可减少计算量,提高在线辨识精度.仿真算例表明了该方法的有效性.
|
| 关 键 词： | 最小二乘支持向量机回归 改进的遗忘因子矩形窗 在线学习 |
An improved online least squares support vector machines regression algorithm |
| |
| GUO Zhen-hai,SONG Zhao-qing,MAO Jian-qin. An improved online least squares support vector machines regression algorithm[J]. Control and Decision, 2009, 24(1): 145-148 |
| |
| Authors: | GUO Zhen-hai SONG Zhao-qing MAO Jian-qin |
| |
| Affiliation: | 1.The Seventh Research Division;Beijing University of Aeronautic and Astronautics;Beijing 100083;China;2.Department of Control Engineering;Naval Aeronautical and Astronautical University;Yantai 264001;China. |
| |
| Abstract: | Aiming at the problem that the large-scale samples training process is slow and large computation,and difficult to train online for the standard least squares support vector machines,a learning algorithm of online least squares support vector machines regression(OLS-SVMR) based on improved rectangular window with forgetting factor(IRWFF) method is proposed by combining the modified rectangular window with forgetting factor algorithm with support vector machines.The present and past window data are considere... |
| |
| Keywords: | Least squares support vector machines regression IRWFF Online learning |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
