计算机工程与应用 ›› 2010, Vol. 46 ›› Issue (9): 215-216.DOI: 10.3778/j.issn.1002-8331.2010.09.061

• 工程与应用 • 上一篇    下一篇

在线模糊最小二乘支持向量机的时间序列预测

王晓兰1,2,康 蕾1   

  1. 1.兰州理工大学 电气工程与信息工程学院,兰州 730050
    2.兰州理工大学 甘肃省有色金属新材料省部共建国家重点实验室,兰州 730050
  • 收稿日期:2008-09-19 修回日期:2008-12-01 出版日期:2010-03-21 发布日期:2010-03-21
  • 通讯作者: 王晓兰

Time series prediction based on online fuzzy least square support vector machine

WANG Xiao-lan1,2,KANG Lei1   

  1. 1.School of Electrical and Information Engineering,Lanzhou University of Technology,Lanzhou 730050,China
    2.State Key Lab of Gansu Advanced Non-ferrous Metal Materials,Lanzhou University of Technology,Lanzhou 730050,China
  • Received:2008-09-19 Revised:2008-12-01 Online:2010-03-21 Published:2010-03-21
  • Contact: WANG Xiao-lan

摘要: 基于模糊最小二乘支持向量机和在线学习算法,提出了一种模糊最小二乘支持向量机的增量式算法。传统最小二乘支持向量机引入模糊加权系数后,有效地提高了其抗噪性能。同时利用递推的核函数计算方法增强了该算法的在线学习能力。仿真结果表明,这一算法在运算精度和运算速度上都优于传统的支持向量机算法。

关键词: 模糊最小二乘支持向量机, 增量式算法, 电压偏离值, 风速预测, 时间序列预测

Abstract: On the base of fuzzy least square support vector machine and the online learning algorithm,an incremental fuzzy least square support vector machine is proposed.The fuzzy weighting parameters are introduced into incremental least square support vector machine,which effectively increases the noise immunity.And the online learning ability of this algorithm is increased by the incremental kernel function algorithm.Experimental results on voltage deviations and wind speed show that this method is much better than the traditional LSSVM algorithm in accuracy and learning speed.

Key words: fuzzy least squares support vector machine, incremental algorithm, voltage deviations, wind speed forecasting, time series forecasting

中图分类号: