|本期目录/Table of Contents|

[1]田中大,李树江,王艳红,等. IFS-LSSVM 及其在时延序列预测中的应用[J].电机与控制学报,2015,19(11):104-110.[doi:10. 15938 / j. emc. 2015. 11. 016]
 TIAN Zhong-da,LI Shu-jiang,WANG Yan-hong,et al. IFS-LSSVM and its application in time-delay series prediction [J].,2015,19(11):104-110.[doi:10. 15938 / j. emc. 2015. 11. 016]
点击复制

 IFS-LSSVM 及其在时延序列预测中的应用(PDF)
分享到:

《电机与控制学报》[ISSN:1007-449X/CN:23-1 408/TM]

卷:
19
期数:
2015年11
页码:
104-110
栏目:
出版日期:
2015-12-31

文章信息/Info

Title:
 IFS-LSSVM and its application in time-delay series prediction


作者:
 田中大1 李树江1 王艳红1 高宪文2
 ( 1. 沈阳工业大学 信息科学与工程学院,辽宁 沈阳 110870; 2. 东北大学 信息科学与工程学院,辽宁 沈阳 110819)
Author(s):
 TIAN Zhong-da1 LI Shu-jiang1 WANG Yan-hong1 GAO Xian-wen2
 (1. College of Information Science and Engineering,Shenyang University of Technology,Shenyang 110870,China; 2. College of Information Science and Engineering,Northeastern University,Shenyang 110819,China)
关键词:
最小二乘支持向量机 自由搜索 时延序列 预测 时间序列
Keywords:
least squares support machines free search time-delay series prediction time series
分类号:
TP 393
DOI:
10. 15938 / j. emc. 2015. 11. 016
文献标志码:
A
摘要:
针对最小二乘支持向量机预测模型中最优参数难以确定的问题,提出一种基于改进的自由搜索算法确定最小二乘支持向量机最优参数的方法( IFS-LSSVM) 。对标准自由搜索算法进行改进,使之可应用于最小二乘支持向量机的参数优化,改进之后的算法具有更好的优化性能。将具有 时间序列性质的网络时延作为预测对象,利用本文的 IFS-LSVM 算法进行预测。在仿真中与遗传算法优化的最小二乘支持向量机( GA-LSSVM) 、粒子群优化算法优化的最小二乘支持向量机( PSO- LSSVM) 、标准最小二乘支持向量机工具箱中的网格搜索算法( Grid-LSSVM) 进行了对比。仿真对比结果表明本文的方法具有更高的预测精度与更小的预测误差。

Abstract:
 It is difficult to determine the optimal parameters of least squares support vector machine pre-diction model,so a prediction method based on improved free search algorithm ( IFS-LSSVM) was pro-posed to determine the optimal parameters of least squares support vector machines. First,the standard free search algorithm was improved so that it can be applied to the parameter optimization of least squares support vector machines,the improved harmony search algorithm has better optimization performance. Then the least squares support vector machines was applied to predict the time-delay series of the network based on improved free search optimization algorithm. Finally,time-delay series was used as prediction simulation object,genetic algorithm optimized least squares support vector machines ( GA-LSSVM) ,par-ticle swarm optimization algorithm optimized least squares support vector machines ( PSO-LSSVM ) , standard grid search method of least squares support vector machines ( Grid-LSSVM) toolbox were com-pared. Simulation comparison results show that the proposed method has higher prediction accuracy and smaller prediction error.

参考文献/References:

-

相似文献/References:

[1]周欣然,滕召胜,易钊,等.构造稀疏最小二乘支持向量机的快速剪枝算法[J].电机与控制学报,2009,(04):626.
 ZHOU Xin-ran,TENG Zhao-sheng,et al.Fast pruning algorithm for designing sparse least squares support vector machine[J].,2009,(11):626.
[2]徐宇拓,曹彦萍,钟锐. 基于LSSVM的多输入多输出开关磁阻电机建模[J].电机与控制学报,2015,19(06):41.[doi:10. 15938/j. emc.2015.06.007]
 XU Yu-zhe,CAO Yan-ping,ZHONG Rui. MIMO modeling of switched reluctance motors based on LSSVM[J].,2015,19(11):41.[doi:10. 15938/j. emc.2015.06.007]
[3]于洪亮,王旭,杨丹,等.基于自适应最小二乘支持向量机逆系统的链式STATCOM 控制策略[J].电机与控制学报,2017,21(07):107.[doi:10.15938/j.emc.2017.07.015]
 YU Hong-liang,WANG Xu,YANG Dan,et al.Control strategy of cascade STATCOM based on adaptive least square support vector machine and inverse system [J].,2017,21(11):107.[doi:10.15938/j.emc.2017.07.015]

备注/Memo

备注/Memo:
 收稿日期: 2013 - 12 - 12
基金项目: 国家自然科学基金( 61034005) ; 辽宁省博士科研启动基金( 20141070)
作者简介: 田中大( 1978—) ,男,博士,讲师,研究方向为混沌时间序列预测、网络控制系统;
李树江( 1966—) ,男,博士,教授,研究方向为复杂工业过程建模与控制;
王艳红( 1967—) ,女,博士,教授,研究方向为生产过程调度与优化控制;
高宪文( 1955—) ,男,博士,教授,博士生导师,研究方向为复杂工业过程建模与控制。
更新日期/Last Update: 2016-03-13