福州大学学报（自然科学版）2017，Vol.45Issue(1)：37-43,7.DOI:10.7631/issn.1000-2243.2017.01.0037
基于奇异值分解的极限学习机多变量时间序列预测模型
Multivariate time series prediction based on extreme learning machine with singular value decomposition
摘要
Abstract
In multivariate time series prediction based on extreme learning machine (ELM),the prediction precision will be reduced due to convert matrix to vector.In this paper,based on singular value decomposition and extreme learning machine,a multivariate time series prediction model(SVDELM) is proposed to suit for the matrix input.Simulation results on Rossler,Chen's,Lorentz and stock multivariate time series show that the SVDELM is an effective prediction model for multivariate time series.关键词
多变量时间序列/预测模型/极限学习机/奇异值分解Key words
multivariate time series/prediction model/extreme learning machine/singular value decomposition分类
信息技术与安全科学引用本文复制引用
梁小春,陈晓云..基于奇异值分解的极限学习机多变量时间序列预测模型[J].福州大学学报（自然科学版）,2017,45(1):37-43,7.基金项目
国家自然科学基金资助项目(71273053) （71273053）
福建省自然科学基金资助项目(2014J01009) （2014J01009）
