基于混沌最小二乘支持向量机的时间序列预测研究  

Time series Prediction Based on Chaotic Least Squares Support Vector Machines

作　　者：高雄飞 GAO Xiong-fei(College of Science, Engineering University of PAP, Xi＇an 710072, China)

机构地区：[1]武警工程大学理学院

出　　处：《数学的实践与认识》2018年第8期239-244,共6页Mathematics in Practice and Theory

基　　金：国家自然科学基金(11171043)

摘　　要：为了对这种具有非线性特性的时间序列进行预测,提出一种基于混沌最小二乘支持向量机.算法将时间序列在相空间重构得到嵌入维数和时间延滞作为数据样本的选择依据,结合最小二乘法原理和支持向量机构建了基于混沌最小二乘支持向量机的预测模型.利用此预测模型对栾城站土壤含水量时间序列进行了预测.结果表明,经过相空间重构优化了数据样本的选取,通过模型的评价指标,混沌最小二乘支持向量机的预测模型能精确地预测具有非线性特性的时间序列,具有很好的理论和应用价值.A chaotic least squares support vector machine （CL-SVM） was proposed to predict the time series with nonlinear characteristics. The algorithm will reconstruct the time series embedding dimension and time delay as the basis for the selection of sample data in phase space, combined with the principle of least square method and the support vector machine built chaotic prediction model based on least squares support vector machine. The soil moisture time series of Luancheng station was predicted by the model. The results show that after optimization of the phase space reconstruction of selecting sample data, through the evaluation index model, prediction model of chaotic least squares support vector machine can accurately predict the time series with nonlinear characteristics, which has the very good theoretical and practical value.

关 键 词：时间序列 相空间重构 支持向量机 最小二乘算法 

分 类 号：O211.61[理学—概率论与数理统计]