A hybrid modelling method for time series forecasting based on a linear regression model and deep learning
A hybrid modelling method for time series forecasting based on a linear regression model and deep learning
复制标题
基于线性回归模型和深度学习的时间序列预测混合建模方法
DOI：
10.1007/s10489-019-01426-3
复制
发表时间：
2019-02
影响因子：
5.3
通讯作者：
Peng Xiaoyan
中科院分区：
文献类型：
--
作者：
Xu Wenquan;Peng Hui;Zeng Xiaoyong;Zhou Feng;Tian Xiaoying;Peng Xiaoyan
时间序列预测具有重要的理论意义和工程应用价值。大量研究表明，混合建模在各种建模应用中非常成功，理论和实证研究结果都表明，混合建模是提高时间序列模型精度的有效方法。本文提出了一种混合模型，结合线性回归（LR）模型和深度信念网络（DBN）模型的时间序列数据的预测。在混合模型中，线性AR（自回归）LR模型或ARIMA（自回归积分移动平均）模型和非线性DBN模型分别捕捉时间序列的线性和非线性行为。我们首先使用LR模型来拟合原始数据，并获得原始数据和LR模型的预测数据之间的LR模型残差。然后，残差被视为非线性分量，并作为输入到DBN模型。LR模型的预测和DBN模型的输出是时间序列的最终预测值，充分利用了两种模型对时间序列进行预测。将该混合模型与已有的其他模型应用于4个著名的时间序列进行比较，结果表明，该混合模型具有较高的预测精度，可以作为时间序列预测的有用工具。
Time series forecasting has important theoretical significance and engineering application value. A number of studies have shown that hybrid modelling is very successful in various modelling applications, and both theoretical and empirical findings have shown that hybrid modelling is an effective method to improve the accuracy of time series models. This paper proposes a hybrid model that combines a linear regression (LR) model and deep belief network (DBN) model for the prediction of time series data. In the hybrid model, the linear AR (auto-regression) LR model or ARIMA (auto-regressive integrated moving average) model and the nonlinear DBN model are explored to capture the linear and nonlinear behaviours of a time series, respectively. We first use an LR model to fit the original data and obtain the LR model residuals between the original data and the predicted data of the LR model. Then, the residuals are regarded as the nonlinear component and are used as inputs into the DBN model. The LR model prediction and the output of the DBN model are the final forecasting value for the time series, which takes full advantage of the two models for predicting time series. The proposed hybrid model and other existing models are applied to four well-known time series for comparison, and the results show that the proposed hybrid model has a high prediction accuracy and may be a useful tool for time series forecasting.
登录
查看更多内容
DOI：
10.1007/3-540-45718-6_35
发表时间：
2001-05
期刊：
--
影响因子：
--
作者：
Kok Keong Teo;Lipo Wang;Zhiping Lin
通讯作者：
Kok Keong Teo;Lipo Wang;Zhiping Lin
影响因子：
6
作者：
Chandra, Rohitash;Zhang, Mengjie
通讯作者：
Zhang, Mengjie
影响因子：
2.9
作者：
Memisevic, Roland;Hinton, Geoffrey E.
通讯作者：
Hinton, Geoffrey E.
影响因子：
8.7
作者：
Khashei, Mehdi;Bijari, Mehdi
通讯作者：
Bijari, Mehdi
DOI：
--
发表时间：
2007-12
期刊：
--
影响因子：
--
作者：
R. Salakhutdinov;Geoffrey E. Hinton
通讯作者：
R. Salakhutdinov;Geoffrey E. Hinton