The auto-regressive moving-average (ARMA) model with time-varying parameters is analyzed. The time-varying parameters are assumed to be a linear combination of a set of basis time-varying functions, and the feedbac...The auto-regressive moving-average (ARMA) model with time-varying parameters is analyzed. The time-varying parameters are assumed to be a linear combination of a set of basis time-varying functions, and the feedback linear estimation algorithm is used to estimate the time-varying parameters of the ARMA model. This algorithm includes 2 linear least squares estimations and a linear filter. The influence of the order of basis time-(varying) functions on parameters estimation is analyzed. The method has the advantage of simple, saving computation time and storage space. Theoretical analysis and experimental results show the validity of this method.展开更多
Because growth ring data have temporal features, time series analysis can be used to simulate and reveal changes in the life of a tree and contribute to plantation management. In this study, the autoregressive(AR) and...Because growth ring data have temporal features, time series analysis can be used to simulate and reveal changes in the life of a tree and contribute to plantation management. In this study, the autoregressive(AR) and moving average modeling method was used to simulate the time series for growth ring density in a larch plantation with different initial planting densities. We adopted the Box–Jenkins method for the modeling, which was initially based on an intuitive analysis of sequence graphs followed by the augmented Dickey–Fuller stationarity test. The order p and q of the ARMA(p, q) model was determined based on the autocorrelation and partial correlation coefficient figure truncated on the respective order.Through the residual judgment, the model AR(2) was only fitted to the larch growth ring density series for the plantation with the 1.5 9 2.0 m^2 initial planting density.Because the residuals series for the other three series was not shown as a white noise sequence, the modeling was rerun. Larch wood from the initial planting density of2.0 9 2.0 m^2 was modeled by ARMA(2, 1), and ARMA((1, 5), 3) fitted to the 2.5 9 2.5 m^2 initial planting density,and the 3.0 9 3.0 m^2 was modeled by AR(1, 2, 5).Although the ARMA modeling can simulate the change in growth ring density, data for the different growth ring time series were described by different models. Thus, time series modeling can be suitable for growth ring data analysis, revealing the time domain and frequency domain of growth ring data.展开更多
针对导弹备件消耗呈现"小样本、非平稳"的特点,为了克服传统预测方法依靠大样本数据进行建模的不足,提出了把基于小波变换和改进GM-ARMA的组合预测方法应用于导弹备件消耗预测的构想.在利用小波分解和其他模型建立组合模型的...针对导弹备件消耗呈现"小样本、非平稳"的特点,为了克服传统预测方法依靠大样本数据进行建模的不足,提出了把基于小波变换和改进GM-ARMA的组合预测方法应用于导弹备件消耗预测的构想.在利用小波分解和其他模型建立组合模型的过程中,提出了先对小波基方程和分解层数2个特征进行参数化,再定量地对所有子模型的特征参数进行统一、综合的评估,以达到建立最佳组合模型的目的;然后对具有平稳特性的高频信息用阻尼最小二乘法优化的ARMA(Autoregressive and Moving Average)模型进行预测,对反映整体趋势体现非平稳的低频信息用背景值优化和数据变换技术改进的GM(1,1)模型进行预测.实例结果表明所提出的组合预测方法大大降低了预测误差,说明了该方法的有效性、可行性和实用性.展开更多
文摘The auto-regressive moving-average (ARMA) model with time-varying parameters is analyzed. The time-varying parameters are assumed to be a linear combination of a set of basis time-varying functions, and the feedback linear estimation algorithm is used to estimate the time-varying parameters of the ARMA model. This algorithm includes 2 linear least squares estimations and a linear filter. The influence of the order of basis time-(varying) functions on parameters estimation is analyzed. The method has the advantage of simple, saving computation time and storage space. Theoretical analysis and experimental results show the validity of this method.
基金financially supported by the National Sci-Tech Support Plan of China(Grant No.2015BAD14B05)
文摘Because growth ring data have temporal features, time series analysis can be used to simulate and reveal changes in the life of a tree and contribute to plantation management. In this study, the autoregressive(AR) and moving average modeling method was used to simulate the time series for growth ring density in a larch plantation with different initial planting densities. We adopted the Box–Jenkins method for the modeling, which was initially based on an intuitive analysis of sequence graphs followed by the augmented Dickey–Fuller stationarity test. The order p and q of the ARMA(p, q) model was determined based on the autocorrelation and partial correlation coefficient figure truncated on the respective order.Through the residual judgment, the model AR(2) was only fitted to the larch growth ring density series for the plantation with the 1.5 9 2.0 m^2 initial planting density.Because the residuals series for the other three series was not shown as a white noise sequence, the modeling was rerun. Larch wood from the initial planting density of2.0 9 2.0 m^2 was modeled by ARMA(2, 1), and ARMA((1, 5), 3) fitted to the 2.5 9 2.5 m^2 initial planting density,and the 3.0 9 3.0 m^2 was modeled by AR(1, 2, 5).Although the ARMA modeling can simulate the change in growth ring density, data for the different growth ring time series were described by different models. Thus, time series modeling can be suitable for growth ring data analysis, revealing the time domain and frequency domain of growth ring data.
文摘针对导弹备件消耗呈现"小样本、非平稳"的特点,为了克服传统预测方法依靠大样本数据进行建模的不足,提出了把基于小波变换和改进GM-ARMA的组合预测方法应用于导弹备件消耗预测的构想.在利用小波分解和其他模型建立组合模型的过程中,提出了先对小波基方程和分解层数2个特征进行参数化,再定量地对所有子模型的特征参数进行统一、综合的评估,以达到建立最佳组合模型的目的;然后对具有平稳特性的高频信息用阻尼最小二乘法优化的ARMA(Autoregressive and Moving Average)模型进行预测,对反映整体趋势体现非平稳的低频信息用背景值优化和数据变换技术改进的GM(1,1)模型进行预测.实例结果表明所提出的组合预测方法大大降低了预测误差,说明了该方法的有效性、可行性和实用性.
