-
摘要: 介绍了一种可以提高非平稳时间序列预测精度的新方法, 该方法应用 Hilbert-Huang 变换的核心内容---经验模态分解法 (Empirical mode decomposition, EMD) 对非平稳时间序列进行分解, 以降低被预测信号中的非平稳性, 利用神经网络对分解后的各分量进行预测, 再将预测结果叠加. 利用该方法对石家庄市年逐月降水量进行预测, 预测结果显示, 其预测精度比直接用神经网络预测的预测精度有较明显的提高.
-
关键词:
- Hilbert-Huang变换 /
- 预测 /
- 非平稳性 /
- 非线性 /
- 经验模态分解法(EMD) /
- 人工神经网络(ANN) /
- 时间序列
Abstract: In this paper, a new method to improve non-stationary time series prediction accuracy is introduced. The non-stationary time series is decomposed by empirical mode decomposition (EMD) in Hilbert-Huang transform to reduce the non-stationarity in the signals. By using neural network, the component of decomposition is predicted, then the predicted results are added. The author has predicted monthly precipitation data at Shijiazhuang with the method. The study shows that the prediction accuracy of the neural network based on EMD is higher than that of prediction method using the neural network.
点击查看大图
计量
- 文章访问数: 2519
- HTML全文浏览量: 71
- PDF下载量: 1525
- 被引次数: 0