A 2-Stage Strategy for Non-Stationary Signal Prediction and Recovery Using Iterative Filtering and Neural Network

A 2-Stage Strategy for Non-Stationary Signal Prediction and Recovery Using Iterative Filtering and Neural Network
复制标题

使用迭代滤波和神经网络的非平稳信号预测和恢复的两阶段策略

DOI:
10.1007/s11390-019-1913-0
复制
发表时间:
2019-03
影响因子:
0.7
通讯作者:
Yang Li Hua
Yang Li Hua
中科院分区:
--
文献类型:
--
作者:
Zhou Feng;Zhou Hao Min;Yang Zhi Hua;Yang Li Hua

文献摘要

参考文献

被引文献

相似文献

预测时间序列的未来信息和恢复缺失数据是各种应用领域面临的两个重要任务。特别是当信号为非线性、非平稳信号时,它们往往面临很大的挑战。在本文中,我们提出了一种混合2阶段的方法,命名为IF 2FNN,预测(包括短期和长期预测)和恢复的一般类型的时间序列。在第一阶段中,我们用迭代滤波(IF)方法将原始的非平稳序列分解成几个“准平稳”的本征模函数(IMF)。在第二阶段中,所有的IMF作为输入馈送到基于因式分解机的神经网络模型来执行预测和恢复。我们测试了五个数据集,包括人工构建的信号(ACS),和四个真实世界的信号:一天的长度(LOD),北方半球陆地-海洋温度指数(NHLTI),对流层月平均温度(TMMT),和全国证券交易商协会自动报价指数(纳斯达克)的策略。并与其它常用方法的计算结果进行了比较。我们的实验表明,在相同的条件下,所提出的方法优于其他的预测和恢复根据各种指标,如平均绝对误差(MAE),均方根误差(RMSE),平均绝对百分比误差(MAPE)。
Predicting the future information and recovering the missing data for time series are two vital tasks faced in various application fields. They are often subjected to big challenges, especially when the signal is nonlinear and non-stationary which is common in practice. In this paper, we propose a hybrid 2-stage approach, named IF2FNN, to predict (including short-term and long-term predictions) and recover the general types of time series. In the first stage, we decompose the original non-stationary series into several “quasi stationary” intrinsic mode functions (IMFs) by the iterative filtering (IF) method. In the second stage, all of the IMFs are fed as the inputs to the factorization machine based neural network model to perform the prediction and recovery. We test the strategy on five datasets including an artificial constructed signal (ACS), and four real-world signals: the length of day (LOD), the northern hemisphere land-ocean temperature index (NHLTI), the troposphere monthly mean temperature (TMMT), and the national association of securities dealers automated quotations index (NASDAQ). The results are compared with those obtained from the other prevailing methods. Our experiments indicate that under the same conditions, the proposed method outperforms the others for prediction and recovery according to various metrics such as mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE).
DOI: 10.1016/j.asoc.2016.01.027
发表时间: 2016-05
期刊: Appl. Soft Comput.
影响因子: --
作者:
Liang-Ying Wei
通讯作者: Liang-Ying Wei
DOI: 10.1016/s0957-4174(01)00047-1
发表时间: 2002
期刊: Expert Syst. Appl.
影响因子: --
作者:
Yi-Fan Wang
通讯作者: Yi-Fan Wang
DOI: 10.1016/j.eswa.2014.12.003
发表时间: 2015-04-15
影响因子: 8.5
作者:
Rather, Akhter Mohiuddin;Agarwal, Arun;Sastry, V. N.
通讯作者: Sastry, V. N.
DOI: 10.4018/978-1-7998-1192-3.ch008
发表时间: 2020
期刊: Advances in Systems Analysis, Software Engineering, and High Performance Computing
影响因子: --
作者:
Menaga D.;R. S.
通讯作者: Menaga D.;R. S.
DOI: 10.4018/978-1-5225-9096-5.ch007
发表时间: 2021-07
期刊: Smart Computational Intelligence in Biomedical and Health Informatics
影响因子: --
作者:
A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi
通讯作者: A. Sinha;S. Gupta;Anurag Tiwari;Amrita Chaturvedi