Multi-state delayed echo state network with empirical wavelet transform for time series prediction

被引：5
作者：
Yao, Xianshuang [1 ]
Wang, Huiyu [1 ]
Shao, Yanning [1 ]
Huang, Zhanjun [2 ]
Cao, Shengxian [1 ]
Ma, Qingchuan [3 ]
机构：
[1] Northeast Elect Power Univ, Sch Automat Engn, Jilin, Peoples R China
[2] Northwestern Polytech Univ, Coll Aeronaut, Xian, Peoples R China
[3] Shandong Henghui Energy Saving Technol Grp Co Ltd, Yantai, Peoples R China
来源：
APPLIED INTELLIGENCE | 2024年 / 54卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Echo state network; Empirical wavelet transform; Multi-state delayed; Time series prediction; MODE DECOMPOSITION;
D O I：
10.1007/s10489-024-05386-1
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper, considering the effect of multiple delayed states on the reservoir itself, based on the advantage of the empirical wavelet transform, an improved ESN with multiple delayed states is proposed, called multi-state delayed echo state network with empirical wavelet transform (EWT-MSD-ESN). Firstly, the empirical wavelet transform is used to decompose the input signal, and then the main features of all decomposed components of the input signal can be extracted. Secondly, considering the multi-state delayed capability of the reservoir, the reservoir state equation of the EWT-MSD-ESN can be adjusted adaptively by using the autocorrelation coefficient of the input signal, such that the intrinsic characteristics of different learning tasks can be fully reflected. Finally, four numerical simulation examples and two actual examples are used to validate the predictive performance of EWT-MSD-ESN.
引用
收藏
页码：4646 / 4667
页数：22
相关论文
共 37 条
[1]   Daily global solar radiation time series prediction using variational mode decomposition combined with multi-functional recurrent fuzzy neural network and quantile regression forests algorithm [J].
Abdallah, Mohammed ;
Mohammadi, Babak ;
Nasiri, Hamid ;
Katipoglu, Okan Mert ;
Abdalla, Modawy Adam Ali ;
Ebadzadeh, Mohammad Mehdi .
ENERGY REPORTS, 2023, 10 :4198-4217
[2]   Wavelet transform-based trend analysis of streamflow and precipitation in Upper Blue Nile River basin [J].
Abebe, Sintayehu A. ;
Qin, Tianling ;
Zhang, Xin ;
Yan, Denghua .
JOURNAL OF HYDROLOGY-REGIONAL STUDIES, 2022, 44
[3]   A hybrid EMD-GRNN-PSO in intermittent time-series data for dengue fever forecasting [J].
Anggraeni, Wiwik ;
Yuniarno, Eko Mulyanto ;
Rachmadi, Reza Fuad ;
Sumpeno, Surya ;
Pujiadi, Pujiadi ;
Sugiyanto, Sugiyanto ;
Santoso, Joan ;
Purnomo, Mauridhi Hery .
EXPERT SYSTEMS WITH APPLICATIONS, 2024, 237
[4]   Evolutionary Echo State Network: A neuroevolutionary framework for time series prediction [J].
Basterrech, Sebastian ;
Rubino, Gerardo .
APPLIED SOFT COMPUTING, 2023, 144
[5]   An asynchronously deep reservoir computing for predicting chaotic time series [J].
Bo, Ying-Chun ;
Wang, Ping ;
Zhang, Xin .
APPLIED SOFT COMPUTING, 2020, 95
[6]   A joint network of non-linear graph attention and temporal attraction force for geo-sensory time series prediction [J].
Dong, Hongbin ;
Han, Shuang ;
Pang, Jinwei ;
Yu, Xiaodong .
APPLIED INTELLIGENCE, 2023, 53 (14) :17346-17362
[7]   Variational Mode Decomposition [J].
Dragomiretskiy, Konstantin ;
Zosso, Dominique .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2014, 62 (03) :531-544
[8]   Monthly runoff time series prediction by variational mode decomposition and support vector machine based on quantum-behaved particle swarm optimization [J].
Feng, Zhong-kai ;
Niu, Wen-jing ;
Tang, Zheng-yang ;
Jiang, Zhi-qiang ;
Xu, Yang ;
Liu, Yi ;
Zhang, Hai-rong .
JOURNAL OF HYDROLOGY, 2020, 583
[9]   Dynamic ensemble deep echo state network for significant wave height forecasting [J].
Gao, Ruobin ;
Li, Ruilin ;
Hu, Minghui ;
Suganthan, Ponnuthurai Nagaratnam ;
Yuen, Kum Fai .
APPLIED ENERGY, 2023, 329
[10]   Time series forecasting based on echo state network and empirical wavelet transformation [J].
Gao, Ruobin ;
Du, Liang ;
Duru, Okan ;
Yuen, Kum Fai .
APPLIED SOFT COMPUTING, 2021, 102 (102)
1234