2025年 01期

Echo State Network Model Combined with Gaussian Noise and Its Time Series Prediction Performance

摘要(Abstract):

为了模拟回声状态网络模型在时间序列预测实例中的影响因素,在回声状态网络模型的储备池层引入高斯噪声,构建结合高斯噪声的回声状态网络模型;利用公式推导分析所提模型的非线性性质;采用股票序列数据与Logistic混沌序列数据进行实验验证和对比分析。结果表明,本文所提模型的预测效果优于回声状态网络模型、压缩感知回声状态网络模型和反向传播神经网络模型,股票收盘价预测、Logistic混沌序列预测的平均绝对误差均最小,分别为1.33×10~(-3)、 5.21×10~(-4)。

关键词(KeyWords): 时间序列预测;回声状态网络模型;高斯噪声;储备池层;

基金项目(Foundation): 国家自然科学基金项目(62103165);; 算力互联网与信息安全教育部重点实验室开放课题项目(2023ZD038);; 山东省自然科学基金项目(ZR2022ZD01,ZR2023MF036);; 山东省科技型中小企业创新工程项目(2023TSGC0150)

作者(Author): 王梓鉴,赵慧,郑明文,李鑫

DOI: 10.13349/j.cnki.jdxbn.20241212.001

参考文献(References):

[1] JAEGER H,HAAS H.Harnessing nonlinearity:prediction of chaotic time series with neural networks[J].Science,2004,304(5667):78.

[2] 甄远婷,冶继民,李国荣.基于中心Copula函数相似性度量的时间序列聚类方法[J].陕西师范大学学报(自然科学版),2021,49(1):29.

[3] HU H L,LIN W,LYU S X.Forecasting energy consumption and wind power generation using deep echo state network[J].Renewable Energy,2020,154:598.

[4] CHEN H C,WEI D Q.Chaotic time series prediction using echo state network based on selective opposition grey wolf optimizer[J].Nonlinear Dynamics,2021,104(4):3925.

[5] RIBEIRO G T,SANTOS A A P,MARIANI V C,et al.Novel hybrid model based on echo state neural network applied to the prediction of stock price return volatility[J].Expert Systems with Applications,2021,184:115490.

[6] SUN C X,SONG M X,CAI D R,et al.A systematic review of echo state networks from design to application[J].IEEE Transactions on Artificial Intelligence,2022,5(1):23.

[7] WANG H,LONG X Y,LIU X X.FastESN:fast echo state network[J].IEEE Transactions on Neural Networks and Learning Systems,2023,34(12):10487.

[8] ZHANG H,ZHENG M W,ZHANG Y P,et al.Application of ESN prediction model based on compressed sensing in stock market[J].Communications in Nonlinear Science and Numerical Simulation,2021,101:105857.

[9] WANG Z J,ZHAO H,ZHENG M W,et al.A novel time series prediction method based on pooling compressed sensing echo state network and its application in stock market[J].Neural Networks,2023,164:216.

[10] LIU J M,XU X,LI E.A minimum complexity interaction echo state network[J].Neural Computing and Applications,2024,36:4013.

[11] 高健,颜子翔,肖井华.储备池算法与动力系统分析研究进展[J].北京师范大学学报(自然科学版),2023,59(6):860.

[12] 秦凤鸣,徐宗玲,王有贵.政府政策对股价波动的影响:基于中国市场的证据[J].数量金融学,2018,18(9):1479.

[13] YUN S S,KANG J M,KIM I M,et al.Deep artificial noise:deep learning-based precoding optimization for artificial noise scheme[J].IEEE Transactions on Vehicular Technology,2020,69(3):3465.

[14] CARTIS C,ROBERTS L,SHERIDAN M O.Escaping local minima with local derivative-free methods:a numerical investigation[J].Optimization,2022,71(8):2343.

[15] KHAN S H,HAYAT M,PORIKLI F.Regularization of deep neural networks with spectral dropout[J].Neural Networks,2019,110:82.

[16] LI D C,HAN M,WANG J.Chaotic time series prediction based on a novel robust echo state network[J].IEEE Transactions on Neural Networks and Learning Systems,2012,23(5):787.

[17] SORIANO M C,ORTIN S,KEUNINCKX L,et al.Delay-based reservoir computing:noise effects in a combined analog and digital implementation[J].IEEE Transactions on Neural Networks and Learning Systems,2014,26(2):388.

[18] PATHAK J,HUNT B,GIRVAN M,et al.Model-free prediction of large spatiotemporally chaotic systems from data:a reservoir computing approach[J].Physical Review Letters,2018,120(2):024102.

[19] 李立祥,李鹏,张鑫.基于高斯噪声扰动和多群体粒子群优化的混沌时间序列预测[J].非线性动力学学报,2021,101(2):1149.

[20] WANG C,PENG G H,LIN W.Robust local metric learning via least square regression regularization for scene recognition[J].Neurocomputing,2021,423:179.

[21] WYTHOFF B J.Backpropagation neural networks:a tutorial[J].Chemometrics and Intelligent Laboratory Systems,1993,18(2):115.

[22] 徐震,沈云柱.概周期驱动的二维分段线性范式系统的奇异非混沌吸引子[J].济南大学学报(自然科学版),2022,36(2):231.