Abstract
We present a new chaotic times prediction model inspired by the bubble-net predation of whales. The echo state network (ESN) is a new type of recurrent neural network. However, selecting parameters empirically for the ESN cannot guarantee the accuracy of the prediction. The whale optimization algorithm (WOA) imitates the bubble-net predation of whales and ensures the rapid convergence of selecting network parameters. A new prediction model, WOA-ESN, in which the WOA and the ESN are incorporated, is proposed in this paper. In addition, a simplified cross-validation (CV) method is proposed to take into account the approximation performance and generalization ability of the WOA-ESN. In experiments, the WOA-ESN is used for Mackey-Glass and Lorenz chaotic time series predictions, and the results are compared with the ESN based on particle swarm optimization (PSO-ESN), the ESN based on genetic algorithm (GA-ESN), and ESN. The results show that the proposed model has the best prediction performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Z. D. Tian et al., Chaos Soliton. Fract. 98, 158 (2017).
G. Heydari, M. A. Vali and A. A. Gharaveisi, Expert Syst. Appl. 55, 461 (2016).
P. F. Zhao, L. Xing and J. Yu, Phys. Lett. A 373, 2174 (2009).
R. Chandra, Y. S. Ong and C. K. Goh, Neurocomputing 243, 21 (2017).
Y. Yuan et al., Chin. Phys. B 18, 958 (2009).
Y. F. Li et al., Nolinear Dyn. 85, 179 (2016).
J. S. Zhang and X. C. Xiao, Chin. Phys. Lett. 18, 337 (2001).
Y. T. Zhou et al., Chin. Phys. Lett. 34, 29 (2017).
J. B. Pollack, Artif. Intell. 46, 77 (1990).
X. L. Hu and B. Zhang, Sixth International Symposium on Neural Networks (Wuhan, China, May 26-29, 2009).
J. T. Connor, R. D. Martin and L. E. Atlas, IEEE Trans. Neural Netw. 5, 240 (2002).
Y. J. Huang and H. G. Hu, Chin. Phys. B 24, 120701 (2015).
C. Smith and Y. C. Jin, Neurocomputing 143, 302 (2014).
H. Jaeger, Germany National Research Center for Information Technology GMD Technical Report 148 (Bremen, Germany, 2001).
L. Boccato et al., Neural Netw. 32, 292 (2012).
A. A. Rodan, IEEE Trans. Neural Netw. 22, 131 (2011).
S. Mirjalili and A. Lewis, Adv. Eng. Softw. 95, 51 (2016).
J. Huang et al., J. Franklin Inst. 353, 2761 (2016).
S. S. Zhong et al., Neurocomputing 238, 191 (2017).
H. Jaeger and H. Haass, Science 304, 78 (2004).
H. Jaeger, in Proceedings of Nips (Vancouver, Canada, December 2002), p. 609.
M. H. Yusoff, J. Chrol-Cannon and Y. C. Jin, Inform. Sci. 364-365, 184 (2016).
K. Yeo, J. Comput. Phys. 395, 671 (2019).
H. Jaeger et al., Neural Netw. 20, 335 (2007).
M. Lukoševičius, H. Jaeger and B. Schrauwen, KIK ünstliche Intelligenz 26, 365 (2012).
P. Hof and E. van der Gucht, Anat. Rec. 290, 1 (2007).
W. A. William and S. E. William. J. Mammal. 60, 155 (1979).
N. Chouikhi et al., Appl. Soft Comput. 55, 211 (2017).
Z. Tian et al., J. Comput. Res. Dev. 52, 1137 (2015).
C. Y. Sheng et al., Neurocomputing 82, 186 (2012).
J. F. Qiao et al., IEEE Trans. Neural Netw. Learn. Syst. 28, 391 (2017).
J. McNames, Neurocomputing 48, 279 (2002).
Acknowledgments
The authors would like to gratefully acknowledge support by the Hebei Province Natural Science Foundation (F2019202364) and the Humanity and Social Science Foundation of the Ministry of Education of China (15YJA630108).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, M., Wang, B., Zhou, Y. et al. WOA-Based Echo State Network for Chaotic Time Series Prediction. J. Korean Phys. Soc. 76, 384–391 (2020). https://doi.org/10.3938/jkps.76.384
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3938/jkps.76.384