Research Article

Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System

Volume: 10 Number: 37 April 1, 2019
  • Engin Kandıran
  • Avadis Hacınlıyan
TR EN

Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System

Abstract

Artificial neural networks are commonly accepted as a very successful tool for global function approximation. Because of this reason, they are considered as a good approach to forecasting chaotic time series in many studies. For a given time series, the Lyapunov exponent is a good parameter to characterize the series as chaotic or not. In this study, we use three different neural network architectures to test capabilities of the neural network in forecasting time series generated from different dynamical systems. In addition to forecasting time series, using the feedforward neural network with single hidden layer, Lyapunov exponents of the studied systems are forecasted.

Keywords

References

  1. Casdagli, M. (1989). Nonlinear prediction of chaoti time series. Physica D, 335-356.
  2. de Oliveira, K. A., Vanucci, A., & da Silva, E. C. (2000). Using artificial neural networks to forecast chaotic time series. Physica A, 393-404.
  3. de Oliveira, K., Vannucci, A., & da Silva, E. C. (2000). Using artificial neural networks to forecast chaotic time series. (284).
  4. Eckman, J., & Ruelle, D. (1985). Ergodic theory of chaos and strange attractors. Rev Mod Phys.
  5. Eckmann, J.-P. &. (1987). Liapunov exponents from time series. Physical review. A, 4971- 4979.
  6. Gencay, R., & Dechert, D. W. (1992). An algorithm for the n Lyapunov exponents of an n-dimensional unknown dynamical system. Physica D, 142-157.
  7. Gencay, R., & Tung, L. (1997). Nonlinear modelling and prediction with feedforward and recurrent networks. Physica D: Nonlinear Phenomena, 119-134.
  8. Takens, F. (1980). Detecting strange attractors in turbulance. Dynamical Systems and turbulance.

Details

Primary Language

English

Subjects

-

Journal Section

Research Article

Authors

Engin Kandıran This is me

Avadis Hacınlıyan This is me

Publication Date

April 1, 2019

Submission Date

April 1, 2019

Acceptance Date

-

Published in Issue

Year 2019 Volume: 10 Number: 37

APA
Kandıran, E., & Hacınlıyan, A. (2019). Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System. AJIT-E: Academic Journal of Information Technology, 10(37), 31-44. https://doi.org/10.5824/1309-1581.2019.2.002.x
AMA
1.Kandıran E, Hacınlıyan A. Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System. AJIT-e: Academic Journal of Information Technology. 2019;10(37):31-44. doi:10.5824/1309-1581.2019.2.002.x
Chicago
Kandıran, Engin, and Avadis Hacınlıyan. 2019. “Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System”. AJIT-E: Academic Journal of Information Technology 10 (37): 31-44. https://doi.org/10.5824/1309-1581.2019.2.002.x.
EndNote
Kandıran E, Hacınlıyan A (April 1, 2019) Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System. AJIT-e: Academic Journal of Information Technology 10 37 31–44.
IEEE
[1]E. Kandıran and A. Hacınlıyan, “Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System”, AJIT-e: Academic Journal of Information Technology, vol. 10, no. 37, pp. 31–44, Apr. 2019, doi: 10.5824/1309-1581.2019.2.002.x.
ISNAD
Kandıran, Engin - Hacınlıyan, Avadis. “Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System”. AJIT-e: Academic Journal of Information Technology 10/37 (April 1, 2019): 31-44. https://doi.org/10.5824/1309-1581.2019.2.002.x.
JAMA
1.Kandıran E, Hacınlıyan A. Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System. AJIT-e: Academic Journal of Information Technology. 2019;10:31–44.
MLA
Kandıran, Engin, and Avadis Hacınlıyan. “Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System”. AJIT-E: Academic Journal of Information Technology, vol. 10, no. 37, Apr. 2019, pp. 31-44, doi:10.5824/1309-1581.2019.2.002.x.
Vancouver
1.Engin Kandıran, Avadis Hacınlıyan. Comparison of Feedforward and Recurrent Neural Network in Forecasting Chaotic Dynamical System. AJIT-e: Academic Journal of Information Technology. 2019 Apr. 1;10(37):31-44. doi:10.5824/1309-1581.2019.2.002.x