On the Identification and Generation of Discrete-Time Chaotic Systems with Recurrent Neural Networks

  • Seungwon Lee
  • Sung Hwan Won
  • Iickho Song
  • Seokho Yoon
  • Sun Yong KimEmail author
Original Article


We address the identification and generation of the discrete-time chaotic system (DTCS) with a two-layered recurrent neural network (RNN). First, we propose an identification procedure of the DTCS in which the RNN is required to have less layers than in the conventional procedures. Next, based on Li–Yorke theorem, we propose a generation procedure which enables us to predict a range of chaotic behavior of the DTCS in advance. Simulation results demonstrate that the proposed identification procedure, employing the Levenberg–Marquardt algorithm and a two-layered RNN, requires lower computational complexity than the conventional identification procedures at comparable performance.


Discrete-time chaotic system Recurrent neural network (RNN) System generation System identification 



This work was supported by the National Research Foundation of Korea under Grant NRF-2018R1A2A1A05023192, for which the authors wish to express their appreciation. The authors would also like to thank the Associate Editor and two anonymous reviewers for their constructive suggestions and helpful comments.


  1. 1.
    Yi Z, Tan KK (2004) Multistability of discrete-time recurrent neural networks with unsaturating piecewise linear activation functions. IEEE Trans Neural Netw 15(2):329–336CrossRefGoogle Scholar
  2. 2.
    Khansari-Zadeh S-M, Billard A (2012) A dynamical system approach to realtime obstacle avoidance. Auton Robots 32(4):433–454CrossRefGoogle Scholar
  3. 3.
    Li Y, Huang X, Guo M (2013) The generation, analysis, and circuit implementation of a new memristor based chaotic system. Math Probl Eng 1:398306-1–398306-8MathSciNetzbMATHGoogle Scholar
  4. 4.
    Gotoda H, Shinoda Y, Kobayashi M, Okuno Y, Tachibana S (2014) Detection and control of combustion instability based on the concept of dynamical system theory. Phys Rev 82(2):022910Google Scholar
  5. 5.
    Alombah NH, Fotsin H, Ngouonkadi EBM, Nguazon T (2016) Dynamics, analysis and implementation of a multiscroll memristor-based chaotic circuit. Int J Bif Chaos 26(8):1650128-1–1650128-20MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Li T-Y, Yorke A (1975) Period three implies chaos. Amer. Math. Monthly 82(10):985–992MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Casdagli M (1989) Nonlinear prediction of chaotic time series. Phys D Nonlinear Phen 35(3):335–356MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Cook ER, Kairiukstis LA (1990) Methods of dendrochronology: applications in the environmental science. Kluwer, NorwellCrossRefGoogle Scholar
  9. 9.
    Moskalenko OI, Koronovskii AA, Hramov AE (2010) Generalized synchronization of chaos for secure communication: remarkable stability to noise. Phys Lett A 374(29):2925–2931CrossRefzbMATHGoogle Scholar
  10. 10.
    Zounemat-Kermani M, Kisi O (2015) Time series analysis on marine wind-wave characteristics using chaos theory. Ocean Eng 100:46–53CrossRefGoogle Scholar
  11. 11.
    Ghanem R, Romeo F (2001) A wavelet-based approach for model and parameter identification of non-linear systems. Int J Non-Linear Mech 36(5):835–859CrossRefzbMATHGoogle Scholar
  12. 12.
    Bodyanskiy Y, Vynokurova O (2013) Hybrid adaptive wavelet-neuro-fuzzy system for chaotic time series identification. Inf Sci 220:170–179CrossRefGoogle Scholar
  13. 13.
    Lee C-H, Teng C-C (2000) Identification and control of dynamic systems using recurrent fuzzy neural networks. IEEE Trans Fuzzy Syst 8(4):349–366CrossRefGoogle Scholar
  14. 14.
    Won SH, Song I, Lee SY, Park CH (2010) Identification of finite state automata with a class of recurrent neural networks. IEEE Trans Neural Netw 21(9):1408–1421CrossRefGoogle Scholar
  15. 15.
    Dong L, Wei F, Xu K, Liu S, Zhou M (2016) Adaptive multi-compositionality for recursive neural network models. IEEE/ACM Tr. Audio Speech Lang Process 24(3):422–431CrossRefGoogle Scholar
  16. 16.
    Su B, Lu S (2017) Accurate recognition of words in scenes without character segmentation using recurrent neural network. Pattern Recogn 63:397–405CrossRefGoogle Scholar
  17. 17.
    Cannas B, Cincotti S, Marchesi M, Pilo F (2001) Learning of Chua’s circuit attractors by locally recurrent neural networks. Chaos Solitons Fractals 12(11):2109–2115CrossRefzbMATHGoogle Scholar
  18. 18.
    Pan S-T, Lai C-C (2008) Identification of chaotic systems by neural network with hybrid learning algorithm. Chaos Solitons Fractals 37(1):233–244CrossRefGoogle Scholar
  19. 19.
    Mirzaee H (2009) Long-term prediction of chaotic time series with multi-step prediction horizons by a neural network with Levenberg-Marquardt learning algorithm. Chaos Solitons Fractals 41(4):1975–1979CrossRefGoogle Scholar
  20. 20.
    Ko C-N (2012) Identification of chaotic system using fuzzy neural networks with time-varying learning algorithm. Int J Fuzzy Syst 14(4):540–548Google Scholar
  21. 21.
    Lin Y-Y, Chang J-Y, Lin C-T (2013) Identification and prediction of dynamic systems using an interactively recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 24(2):310–321CrossRefGoogle Scholar
  22. 22.
    Oliver N, Soriano M-C, Sukow D-W, Fischer I (2013) Fast random bit generation using a chaotic laser: approaching the information theoretic limit. IEEE J Quantum Electron 49(11):910–918CrossRefGoogle Scholar
  23. 23.
    Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366CrossRefzbMATHGoogle Scholar
  24. 24.
    Lera G, Pinzolas M (2002) Neighborhood based Levenberg–Marquardt algorithm for neural network training. IEEE Trans Neural Netw 13(5):1200–1203CrossRefGoogle Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2019

Authors and Affiliations

  • Seungwon Lee
    • 1
  • Sung Hwan Won
    • 2
  • Iickho Song
    • 1
  • Seokho Yoon
    • 3
  • Sun Yong Kim
    • 4
    Email author
  1. 1.School of Electrical EngineeringKorea Advanced Institute of Science and TechnologyDaejeonSouth Korea
  2. 2.Nokia Bell LabsSeoulSouth Korea
  3. 3.College of Information and Communication EngineeringSungkyunkwan UniversitySuwonSouth Korea
  4. 4.Department of Electronics EngineeringKonkuk UniversitySeoulSouth Korea

Personalised recommendations