• DocumentCode
    510197
  • Title

    The Chaotic Neural Network is Used to Predict the Sea Clutter Signal

  • Author

    Shen, Yan ; Li, Guoqiang

  • Author_Institution
    Coll. of Sci., Harbin Eng. Univ., Harbin, China
  • Volume
    3
  • fYear
    2009
  • fDate
    7-8 Nov. 2009
  • Firstpage
    25
  • Lastpage
    30
  • Abstract
    The study includes the correlation dimension and the largest Lyapunov exponent of sea clutter based on real radar data obtained with IPIX X-band polarimetric coherent radar, which proved that sea clutter has chaotic characteristics. A method of prediction about sea clutter signal based on chaotic neural network and theory of phase-space reconstruction is established, which has a in-depth analysis of the chaotic neural network and modulates the network parameters to improve the convergence rate of the network. The numerical results of prediction model demonstrate that chaotic neural network is better than traditional methods.
  • Keywords
    Lyapunov methods; chaos; convergence; correlation methods; neural nets; phase space methods; prediction theory; radar clutter; radar signal processing; IPIX X-band polarimetric coherent radar; Lyapunov exponent; chaotic characteristics; chaotic neural network; convergence rate; correlation dimension; in-depth analysis; network parameters; phase-space reconstruction; prediction model; radar data; sea clutter signal; Artificial intelligence; Chaos; Computational intelligence; Educational institutions; Hopfield neural networks; Neural networks; Neurons; Predictive models; Radar clutter; Radar polarimetry; Lyapunov exponen; chaotic neural network; minimum embedding dimension; sea clutter; time delay;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Artificial Intelligence and Computational Intelligence, 2009. AICI '09. International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-3835-8
  • Electronic_ISBN
    978-0-7695-3816-7
  • Type

    conf

  • DOI
    10.1109/AICI.2009.270
  • Filename
    5376501