The prediction of behaviours of chaotic dynamical systems in 3D state space

  • M. Pankiewicz
  • R. Mosdorf


In the paper a new three-dimensional visualization technique of results of methods of prediction of chaotic time series has been analyzed. The influence of graphical presentation of attractors on the quality of forecasting results has been tested. The following methods of prediction of behaviours of chaotic dynamical systems have been considered: method of analogs, centre-of-mass-prediction method and local linear prediction method. The forecasting quality has been evaluated with using the error function and the correlation coefficient. It has been shown that 3D visualization of attractor is a necessary condition for obtaining the proper result of forecasting with using the deterministic chaos methods.


deterministic chaos forecasting method of analogs center-of-mass-prediction local linear prediction method 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

6 References

  1. [1]
    Box G. E. P., Jenkis G. M., „Analiza szeregów czasowych i prognozowanie, Wydawnictwo Naukowe PWN, Warszawa 1983.Google Scholar
  2. [2]
    Schuster H.G., Chaos deterministyczny — wprowadzenie, Wydawnictwo Naukowe PWN, Warszawa 1993.Google Scholar
  3. [3]
    Mosdorf R., Shoji M., Chaos in bubbling — nonlinear analysis and modeling, Chemical Engineering Science 58, 3837–3846, 2003.CrossRefGoogle Scholar
  4. [4]
    Singh S., Multiple forecasting using local approximation, Pattern Recognition, 34, 443–445, 2001.zbMATHCrossRefGoogle Scholar
  5. [5]
    Reick Ch. H., Page B., Time series prediction by multivariate next neighbor methods with application to zooplankton forecasts, Mathematics and Computers in simulation 52, 289–310, 2000.CrossRefGoogle Scholar
  6. [6]
    Baker G.L., Gollub J.P., Wstęp do dynamiki układów chaotycznych, Wydawnictwo Naukowe PWN, Warszawa, 1998.Google Scholar
  7. [7]
    Abarbanel H. D. I., Brown R., Sidorowich J. J., Tsimring L. S., The analysis of observed chaotic data in physical system, Reviews of Modern Physics, 65(4), 1331–1392, October 1993.MathSciNetCrossRefGoogle Scholar
  8. [8]
    Little S., Ellner S., Pascual M., Kaplan D., Sauer T., Caswell H., Solow A., Detecting nonlinear dynamics in spatio-temporal systems, examples from ecological models, Physica D 96, 321–333, 1996.CrossRefGoogle Scholar
  9. [9]
    Sidorowich J.J., Farmer J.D., Predicting chaotic time series, Physical Review Letters, 59(8), 1987.Google Scholar
  10. [10]
    Żmijkowska M., Wykorzystanie analizy fraktalnej w prognozowaniu. Praca magisterska, Politechnika Białostocka, 2003.Google Scholar
  11. [11]
    Sidorowich J.J., Farmer J.D., Predicting chaotic time series, Physical Review Letters, 59(8), 845–848, 1987.MathSciNetCrossRefGoogle Scholar
  12. [12]
    Hyrskykari A., Development of Program Visualization Systems, 2nd Czech British Symposium of Visual Aspects of Man-Machine, Systems, Praha, 1993.Google Scholar
  13. [13]
    Szmal P., Francik J., Nowak M., Systemy wizualizacji algorytmów wspomagające badania naukowe, III Konferencja Komputery w badaniach naukowych KOWBAN, 317–322, Polanica Zdrój, 1996.Google Scholar
  14. [14]
    Peters E.E., Teoria chaosu a rynki kapitałowe, WIG-Press, Warszawa 1997.Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • M. Pankiewicz
    • 1
  • R. Mosdorf
    • 1
  1. 1.Faculty of EngineeringThe University of Finance and Management in BiałystokElkPoland

Personalised recommendations