On difficulties in identification of simple linear-bilinear time-series models using memetic algorithm

• Autorzy: Maliński Ł.
• Języki publikacji: EN

Abstrakty

EN

The new approach to identification of linear-bilinear time-series models has been recently proposed. It is based on separated identification of linear and bilinear parts of the model and exploits the advantages of Memetic Algorithms Therefore, simple survey tests have been performed for different sets of time-series and some difficulties have been recognized. The results of the tests and possible explanations of problem are presented on following pages.

Słowa kluczowe

EN

memetic algorithm; time series

PL

algorytm memetyczny; szereg czasowy

• Wydawca: Instytut Automatyzacji Procesów Technologicznych i Zintegrowanych Systemów Wytwarzania Politechniki Śląskiej
• Czasopismo: Selected Engineering Problems
• Rocznik: 2012
• Tom: nr 3
• Strony: 129--138

Twórcy

autor

Maliński Ł.

• Institute of Automatic Control, Faculty of Automatic Control Electronics and Computer Science, Silesian University of Technology, Gliwice, Poland

Bibliografia

• 1. C., Granger, A. Andersen. Nonlinear time series modelling Applied Time series analysis, Academic Press, 1978.
• 2. C. Granger, A. Andersen. An introduction to bilinear time series models. Vandenhoeck and Ruprecht, 1978.
• 3. T. Subba Rao. On the Theory of Bilinear Time Series Models. Journal of the Royal Statistical Society, vol. B44, pp. 244-255, 1981.
• 4. B. Quinn. Stationarity and invertibility of simple bilinear models. Stochastic Processes and Their Applications, vol. 12, pp. 225-230, 1982.
• 5. D. Guegan, D. T. Pham. A Note on the Estimation of the Parameters of the Diagonal Bilinear Model by Method of Least Squares. Scandinavian Journal of Statistics, vol. 16, pp. 129-136, 1989.
• 6. J. Gooijger, R. Heuts. Higher order moments of bilinear time series processes with symmetrically distributed errors. Proceedings to Second International Tempere Conference in Statistics, pp. 467-478, 1987.
• 7. J. Lee, J. Mathews. A Stability Condition For Certain Bilinear Systems. Signal Processing, vol. 42, pp. 1871-1973, 1994.
• 8. E. Bielińska, I. Nabagło. A modification of ELS algorithm for bilinear time-series model identification. Zeszyty Naukowe Politechniki Śląskiej: Automatyka, vol. 108, pp. 7-24, 1994 (in Polish).
• 9. A. Brunner, G. Hess. Potential problems in estimating bilinear time-series models. Journal of Economic Dynamics and Control, vol. 19, pp. 663-681, 1995.
• 10. H. Wang. Parameter Estimation and Subset Detection For Separable Lower Triangular Bilinear Models. Journal of Time Series Analysis, vol. 26, pp. 743-757, 2004.
• 11. E Bielińska. Bilinear time series models in signal analysis. Zeszyty Naukowe Politechniki Śląskiej, 2007 (in Polish).
• 12. Ł. Maliński. An Identification Procedure For Elementary Bilinear Time-series Model Based on the Evolutionary Programming. Forum Innowacji Młodych Badaczy (FIMB) – II Ogólnopolskie Seminarium, Łódź, 2011.
• 13. Ł. Maliński. On identification of coefficient of indivertible elementary bilinear timeseries model. Proceedings XIV Symposium: Fundamental Problem Of Power Electronics Electromechanics and Mechatronics PPEEm, 2011, Wisła, Poland.
• 14. E. Bielińska, “Prognozowanie ciągów czasowych”, Wydawnictwo Politechniki Śląskiej, Gliwice 2007 (In Polish).
• 15. Ł. Maliński. An Analysis of Parameters Selection of the Recursive Least Squares Identification Method with Application to a Simple Bilinear Stochastic Model. Advances in System Science, Academic Publishing House EXIT 2010, str. 189-196.
• 16. Ł. Maliński. The Evaluation of Saturation Level for SMSE Cost Function in Identification of Elementary Bilinear Time-Series Model. 17 International Conference on Methods and Models in Automation and Robotics, Międzyzdroje, Poland, 2012
• 17. Ł. Maliński. Memetic Algorithm for identification of linear-bilinear time-series model. XIV International PhD Workshop, Wisła 2012.