Parametric, nonparametric and parametric modelling of a chaotic circuit time series. (English) Zbl 1055.37586

Summary: The determination of a differential equation underlying a measured time series is a frequently arising task in nonlinear time series analysis. In the validation of a proposed model one often faces the dilemma that it is hard to decide whether possible discrepancies between the time series and model output are caused by an inappropriate model or by bad estimates on parameters in a correct type of model, or both. We propose a combination of parametric modelling based on Bock’s multiple shooting algorithm and nonparametric modelling based on optimal transformations as a strategy to test proposed models and if rejected suggest and test new ones. We exemplify this strategy on an experimental time series from a chaotic circuit where we obtain an extremely accurate reconstruction of the observed attractor.


37M10 Time series analysis of dynamical systems
Full Text: DOI arXiv


[1] Crutchfield, J.; McNamara, B., Complex systems, 1, 417, (1987)
[2] J. Elder, D. Pregibon, in: U. Fayad et al. (Eds.), Advances in Knowledge Discovery and Data Mining, AAAI Press, Menlo Park, California, 1996.
[3] Packard, N.; Crutchfield, J.; Farmer, D.; Shaw, R., Phys. rev. lett., 45, 712, (1980)
[4] Cremers, J.; Hübler, A., Z. naturforsch., 42a, 797, (1987)
[5] Gouesbet, G., Ann. acad. sci. (NY), 808, 25, (1996)
[6] Hegger, R., Chaos, 8, 727, (1998)
[7] Irving, A.; Dewson, T., Physica D, 102, 15, (1997)
[8] Rulkov, N.; Tsimring, L.; Abarbanel, H., Phys. rev. E, 50, 314, (1994)
[9] Weiss, C., Appl. phys. B, 61, 223, (1995)
[10] H. Bock, in: K. Ebert, P. Deuflhard, W. Jäger (Eds.), Modelling of Chemical Reaction Systems, Springer, Berlin, 1981, vol. 18, Chap. 8, pp. 102-125.
[11] H. Bock, in: P. Deuflhard, E. Hairer (Eds.), Progress in Scientific Computing, Birkhäuser, Boston, 1983, vol. 2, pp. 95-121.
[12] Breiman, L.; Friedman, J., J. am. stat. assoc., 80, 580, (1985)
[13] W. Härdle, Applied Nonparametric Regression, Cambridge Univ. Press, Cambridge, 1989.
[14] Voss, H.; Kurths, J., Phys. lett. A, 234, 336, (1997)
[15] Rulkov, N., Int. J. bifurc. chaos, 2, 669, (1992)
[16] Edsberg, L.; Wedin, P., Opt. meth. software, 6, 193, (1995)
[17] Schittkowski, K., Num. math., 68, 129, (1994)
[18] W. Press, B. Flannery, S. Saul, W. Vetterling, Numerical Recipes, Cambridge Univ. Press, Cambridge, 1992. · Zbl 0778.65003
[19] Richter, O.; Nörtersheuser, P.; Pestemer, W., Science total env., 123/124, 435, (1992)
[20] Timmer, J.; Müller, T.; Melzer, W., Biophys. J., 74, 1694, (1998)
[21] J. Timmer et al., in: P.M.D.S. Broomhead, E.A. Luchinskaya, T. Mullin (Eds.), Stochaos: Stochastic and Chaotic Dynamics in the Lakes, American Institute of Physics, Melville, NY, USA, 2000, pp. 617-623.
[22] Baake, E.; Baake, M.; Bock, H.; Briggs, K., Phys. rev. A, 45, 5524, (1992)
[23] Timmer, J., Int. J. bifurc. chaos, 8, 1505, (1998)
[24] Baake, E.; Schlöder, J., Bull. math. biol., 54, 999, (1992)
[25] Gebelein, H., Z. angew. math. mech., 21, 364, (1941)
[26] Hirschfeld, H., Proc. camb. phil. soc., 31, 520, (1935)
[27] A. Rényi, Probability Theory, Akadémiai Kiadó, Budapest, 1970.
[28] Voss, H.; Bünner, M.; Abel, M., Phys. rev. E, 57, 2820, (1998)
[29] Voss, H.; Schwache, A.; Kurths, J.; Mitschke, F., Phys. lett. A, 256, 47, (1999)
[30] Voss, H.; Kolodner, P.; Abel, M.; Kurths, J., Phys. rev. lett., 83, 3422, (1999)
[31] L. Smith, http://y2k.maths.ox.ac.uk/systems/egbanalysis.html#psd, Y2K Benchmarks of Predictability, 2000.
[32] H. Kantz, T. Schreiber, Nonlinear Time Series Analysis, Cambridge Univ. Press, Cambridge, 1997. · Zbl 0873.62085
[33] F. Takens, in: D. Rand, L. Young (Eds.), Dynamical Systems and Turbulence, vol. 898 of Lecture Notes in Mathematics, Springer, Berlin, 1981, pp. 366-381.
[34] Kirchhoff, G., Poggendorfs ann. phys. chem., 64, 513, (1845)
[35] F. Moon, Chaotic Vibrations: An Introduction for Applied Scientists and Engineers, Wiley, New York, 1987. · Zbl 0745.58003
[36] T. Creighton, Protein Folding, Freeman, New York, 1992.
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.