×

zbMATH — the first resource for mathematics

On selecting models for nonlinear time series. (English) Zbl 0888.58034
Summary: Constructing models from time series with nontrivial dynamics involves the problem of how to choose the best model from within a class of models, or to choose between competing classes. This paper discusses a method of building nonlinear models of possibly chaotic systems from data, while maintaining good robustness against noise. The models that are built are close to the simplest possible according to a description length criterion. The method will deliver a linear model if that has shorter description length than a nonlinear model. We show how our models can be used for prediction, smoothing and interpolation in the usual way. We also show how to apply the results to identification of chaos by detecting the presence of homoclinic orbits directly from time series.

MSC:
37D45 Strange attractors, chaotic dynamics of systems with hyperbolic behavior
37N99 Applications of dynamical systems
PDF BibTeX XML Cite
Full Text: DOI
References:
[1] Abarbanel, H.D.I.; Kennel, M.B., Local false nearest neighbors and dynamical dimensions from observed chaotic data, () · Zbl 0802.58041
[2] Albano, A.M.; Muench, J.; Schwartz, C.; Mees, A.I.; Rapp, P.E., Singular value decomposition and the grassberger-procaccia algorithm, Phys. rev. A, 38, 3017-3026, (1988)
[3] Barron, A.R., Universal approximation bounds for superpositions of a sigmoidal function, IEEE transactions on information theory, 39, 930-945, (1993) · Zbl 0818.68126
[4] Chen, S.; Cowan, C.F.N.; Grant, P.M., Orthogonal least squares learning algorithm for radial basis function networks, IEEE transactions on neural networks, 2, 302-309, (1991)
[5] Garey, M.R.; Johnson, D.S., Computers and intractability: A guide to the theory of NP-completeness, (1979), Freeman San Francisco · Zbl 0411.68039
[6] Ghaddar, D.K.; Tong, H., Data transformation and self-exciting threshold autoregression, J.R. stat. soc. C, 30, 238-248, (1981)
[7] Glendinning, P.; Sparrow, C.T., Local and global behavior near homoclinic orbits, J. stat. phys., 35, 645-697, (1983) · Zbl 0588.58041
[8] Glover, J.; Mees, A.I., Reconstructing the dynamics of Chua’s circuit, J. circuits syst. comput., 3, 201-214, (1992)
[9] Goldie, C.M.; Pinch, R.G.E., ()
[10] Kline, M., Mathematical thought from ancient to modern times, (1972), Oxford Univ. Press New York · Zbl 0277.01001
[11] LeBaron, B., Persistence of the dow Jones index on rising volume, ()
[12] Leonard, J.A.; Kramer, M.A., Radial basis function networks for classifying process faults, (), 281-294
[13] Mees, A.I., Dynamical systems and tesselations: detecting determinism in data, Int. J. bifurcation and chaos, 1, 777-794, (1991) · Zbl 0876.58045
[14] Mees, A.I., Parsimonious dynamical reconstruction, Int. J. bifurcation and chaos, 3, 669-675, (1993) · Zbl 0875.62426
[15] Mees, A.I., Reconstructing chaotic systems in the presence of noise, (), 305-321
[16] Mees, A.I.; Smith, R.K., Estimation and reconstruction in noisy chaotic systems, (1995), in preparation
[17] Mees, A.I.; Sparrow, C.T., Some tools for analyzing chaos, (), 1058-1070
[18] Murty, K., A fundamental problem in linear inequalities with an application to tsp, Math. prog., 2, 296-308, (1972) · Zbl 0249.90038
[19] Noakes, L., The Takens embedding theorem, Int. J. bifurcation and chaos, 1, 867-872, (1991) · Zbl 0874.58075
[20] Rissanen, J., ()
[21] Sauer, T.; Yorke, J.A.; Casdagli, M., Embedology, J. stat. phys., 65, 579-616, (1992) · Zbl 0943.37506
[22] Schwarz, G., Estimating the dimension of a model, Ann. stat., 6, 461-464, (1978) · Zbl 0379.62005
[23] Takens, F., Detecting strange attractors in turbulence, (), 365-381
[24] Tong, H., Nonlinear time series: a dynamical systems approach, (1990), Oxford Univ. Press Oxford
[25] Whittle, P., Optimization under constraints, (1971), Wiley Chichester · Zbl 0218.90041
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.