Advertisement

Data Compression, Dynamics, and Stationarity

  • Matthew B. Kennel
  • Alistair I. Mees
Chapter

Abstract

One of the main themes of this book is the considerable progress that has been made in modeling data from nonlinear systems that may be affected by noise. In this chapter, we describe a modeling method based on an idealization that gives fast algorithms with known properties based on rigorous results from data-compression theory. The idealization is that the system outputs symbols from a finite alphabet, rather than outputting a real number; we also make a reasonable assumption which is the discrete analogue of the standard embedding theorem. The models that result can be used to simulate and to estimate many of the usual dynamically interesting quantities such as topological entropy. They are also well-suited for a specific new application: testing the stationarity of time-series of discrete symbols, whether two data streams appear to originate from the same underlying unknown dynamical system.

Keywords

Data Compression Strange Attractor Code Length Topological Entropy Chaotic Time Series 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    H. D. I. Abarbanel. Analysis of Observed Chaotic Data. Institute for Nonlinear Science. Springer, New York, 1996.MATHCrossRefGoogle Scholar
  2. [2]
    R. Brown, V. In, and E.R. Tracy. Parameter uncertainties in models of equivariant dynamical systems. Physica D, 102 (3–4): 208–226, 1997.MathSciNetMATHCrossRefGoogle Scholar
  3. [3]
    M. Casdagli. Nonlinear prediction of chaotic time series. Physica D, 35 (3): 335–356, 1989.MathSciNetMATHCrossRefGoogle Scholar
  4. [4]
    T. Cover and J. Thomas. Elements of Information Theory. Wiley Interscience, New York, 1991.MATHCrossRefGoogle Scholar
  5. [5]
    C S Daw, M B Kennel, C E A Finney, and F T Connolly. Observing and modeling nonlinear dynamics in an internal combustion engine. Phys. Rev. E, 57 (3-A): 2811–2819, 1998.CrossRefGoogle Scholar
  6. [6]
    C.S. Daw, Finney C.E.A., Vasudevan M., N.A. van Goor, K. Nguyen, D.D. Bruns, E.J. Kostelich, C. Grebogi, Ott E., and J.A. Yorke. Self-organization and chaos in a fluidized bed. Phys. Rev. Lett, (75): 2308–2311, 1995.Google Scholar
  7. [7]
    J. D. Farmer and J. J. Sidorowich. Predicting chaotic time series. Phys. Rev. Letters, 59 (8): 845–848, 1987.MathSciNetMATHCrossRefGoogle Scholar
  8. [8]
    A. Fraser. Information and entropy in strange attractors. IEEE Trans. Information Theory, 35: 245–262, 1989.MathSciNetMATHCrossRefGoogle Scholar
  9. [9]
    A. M. Fraser and H. L. Swinney. Independent coordinates for strange attractors from mutual information. Physical Review A, 33 (2): 1134–1140, 1986.MathSciNetMATHCrossRefGoogle Scholar
  10. [10]
    G. Froyland, K. Judd, A. I. Mees, K. Murao, and D. Watson. Constructing invariant measures from data. International Journal of Bifurcation and Chaos, 5 (4): 1181–1192, 1995.MATHCrossRefGoogle Scholar
  11. [11]
    D.E. Harrison and N.K. Larkin. Darwin sea level pressure, 1876–1996: evidence for climate change? Geophys. Res. Lett, 24: 1779–1782, 1997.CrossRefGoogle Scholar
  12. [12]
    K. Judd and A. I. Mees. On selecting models for nonlinear time series. Physica D, 82: 426–444, 1995.MATHCrossRefGoogle Scholar
  13. [13]
    K. Judd and A. I. Mees. Embedding as a modeling problem. Physics D, 120: 273–286, 1998.MATHCrossRefGoogle Scholar
  14. [14]
    M. B. Kennel, R. Brown, and H. D. I. Abarbanel. Determining embedding dimension for phase-space reconstruction using a geometrical construction. Physical Review A, 45 (6): 3403–3411, 1992.CrossRefGoogle Scholar
  15. [15]
    M.B. Kennel. Statistical test for dynamical nonstationarity in observed time-series data. Phys. Rev. E, 78: 316, 1997.CrossRefGoogle Scholar
  16. [16]
    M. Li and P.M.B. Vitanyi. An Introduction to Kolmogorov Complexity and its Applications. Springer, New York, 2nd edition, 1997.MATHGoogle Scholar
  17. [17]
    D. Lind and B. Marcus. Symbolic Dynamics and Coding. Cambridge University Press, 1995.Google Scholar
  18. [18]
    E.N. Lorenz. Talus, 36A:98–110, 1984. The model is dx/dt = -y 2 - z 2 - a(x - F), dy/dt = xy - bxz - y+ 1, dzidt = bxy + xz - z, a = 1/4, b = 4, F = 8. Each set was 5000 points long sampled every öt = 0. 08.Google Scholar
  19. [19]
    A. I. Mees. Modelling complex systems. In T. Vincent, A. I. Mees, and L. S. Jennings, editors, Dynamics of Complex Interconnected Biological Systems, volume 6 of Mathematical Modeling, pages 104–124. Birkhauser, Boston, 1990.CrossRefGoogle Scholar
  20. [20]
    A. I. Mees. Dynamical systems and tesselations: Detecting determinism in data. International Journal of Bifurcation and Chaos, 1(4): 777–794, 1991.MathSciNetMATHCrossRefGoogle Scholar
  21. [21]
    A. I. Mees. Parsimonious dynamical reconstruction. International Journal of Bifurcation and Chaos, 3 (3): 669–675, 1993.MathSciNetMATHCrossRefGoogle Scholar
  22. [22]
    B. Pilgram, K. Judd, and A. I. Mees. Modelling the dynamics of nonlinear time series using canonical variate analysis. Physica D, in press, 2000.Google Scholar
  23. [23]
    J. Rissanen. Universal coding, information, prediction and estimation. IEEE ‘flans. Inf. Theory, IT-30(4): 629–636, 1984.MathSciNetMATHCrossRefGoogle Scholar
  24. [24]
    J. Rissanen. Stochastic Complexity in Statistical Inquiry, volume 15 of Series in Computer Science. World Scientific, Singapore, 1989.Google Scholar
  25. [25]
    T. Schreiber. Detecting and analyzing nonstationarity in a time series using nonlinear cross predictions. Phys. Rev. Lett., 78: 843, 1997.CrossRefGoogle Scholar
  26. [26]
    Y.M. Shtarkov, T.J. Tjalkens, and F.M.J. Willems. Multialphabet weighting universal coding of context tree sources. Problems of Information Transmission, 33 (1): 17–28, 1997.MathSciNetGoogle Scholar
  27. [27]
    J. Stark, D.S. Broomhead, M.E. Davies, and J. Huke. Takens embedding theorems for forced and stochastic systems. Nonlinear Analysis, 30: 5303–5314, 1997.MathSciNetCrossRefGoogle Scholar
  28. [28]
    G. Sugihara and R. M. May. Nonlinear forecasting as a way of distinguishing chaos from measurement error in time series. Nature, 344: 734–741, 1990.CrossRefGoogle Scholar
  29. [29]
    F. Takens. Detecting strange attractors in turbulence. In D. A. Rand and L. S. Young, editors, Dynamical Systems and Turbulence, volume 898 of Lecture Notes in Mathematics, pages 365–381. Springer, Berlin, 1981.Google Scholar
  30. [30]
    X.Z. Tang, E.R. Tracy, Boozer A.D., A. deBrauw, and R. Brown. Symbol sequence statistics in noisy chaotic signal reconstruction. Phys. Rev. E, 51: 3871, 1995.CrossRefGoogle Scholar
  31. [31]
    K.E. Trenberth and T.J. Hoar. The 1990–1995 el nino-southern oscillation event: longest on record. Geophys. Res. Lett, 23: 57–60, 1996.CrossRefGoogle Scholar
  32. [32]
    A. S. Weigend, B. A. Huberman, and D. E. Rumelhart. Predicting the future: A connectionist approach. International Journal of Neural Systems, Vol 1 (No 3): 193–209, 1990.CrossRefGoogle Scholar
  33. [33]
    F.M.J. Willems. The context tree weighting method: Extensions. IEEE Trans IT, 44 (2): 792–798, 1998.MathSciNetMATHCrossRefGoogle Scholar
  34. [34]
    F.M.J. Willems, Y.M. Shtarkov, and T.J. Tjalkens. The context tree weighting method: Basic properties. IEEE Trans IT, 41 (2): 653–664, 1995.MathSciNetMATHCrossRefGoogle Scholar
  35. [35]
    A. Witt, J. Kurths, and A. Pikovsky. Testing stationarity in time series. Phys. Rev. E, 58: 1800, 1998.CrossRefGoogle Scholar
  36. [36]
    L.-S. Young. Entropy, Lyapunov exponents, and Hausdorff dimension in differentiable dynamical systems. IEEE Transactions on Circuits and Systems, CAS-30(8): 599–607, 1983.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2001

Authors and Affiliations

  • Matthew B. Kennel
  • Alistair I. Mees

There are no affiliations available

Personalised recommendations