Multiscale Bayesian Estimation and Data Rectification

  • Sridhar Ungarala
  • Bhavik R. Bakshi
Part of the Computational Imaging and Vision book series (CIVI, volume 19)


Most measured data contain features localized at multiple scales in time and frequency. Multiscale approaches to state estimation and data rectification offer attractive alternatives to traditional single scale methods by exploiting the ability of wavelets to approximately decorrelate many autocorrelated stochastic processes and extract deterministic features in a signal. This chapter describes several important features of the framework, (a) a Bayesian approach for efficiently fusing prior information with measured data subject to process model constraints, (b) the ability of wavelets to extract temporal dynamics in scale leading to efficient rectification methods for processes lacking accurate models, (c) multiscale linear models to describe the time—scale localized evolution of the system leading to adaptive estimation in time and scale and (d) parallelizable and computationally efficient algorithms. Most existing single scale methods as well their multiscale analogues are shown to be special cases of the general multiscale Bayesian approach.


Fine Scale Wavelet Coefficient Data Rectification Coarse Scale Single Scale 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Bakshi, B. R. (1998). Multiscale PCA with application to multivariate statistical process monitoring. AIChE J., 44:1596.CrossRefGoogle Scholar
  2. Bakshi, B. R., Nounou, M. N., Goel, P. K., and Shen, X. (2001). Multiscale Bayesian rectification of data from linear steady-state and dynamic systems without accurate models. Ind. Eng. Chem. Res., 40:261–274.CrossRefGoogle Scholar
  3. Benveniste, A., Nikoukhah, R., and Willsky, A. S. (1994). Multiscale system theory. IEEE Trans. Circuit Systems-I: Fundamental Theory Appl., 41:2–14.MathSciNetzbMATHCrossRefGoogle Scholar
  4. Berger, J. O. (1985). Statistical Decision Theory and Bayesian Analysis. Springer-Verlag, New York.zbMATHCrossRefGoogle Scholar
  5. Beylkin, G., Coifman, R., and Rokhlin, V. (1991). Wavelet transforms and numerical algorithms I. Comm. Pure Appl. Math., XLIV:141.Google Scholar
  6. Briggs, W. L. (1987). A Multigrid Tutorial. SIAM, Philadelphia.zbMATHGoogle Scholar
  7. Chen, B., Chung, Y., and Huang, D. (1999a). A wavelet time-scale deconvolution filter design for nonstationary signal transmission systerns through a multipath fading channel. IEEE Trans. Signal Proc., 47:1441.CrossRefGoogle Scholar
  8. Chen, S. S. B., Donoho, D. L., and Saunders, M. A. (1999b). Atomic decomposition of basis pursuit. SIAM J. Sci. Comp., 20:23.MathSciNetGoogle Scholar
  9. Chou, K. C., Golden, S. A., and Willsky, A. S. (1993). Multiscale stochastic models, data fusion and wavelet transforms. Signal Processing, 34:257–282.zbMATHCrossRefGoogle Scholar
  10. Chou, K. C., Willsky, A. S., and Benveniste, A. (1994). Multiscale recursive estimation, data fusion, and regularization. IEEE Trans. Auto. Control, 39:464.MathSciNetzbMATHCrossRefGoogle Scholar
  11. Claus, B. (1993). Multiscale statistical signal processing: Identification of a multiscale AR signal from a sample of an ordinary signal. IEEE Trans. Signal Proc., 41:3266–3274.zbMATHCrossRefGoogle Scholar
  12. Donoho, D. L., Johnstone, I. M., Kerkyacharian, G., and Picard, D. (1995). Wavelet s hr inkag e: As ymp topia. J. Royal Stat. Soc. Ser B, 57:41.MathSciNetGoogle Scholar
  13. Friedman, J. H. and Stuetzle, W. (1989). Projection pursuit regression. J.Amer. Stat. Assoc., 76:817.MathSciNetCrossRefGoogle Scholar
  14. Harris, T. J. and Ross, W. H. (1991). Statistical process control procedures for correlated observations. Can. J. Che. Eng., 69:48.CrossRefGoogle Scholar
  15. Hirchoren, G. A. and D’Attellis, C. E. (1999). Estimation of fractional brownian motion with multiresolution Kalman filter banks. IEEE Trans. Signal Proc., 47:1431.MathSciNetzbMATHCrossRefGoogle Scholar
  16. Ho, Y. C. and Lee, R. C. K. (1964). A bayesian approach to problems in stochastic estimation and control. IEEE Trans. Auto. Control, 9:333–339.MathSciNetCrossRefGoogle Scholar
  17. Jazwinski, A. H. (1970). Stochastic Processes and Filtering Theory. Academic Press, New York.zbMATHGoogle Scholar
  18. Johnston, L. P. M. and Kramer, M. A. (1994). Probability density estimation using elliptical basis function networks. AIChE J., 40:1639.CrossRefGoogle Scholar
  19. Johnston, L. P. M. and Kramer, M. A. (1995). Maximum likelihood data rectification: Steady-state systems. AIChE J., 41:2415.CrossRefGoogle Scholar
  20. Ku, W., Storer, R. H., and Georgakis, C. (1995). Disturbance detection and isolation by dynamic principal component analysis. Chem. Intell. Lab. Syst., 30:179.CrossRefGoogle Scholar
  21. Lewis, T. O. and Odell, P. L. (1971). Estimation in Linear Models. Prentice-Hall, Englewood Cliffs, NJ.Google Scholar
  22. Mallat, S. G. (1989). A theory of multiresolution signal decompositions: The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intel., 11:764.CrossRefGoogle Scholar
  23. Miller, E. and Willsky, A. S. (1995). A multiscale approach to sensor fusion and the solution of linear inverse problems. A ppl. Comp. Harm. Anal., 2:127.zbMATHCrossRefGoogle Scholar
  24. Narasimhan, S. and Mah, R. S. H. (1988). Generalized likelihood ratios for gross error identification in dynamic processes. AIChE J., 34:1321.MathSciNetCrossRefGoogle Scholar
  25. Nounou, M. N. and Bakshi, B. R. (1999). Online multiscale filtering of random and gross errors without process models. AIChE J., 45:1041.CrossRefGoogle Scholar
  26. Robert, C. P. (1994). The Bayesian Choice: A Decision-Theorectic Motivation. Springer-Verlag, New York.Google Scholar
  27. Romagnoli, J. A., Alvarez, J., and Stephanopoulos, G. (1981). Variable measurement structures for process control. Int. J. Cont., 33:269–289.zbMATHCrossRefGoogle Scholar
  28. Rudin, L. J., Osher, S., and Ratemi, E. (1992). Nonlinear total-variationbased noise removal algorithms. Physica, 60:259.zbMATHGoogle Scholar
  29. Stephanopoulos, G., Karsligil, O., and Dyer, M. S. (1997). Multi-scale modeling, estimation and control of processing systems. Comput. Chem. Eng., 21: S 79 7—S 803.Google Scholar
  30. Stephanopoulos, G., Karsligil, O., and Dyer, M. S. (1998). Multiscale aspects in model predictive control. In Berber, R. and Kravaris, C., editors, Nonlinear Model Based Control, NATO ASI, pages 667–734. Kluwer Academic, The Netherlands.CrossRefGoogle Scholar
  31. Ungarala, S. and Bakshi, B. R. (2000). A multiscale, Bayesian and error-in-variables approach for linear dynamic data rectification. Comp. Chem. Eng., 24:445–451.CrossRefGoogle Scholar
  32. Ungarala, S. and Bakshi, B. R. (2001). Bayesian error-in-variables rectification of data from linear dynamic systems. AIChE J., Submitted.Google Scholar
  33. West, M. and Harrison, J. (1997). Bayesian Forecasting and Dynamic Models. Springer, New York.zbMATHGoogle Scholar
  34. Wornell, G. W. (1990). A Karhunen-Loeve-like expansion for 1/f processes via wavelets. IEEE Trans. Info. Theory, 36:859.CrossRefGoogle Scholar
  35. Wornell, G. W. and Oppenheim, A. V. (1992). Wavelet-based representations for a class of self-similar signals with applications to fractal modulation. IEEE Trans. Info. Theory, 38:785.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2001

Authors and Affiliations

  • Sridhar Ungarala
    • 1
  • Bhavik R. Bakshi
    • 2
  1. 1.Department of Chemical EngineeringCleveland State UniversityClevelandUSA
  2. 2.Department of Chemical EngineeringThe Ohio State UniversityColumbusUSA

Personalised recommendations