Abstract:
The standard discrete-time autoregressive model is poorly suited for modeling series obtained by sampling continuous-time processes at fairly rapid rates. Large computati...Show MoreMetadata
Abstract:
The standard discrete-time autoregressive model is poorly suited for modeling series obtained by sampling continuous-time processes at fairly rapid rates. Large computational errors can occur when the Levinson algorithm is used to estimate the parameters of this model, because the Toeplitz covariance matrix is ill-suited for inversion. An alternative model is developed based on an incremental difference operator, rather than the shift operator. It is shown that, as the sampling period goes to zero, unlike the standard autoregressive parameters, the coefficients of this model converge to certain parameters that depend directly on the statistics of the continuous-time process. A Levinson-type algorithm for efficiently estimating the parameters of this model is derived. Numerical examples are given to show that when the sampling interval is small this algorithm is considerably less sensitivity to arithmetic roundoff errors than the Levinson algorithm.<>
Published in: IEEE Transactions on Automatic Control ( Volume: 36, Issue: 3, March 1991)
DOI: 10.1109/9.73564
References is not available for this document.
Select All
1.
R. C. Agarwall and C. S. Burrus, "New recursive digital filter structures having very low sensitivity and roundoff noise", IEEE Trans. Circuits Syst., vol. CAS-22, pp. 921-927, Dec. 1975.
2.
G. Cybenko, "The numerical stability of the Levinson-Durbin algorithm for Toeplitz systems of equations", SIAM J. Sci. Statist. Comput., vol. J, no. 3, pp. 303-319, Sept. 1980.
3.
P. Dewilde, A. C. Vieira and T. Kailath, "On a generalized Szego-Levinson realization algorithm for optimal linear predictors based on a network synthesis approach", IEEE Trans. Circuits Syst., vol. CAS-25, no. 9, pp. 663-675, Sept. 1978.
4.
T. Kailath, B.C. Levy, L. Ljung and M. Morf, "Fast tiine-invariant implementations of Gaussian signal detectors", IEEE Trans. Informat. Theory, vol. IT 24, no. 4, pp. 469-477, July 1978.
5.
T. Kailath, A. Vieira and M. Morf, "Inverses of Toeplitz operators innovations and orthogonal polynomials", SIAM J. Review, vol. 20, no. 1, pp. 106, Jan. 1978.
6.
J. le Roux and C. Gueguen, "A fixed point computation of partial correlation coefficients", IEEE Trans. Acoust. Speech Signal Processing, vol. ASSP-25, no. 3, pp. 257-259, June 1977.
7.
D. G. Messerschmitt, "A class of generalized lattice filters", IEEE Trans. Acoust. Speech. Signal Processing, vol. ASSP-28, pp. 198-204, Apr. 1980.
8.
R. H. Middleton and G. C. Goodwin, "Improved finite word length characteristics in digital control using delta operators", IEEE Trans. Automat. Contr., vol. AC-31, pp. 1015-1021, Nov. 1986.
9.
G. Orlandi and G. Martinelli, "Low-sensitivity recursive digital filters obtained via the delav replacement", IEEE Trans. Circuits Syst., vol. CAS-31, pp. 654-656, July 1984.
10.
D. T. Pham and A. le Breton, "Levinson-Durbin type algorithms for continuous time autoregressive models and applications", Math. Contr. Signals Syst., vol. 4, no. 1, pp. 69-79, 1991.
11.
H. V. Poor, An Introduction to Signal Detection and Estimation, New York:Springer-Verlag, 1988.
12.
M. Salgado, R. H. Middleton and G. C. Goodwin, "Connection between continuous and discrete Riccati equations with applications to Kalman filtering", IEE Proc., vol. 135, no. 1, pp. 28-34, Jan. 1988.
13.
G. Szegö, "Orthogonal polynomials" in Amer. Math. Society, RI, Providence:Colloquium Publications, vol. 23, 1975.
14.
D. Williamson, "Delay replacement in direct form structures", IEEE Trans Acoust. Speech Signal Processing, vol. ASSP36, pp. 453-460, Apr. 1988.
15.
A. E. Yagle and B. C. Levy, "The Schur algorithm and its applications", Acta AppUcandae Mathematieae, vol. 3, no. 3, pp. 255-284, May 1985.