A numerically stable fast RLS algorithm for adaptive filtering and prediction based on the UD factorization (original) (raw)

Abstract

The use of UD factorization in adaptive RLS algorithms is interesting for its numeric robustness and because no square-root operations at all are involved. In this correspondence, we describe a square root free fast RLS algorithm based on the UD factorization of the autocorrelation matrix. Numerous finite precision simulations tend to indicate that this algorithm is numerically stable. The algorithm requires O(N) operations, where N is the linear filter order.

Loading...

Loading Preview

Sorry, preview is currently unavailable. You can download the paper by clicking the button above.

References (10)

  1. S. Haykin, Adaptive Filter Theory. Englewood Cliffs, NJ: Prentice Hall, 1991.
  2. J. Lee and V. J. Mathews, "A fast recursive least squares adaptive second-order Volterra filter and its performance analysis," IEEE Trans. Signal Processing, vol. 41, Mar. 1993.
  3. S. T. Alexander and A. L. Ghirnikar, "A method for recursive least squares filtering based upon an inverse QR decomposition," IEEE Trans. Signal Processing, vol. 41, Jan. 1993.
  4. D. T. Slock and T. Kailath, "Numerically stable fast transversal fil- ters for recursive least squares adaptive filtering," IEEE Trans. Signal Processing, vol. 39, no. 1, Jan. 1991.
  5. G. J. Bierman, Factorization Methods for Discrete Sequential Estima- tion. New York: Academic, 1977.
  6. I. K. Proudler, J. G. McWhirter, and T. J. Shepherd, "Computationally efficient QR decomposition approach to least squares adaptive filtering," Proc. Inst. Elect. Eng. F, vol. 138, pp. 341-353, Aug. 1991.
  7. I. K. Proudler, "Fast time-series adaptive-filtering algorithm based on the QRD inverse-updates method," Proc. Inst. Elect. Eng. Vis. Image Signal Process., vol. 141, pp. 325-332, Oct. 1994.
  8. E. Mumolo, M. Scagnol, and A. Carini, "An algorithm for wideband audio coding based on LMS/RLS switched predictors," in Proc. IX Euro. Signal Process. Conf., Rodos, Greece, Sept. 8-11, 1998.
  9. A. Carini, "A novel givens rotation based fast SQR-RLS algorithm," in Proc. VIII Euro. Signal Process. Conf., Trieste, Italy, Sept. 10-13, 1996, pp. 1235-1238.
  10. Algorithms for Adaptive Transform Edge Detection R. Abstract-Edge grayscale digital based on the locations of zero crossings has been investigated. Samples of the image are transformed using the discrete symmetric cosine transform (DSCT) and filtered using truncated time or frequency sampled forms of the Laplacian-of-Gaussian (LOG) filter. This correspondence presents and evaluates adaptive block-based filtering procedures to localize edges based on discrete circular and real transforms. Measures of the signal-to-noise ratio (SNR) and edge localization are provided. Index Terms-Adaptive filters, bandpass filters, discrete transforms, level-crossing problems.