Alpha stable distribution, a generalization of Gaussian, is better for modeling impulsive noises than Gaussian distribution in signal processing. This class of process has no close form of probability density function and finite second order moments. In this paper, a new adaptive generalized recursive least p-norm filtering algorithm is proposed based on SSG noise model. The simulation experiments show that the proposed new algorithm is more robust than the conventional algorithm.
[1] Nikias C L and Shao M. Signal Processing with Alpha-Stable Distributions and Applications. New York: John Wiley Sons Inc., 1995: 2-45. [2] Nikias C L and Shao M. Signal processing with fractional lower order moments: Stable processes and their applications[J].Proc. IEEE.1993, 81(7):986- [3] Samorodnitsky G and Taqqu M S. Stable Non-Gaussian Random Process: Stochastic Models with Infinite Variance. New York: Chapman and Hall, 1994: 102-145. [4] Brcich R and Zoubir A. Estimation and detection in a mixture of symmetric alpha stable and Gaussian interference. Higher-Order Statistics, Proceedings of the IEEE Signal Processing Workshop on. 1999: 219-223. [5] Ilow J, Hatzinakos D and Venetsanopoulos A N. Performance of FH SS radio networks with interference modeled as a mixture of Gaussian and alpha-stable noise[J].IEEE Trans. on Communications.1998, 46(4):509- [6] Kuruoglu E E, Peter J W, and William J F. Least lp-norm estimation of autoregressive model coefficients of symmetric -stable processes. IEEE Signal Processing Letters, 1997, 4(7): 402-412. [7] Bodenschatz J S and Nikias C L. Symmetric alpha-stable filter theory[J].IEEE Trans. on Signal Processing.1997, 45(5):2301- [8] Yarlagadda R, Bednar J, and Watt T. Fast algorithms for lp deconvolution[J].IEEE Trans. on Acoust. Speech Signal Process.1985, 33(4):174- [9] Todd K. Moon and Wynn C. Stirling. Mathematical methods and algorithms for signal processing. Upper Saddle River, NJ: Prentice Hall, 2000: 120-131. [10] Haykin S. Adaptive Filter Theory. 3rd ed. Englewood Cliffs, N.J.: Prentice-Hall, 1996: 140-151. [11] Zou Y S, Chan C, and Ng T S. A Recursive Least M-estimate (RLM) adaptive filter for robust filtering in impulsive noise[J].IEEE Signal Processing Letters.2000, 7(6):324- [12] Weng J F and Leung S H. Adaptive nonlinear RLS algorithm for robust filtering in impulse noise. Proc. IEEE Int. Symp. Circuits Syst., 1997, vol. 4: 2337-2340. [13] 邱天爽等. 统计信号处理非高斯信号处理及其应用. 北京: 电子工业出版社, 2004.