The parameter estimation problem of linear systems from input output measurements, corrupted with nonwhite noise of unknown covariance, is considered. Under this realistic situation, the least squares parameters estimation is known to be biased. In this paper, a recursive parameters estimation algorithm, which is unbiased for a wide class of measurement noise, is developed. Monte Carlo simulation results show the effectiveness of the developed parameters' estimator and its superiority over the least squares-based estimator.
Emara-Shabaik, H.E. and Moustafa, K.A.F. , 1994, "Characterization of dynamic system nonlinearities via probabilistic approach," International Journal of Systems Science25(3), 603-611.
Mendel, J.M., 1991, "Tutorial on higher-order statistics (Spectra) in signal processing and system theory: Theoretical results and some applications ," Proceedings of the IEEE79(3), 278-305.
4.
Nickias, C.L. and Mendel J.M., 1993, "Signal processing with higher-order Spectra," IEEE Signal Processing Magazine July, 10-37.
5.
Soderstrom, T. and Stoica, P., 1989, System Identification, Prentice Hall , New York.
