FAST ADAPTIVE ALGORITHMS FOR AR PARAMETERS ESTIMATION USING HIGHER-ORDER STATISTICS

With the rapid availability of vast and inexpensive computation power, models which are non-Gaussian even nonstationary are being investigat ed at increasing intensity. Statistical tools used in such investigati ons usually involve higher order statistics (HOS). The classical instr umental variable (IV) principle has been widely used to develop adapti ve algorithms for the estimation of ARMA processes, Despite, the great number of IV methods developed in the literature, the cumulant-based procedures for pure autoregressive (AR) processes are almost nonexiste nt, except lattice versions of TV algorithms, This paper deals with th e derivation and the properties of fast transversal algorithms. Hence, by establishing a relationship between classical (IV) methods acid cu mulant-based AR estimation problems, new fast adaptive algorithms, (fa st transversal recursive instrumental variabie-FTRIV) and (generalized least mean squares-GLMS), are proposed for the estimation of AR proce sses. The algorithms are seen to have better performance in terms of c onvergence speed and misadjustment even in low SNR. The extra computat ional complexity is negligible, The performance of the algorithms, as well as some illustrative tracking comparisons with the existing adapt ive ones in the literature, are verified via simulations. The conditio ns of convergence are investigated for the GLMS.