A computationally efficient and interference tolerant nonparametric algorithm for LTI system identification based on higher order cyclostationarity

A new nonparametric algorithm for the identification of linear time-invaria nt systems is proposed, The method is based on the cyclic correlations of t he input and output signals with a nonlinear transformation of the input si gnal. Consequently, although it exploits the higher order cyclostationarity properties of the input and output signals, its computational complexity i s comparable with that of methods based on second-order statistics. The pro posed estimator of the system transfer function is inherently immune to the presence of noise and interference on both input and output signal measure ments and turns out to be asymptotically unbiased and consistent. Moreover, bias and variance of the estimate exhibit a rate of convergence to zero eq ual to that of estimates based on second-order statistics. Finally, simulat ion results show that the proposed algorithm significantly outperforms, in terms of both bias and variance of the estimates, several nonparametric ide ntification algorithms previously presented in the literature.