Nonlinearity recovering in Wiener system driven with correlated signal

The characteristic of the nonlinear part of the Wiener system is estimated. The system is driven by a Gaussian random process which may not be white. Three algorithms are presented, two semirecursive and one of the offline type. Their pointwise convergence in probability is shown and results of numerical simulation are given. Index Terms--Nonparametric identification, nonparametric regression, system identification, Wiener system.