Identification of errors-in-variables systems with nonlinear output observations

This paper concerns the identification problem of errors-in-variables (EIV) systems with nonlinear output observations. Under independent and identically distributed (iid) Gaussian inputs with unknown variance, recursive algorithms for estimating the parameters of the EIV systems are presented. For a large class of nonlinear observations, conditions on the system are imposed to guarantee the almost sure convergence of the estimates. Some simulation examples are included to justify the theoretical results.