A NEW CUMULANT-BASED PARAMETER-ESTIMATION METHOD FOR NONCAUSAL AUTOREGRESSIVE SYSTEMS

This correspondence proposes a new nonlinear parameter estimation meth od for a noncausal autoregressive (AR) system based on a new quadratic equation relating the unknown AR parameters to higher order (greater- than-or-equal-to 3) cumulants of nonGaussian output measurements in th e presence of additive Gaussian noise. A gradient-type numerical optim ization algorithm is used to search for the optimal AR parameter estim ates. It is applicable regardless of whether or not the order of the s ystem is known in advance; it is also applicable for the case of the c ausal AR system. Some simulation results are offered to justify that t he proposed method is effective.