AN APPLICATION TO FIR SYSTEM IDENTIFICATION OF THE THIRD- AND FOURTH-ORDER CUMULANTS

We present an algorithm for identification of moving average systems using the third- and fourthorder cumulants of noisy observations. The system is driven by an independent and identically distributed non-Gaussian signal which has an asymmetric probability density function, and the Gaussian measurement noise may be either white or colored. The proposed algorithm is more useful than other linear methods when the characteristic of noise is not known or when the signal-to-noise ratio is low.