Volterra kernels identification using higher order moments for different input signals

This paper deals with a comparison analysis between a couples of Volterra kernels identification algorithms, namely an iterative algorithm (IA) of Tummala (May,1991) and a cubic i.i.d (C.i.i.d) algorithm proposed by Tseng et al. (July, 1995). The input signal is chosen to be an i.i.d. signal. The comparison analysis is performed using a Monte Carlo test showing that the Cubic i.i.d. algorithm is superior in terms of accurate estimation despite the outliers encountered for some input signal realizations. Moreover, the (IA) may handle other type of input signals such as non Gaussian independent input and Gaussian signal.