Blind Nonlinear System Identification Under Gaussian And / Or I.I.D. Excitation Using Genetic Algorithms

The blind identification of a special class of nonlinear system is pursued in this paper. In particular a genetic algorithm is developed for blind identification of quadratic Volterra model excited by an unobservable input signal which can either be a stationary Gaussian process or an i.i.d process. This approach enables a nonlinear relationship between model kernels and output cumulants up to third order. Simulation results are presented to show good performance of this approach.