A global-local optimization approach to parameter estimation of RBF-type models
Information Sciences: an International Journal
Hi-index | 0.00 |
This paper presents a new type of nonlinear signal model which constitutes a natural extension of the classical Exponential Autoregressive (EXPAR) model introduced by Ozaki [1]. The EXPAR model is known to have the ability to reproduce phenomena such as limit cycles and chaos. It presents however limitations which have limited its range of applications. It is shlown in this paper that a proper interpretation of the dependence of the EXPAR coefficients upon the past values of the signal in terms of a limited radial basis functions (RBF) expansion produces in a natural way a more general model free of the limitations of the EXPAR one. Results on real and simulated signals are shown which demonstrate the potentialities of the new model.