Title :
Cumulants and genetic algorithm for parameters estimation of noncausal AR models
Author :
Alshebeili, Saleh A. ; ALsehaili, Mohammad A. ; Anhal, Majeed A Alk
Author_Institution :
Dept. of Electr. Eng., King Saud Univ., Riyadh, Saudi Arabia
Abstract :
This paper introduces a new method to estimating the parameters of a noncausal AR model. This method is based on a new formulation that relates the unknown AR parameters to both second- and higher-order cumulants. A genetic algorithm has been used to solve for the unknown AR parameters by minimizing a nonlinear cost function that is defined in terms of model´s output cumulants.
Keywords :
autoregressive processes; filtering theory; genetic algorithms; higher order statistics; parameter estimation; all-pole filter; cumulants; genetic algorithm; higher-order cumulants; noncausal AR models; nonlinear cost function minimization; nonlinear identification; output cumulants; parameter estimation; second-order cumulants; Biomedical engineering; Cost function; Filters; Genetic algorithms; Genetic engineering; Nonlinear equations; Optimization methods; Parameter estimation; Seismology; Speech processing;
Conference_Titel :
Electrical and Computer Engineering, 1999 IEEE Canadian Conference on
Conference_Location :
Edmonton, Alberta, Canada
Print_ISBN :
0-7803-5579-2
DOI :
10.1109/CCECE.1999.807997
