Title :
On optimal global rate of convergence of some nonparametric identification procedures
Author :
Rutkowski, Leszek ; Rafajlowicz, Ewaryst
Author_Institution :
Sch. of Electr. & Comput. Eng., Oklahoma State Univ., Stillwater, OK, USA
fDate :
10/1/1989 12:00:00 AM
Abstract :
A study of orthogonal series procedures for function fitting, motivated by an interest in nonparametric identification of linear dynamic systems, is reported. It is shown that the procedures attain the optimal rate of convergence for the Fourier and the Walsh orthonormal systems. These rates cannot be exceeded by any method of estimation. This is the first analytical result giving a clear answer to the question of which orthonormal system is the best one for the purpose of system identification
Keywords :
convergence; identification; linear systems; series (mathematics); Fourier orthonormal systems; Walsh orthonormal systems; dynamic systems; function fitting; linear systems; nonparametric identification; optimal global convergence rate; orthogonal series; Artificial intelligence; Convergence; Higher order statistics; Parameter estimation; Parametric statistics; Poles and zeros; Signal processing; Stochastic processes; Stochastic systems; Transfer functions;
Journal_Title :
Automatic Control, IEEE Transactions on
