A finite-step global convergence algorithm for the cumulant-based parameter estimation of multichannel moving average processes

Author

Tong, Lang ; Inouye, Yujiro ; Liu, Rueywen

Author_Institution

Dept. of Electr. Eng., Notre Dame Univ., IN, USA

fYear

1991

fDate

14-17 Apr 1991

Firstpage

3445

Abstract

An iterative algorithm for the identification of multichannel moving average (MA) processes driven by mutually independent and identically distributed (i.i.d.) input signals is proposed. It is shown that the algorithm has a finite-step global convergence property. This algorithm is computationally efficient and numerically stable. Two multichannel MA models, including one nonminimum-phase MA model, are estimated by this algorithm with satisfactory performances. It is shown that this algorithm guarantees a solution of third-order cumulant-based identification equations

Keywords

convergence of numerical methods; iterative methods; parameter estimation; signal processing; cumulant-based parameter estimation; finite-step global convergence algorithm; identification equations; independent identically distributed signals; input signals; iterative algorithm; matrix algebra; multichannel MA models; multichannel moving average processes; nonminimum-phase MA model; signal processing; third order cumulants; Closed-form solution; Convergence; Iterative algorithms; Maximum likelihood detection; Maximum likelihood estimation; Nonlinear equations; Parameter estimation; Phase estimation; Signal processing; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on

Conference_Location

Toronto, Ont.

ISSN

1520-6149

Print_ISBN

0-7803-0003-3

Type

conf

DOI

10.1109/ICASSP.1991.150195

Filename

150195