Cumulant based parameter estimation of multichannel moving-average processes

Author

Inouye, Yujiro ; Giannakis, Georgios B. ; Mendel, Jerry M.

Author_Institution

Dept. of Control Eng., Osaka Univ., Japan

fYear

1988

fDate

11-14 Apr 1988

Firstpage

1252

Abstract

Given finite samples of a stationary, perhaps noisy, nonGaussian r-variate moving-average, MA(q) process, the authors study cumulant based identifiability conditions, under which the MA coefficient matrices, the input statistics, and the order q, can be uniquely determined. The selection of a unique representative from the equivalence class corresponding to a given cumulant structure involves less restrictions than that corresponding to a given covariance structure. They derive two algorithms for estimating the (possibly) nonminimum phase MA coefficient matrices

Keywords

parameter estimation; signal processing; MA coefficient matrices; algorithms; covariance structure; cumulant based identifiability conditions; cumulant based parameter estimation; input statistics; multichannel moving-average processes; signal processing; stationary nonGaussian process; Additive noise; Covariance matrix; Econometrics; Gaussian noise; Gaussian processes; Image processing; Parameter estimation; Parametric statistics; Phase estimation; Signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196828

Filename

196828