DocumentCode
1482639
Title
On the identification of noisy MA models
Author
Desbouvries, F. ; Fijalkow, I. ; Loubaton, Ph
Author_Institution
INT/SIM, Evry, France
Volume
41
Issue
12
fYear
1996
fDate
12/1/1996 12:00:00 AM
Firstpage
1810
Lastpage
1814
Abstract
In this paper, we address the identification problem of p-input q-output MA models corrupted by a white noise with an unknown covariance matrix in the case where p<q. Under certain additional conditions, we show that the generating function of the MA model is identifiable from the autocovariance function of the observation. Some simple algebraic identification procedures are also given
Keywords
controllability; covariance matrices; identification; observability; spectral analysis; state-space methods; time series; white noise; autocovariance function; controllability; covariance matrix; identification; noisy MA models; observability; state space; time series; white noise; Blind equalizers; Context; Covariance matrix; Digital communication; Linear matrix inequalities; Polynomials; Singular value decomposition; Stochastic processes; Transfer functions; White noise;
fLanguage
English
Journal_Title
Automatic Control, IEEE Transactions on
Publisher
ieee
ISSN
0018-9286
Type
jour
DOI
10.1109/9.545746
Filename
545746
Link To Document