Consistent identification of stochastic linear systems with noisy input-output data

Delopoulos, A; Giannakis, GB

dc.contributor.author	Delopoulos, A	en
dc.contributor.author	Giannakis, GB	en
dc.date.accessioned	2014-03-01T01:09:46Z
dc.date.available	2014-03-01T01:09:46Z
dc.date.issued	1994	en
dc.identifier.issn	0005-1098	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/11186
dc.subject	Identifiability	en
dc.subject	Modeling (errors-in-variable)	en
dc.subject	Parameter estimation	en
dc.subject	Recursive estimation	en
dc.subject	Statistics (cumulants)	en
dc.subject	Stochastic systems	en
dc.subject	System identification	en
dc.subject	Time-delay estimation	en
dc.subject.classification	Automation & Control Systems	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.other	Computational methods	en
dc.subject.other	Computer simulation	en
dc.subject.other	Data processing	en
dc.subject.other	Least squares approximations	en
dc.subject.other	Linear control systems	en
dc.subject.other	Parameter estimation	en
dc.subject.other	Random processes	en
dc.subject.other	Recursive functions	en
dc.subject.other	Signal to noise ratio	en
dc.subject.other	Statistics	en
dc.subject.other	Transfer functions	en
dc.subject.other	White noise	en
dc.subject.other	Cumulants	en
dc.subject.other	Errors in variables	en
dc.subject.other	Identifiability	en
dc.subject.other	Mean squared error	en
dc.subject.other	Noisy input output data	en
dc.subject.other	Recursive estimation	en
dc.subject.other	Stochastic linear systems	en
dc.subject.other	Time delay estimation	en
dc.subject.other	Identification (control systems)	en
dc.title	Consistent identification of stochastic linear systems with noisy input-output data	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/0005-1098(94)90108-2	en
heal.identifier.secondary	http://dx.doi.org/10.1016/0005-1098(94)90108-2	en
heal.language	English	en
heal.publicationDate	1994	en
heal.abstract	A novel criterion is introduced for parametric errors-in-variables identification of stochastic linear systems excited by non-Gaussian inputs. The new criterion is (at least theoretically) insensitive to a class of input-output disturbances because it implicitly involves higher- than second-order cumulant statistics. In addition, it is shown to be equivalent to the conventional Mean-Squared Error (MSE) as if the latter was computed in the ideal case of noise-free input-output data. The sampled version of the criterion converges to the novel MSE and guarantees strongly consistent parameter estimators. The asymptotic behavior of the resulting parameter estimators is analyzed and guidelines for minimum variance experiments are discussed briefly. Informative enough input signals and persistent of excitation conditions are specified. Computatonally attractive Recursive-Least-Squares variants are also developed for on-line implementation of ARMA modeling, and their potential is illustrated by applying them to time-delay estimation in low SNR environment. The performance of the proposed algorithms and comparisons with conventional methods are corroborated using simulated data.	en
heal.publisher	PERGAMON-ELSEVIER SCIENCE LTD	en
heal.journalName	Automatica	en
dc.identifier.doi	10.1016/0005-1098(94)90108-2	en
dc.identifier.isi	ISI:A1994PC78900003	en
dc.identifier.volume	30	en
dc.identifier.issue	8	en
dc.identifier.spage	1271	en
dc.identifier.epage	1294	en