Change search
ReferencesLink to record
Permanent link

Direct link
Structured Covariance Matrix Estimation: A Parametric Approach
KTH, Superseded Departments, Signals, Sensors and Systems.ORCID iD: 0000-0002-6855-5868
KTH, Superseded Departments, Signals, Sensors and Systems.ORCID iD: 0000-0003-2298-6774
2000 (English)In: Proceedings IEEE International Conference on Acoustics, Speech, and Signal Processing, IEEE , 2000, 3172-3175 p.Conference paper (Refereed)
Abstract [en]

The problem of estimating a positive semi-definite Toeplitz covariance matrix consisting of a low rank matrix plus a scaled identity from noisy data arises in many applications. We propose a computationally attractive (noniterative) covariance matrix estimator with certain optimality properties. For example, under suitable assumptions the proposed estimator achieves the Cramer-Rao lower bound on the covariance matrix parameters. The resulting covariance matrix estimate is also guaranteed to possess all of the structural properties of the true covariance matrix. Previous approaches to this problem have either resulted in computationally unattractive iterative solutions or have provided estimates that only satisfy some of the structural relations

Place, publisher, year, edition, pages
IEEE , 2000. 3172-3175 p.
Keyword [en]
Approximation methods, Covariance matrix, Gaussian distribution, Iterative methods, Maximum likelihood estimation, Minimization methods, Optimization methods, Sensor systems, Signal processing, Signal to noise ratio
National Category
Signal Processing
URN: urn:nbn:se:kth:diva-82688DOI: 10.1109/ICASSP.2000.861211OAI: diva2:498511
ICASSP Istanbul, Turkey, June 2000
NR 20140805Available from: 2012-02-12 Created: 2012-02-12 Last updated: 2012-04-02Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full text

Search in DiVA

By author/editor
Jansson, MagnusOttersten, Björn
By organisation
Signals, Sensors and Systems
Signal Processing

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 34 hits
ReferencesLink to record
Permanent link

Direct link