uu.seUppsala University Publications
Change search
Link to record
Permanent link

Direct link
BETA
Selén, Y
Alternative names
Publications (10 of 29) Show all publications
Selén, Y., Abrahamsson, R. & Stoica, P. (2008). Automatic robust adaptive beamforming via ridge regression. Signal Processing, 88(1), 33-49
Open this publication in new window or tab >>Automatic robust adaptive beamforming via ridge regression
2008 (English)In: Signal Processing, ISSN 0165-1684, E-ISSN 1872-7557, Vol. 88, no 1, p. 33-49Article in journal (Refereed) Published
National Category
Signal Processing
Identifiers
urn:nbn:se:uu:diva-104184 (URN)10.1016/j.sigpro.2007.07.003 (DOI)000250237100003 ()
Available from: 2009-05-27 Created: 2009-05-27 Last updated: 2018-10-01Bibliographically approved
Selén, Y. & Larsson, E. G. (2008). Empirical Bayes linear regression with unknown model order. Digital signal processing (Print), 18(2), 236-248
Open this publication in new window or tab >>Empirical Bayes linear regression with unknown model order
2008 (English)In: Digital signal processing (Print), ISSN 1051-2004, E-ISSN 1095-4333, Vol. 18, no 2, p. 236-248Article in journal (Refereed) Published
Abstract [en]

We study maximum a posteriori probability model order selection for linear regression models, assuming Gaussian distributed noise and coefficient vectors. For the same data model, we also derive the minimum mean-square error coefficient vector estimate. The approaches are denoted BOSS (Bayesian order selection strategy) and BPM (Bayesian parameter estimation method), respectively. In their simplest form, both BOSS and BPM require a priori knowledge of the distribution of the coefficients. However, under the assumption that the coefficient variance profile is smooth, we derive "empirical Bayesian" versions of our algorithms which estimate the coefficient variance profile from the observations and thus require little or no information from the user. We show in numerical examples that the estimators can outperform several classical methods, including the well-known AICc and BIC for model order selection.

National Category
Signal Processing Information Systems
Identifiers
urn:nbn:se:uu:diva-10384 (URN)10.1016/j.dsp.2007.03.005 (DOI)000254781300013 ()
Note
Conference Information: 14th European Signal Processing Conference Florence, ITALY, SEP 04-08, 2006Available from: 2007-03-21 Created: 2007-03-21 Last updated: 2018-01-12Bibliographically approved
Selén, Y. & Stoica, P. (2008). Estimation of semi-sparse radar range profiles. Digital signal processing (Print), 18(4), 543-560
Open this publication in new window or tab >>Estimation of semi-sparse radar range profiles
2008 (English)In: Digital signal processing (Print), ISSN 1051-2004, E-ISSN 1095-4333, Vol. 18, no 4, p. 543-560Article in journal (Refereed) Published
National Category
Signal Processing
Identifiers
urn:nbn:se:uu:diva-104407 (URN)10.1016/j.dsp.2007.09.004 (DOI)000256820200007 ()
Available from: 2009-05-28 Created: 2009-05-28 Last updated: 2018-10-01Bibliographically approved
Selén, Y., Abrahamsson, R. & Stoica, P. (2007). Automatic robust adaptive beamforming via ridge regression. In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol II, Pts 1-3. Paper presented at 32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007 (pp. 965-968).
Open this publication in new window or tab >>Automatic robust adaptive beamforming via ridge regression
2007 (English)In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol II, Pts 1-3, 2007, p. 965-968Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we derive a class of new parameter free robust adaptive beamformers using the generalized sidelobe canceler reparameterization of the Capon beamformer. In this parameterization the minimum variance beamformer is obtained as the solution of a linear least squares problem. In the case of an inaccurate steering vector and/or few data snapshots this marginally overdetermined system gives an ill fit causing signal cancellation in the standard minimum variance solution. By regularizing the problem using ridge regression techniques we get a whole class of robust adaptive beamformers, none of which requires the choice of a user parameter. We also propose a novel empirical Bayes-based ridge regression technique. The performance is compared to other robust adaptive beamformers.

Series
International Conference on Acoustics Speech and Signal Processing (ICASSP), ISSN 1520-6149 ; 2
Keywords
minimum variance beamforming, Capon beamforming, robust beamforming, ridge regression, regularization
National Category
Engineering and Technology
Identifiers
urn:nbn:se:uu:diva-18255 (URN)000248908100242 ()
Conference
32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007
Note
Student Paper Award Winner: Honorary MentionAvailable from: 2007-04-24 Created: 2007-04-24 Last updated: 2018-10-01Bibliographically approved
Selén, Y. & Larsson, E. G. (2007). Empirical Bayes linear regression with unknown model order. In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol III, Pts 1-3, Proceedings. Paper presented at 32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007 (pp. 773-776).
Open this publication in new window or tab >>Empirical Bayes linear regression with unknown model order
2007 (English)In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol III, Pts 1-3, Proceedings, 2007, p. 773-776Conference paper, Published paper (Refereed)
Abstract [en]

We study the maximum a posteriori probability model order selection algorithm for linear regression models, assuming Gaussian distributed noise and coefficient vectors. For the same data model, we also derive the minimum mean-square error coefficient vector estimate. The approaches are denoted BOSS (Bayesian Order Selection Strategy) and BPM (Bayesian Parameter estimation Method), respectively. Both BOSS and BPM require a priori knowledge on the distribution of the coefficients. However, under the assumption that the coefficient variance profile is smooth, we derive "empirical Bayesian" versions of our algorithms, which require little or no information from the user. We show in numerical examples that the estimators can outperform several classical methods, including the well-known AIC and BIC for order selection.

Series
International Conference on Acoustics Speech and Signal Processing (ICASSP), ISSN 1520-6149 ; 3
Keywords
linear systems, Bayes procedures, modeling, least mean square methods, parameter estimation
National Category
Engineering and Technology
Identifiers
urn:nbn:se:uu:diva-18253 (URN)10.1109/ICASSP.2007.366794 (DOI)000248906600194 ()1-4244-0727-3 (ISBN)
Conference
32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007
Available from: 2006-12-20 Created: 2006-12-20 Last updated: 2011-04-14Bibliographically approved
Abrahamsson, R., Selén, Y. & Stoica, P. (2007). Enhanced covariance matrix estimators in adaptive beamforming. In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol II, Pts 1-3. Paper presented at 32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007 (pp. 969-972).
Open this publication in new window or tab >>Enhanced covariance matrix estimators in adaptive beamforming
2007 (English)In: 2007 IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol II, Pts 1-3, 2007, p. 969-972Conference paper, Published paper (Refereed)
Abstract [en]

In this paper a number of covariance matrix estimators suggested in the literature are compared in terms of their performance in the context of array signal processing. More specifically they are applied in adaptive beamforming which is known to be sensitive to errors in the covariance matrix estimate and where often only a limited amount of data is available for estimation. As many covariance matrix estimators have the form of diagonal loading or eigenvalue adjustments of the sample covariance matrix and as they sometimes offer robustness to array imperfections and finite sample error, they are compared to a recent robustified adaptive Capon beamforming (RCB) method which also has a diagonal loading interpretation. Some of the covariance estimators show a significant improvement over the sample covariance matrix and in some cases they match the performance of the RCB even when a priori knowledge, which is not available in practice, is used for choosing the user parameter of RCB.

Series
International Conference on Acoustics Speech and Signal Processing (ICASSP), ISSN 1520-6149 ; 2
Keywords
array signal processing, covariance matrices, direction of arrival estimation
National Category
Engineering and Technology
Identifiers
urn:nbn:se:uu:diva-18247 (URN)000248908100243 ()
Conference
32nd IEEE International Conference on Acoustics, Speech and Signal Processing Honolulu, HI, APR 15-20, 2007
Available from: 2006-12-20 Created: 2006-12-20 Last updated: 2018-10-01Bibliographically approved
Larsson, E. G. & Selén, Y. (2007). Linear Regression With a Sparse Parameter Vector. IEEE Transactions on Signal Processing, 55(2), 451-460
Open this publication in new window or tab >>Linear Regression With a Sparse Parameter Vector
2007 (English)In: IEEE Transactions on Signal Processing, ISSN 1053-587X, E-ISSN 1941-0476, Vol. 55, no 2, p. 451-460Article in journal (Refereed) Published
Abstract [en]

We consider linear regression under a model where the parameter vector is known to be sparse. Using a Bayesian framework, we derive the minimum mean-square error (MMSE) estimate of the parameter vector, and a computationally efficient approximation of it. We also derive an empirical-Bayesian version of the estimator, which does not need any a priori information, nor does it need the selection of any user parameters. As a byproduct, we obtain a powerful model (``basis'') selection tool for sparse models. The performance and robustness of our new estimators are illustrated via numerical examples.

Keywords
Linear regression, sparse models, Bayesian inference, MMSE estimation, basis selection, model selection, variable selection, model averaging, Lasso
National Category
Engineering and Technology
Identifiers
urn:nbn:se:uu:diva-82080 (URN)10.1109/TSP.2006.887109 (DOI)000243952600005 ()
Available from: 2007-02-15 Created: 2007-02-15 Last updated: 2017-12-14Bibliographically approved
Selén, Y. & Larsson, E. G. (2007). RAKE Receiver for Channels with a Sparse Impulse Response. IEEE Transactions on Wireless Communications, 6(9), 3175-3180
Open this publication in new window or tab >>RAKE Receiver for Channels with a Sparse Impulse Response
2007 (English)In: IEEE Transactions on Wireless Communications, ISSN 1536-1276, E-ISSN 1558-2248, Vol. 6, no 9, p. 3175-3180Article in journal (Refereed) Published
Abstract [en]

We derive the optimal receiver for RAKE diversity combining on channels with a sparse impulse response. The receiver is based on the Bayesian philosophy and thus it requires the knowledge of certain a priori parameters. However, we also derive an empirical Bayesian version of our receiver, which does not require any a priori knowledge, nor the choice of any user parameters. We show that both versions of our detector can outperform a classical training-based maximum-ratio-combining detector.

Keywords
RAKE receiver, diversity combining, optimal receiver, empirical Bayes
National Category
Computer and Information Sciences
Identifiers
urn:nbn:se:uu:diva-82079 (URN)10.1109/TWC.2007.06030033 (DOI)000249309000008 ()
Available from: 2007-09-05 Created: 2007-09-05 Last updated: 2018-01-13Bibliographically approved
Selén, Y., Gudmundson, E. & Stoica, P. (2006). An approach to sparse model selection and averaging. In: Conference Record of the 2006 IEEE Instrumentation and Measurement Technology Conference (IMTC 2006): Sorrento, Italy 24-27 April 2006.
Open this publication in new window or tab >>An approach to sparse model selection and averaging
2006 (English)In: Conference Record of the 2006 IEEE Instrumentation and Measurement Technology Conference (IMTC 2006): Sorrento, Italy 24-27 April 2006, 2006Conference paper, Published paper (Refereed)
Abstract [en]

Parameter estimation when the true model structure is unknown is a commonly occurring task in measurement problems. In a sparse modeling scenario, the number of possible models grows exponentially with the total number of parameters. The full set of models therefore becomes computationally infeasible to handle. We propose a method, based on successive model reduction, for finding a sound and computationally feasible set of sparse linear regression models. Once this set of models has been found, standard model selection or model averaging techniques can be applied. We demonstrate the performance of our method by some numerical examples.

Keywords
linear systems, model reduction, channel measurement, least squares estimation, parameter estimation, signal processing, system identification
National Category
Signal Processing
Identifiers
urn:nbn:se:uu:diva-79396 (URN)
Available from: 2006-12-20 Created: 2006-12-20 Last updated: 2018-10-01
Larsson, E. G. & Selén, Y. (2006). Linear regression with a sparse parameter vector. In: Conference Record of the 31st International Conference on Acoustics, Speech, and Signal Processing (ICASSP).
Open this publication in new window or tab >>Linear regression with a sparse parameter vector
2006 (English)In: Conference Record of the 31st International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2006Conference paper, Published paper (Refereed)
Abstract [en]

We consider linear regression under a model where the parameter vector is known to be sparse. Using a Bayesian framework, we derive a computationally efficient approximation to the minimum mean-square error (MMSE) estimate of the parameter vector. The performance of the so-obtained estimate is illustrated via numerical examples.

Keywords
Linear regression, sparse models, Bayesian inference, MMSE estimation, variable selection, model averaging
National Category
Signal Processing
Identifiers
urn:nbn:se:uu:diva-79395 (URN)
Available from: 2006-04-07 Created: 2006-04-07
Organisations

Search in DiVA

Show all publications