| 1. |
- Adalbjörnsson, Stefan Ingi, et al.
(författare)
-
Efficient Block and Time-Recursive Estimation of Sparse Volterra Systems
- 2012
-
Ingår i: 2012 IEEE Statistical Signal Processing Workshop (SSP), Proceedings of. - 9781467301831 ; , s. 173-176
-
Konferensbidrag (refereegranskat)abstract
- We investigate the application of non-convex penalized least squares for parameter estimation in the Volterra model. Sparsity is promoted by introducing a weighted !q penalty on the parameters and efficient batch and time recursive algorithms are devised based on the cyclic coordinate descent approach. Numerical examples illustrate the improved performance of the proposed algorithms as compared the weighted !1 norm.
|
|
| 2. |
- Aggelopoulos, Kostas, et al.
(författare)
-
Efficient Implementation of the IAA-based Magnitude Squared Coherence Estimator
- 2011
-
Ingår i: Digital Signal Processing (DSP), 2011 17th International Conference on. - 9781457702730
-
Konferensbidrag (refereegranskat)abstract
- Recently, a novel Magnitude Squared Coherence (MSC) estimator was proposed using the Iterative Adaptive Approach (IAA) algorithm. In this paper, we present a computationally efficient implementation of this estimator, exploiting the inherently low displacement rank of the necessary products of Toeplitz-like matrices, thereby allowing for the development of appropriate Gohberg-Semencul (GS) representations of these matrices. Together with relevant data dependent trigonometric polynomials, the presented implementation offers a substantial computational reduction as compared to earlier implementations. Numerical simulations along with theoretical complexity estimations illustrate the performance of the proposed algorithm.
|
|
| 3. |
- Angelopoulos, Kostas, et al.
(författare)
-
Computationally Efficient Capon- and APES-based Coherence Spectrum Estimation
- 2012
-
Ingår i: IEEE Transactions on Signal Processing. - 1053-587X. ; 60:12, s. 6674-6681
-
Tidskriftsartikel (refereegranskat)abstract
- The coherence spectrum is of notable interest as a bivariate spectral measure in a variety of application, and the topic has lately attracted interest with the recent formulation of several ligh-resolution data adaptive estimators. In this work, we further this development with the presentation of computationally efficient implementations of the Caponand APE S-based MSC estimators. The presented implementations furthers the recent development of exploiting the estimators’ inherently low displacement rank of the necessary products of Toeplitz-like matrices to include also the required cross-correlation covariance matrices for the mentioned coherence algorithms. Numerical simulations together with theoretical complexity measures illustrate the performance of the proposed implementations.
|
|
| 4. |
- Angelopoulos, Kostas, et al.
(författare)
-
Computationally Efficient Sparsity-Inducing Coherence Spectrum Estimation of Complete and Non-Complete Data Sets
- 2013
-
Ingår i: Signal Processing. - : Elsevier BV. - 0165-1684. ; 93:5, s. 1221-1234
-
Tidskriftsartikel (refereegranskat)abstract
- The magnitude squared coherence (MSC) spectrum is an often used frequency-dependent measure for the linear dependency between two stationary processes, and the recent literature contain several contributions on how to form high-resolution data-dependent and adaptive MSC estimators, and on the efficient implementation of such estimators. In this work, we further this development with the presentation of computationally efficient implementations of the recent iterative adaptive approach (IAA) estimator, present a novel sparse learning via iterative minimization (SLIM) algorithm, discuss extensions to two-dimensional data sets, examining both the case of complete data sets and when some of the observations are missing. The algorithms further the recent development of exploiting the estimators' inherently low displacement rank of the necessary products of Toeplitz-like matrices, extending these formulations to the coherence estimation using IAA and SLIM formulations. The performance of the proposed algorithms and implementations are illustrated both with theoretical complexity measures and with numerical simulations.
|
|
| 5. |
- Angelopoulos, Kostas, et al.
(författare)
-
Efficient Time Recursive Coherence Spectrum Estimation
- 2012
-
Ingår i: Signal Processing Conference (EUSIPCO), 2012 Proceedings of the 20th European. - 2076-1465 .- 2219-5491. - 9781467310680 ; , s. 425-429
-
Konferensbidrag (refereegranskat)abstract
- The coherence spectrum is of notable interest as a bivariate spectral measure in a variety of application, and the topic has lately attracted notable interest with the recent formulation of several high-resolution data adaptive estimators. In this work, we present computationally efficient time recursive implementations of the recent iterative adaptive approach (IAA) estimator, examining both the case of complete data sets and when some observations are missing. The algorithms continues the recent development of exploiting the estimators’ inherently low displacement rank of the necessary products of Toeplitz-like matrices, extending these to time-updating formulations for the IAA-based coherence estimation algorithm. Numerical simulations together with theoretical complexity measures illustrate the performance of the proposed algorithm.
|
|
| 6. |
- Glentis, George-Othan, et al.
(författare)
-
Computationally efficient damped Capon and APES spectral estimation
- 2013
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we introduce computationally efficient imple- mentations of the data-dependent non-parametric damped Capon (dCapon) and APES (dAPES) spectral estimators. These estimators form two-dimensional frequency represen- tations over both frequency and damping, and have been shown to enable an efficient separation of closely spaced spectral lines with different line widths. The proposed imple- mentations are formed using an FFT-based fast polynomial reformulation exploiting the displacement structure of the matrices associated with the trigonometric polynomials that appear in the nominator and the denominator of the spec- tral estimators. The resulting implementations are exact and notably reduces the required computational complexity of the estimators. Numerical simulations illustrates the perfor- mance and the achieved complexity gain of the proposed implementations
|
|
| 7. |
|
|
| 8. |
- Glentis, George-Othan, et al.
(författare)
-
Fast Algorithms for Iterative Adaptive Approach Spectral Estimation Techniques
- 2011
-
Konferensbidrag (refereegranskat)abstract
- This paper presents computationally efficient implementations for Iterative Adaptive Approach (IAA) spectral estimation techniques for uniformly sampled data sets. By exploiting the methods inherent low displacement rank, together with the development of suitable Gohberg-Semencul representations, and the use of data dependent trigonometric polynomials, the proposed implementations are shown to offer a reduction of the necessary computational complexity with at least one order of magnitude. Numerical simulations together with theoretical complexity measures illustrate the achieved performance gain.
|
|
| 9. |
- Glentis, George-Othan, et al.
(författare)
-
Non-Parametric High-Resolution SAR Imaging
- 2013
-
Ingår i: IEEE Transactions on Signal Processing. - 1053-587X. ; 61:7, s. 1614-1624
-
Tidskriftsartikel (refereegranskat)abstract
- The development of high-resolution two-dimensional spectral estimation techniques is of notable interest in synthetic aperture radar (SAR) imaging. Typically, data-independent techniques are exploited to form the SAR images, although such approaches will suffer from limited resolution and high sidelobe levels. Recent work on data-adaptive approaches have shown that both the iterative adaptive approach (IAA) and the sparse learning via iterative minimization (SLIM) algorithm offer excellent performance with high-resolution and low side lobe levels for both complete and incomplete data sets. Regrettably, both algorithms are computationally intensive if applied directly to the phase history data to form the SAR images. To help alleviate this, efficient implementations have also been proposed. In this paper, we further this work, proposing yet further improved implementation strategies, including approaches using the segmented IAA approach and the approximative quasi-Newton technique. Furthermore, we introduce a combined IAA-MAP algorithm as well as a hybrid IAA- and SLIM-based estimation scheme for SAR imaging. The effectiveness of the SAR imaging algorithms and the computational complexities of their fast implementations are demonstrated using the simulated Slicy data set and the experimentally measured GOTCHA data set.
|
|
| 10. |
- Glentis, George-Othan, et al.
(författare)
-
Preconditioned Conjugate Gradient IAA Spectral Estimation
- 2011
-
Ingår i: European Signal Processing Conference. - 2219-5491. ; 2001, s. 1195-1199
-
Konferensbidrag (refereegranskat)abstract
- In this paper, we develop superfast approximative algorithms for the computationally efficient implementation of the recent Iterative Adaptive Approach (IAA) spectral estimate. The proposed methods are based on rewriting the IAA algorithm using suitable Gohberg-Semencul representations, solving the resulting linear systems of equations using the preconditioned conjugate gradient method, where a novel preconditioning is applied using an incomplete factorization of the Toeplitz matrix. Numerical simulations illustrate the efficiency of the proposed algorithm.
|
|
