| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Barral, Joelle K., et al.
(författare)
-
Skin T1 Mapping at 1.5T, 3T, and 7T
- 2009
-
Ingår i: Proceedings 17th Scientific Meeting, International Society for Magnetic Resonance in Medicine (2009).
-
Konferensbidrag (refereegranskat)abstract
- Increasing the field strength seems promising for high-resolution skin imaging but a legitimate concern is the increase in the spin-lattice relaxation parameter T1. Skin T1 maps at 1.5T, 3T, and 7T are compared and a novel non-linear least-square approach for fast and accurate T1-estimation is proposed.
|
|
| 6. |
- Fatima, Ghania, et al.
(författare)
-
Covariance Matrix Estimation Under Positivity Constraints With Application to Portfolio Selection
- 2022
-
Ingår i: IEEE Signal Processing Letters. - : Institute of Electrical and Electronics Engineers (IEEE). - 1070-9908 .- 1558-2361. ; 29, s. 2487-2491
-
Tidskriftsartikel (refereegranskat)abstract
- In this letter we propose a new method to estimate the covariance matrix under the constraint that its off-diagonal elements are non-negative, which has applications to portfolio selection in finance. We incorporate the non-negativity constraint in the maximum likelihood (ML) estimation problem and propose an algorithm based on the block coordinate descent method to solve for the ML estimate. To study the effectiveness of the proposed algorithm, we perform numerical simulations on both synthetic and real-world financial data, and show that our proposed method has better performance than that of a state-of-the-art method.
|
|
| 7. |
- Fatima, Ghania, et al.
(författare)
-
Two New Algorithms for Maximum Likelihood Estimation of Sparse Covariance Matrices With Applications to Graphical Modeling
- 2024
-
Ingår i: IEEE Transactions on Signal Processing. - : Institute of Electrical and Electronics Engineers (IEEE). - 1053-587X .- 1941-0476. ; 72, s. 958-971
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper, we propose two new algorithms for maximum-likelihood estimation (MLE) of high dimensional sparse covariance matrices. Unlike most of the state-of-the-art methods, which either use regularization techniques or penalize the likelihood to impose sparsity, we solve the MLE problem based on an estimated covariance graph. More specifically, we propose a two-stage procedure: in the first stage, we determine the sparsity pattern of the target covariance matrix (in other words the marginal independence in the covariance graph under a Gaussian graphical model) using the multiple hypothesis testing method of false discovery rate (FDR), and in the second stage we use either a block coordinate descent approach to estimate the non-zero values or a proximal distance approach that penalizes the distance between the estimated covariance graph and the target covariance matrix. Doing so gives rise to two different methods, each with its own advantage: the coordinate descent approach does not require tuning of any hyper-parameters, whereas the proximal distance approach is computationally fast but requires a careful tuning of the penalty parameter. Both methods are effective even in cases where the number of observed samples is less than the dimension of the data. For performance evaluation, we test the proposed methods on both simulated and real-world data and show that they provide more accurate estimates of the sparse covariance matrix than the state-of-the-art methods.
|
|
| 8. |
- Ganesan, Girish, et al.
(författare)
-
Diagonally weighted orthogonal space-time block codes
- 2002
-
Ingår i: Proc. of Asilomar Conference on Signals, Systems and Computers. 2002. Vol. 2. - : IEEE. - 0780375769 ; , s. 1147-1151
-
Konferensbidrag (refereegranskat)abstract
- This paper shows how the performance of orthogonal space-time block codes can be improved by using a diagonal weighting matrix at the transmitter. The optimal diagonal weighting matrix which minimizes the bit-error-rate is derived. Since the optimal weights depend on the channel, a feedback from the transmitter to the receiver is necessary. However this feedback can be achieved using only log/sub 2/(n/sub t/) bits where n/sub t/ is the number of transmit antennas. Simulations show that for a system with two transmit antennas and one receive antenna, an improvement of 1.5 dB can be achieved with a feedback of only one bit. The effect of errors in the feedback is also analyzed, and an error tolerant weighting scheme is introduced to reduce the adverse effects of feedback errors.
|
|
| 9. |
- Ganesan, Girish, et al.
(författare)
-
Orthogonal Space-Time Block Codes with Feedback
- 2004
-
Ingår i: Wireless personal communications. - : Kluwer Academic Publishers. - 0929-6212 .- 1572-834X. ; 28:4, s. 287-312
-
Tidskriftsartikel (refereegranskat)abstract
- In this paper we consider how Orthogonal Space-Time Block Codes (OSTBC) can be used in the presence of feedback from the receiver to the transmitter. First, we survey how some of the feedback techniques for AWGN channels with fading can be applied to OSTBC. Then we consider a simple scheme with diagonal weighting. The optimal diagonal weighting matrix, which minimizes the probability of error, is derived. The optimal weights depend on the channel and, hence, a feedback becomes necessary. However, the required feedback can be accomplished using log2 (n t) bits, where n t is the number of transmit antennas. Simulations show that relatively significant gains can be achieved with the diagonal weighting scheme. In a practical system it is quite possible that the bits that are fed back to the transmitter are in error. In that case we show that there will be a loss of diversity. To overcome this loss, we develop weighting schemes that are error tolerant and always perform better than the unweighted OSTBC (even in the presence of feedback errors).
|
|
| 10. |
- Gershman, Alex B., et al.
(författare)
-
The stochastic CRB for array processing in unknown noise fields
- 2001
-
Ingår i: 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. - : IEEE. - 0780370414 ; , s. 2989-2992
-
Konferensbidrag (refereegranskat)abstract
- The stochastic Cramer-Rao bound (CRB) plays an important role in array processing because several high-resolution direction-of-arrival (DOA) estimation methods are known to achieve this bound asymptotically. In this paper, we study the stochastic CRB on DOA estimation accuracy in the general case of arbitrary unknown noise field parametrized by a vector of unknowns. We derive explicit closed-form expressions for the CRB and examine its properties theoretically and by representative numerical examples.
|
|
