Showing papers in "Signal Processing in 2007"
••
TL;DR: It is explained how special structure of the weight matrix and the data matrix can be exploited for efficient cost function and first derivative computation that allows to obtain computationally efficient solution methods.
745 citations
••
TL;DR: This paper shows that the space of diffusion tensors is a type of curved manifold known as a Riemannian symmetric space, and develops methods for producing statistics, namely averages and modes of variation, in this space, which preserve natural geometric properties of the tensors.
362 citations
••
TL;DR: It is shown that as long as the sources are reasonably spectrally disjoint then they can identify and approximately separate out individual sources, but when the sources have substantially overlapping spectra both identification using standard ICA and linear separation are no longer possible.
299 citations
••
TL;DR: This paper presents a new method for blind sparse source separation that can be clustered by the k-means algorithm and easily applied to more than three sensors arranged non-linearly, and has obtained promising results for two- and three-dimensionally distributed speech separation with non-linear/non-uniform sensor arrays in a real room even in underdetermined situations.
260 citations
••
225 citations
••
TL;DR: This paper proposes the adaptive model selection algorithm, a lightweight, online algorithm that allows sensor nodes to autonomously determine a statistically good performing model among a set of candidate models, and demonstrates the efficiency and versatility of the proposed framework in improving the communication savings.
185 citations
••
TL;DR: A new set of discrete orthogonal moments is proposed, based on the discrete Racah polynomials, which eliminate the need for numerical approximations and demonstrate Racah moments' feature representation capability by means of image reconstruction and compression.
182 citations
••
TL;DR: New sampling formulae for reconstructing signals that are band-limited or time-limited in the linear canonical transform sense have been proposed and well-known sampling theorems in Fourier domain or fractional Fourierdomain are shown to be special cases of the achieved results.
143 citations
••
TL;DR: This paper investigates security in hierarchical WSNs with dynamic cluster formation, and shows how random key predistribution, widely studied in the context of flat networks, and μTESLA, a building block from SPINS, can be both used to secure communications in this type of network.
141 citations
••
TL;DR: New deterministic tensor-based techniques for the blind separation of a mixture of DS-CDMA signals received by an antenna array are presented and it is shown that the blind receiver follows from a simultaneous matrix decomposition.
133 citations
••
TL;DR: The proposed IF estimator is tested on noisy synthetic monocomponent and multicomponent signals exhibiting linear and nonlinear laws and a classification method using least squares data-fitting is proposed and illustrated on synthetic and real signals.
••
TL;DR: This work examines available contrasts for the new formulation that can solve the frequency-domain blind source separation problem and introduces a quadratic Taylor polynomial in the notations of complex variables which is very useful in directly applying Newton's method to a contrast function of complex-valued variables.
••
TL;DR: A generalized tensor decomposition known as constrained Block-PARAFAC is used and a tensor (3D) model is proposed for the signal received by three types of wireless communication systems, which are multiuser systems subject to frequency-selective multipath and employing multiple receiver antennas.
••
TL;DR: In this paper, the design of fractional order Simpson digital integrator is investigated and it is shown that the IIR fractional Integrator is always stable.
••
TL;DR: In this paper, a nonparametric shape prior model is proposed for image segmentation problems, where the underlying shape distribution is estimated by extending a Parzen density estimator to the space of shapes.
••
TL;DR: A novel Gabor-based supervised locality preserving projection (GSLPP) method for face recognition using class labels of data points to enhance its discriminant power in their mapping into a low-dimensional space is introduced.
••
TL;DR: This article defines oracle estimators which compute the best performance achievable by different classes of algorithms on a given mixture, in a theoretical evaluation framework where the reference sources are available, and shows that it is worth developing blind time-frequency masking algorithms relaxing the common assumption of a single active source per time- frequencies point.
••
TL;DR: The spectral decomposition of a 4th-order covariance tensor, @S, is proposed and suggests a hierarchy of symmetries with which to classify the statistical anisotropy inherent in tensor data.
••
TL;DR: This paper presents a content-based digital image-watermarking scheme, which is robust against a variety of common image-processing attacks and geometric distortions and yields a better performance as compared with some peer systems in the literature.
••
TL;DR: This paper proposes to take advantage of the second-order terms of a cost function to overcome the disadvantages of gradient (multiplicative) algorithms, and presents a projected quasi-Newton method, which was applied to a BSS problem with mixed signals and images.
••
TL;DR: An algebraic approach is proposed for the fast and reliable, on line, identification of the amplitude, frequency and phase parameters in unknown noisy sinusoidal signals.
••
TL;DR: Experimental results prove that the prediction of the trained GAP-RBF network does emulate the mean opinion score (MOS), and the subjective test results of the proposed metric are compared with JPEG no-reference image quality index as well as full-reference structural similarity imagequality index and it is observed to outperform both.
••
TL;DR: In this article, a new algorithm for the detection of clustered microcalcifications using mathematical morphology and artificial neural networks was proposed, where each microcification appears as an elevation constituting a regional maximum and each candidate object is marked as such, using a binary image.
••
TL;DR: The simulations for impulsive noise and co-channel interference in presence of Gaussian noise, confirms that a better estimate can be obtained by using the proposed technique as compared to the traditional least-squares-based algorithms in highly non-Gaussian environments.
••
TL;DR: A way of achieving and maintaining sequence synchronization in multi-user direct sequence code division multiple access (DS-CDMA) based chaotic communication systems by using a pseudo-random binary sequence as the synchronizing pilot signal within the multi- user chaotic communication system.
••
TL;DR: The proposed solution is a switching vector filter which analyzes the color difference of two pixels in the CIELAB color space using four directional operators and can effectively preserve the thin lines, fine details, and image edges.
••
TL;DR: The performances and comparative results between all these tensor filtering methods are presented in the case of noise reduction in color images and multicomponent seismic data.
••
TL;DR: This analysis shows that for chirp-periodic signals the FChT can reach the limit of the time-frequency (TF) uncertainty principle, while simultaneously keeping the cross-terms at minimum level.
••
TL;DR: This paper investigates two classes of particle filtering techniques, distributed resampling with non-proportional allocation (DRNA) and local selection (LS), and analyzes the effect of DRNA and LS on the sample variance of the importance weights; the distortion, due to the resamplings step, of the discrete probability measure given by the particle filter; and the variance of estimators after resampled.
••
TL;DR: A very sensitive similarity measure that distinguishes very subtle differences between regions within, for example, the thalamus and its nuclei is presented and a new way of selecting the most representative tensor for group of tensors for these kinds of applications is presented.