Showing papers by "Mohamed Sahmoudi published in 2005"

Blind separation of impulsive alpha-stable sources using minimum dispersion criterion

Abstract: This letter introduces a novel blind source separation (BSS) approach for extracting impulsive signals from their observed mixtures. The impulsive signals are modeled as real-valued symmetric alpha-stable (S/spl alpha/S) processes characterized by infinite second- and higher-order moments. The proposed approach uses the minimum dispersion (MD) criterion as a measure of sparseness and independence of the data. A new whitening procedure by a normalized covariance matrix is introduced. We show that the proposed method is robust, so-named for the property of being insensitive to possible variations in the underlying form of sampling distribution. Algorithm derivation and simulation results are provided to illustrate the good performance of the proposed approach. The new method has been compared with three of the most popular BSS algorithms: JADE, EASI, and restricted quasi-maximum likelihood (RQML).

Blind source separation of noisy mixtures using a semi-parametric approach with application to heavy-tailed signals

Abstract: In this paper, we propose a new semi-parametric approach for blind source separation (BSS) of noisy mixtures with application to heavy-tailed signals. The semi-parametric statistical principle is used to formulate the BSS problem as a maximum likelihood (ML) estimation. More precisely, this approach consists of combining the logspline model for sources density approximation with a stochastic version of the EM algorithm for mixing matrix estimation. The proposed method is truly blind to the particular underlying distribution of the mixed signals and performs simultaneously the estimation of the unknown probability density functions (pdf) of the source signals and the estimation of the mixing matrix. The application of logspline density approximation also enables the algorithm to be robust to modelization errors of the sources. In addition, it is robust against outliers and impulsive effect. Computer simulations are provided to illustrate the effectiveness of the proposed separation method comparatively with classical ones.

Robust quadratic time-frequency distributions for the analysis of mulicomponent FM signals in heavy-tailed noise

Abstract: We consider the problem of instantaneous frequency estimation of multicomponent frequency-modulated signals corrupted by additive heavy-tailed noise. For that, a new time-frequency distribution, named the robust modified B-distribution (R-MBD), is developed as a generalization of the robust minimax M-estimates to handle such signals. We show that this representation outperforms the robust polynomial Wigner-Ville distribution (r-PWVD) in term of high resolution for this class of non-stationary signals. The proposed approach is compared to the higher-order ambiguity function (HAF) algorithm, for the instantaneous frequency estimation of a multicomponent signal. Computer simulations show the superiority of the proposed algorithm over the HAF

Investigations on contrast functions for blind source separation based on non-Gaussianity and sparsity measures

Abstract: In this paper, we provide a systematic method to construct contrast functions through the use of sub- or super- additive functionals. The used sub- or super-additive functionals are applied to the distributions of the extracted sources to quantify the degree of non-Gaussianity or sparsity. In this work, we assume a completely blind scenario where one knows only the observations and the existence of at most one Gaussian independent component in the mixture. However, there is no a priori information about the mixing matrix nor about the source density. Some practical examples of useful contrast functions are introduced and discussed in order to illustrate the usefulness of the proposed approach.

Robust detection of distributed CA-CFAR in presence of extraneous tagets and non-Gaussian clutter

Abstract: This paper deals with distributed CA-CFAR detection in presence of Gaussi an and non-Gaussian clutter. In Gaussian environment, we propose to apply a wavelet transform based on soft-thresholding in multisensor CA-CFAR systems employing parallel decision fu­ sion in both homogeneous and non homogeneous background in the sense of the Neyman-Pearson (N-P) test. In that context, we propose two approaches to combine the data from the different CA-CFAR detectors to achieve even better detection performance. In the non-Gaussian environment, we propose another preprocess­ ing approach, based on a non-linear compressing filter, to reduce the noise effect. The three proposed new methods are shown to provide better detection performance, especially in lower SNR and in the presence of extraneous targets and heavy-tailed noise_