Bayesian blind separation of generalized hyperbolic processes in noisy and underdeterminate mixtures

In this paper, we propose a Bayesian sampling solution to the noisy blind separation of generalized hyperbolic signals. Generalized hyperbolic models, introduced by Barndorff-Nielsen in 1977, represent a parametric family able to cover a wide range of real signal distributions. The alternative construction of these distributions as a normal mean variance (continuous) mixture leads to an efficient implementation of the Markov chain Monte Carlo method applied to source separation. The incomplete data structure of the generalized hyperbolic distribution is indeed compatible with the hidden variable nature of the source separation problem. Both overdeterminate and underdeterminate noisy mixtures are solved by the same algorithm without a prewhitening step. Our algorithm involves hyperparameters estimation as well. Therefore, it can be used, independently, to fitting the parameters of the generalized hyperbolic distribution to real data

[1]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[2]  Moeness G. Amin,et al.  Blind source separation using time-frequency distributions: algorithm and asymptotic performance , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Hoon Kim,et al.  Monte Carlo Statistical Methods , 2000, Technometrics.

[4]  Hagai Attias,et al.  Independent Factor Analysis , 1999, Neural Computation.

[5]  M. Sørensen,et al.  Hyperbolic Processes in Finance , 2003 .

[6]  S. Rachev.  Handbook of heavy tailed distributions in finance , 2003 .

[7]  Dinh-Tuan Pham,et al.  Blind separation of instantaneous mixtures of nonstationary sources , 2001, IEEE Trans. Signal Process..

[8]  Ronald W. Golland,et al.  Principles of Random Variate Generation , 1990 .

[9]  Kiyotoshi Matsuoka,et al.  A neural net for blind separation of nonstationary signals , 1995, Neural Networks.

[10]  S. Adler.  Over-relaxation method for the Monte Carlo evaluation of the partition function for multiquadratic actions , 1981 .

[11]  Donald B. Rubin,et al.  Max-imum Likelihood from Incomplete Data , 1972 .

[12]  Simon J. Godsill,et al.  Bayesian Approach for Blind Separation of Underdetermined Mixtures of Sparse Sources , 2004, ICA.

[13]  Joe Brewer,et al.  Kronecker products and matrix calculus in system theory , 1978 .

[14]  J. Dagpunar.  Principles of Random Variate Generation , 1988 .

[15]  Jostein Lillestøl,et al.  Bayesian Estimation of NIG-parameters by Markov Chain Monte Carlo Methods , 2000 .

[16]  Radford M. Neal,et al.  Suppressing Random Walks in Markov Chain Monte Carlo Using Ordered Overrelaxation , 1995, Learning in Graphical Models.

[17]  Pierre Comon,et al.  Independent component analysis, A new concept? , 1994, Signal Process..

[18]  K. Prause.  The Generalized Hyperbolic Model: Estimation, Financial Derivatives, and Risk Measures , 1999 .

[19]  Terrence J. Sejnowski,et al.  An Information-Maximization Approach to Blind Separation and Blind Deconvolution , 1995, Neural Computation.

[20]  A. Cichocki,et al.  Blind separation of nonstationary sources in noisy mixtures , 2000 .

[21]  Hichem Snoussi,et al.  Fast joint separation and segmentation of mixed images , 2004, J. Electronic Imaging.

[22]  Ole E. Barndorff-Nielsen,et al.  Hyperbolic Distributions and Ramifications: Contributions to Theory and Application , 1981 .

[23]  Eric Moreau,et al.  High order contrasts for self-adaptive source separation criteria for complex source separation , 1996 .

[24]  Christian Jutten,et al.  Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture , 1991, Signal Process..

[25]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[26]  O. Barndorff-Nielsen.  Exponentially decreasing distributions for the logarithm of particle size , 1977, Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences.

[27]  Hichem Snoussi,et al.  Blind separation of noisy Gaussian stationary sources. Application to cosmic microwave background imaging , 2002, 2002 11th European Signal Processing Conference.

[28]  Antoine Souloumiac,et al.  Blind source detection and separation using second order non-stationarity , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[29]  Rostislav S. Protassov,et al.  EM-based maximum likelihood parameter estimation for multivariate generalized hyperbolic distributions with fixed λ , 2004, Stat. Comput..

[30]  A. Mohammad-Djafari,et al.  Information geometry and prior selection , 2003 .

[31]  H. Snoussi,et al.  Bayesian blind component separation for Cosmic Microwave Background observations , 2001 .

[32]  James P. Reilly,et al.  Blind source separation of convolved sources by joint approximate diagonalization of cross-spectral density matrices , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[33]  Aapo Hyvärinen,et al.  Gaussian moments for noisy independent component analysis , 1999, IEEE Signal Processing Letters.

[34]  Eric Moulines,et al.  Maximum likelihood for blind separation and deconvolution of noisy signals using mixture models , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[35]  Hichem Snoussi,et al.  Bayesian Unsupervised Learning for Source Separation with Mixture of Gaussians Prior , 2004, J. VLSI Signal Process..

[36]  Dimitris Karlis,et al.  Bayesian estimation of NIG models via Markov chain Monte Carlo methods , 2004 .