A unified balanced approach to multichannel blind deconvolution

In this paper, we explore the application of a common operator used in systems theory, viz., the delta operator, to formulate a unified theory of multichannel blind deconvolution (MBD) which is valid in both discrete and continuous time domains. Apart from providing a unified treatment of MBD problems, this formulation permits a smooth transition of the demixer from a discrete time domain to a continuous time domain when the sampling rate is high. Furthermore we give a unified treatment of a balanced parameterized state space formulation to solving the MBD problem in both discrete and continuous time domains when the number of states is unknown.

[1]  Fathi M. A. Salam,et al.  Voice extraction by on-line signal separation and recovery , 1999 .

[2]  M. Houry,et al.  Very high dynamic range and high sampling rate VME digitizing boards for physics experiments , 2005, IEEE Transactions on Nuclear Science.

[3]  R. Moddemeijer.  On estimation of entropy and mutual information of continuous distributions , 1989 .

[4]  Ah Chung Tsoi,et al.  Blind deconvolution of dynamical systems using a balanced parameterized state space approach , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[5]  Graham C. Goodwin,et al.  Digital control and estimation : a unified approach , 1990 .

[6]  A. Nandi.  Blind estimation using higher-order statistics , 1999 .

[7]  Te-Won Lee,et al.  Independent Component Analysis , 1998, Springer US.

[8]  S.C. Douglas,et al.  Multichannel blind deconvolution and equalization using the natural gradient , 1997, First IEEE Signal Processing Workshop on Signal Processing Advances in Wireless Communications.

[9]  R. A. Choudrey.  FLEXIBLE BAYESIAN INDEPENDENT COMPONENT ANALYSIS FOR BLIND SOURCE SEPARATION , 2001 .

[10]  Tzyy-Ping Jung,et al.  Imaging brain dynamics using independent component analysis , 2001, Proc. IEEE.

[11]  S. Amari,et al.  Natural Gradient Approach To Blind Separation Of Over- And Under-Complete Mixtures , 1999 .

[12]  M. Houry,et al.  Very high dynamic range and high-sampling rate VME digitizing boards for physics experiments , 2004, IEEE Symposium Conference Record Nuclear Science 2004..

[13]  K. Glover.  All optimal Hankel-norm approximations of linear multivariable systems and their L, ∞ -error bounds† , 1984 .

[14]  G. Golub,et al.  The restricted singular value decomposition: properties and applications , 1991 .

[15]  K. Schoen,et al.  100 GHz through-line sampler system with sampling rates in excess of 10 Gsamples/second , 2003, IEEE MTT-S International Microwave Symposium Digest, 2003.

[16]  Fathi M. A. Salam,et al.  Blind source recovery: algorithms for static and dynamic environments , 2001, IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222).

[17]  Liqing Zhang,et al.  Multichannel Blind Deconvolution of Non-minimum Phase System Using Cascade Structure , 2004, ICONIP.

[18]  Liqing Zhang,et al.  Natural gradient algorithm for blind separation of overdetermined mixture with additive noise , 1999, IEEE Signal Processing Letters.

[19]  R. Lambert.  Multichannel blind deconvolution: FIR matrix algebra and separation of multipath mixtures , 1996 .

[20]  G. Goodwin,et al.  High-speed digital signal processing and control , 1992, Proc. IEEE.

[21]  Donald Grahame Holmes,et al.  Delta operator digital filters for high performance inverter applications , 2003 .

[22]  Joydeep Ghosh,et al.  Relationship-based clustering and cluster ensembles for high-dimensional data mining , 2002 .

[23]  Fathi M. A. Salam,et al.  A data-derived quadratic independence measure for adaptive blind source recovery in practical applications , 2002, The 2002 45th Midwest Symposium on Circuits and Systems, 2002. MWSCAS-2002..

[24]  Andrzej Cichocki,et al.  Adaptive Blind Signal and Image Processing - Learning Algorithms and Applications , 2002 .

[25]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[26]  B. Moor,et al.  On the Use of the Singular Value Decomposition in Identification and Signal Processing , 1991 .

[27]  A. Cichocki,et al.  Blind Deconvolution of Dynamical Systems:A State-Space Approach , 2000 .

[28]  Hagai Attias,et al.  Blind Source Separation and Deconvolution: The Dynamic Component Analysis Algorithm , 1998, Neural Computation.

[29]  A. Raftery.  Choosing Models for Cross-Classifications , 1986 .

[30]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[31]  Shun-ichi Amari,et al.  Natural Gradient Works Efficiently in Learning , 1998, Neural Computation.

[32]  J. Maciejowski,et al.  System identification using balanced parametrizations , 1997, IEEE Trans. Autom. Control..

[33]  J. Rissanen.  Estimation of structure by minimum description length , 1982 .

[34]  Kari Torkkola,et al.  Blind deconvolution, information maximization and recursive filters , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[35]  Juha Karhunen,et al.  An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models , 2002, Neural Computation.

[36]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .