Sparse component analysis and blind source separation of underdetermined mixtures

In this letter, we solve the problem of identifying matrices S /spl isin/ /spl Ropf//sup n/spl times/N/ and A /spl isin/ /spl Ropf//sup m/spl times/n/ knowing only their multiplication X = AS, under some conditions, expressed either in terms of A and sparsity of S (identifiability conditions), or in terms of X (sparse component analysis (SCA) conditions). We present algorithms for such identification and illustrate them by examples.

[1]  Özgür Yilmaz,et al.  Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[2]  Miguel Pinzolas,et al.  Isolated hand-written digit recognition using a neurofuzzy scheme and multiple classification , 2002, J. Intell. Fuzzy Syst..

[3]  Barak A. Pearlmutter,et al.  Blind Source Separation by Sparse Decomposition in a Signal Dictionary , 2001, Neural Computation.

[4]  Terrence J. Sejnowski,et al.  Blind source separation of more sources than mixtures using overcomplete representations , 1999, IEEE Signal Processing Letters.

[5]  Julio Ibarrola,et al.  A neurofuzzy scheme for online identification of nonlinear dynamical systems with variable transfer function , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[6]  Michael Elad,et al.  Optimally sparse representation in general (nonorthogonal) dictionaries via ℓ1 minimization , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Miguel Pinzolas,et al.  Neighborhood based Levenberg-Marquardt algorithm for neural network training , 2002, IEEE Trans. Neural Networks.

[8]  Michael A. Saunders,et al.  Atomic Decomposition by Basis Pursuit , 1998, SIAM J. Sci. Comput..

[9]  Andrzej Cichocki,et al.  Adaptive blind signal and image processing , 2002 .

[10]  F. Abrard,et al.  FROM BLIND SOURCE SEPARATION TO BLIND SOURCE CANCELLATION IN THE UNDERDETERMINED CASE : A NEW APPROACH BASED ON TIME-FREQUENCY ANALYSIS , 2001 .

[11]  Fathi M. Salem,et al.  ALGEBRAIC OVERCOMPLETE INDEPENDENT COMPONENT ANALYSIS , 2003 .

[12]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[13]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[14]  Fabian J. Theis,et al.  A geometric algorithm for overcomplete linear ICA , 2004, Neurocomputing.

[15]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .