Neural Computation, Vol 11, Issue 2 417-441, Copyright © 1999 by The MIT Press

LETTERS

Independent component analysis using an extended infomax algorithm for mixed subgaussian and supergaussian sources

TW Lee, M Girolami and TJ Sejnowski
Computational Neurobiology Lab, The Salk Institute, 10010 North Torrey Pines Road, La Jolla, CA 92038, USA. tewon@salk.edu.

An extension of the infomax algorithm of Bell and Sejnowski (1995) is presented that is able blindly to separate mixed signals with sub- and supergaussian source distributions. This was achieved by using a simple type of learning rule first derived by Girolami (1997) by choosing negentropy as a projection pursuit index. Parameterized probability distributions that have sub- and supergaussian regimes were used to derive a general learning rule that preserves the simple architecture proposed by Bell and Sejnowski (1995), is optimized using the natural gradient by Amari (1998), and uses the stability analysis of Cardoso and Laheld (1996) to switch between sub- and supergaussian regimes. We demonstrate that the extended infomax algorithm is able to separate 20 sources with a variety of source distributions easily. Applied to high-dimensional data from electroencephalographic recordings, it is effective at separating artifacts such as eye blinks and line noise from weaker electrical signals that arise from sources in the brain.

This article has been cited by other articles:

				M. M. Van Hulle Sequential Fixed-Point ICA Based on Mutual Information Minimization Neural Comput., May 1, 2008; 20(5): 1344 - 1365. [Abstract] [Full Text] [PDF]

				C.-H. Zheng, D.-S. Huang, K. Li, G. Irwin, and Z.-L. Sun MISEP Method for Postnonlinear Blind Source Separation. Neural Comput., September 1, 2007; 19(9): 2557 - 2578. [Abstract] [Full Text] [PDF]

				M. Dyrholm, S. Makeig, and L. K. Hansen Model Selection for Convolutive ICA with an Application to Spatiotemporal Analysis of EEG. Neural Comput., April 1, 2007; 19(4): 934 - 955. [Abstract] [Full Text] [PDF]

				L. Xu One-Bit-Matching Theorem for ICA, Convex-Concave Programming on Polyhedral Set, and Distribution Approximation for Combinatorics. Neural Comput., February 1, 2007; 19(2): 546 - 569. [Abstract] [Full Text] [PDF]

				D.-S. Huang and C.-H. Zheng Independent component analysis-based penalized discriminant method for tumor classification using gene expression data Bioinformatics, August 1, 2006; 22(15): 1855 - 1862. [Abstract] [Full Text] [PDF]

				T.-K. KIM and J. KITTLER Composite Support Vector Machines with Extended Discriminative Features for Accurate Face Detection IEICE Trans D: Information, October 1, 2005; E88-D(10): 2373 - 2379. [Abstract] [PDF]

				B. Feige, K. Scheffler, F. Esposito, F. Di Salle, J. Hennig, and E. Seifritz Cortical and Subcortical Correlates of Electroencephalographic Alpha Rhythm Modulation J Neurophysiol, May 1, 2005; 93(5): 2864 - 2872. [Abstract] [Full Text] [PDF]

				K. Zhang and L.-W. Chan Extended Gaussianization Method for Blind Separation of Post-Nonlinear Mixtures Neural Comput., February 1, 2005; 17(2): 425 - 452. [Abstract] [Full Text] [PDF]

				Z.-Y. Liu, K.-C. Chiu, and L. Xu One-Bit-Matching Conjecture for Independent Component Analysis Neural Comput., February 1, 2004; 16(2): 383 - 399. [Abstract] [Full Text] [PDF]

				K. Kreutz-Delgado, J. F. Murray, B. D. Rao, K. Engan, T.-W. Lee, and T. J. Sejnowski Dictionary Learning Algorithms for Sparse Representation Neural Comput., February 1, 2003; 15(2): 349 - 396. [Abstract] [Full Text] [PDF]

				E. Doi, T. Inui, T.-W. Lee, T. Wachtler, and T. J. Sejnowski Spatiochromatic Receptive Field Properties Derived from Information-Theoretic Analyses of Cone Mosaic Responses to Natural Scenes Neural Comput., February 1, 2003; 15(2): 397 - 417. [Abstract] [Full Text] [PDF]

				F. J. Theis, A. Jung, C. G. Puntonet, and E. W. Lang Linear Geometric ICA: Fundamentals and Algorithms Neural Comput., February 1, 2003; 15(2): 419 - 439. [Abstract] [Full Text] [PDF]

				B. Sagi, S. C. Nemat-Nasser, R. Kerr, R. Hayek, C. Downing, and R. Hecht-Nielsen A Biologically Motivated Solution to the Cocktail Party Problem Neural Comput., July 1, 2001; 13(7): 1575 - 1602. [Abstract] [Full Text]

				J. S. Lee, D. S. Lee, J. Y. Ahn, G. J. Cheon, S.-K. Kim, J. S. Yeo, K. Seo, K. S. Park, J.-K. Chung, and M. C. Lee Blind Separation of Cardiac Components and Extraction of Input Function from H215O Dynamic Myocardial PET Using Independent Component Analysis J. Nucl. Med., June 1, 2001; 42(6): 938 - 943. [Abstract] [Full Text] [PDF]

				R. Everson and S. Roberts Independent Component Analysis: A Flexible Nonlinearity and Decorrelating Manifold Approach Neural Comput., November 15, 1999; 11(8): 1957 - 1983. [Abstract] [Full Text]

				S. Makeig, M. Westerfield, T.-P. Jung, J. Covington, J. Townsend, T. J. Sejnowski, and E. Courchesne Functionally Independent Components of the Late Positive Event-Related Potential during Visual Spatial Attention J. Neurosci., April 1, 1999; 19(7): 2665 - 2680. [Abstract] [Full Text] [PDF]