Independent Component Analysis and Signal Separation

1. Front Matter

   PDF

2. Theory

   1. A Flexible Component Model for Precision ICA

      • Jean-François Cardoso, Maude Martin

      Pages 1-8

   2. Blind Separation of Instantaneous Mixtures of Dependent Sources

      • Marc Castella, Pierre Comon

      Pages 9-16

   3. The Complex Version of the Minimum Support Criterion

      • Sergio Cruces, Auxiliadora Sarmiento, Iván Durán

      Pages 17-24

   4. Optimal Joint Diagonalization of Complex Symmetric Third-Order Tensors. Application to Separation of Non Circular Signals

      • Christophe De Luigi, Eric Moreau

      Pages 25-32

   5. Imposing Independence Constraints in the CP Model

      • Maarten De Vos, Lieven De Lathauwer, Sabine Van Huffel

      Pages 33-40

   6. Blind Source Separation of a Class of Nonlinear Mixtures

      • Leonardo Tomazeli Duarte, Christian Jutten

      Pages 41-48

   7. Independent Subspace Analysis Is Unique, Given Irreducibility

      • Harold W. Gutch, Fabian J. Theis

      Pages 49-56

   8. Optimization on the Orthogonal Group for Independent Component Analysis

      • Michel Journée, Pierre-Antoine Absil, Rodolphe Sepulchre

      Pages 57-64

   9. Using State Space Differential Geometry for Nonlinear Blind Source Separation

      • David N. Levin

      Pages 65-72

   10. Copula Component Analysis

       • Jian Ma, Zengqi Sun

       Pages 73-80

   11. On Separation of Signal Sources Using Kernel Estimates of Probability Densities

       • Oleg Michailovich, Douglas Wiens

       Pages 81-88

   12. Shifted Independent Component Analysis

       • Morten Mørup, Kristoffer H. Madsen, Lars K. Hansen

       Pages 89-96

   13. Modeling and Estimation of Dependent Subspaces with Non-radially Symmetric and Skewed Densities

       • Jason A. Palmer, Ken Kreutz-Delgado, Bhaskar D. Rao, Scott Makeig

       Pages 97-104

   14. On the Relationships Between Power Iteration, Inverse Iteration and FastICA

       • Hao Shen, Knut Hüper

       Pages 105-112

   15. A Sufficient Condition for the Unique Solution of Non-Negative Tensor Factorization

       • Toshio Sumi, Toshio Sakata

       Pages 113-120

   16. Colored Subspace Analysis

       • Fabian J. Theis, M. Kawanabe

       Pages 121-128

   17. Is the General Form of Renyi’s Entropy a Contrast for Source Separation?

       • Frédéric Vrins, Dinh-Tuan Pham, Michel Verleysen

       Pages 129-136

3. Algorithms

   1. A Variational Bayesian Algorithm for BSS Problem with Hidden Gauss-Markov Models for the Sources

      • Nadia Bali, Ali Mohammad-Djafari

      Pages 137-144

   2. A New Source Extraction Algorithm for Cyclostationary Sources

      • C. Capdessus, A. K. Nandi, N. Bouguerriou

      Pages 145-151

This volume contains the papers presented at the 7th International Conference on Independent Component Analysis (ICA) and Source Separation held in L- don, 9–12 September 2007, at Queen Mary, University of London. Independent Component Analysis and Signal Separation is one of the most exciting current areas of research in statistical signal processing and unsup- vised machine learning. The area has received attention from several research communities including machine learning, neural networks, statistical signal p- cessing and Bayesian modeling. Independent Component Analysis and Signal Separation has applications at the intersection of many science and engineering disciplinesconcernedwithunderstandingandextractingusefulinformationfrom data as diverse as neuronal activity and brain images, bioinformatics, com- nications, the World Wide Web, audio, video, sensor signals, or time series. This year’s event was organized by the EPSRC-funded UK ICA Research Network (www.icarn.org). There was also a minor change to the conference title this year with the exclusion of the word‘blind’. The motivation for this was the increasing number of interesting submissions using non-blind or semi-blind techniques that did not really warrant this label. Evidence of the continued interest in the ?eld was demonstrated by the healthy number of submissions received, and of the 149 papers submitted just over two thirds were accepted.

• DOM
• Estimator
• Information
• Minimum
• Minimum Description Length
• algorithms
• audio segmentation
• auditory perception
• calculus
• data mining
• denoising
• dynamical systems
• graphical models
• information theory
• multimed
• algorithm analysis and problem complexity

Policies and ethics