Independent Component Analysis and Blind Signal Separation: 6th International Conference, Ica 2006, Charleston, Sc, Usa, March 5-8, 2006, Proceedings

ISBN-13: 9783540326304 / Angielski / Miękka / 2006 / 980 str.

Justinian Rosca

Opis

This book constitutes the refereed proceedings of the 6th International Conference on Independent Component Analysis and Blind Source Separation, ICA 2006, held in Charleston, SC, USA, in March 2006. The 120 revised papers presented were carefully reviewed and selected from 183 submissions. The papers are organized in topical sections on algorithms and architectures, applications, medical applications, speech and signal processing, theory, and visual and sensory processing.

Spis treści

Algorithms and Architectures.- Simple LU and QR Based Non-orthogonal Matrix Joint Diagonalization.- Separation of Nonlinear Image Mixtures by Denoising Source Separation.- Second-Order Separation of Multidimensional Sources with Constrained Mixing System.- Fast Kernel Density Independent Component Analysis.- Csiszár’s Divergences for Non-negative Matrix Factorization: Family of New Algorithms.- Second-Order Blind Identification of Underdetermined Mixtures.- Differential Fast Fixed-Point BSS for Underdetermined Linear Instantaneous Mixtures.- Equivariant Algorithms for Estimating the Strong-Uncorrelating Transform in Complex Independent Component Analysis.- Blind Source Separation of Post-nonlinear Mixtures Using Evolutionary Computation and Order Statistics.- Model Structure Selection in Convolutive Mixtures.- Estimating the Information Potential with the Fast Gauss Transform.- K-EVD Clustering and Its Applications to Sparse Component Analysis.- An EM Method for Spatio-temporal Blind Source Separation Using an AR-MOG Source Model.- Markovian Blind Image Separation.- New Permutation Algorithms for Causal Discovery Using ICA.- Eigenvector Algorithms with Reference Signals for Frequency Domain BSS.- Sparse Coding for Convolutive Blind Audio Source Separation.- ICA-Based Binary Feature Construction.- A Novel Dimension Reduction Procedure for Searching Non-Gaussian Subspaces.- Estimating Non-Gaussian Subspaces by Characteristic Functions.- Independent Vector Analysis: An Extension of ICA to Multivariate Components.- A One-Bit-Matching Learning Algorithm for Independent Component Analysis.- Blind Separation of Underwater Acoustic Signals.- Partitioned Factor Analysis for Interference Suppression and Source Extraction.- Recursive Generalized Eigendecomposition for Independent Component Analysis.- Recovery of Sparse Representations by Polytope Faces Pursuit.- ICA Based Semi-supervised Learning Algorithm for BCI Systems.- State Inference in Variational Bayesian Nonlinear State-Space Models.- Quadratic MIMO Contrast Functions for Blind Source Separation in a Convolutive Context.- A Canonical Genetic Algorithm for Blind Inversion of Linear Channels.- Efficient Separation of Convolutive Image Mixtures.- Sparse Nonnegative Matrix Factorization Applied to Microarray Data Sets.- Minimum Support ICA Using Order Statistics. Part I: Quasi-range Based Support Estimation.- Minimum Support ICA Using Order Statistics. Part II: Performance Analysis.- Separation of Periodically Time-Varying Mixtures Using Second-Order Statistics.- An Independent Component Ordering and Selection Procedure Based on the MSE Criterion.- Riemannian Optimization Method on the Flag Manifold for Independent Subspace Analysis.- A Two-Stage Based Approach for Extracting Periodic Signals.- ICA by PCA Approach: Relating Higher-Order Statistics to Second-Order Moments.- Applications.- Separability of Convolutive Mixtures: Application to the Separation of Combustion Noise and Piston-Slap in Diesel Engine.- Blind Signal Separation on Real Data: Tracking and Implementation.- Compression of Multicomponent Satellite Images Using Independent Components Analysis.- Fixed-Point Complex ICA Algorithms for the Blind Separation of Sources Using Their Real or Imaginary Components.- Blind Estimation of Row Relative Degree Via Constrained Mutual Information Minimization.- Undoing the Affine Transformation Using Blind Source Separation.- Source Separation of Astrophysical Ice Mixtures.- Improvement on Multivariate Statistical Process Monitoring Using Multi-scale ICA.- Global Noise Elimination from ELF Band Electromagnetic Signals by Independent Component Analysis.- BLUES from Music: BLind Underdetermined Extraction of Sources from Music.- On the Performance of a HOS-Based ICA Algorithm in BSS of Acoustic Emission Signals.- Two Applications of Independent Component Analysis for Non-destructive Evaluation by Ultrasounds.- Blind Spatial Multiplexing Using Order Statistics for Time-Varying Channels.- Semi-blind Equalization of Wireless MIMO Frequency Selective Communication Channels.- Medical Applications.- Comparison of BSS Methods for the Detection of ?-Activity Components in EEG.- Analysis on EEG Signals in Visually and Auditorily Guided Saccade Task by FICAR.- Cogito Componentiter Ergo Sum.- Kernel Independent Component Analysis for Gene Expression Data Clustering.- Topographic Independent Component Analysis of Gene Expression Time Series Data.- Blind Source Separation of Cardiac Murmurs from Heart Recordings.- Derivation of Atrial Surface Reentries Applying ICA to the Standard Electrocardiogram of Patients in Postoperative Atrial Fibrillation.- Wavelet Denoising as Preprocessing Stage to Improve ICA Performance in Atrial Fibrillation Analysis.- Performance Study of Convolutive BSS Algorithms Applied to the Electrocardiogram of Atrial Fibrillation.- Brains and Phantoms: An ICA Study of fMRI.- Comparison of ICA Algorithms for the Isolation of Biological Artifacts in Magnetoencephalography.- Automatic De-noising of Doppler Ultrasound Signals Using Matching Pursuit Method.- Speech and Signal Processing.- A Novel Normalization and Regularization Scheme for Broadband Convolutive Blind Source Separation.- A Robust Method to Count and Locate Audio Sources in a Stereophonic Linear Instantaneous Mixture.- Convolutive Demixing with Sparse Discrete Prior Models for Markov Sources.- Independent Component Analysis for Speech Enhancement with Missing TF Content.- Harmonic Source Separation Using Prestored Spectra.- Underdetermined Convoluted Source Reconstruction Using LP and SOCP, and a Neural Approximator of the Optimizer.- Utilization of Blind Source Separation Algorithms for MIMO Linear Precoding.- Speech Enhancement Based on the Response Features of Facilitated EI Neurons.- Blind Separation of Sparse Sources Using Jeffrey’s Inverse Prior and the EM Algorithm.- Solution of Permutation Problem in Frequency Domain ICA, Using Multivariate Probability Density Functions.- ICA-Based Speech Features in the Frequency Domain.- Monaural Music Source Separation: Nonnegativity, Sparseness, and Shift-Invariance.- Complex FastIVA: A Robust Maximum Likelihood Approach of MICA for Convolutive BSS.- Under-Determined Source Separation: Comparison of Two Approaches Based on Sparse Decompositions.- Separation of Mixed Audio Signals by Source Localization and Binary Masking with Hilbert Spectrum.- ICA and Binary-Mask-Based Blind Source Separation with Small Directional Microphones.- Blind Deconvolution with Sparse Priors on the Deconvolution Filters.- Estimating the Spatial Position of Spectral Components in Audio.- Separating Underdetermined Convolutive Speech Mixtures.- Two Time-Frequency Ratio-Based Blind Source Separation Methods for Time-Delayed Mixtures.- On Calculating the Inverse of Separation Matrix in Frequency-Domain Blind Source Separation.- Nonnegative Matrix Factor 2-D Deconvolution for Blind Single Channel Source Separation.- Speech Enhancement in Short-Wave Channel Based on ICA in Empirical Mode Decomposition Domain.- Robust Preprocessing of Gene Expression Microarrays for Independent Component Analysis.- Single-Channel Mixture Decomposition Using Bayesian Harmonic Models.- Enhancement of Source Independence for Blind Source Separation.- Speech Enhancement Using ICA with EMD-Based Reference.- Theory.- Zero-Entropy Minimization for Blind Extraction of Bounded Sources (BEBS).- On the Identifiability Testing in Blind Source Separation Using Resampling Technique.- On a Sparse Component Analysis Approach to Blind Source Separation.- Post-nonlinear Underdetermined ICA by Bayesian Statistics.- Relationships Between the FastICA Algorithm and the Rayleigh Quotient Iteration.- Average Convergence Behavior of the FastICA Algorithm for Blind Source Separation.- Multivariate Scale Mixture of Gaussians Modeling.- Sparse Deflations in Blind Signal Separation.- Global Analysis of Log Likelihood Criterion.- A Comparison of Linear ICA and Local Linear ICA for Mutual Information Based Feature Ranking.- Analysis of Source Sparsity and Recoverability for SCA Based Blind Source Separation.- Analysis of Feasible Solutions of the ICA Problem Under the One-Bit-Matching Condition.- Kernel Principal Components Are Maximum Entropy Projections.- Super-Gaussian Mixture Source Model for ICA.- Instantaneous MISO Separation of BPSK Sources.- Blind Partial Separation of Instantaneous Mixtures of Sources.- Contrast Functions for Blind Source Separation Based on Time-Frequency Information-Theory.- Information–Theoretic Nonstationary Source Separation.- Local Convergence Analysis of FastICA.- Testing Significance of Mixing and Demixing Coefficients in ICA.- Cross-Entropy Optimization for Independent Process Analysis.- Uniqueness of Non-Gaussian Subspace Analysis.- A Maximum Likelihood Approach to Nonlinear Convolutive Blind Source Separation.- Visual and Sensory Processing.- On Separation of Semitransparent Dynamic Images from Static Background.- Facial Expression Recognition by ICA with Selective Prior.- An Easily Computable Eight Times Overcomplete ICA Method for Image Data.- The InfoMin Principle for ICA and Topographic Mappings.- Non-negative Matrix Factorization Approach to Blind Image Deconvolution.

O autorze

Simon Haykin, PhD, is Distinguished University Professor and Director of the Cognitive Systems Laboratory in the Faculty of Engineering at McMaster University. A world-renowned authority on adaptive and learning systems, Dr. Haykin has pioneered signal-processing techniques and systems for radar and communication applications, culminating in the study of cognitive dynamic systems, which has become his research passion. José C. Principe is BellSouth Professor in the Electrical and Computer Engineering Department at the University of Florida, Gainesville.