Independent Component Analysis and Signal Separation: 8th International Conference, Ica 2009, Paraty, Brazil, March 15-18, 2009, Proceedings

ISBN-13: 9783642005985 / Angielski / Miękka / 2009 / 808 str.

Tulay Adali

Opis

This volume contains the papers presented at the 8th International Conf- ence on Independent Component Analysis (ICA) and Source Separation held in Paraty, Brazil, March 15-18, 2009. This year's event resulted from scienti?c collaborations between a team of researchers from ?ve di?erent Brazilian u- versities and received the support of the Brazilian Telecommunications Society (SBrT) as well as the ?nancial sponsorship of CNPq, CAPES and FAPERJ. Independent component analysis and signal separation is one of the most - citing current areas of research in statistical signal processing and unsupervised machine learning. The area has received attention from severalresearchcom- nities including machine learning, neural networks, statistical signal processing and Bayesian modeling. Independent component analysis and signal separation has applications at the intersection of many science and engineering disciplines concerned with understanding and extracting useful information from data as diverse as neuronal activity and brain images, bioinformatics, communications, the World Wide Web, audio, video, sensor signals, and time series.

Spis treści

Theory.- Stationary Subspace Analysis.- Reference Based Contrast Functions in a Semi-blind Context.- On the Relationships between MMSE and Information-Theoretic-Based Blind Criterion for Minimum BER Filtering.- Blind Separation of Cyclostationary Signals.- A Novel Subspace Clustering Method for Dictionary Design.- Comparison of Two Main Approaches to Joint SVD.- Optimal Performance of Second-Order Multidimensional ICA.- Using Signal Invariants to Perform Nonlinear Blind Source Separation.- Bayesian Robust PCA for Incomplete Data.- Independent Component Analysis (ICA) Using Pearsonian Density Function.- An Analysis of Unsupervised Signal Processing Methods in the Context of Correlated Sources.- Probabilistic Formulation of Independent Vector Analysis Using Complex Gaussian Scale Mixtures.- Modeling the Short Time Fourier Transform Ratio and Application to Underdetermined Audio Source Separation.- Minimum Determinant Constraint for Non-negative Matrix Factorization.- Separation of Convolutive Mixtures with Hybrid Sources.- Blind Extraction of Chaotic Sources from White Gaussian Noise Based on a Measure of Determinism.- Estimating Squared-Loss Mutual Information for Independent Component Analysis.- Complete Blind Subspace Deconvolution.- Fast Parallel Estimation of High Dimensional Information Theoretical Quantities with Low Dimensional Random Projection Ensembles.- Theoretical Analysis and Comparison of Several Criteria on Linear Model Dimension Reduction.- Factor Analysis as Data Matrix Decomposition: A New Approach for Quasi-Sphering in Noisy ICA.- Signal Subspace Separation Based on the Divergence Measure of a Set of Wavelets Coefficients.- ICA by Maximizing Non-stability.- On Optimal Selection of Correlation Matrices for Matrix-Pencil-Based Separation.- ICA with Sparse Connections: Revisited.- Algorithms and Architectures.- Source Separation of Phase-Locked Subspaces.- Online Subband Blind Source Separation for Convolutive Mixtures Using a Uniform Filter Bank with Critical Sampling.- Cebysev Coefficients – Based Algorithm for Estimating the ICA Model.- Histogram Based Blind Identification and Source Separation from Linear Instantaneous Mixtures.- Blind Source Separation of Post-Nonlinear Mixtures Using Evolutionary Computation and Gaussianization.- Adapted Deflation Approach for Referenced Contrast Optimization in Blind MIMO Convolutive Source Separation.- Blind Order Detection and Parameter Estimation of MISO-FIR Channels.- Hierarchical Extraction of Independent Subspaces of Unknown Dimensions.- On IIR Filters and Convergence Acceleration for Convolutive Blind Source Separation.- A Cascade System for Solving Permutation and Gain Problems in Frequency-Domain BSS.- A Method for Filter Shaping in Convolutive Blind Source Separation.- Cumulative State Coherence Transform for a Robust Two-Channel Multiple Source Localization.- Least Square Joint Diagonalization of Matrices under an Intrinsic Scale Constraint.- Iterative-Shift Cluster-Based Time-Frequency BSS for Fractional-Time-Delay Mixtures.- Blind Non-stationnary Sources Separation by Sparsity in a Linear Instantaneous Mixture.- Blind Separation of Noisy Mixtures of Non-stationary Sources Using Spectral Decorrelation.- Probabilistic Factorization of Non-negative Data with Entropic Co-occurrence Constraints.- A Sparsity-Based Method to Solve Permutation Indeterminacy in Frequency-Domain Convolutive Blind Source Separation.- Canonical Dual Approach to Binary Factor Analysis.- Soft Dimension Reduction for ICA by Joint Diagonalization on the Stiefel Manifold.- Estimating Phase Linearity in the Frequency-Domain ICA Demixing Matrix.- Nonlinear Blind Source Deconvolution Using Recurrent Prediction-Error Filters and an Artificial Immune System.- Arabica: Robust ICA in a Pipeline.- Biomedical Applications.- Estimating Hidden Influences in Metabolic and Gene Regulatory Networks.- Nonnegative Network Component Analysis by Linear Programming for Gene Regulatory Network Reconstruction.- ICA-Based Method for Quantifying EEG Event-Related Desynchronization.- Localization of Generalized Discharge Sources in Patients with Juvenile Myoclonic Epilepsy Using Independent Components Analysis.- Iterative Subspace Decomposition for Ocular Artifact Removal from EEG Recordings.- Denoising Single Trial Event Related Magnetoencephalographic Recordings.- Eye Movement Quantification in Functional MRI Data by Spatial Independent Component Analysis.- Non-independent BSS: A Model for Evoked MEG Signals with Controllable Dependencies.- Atrial Activity Extraction Based on Statistical and Spectral Features.- Blind Source Separation of Sparse Overcomplete Mixtures and Application to Neural Recordings.- BSS-Based Feature Extraction for Skin Lesion Image Classification.- Spike Detection and Sorting: Combining Algebraic Differentiations with ICA.- Image Processing.- Segmentation of Natural and Man-Made Structures by Independent Component Analysis.- Topographic Independent Component Analysis Based on Fractal and Morphology Applied to Texture Segmentation.- Image Source Separation Using Color Channel Dependencies.- Learning Natural Image Structure with a Horizontal Product Model.- Estimating Markov Random Field Potentials for Natural Images.- Blind Source Separation with Spatio-Spectral Sparsity Constraints – Application to Hyperspectral Data Analysis.- Image Coding and Compression with Sparse 3D Discrete Cosine Transform.- Bayesian Non-negative Matrix Factorization.- Blind Decomposition of Spectral Imaging Microscopy: A Study on Artificial and Real Test Data.- Image Denoising Using Sparse Representations.- Speech and Audio Processing.- Target Speech Enhancement in Presence of Jammer and Diffuse Background Noise.- Constructing Time-Frequency Dictionaries for Source Separation via Time-Frequency Masking and Source Localisation.- Time Frequency Masking Strategy for Blind Source Separation of Acoustic Signals Based on Optimally-Modified LOG-Spectral Amplitude Estimator.- Solving the Acoustic Echo Cancellation Problem in Double-Talk Scenario Using Non-Gaussianity of the Near-End Signal.- An ICA-Based Method for Blind Source Separation in Sparse Domains.- Extension of Sparse, Adaptive Signal Decompositions to Semi-blind Audio Source Separation.- Validity of the Independence Assumption for the Separation of Instantaneous and Convolutive Mixtures of Speech and Music Sources.- Limitations of the Spectrum Masking Technique for Blind Source Separation.- Improvement of the Initialization of ICA Time-Frequency Algorithms for Speech Separation.- Audio Watermark Detection Using Undetermined ICA.- Mixtures of Gamma Priors for Non-negative Matrix Factorization Based Speech Separation.- Other Applications.- An Implementation of Floral Scent Recognition System Using ICA Combined with Correlation Coefficients.- Ion-Selective Electrode Array Based on a Bayesian Nonlinear Source Separation Method.- A Robust and Precise Solution to Permutation Indeterminacy and Complex Scaling Ambiguity in BSS-Based Blind MIMO-OFDM Receiver.- Underdetermined BSS of MISO OSTBC Signals.- Narrow-Band Short-Time Frequency-Domain Blind Signal Separation of Passive Sonar Signals.- Blind Channel Identification in (2 ×1) Alamouti Coded Systems Based on Maximizing the Eigenvalue Spread of Cumulant Matrices.- ICA Mixture Modeling for the Classification of Materials in Impact-Echo Testing.- Binary Nonnegative Matrix Factorization Applied to Semi-conductor Wafer Test Sets.- High-Energy Particles Online Discriminators Based on Nonlinear Independent Components.- Network Traffic Flow Separation and Control Through a Hybrid ICA-Fuzzy Adaptive Algorithm.- Special Session on Evaluation.- The 2008 Signal Separation Evaluation Campaign: A Community-Based Approach to Large-Scale Evaluation.- Stereo Source Separation and Source Counting with MAP Estimation with Dirichlet Prior Considering Spatial Aliasing Problem.- Blind Spectral-GMM Estimation for Underdetermined Instantaneous Audio Source Separation.- Application of Two Time-Domain Convolutive Blind Source Separation Algorithms to the 2008 Signal Separation Evaluation Campaign (SiSEC) Data.- Permutation Correction in Blind Source Separation Using Sliding Subband Likelihood Function.- Underdetermined Instantaneous Audio Source Separation via Local Gaussian Modeling.

O autorze

Tülay Adali, PhD, is Professor of Electrical Engineering and Director of the Machine Learning for Signal Processing Laboratory at the University of Maryland, Baltimore County. Her research interests are in statistical and adaptive signal processing, with emphasis on nonlinear and complex-valued signal processing, and applications in biomedical data analysis and communications

Blurb

This book constitutes the refereed proceedings of the 8th International Conference on Independent Component Analysis and Signal Separation, ICA 2009, held in Paraty, Brazil, in March 2009.

The 97 revised papers presented were carefully reviewed and selected from 137 submissions. The papers are organized in topical sections on theory, algorithms and architectures, biomedical applications, image processing, speech and audio processing, other applications, as well as a special session on evaluation.