Ricardo Suyama

Unsupervised Processing of Geophysical Signals: A Review of Some Key Aspects of Blind Deconvolution and Blind Source Separation

This article reviews some key aspects of two important branches in unsupervised signal processing: blind deconvolution and blind source separation (BSS). It also gives an overview of their potential application in seismic processing, with an emphasis on seismic deconvolution. Finally, it presents illustrative results of the application, on both synthetic and real data, of a method for seismic deconvolution that combines techniques of blind deconvolution and blind source separation. Our implementation of this method contains some improvements overthe original method in the literature described.

Blind Compensation of Nonlinear Distortions: Application to Source Separation of Post-Nonlinear Mixtures

In this paper, we address the problem of blind compensation of nonlinear distortions. Our approach relies on the assumption that the input signal is bandlimited. We then make use of the classical result that the output of a nonlinearity has a wider spectrum than the one of the input signal. However, differently from previous works, our approach does not assume knowledge of the input signal bandwidth. The proposal is considered in the development of a two-stage method for blind source separation (BSS) in post-nonlinear (PNL) models. Indeed, once the functions present in the nonlinear stage of a PNL model are compensated, one can apply the well-established linear BSS algorithms to complete the task of separating the sources. Numerical experiments performed in different scenarios attest the viability of the proposal. Moreover, the proposed method is tested in a real situation where the data are acquired by smart chemical sensor arrays.

An immune-inspired information-theoretic approach to the problem of ICA over a Galois field

The problem of independent component analysis (ICA) was firstly formulated and studied in the context of real-valued signals and mixing models, but, recently, an extension of this original formulation was proposed to deal with the problem within the framework of finite fields. In this work, we propose a strategy to deal with ICA over these fields that presents two novel features: (i) it is based on the use of a cost function built directly from an estimate of the mutual information and (ii) it employs an artificial immune system to perform the search for efficient separating matrices, in contrast with the existing techniques, which are based on search schemes of an exhaustive character. The new proposal is subject to a comparative analysis based on different simulation scenarios and the work is concluded by an analysis of perspectives of practical application to digital and genomic data mining.

Characterization of multiscroll attractors using Lyapunov exponents and Lagrangian coherent structures.

The present work aims to apply a recently proposed method for estimating Lyapunov exponents to characterize-with the aid of the metric entropy and the fractal dimension-the degree of information and the topological structure associated with multiscroll attractors. In particular, the employed methodology offers the possibility of obtaining the whole Lyapunov spectrum directly from the state equations without employing any linearization procedure or time series-based analysis. As a main result, the predictability and the complexity associated with the phase trajectory were quantified as the number of scrolls are progressively increased for a particular piecewise linear model. In general, it is shown here that the trajectory tends to increase its complexity and unpredictability following an exponential behaviour with the addition of scrolls towards to an upper bound limit, except for some degenerated situations where a non-uniform grid of scrolls is attained. Moreover, the approach employed here also provides an easy way for estimating the finite time Lyapunov exponents of the dynamics and, consequently, the Lagrangian coherent structures for the vector field. These structures are particularly important to understand the stretching/folding behaviour underlying the chaotic multiscroll structure and can provide a better insight of phase space partition and exploration as new scrolls are progressively added to the attractor.

Blind extraction of chaotic sources from mixtures with stochastic signals based on recurrence quantification analysis

This work aims to present a new method to perform blind extraction of chaotic deterministic sources mixed with stochastic signals. This technique employs the recurrence quantification analysis (RQA), a tool commonly used to study dynamical systems, to obtain the separating system that recovers the deterministic source. The method is applied to invertible and underdetermined mixture models considering different stochastic sources and different RQA measures. A brief discussion about the influence of recurrence plot parameters on the robustness of the proposal is also provided and illustrated by a set of representative simulations.

Blind source separation of overdetermined linear-quadratic mixtures

This work deals with the problem of source separation in overdetermined linear-quadratic (LQ) models. Although the mixing model in this situation can be inverted by linear structures, we show that some simple independent component analysis (ICA) strategies that are often employed in the linear case cannot be used with the studied model. Motivated by this fact, we consider the more complex yet more robust ICA framework based on the minimization of the mutual information. Special attention is given to the development of a solution that be as robust as possible to suboptimal convergences. This is achieved by defining a method composed of a global optimization step followed by a local search procedure. Simulations confirm the effectiveness of the proposal.

Blind extraction of sparse components based on ℓ 0 -norm minimization

We investigate the application of cost functions based on the ℓ0-norm to the problem of blind source extraction (BSE). We show that if the sources have different levels of sparsity, then the minimization of the ℓ0-norm leads to the extraction of the sparsest component even when the sources are statistically dependent. We also study the conditions guaranteeing BSE when an approximation of the ℓ0-norm is considered. Finally, we provide a numerical example to illustrate the applicability of our proposal.

Blind extraction of the sparsest component

In this work, we present a discussion concerning some fundamental aspects of sparse component analysis (SCA), a methodology that has been increasingly employed to solve some challenging signal processing problems. In particular, we present some insights into the use of l1 norm as a quantifier of sparseness and its application as a cost function to solve the blind source separation (BSS) problem. We also provide results on experiments in which source extraction was successfully made when we performed a search for sparse components in the mixtures of sparse signals. Finally, we make an analysis of the behavior of this approach on scenarios in which the source signals are not sparse.

A Proposal for Blind Fir Equalization of Time-Varying Channels

The multimodal and time-varying aspects of blind equalization problems in communication systems are treated here by means of an immune-inspired strategy capable of estimating the coefficients of the FIR equalization filter in an unsupervised manner. The associated optimization problem is solved by means of a population-based search technique characterized by a dynamic control of the population size and diversity maintenance. Static and time-varying channels have been proposed in simulated scenarios, aiming at indicating the tracking capability derived from the adaptive adjustment of the coefficients of the blind equalizer

Music versus motor imagery for BCI systems a study using fMRI and EEG: Preliminary results

The development of brain-computer interfaces (BCIs) for disabled patients is currently a growing field of research. Most BCI systems are based on electroencephalography (EEG) signals, and within this group, systems using motor imagery (MI) are amongst the most flexible. However, for stroke patients, the motor areas of the brain are not always available for use in these types of devices. The aim of this work was to evaluate a set of imagery-based cognitive tasks (right-hand MI versus music imagery, with rest or “blank” periods in between), using functional Magnetic Resonance Imaging (fMRI) and EEG. Eleven healthy subjects (control group) and four stroke patients were evaluated with fMRI, and nine of the healthy subjects also underwent an EEG test. The fMRI results for the control group showed specific and statistically differentiable activation patterns for motor versus music imagery (t-test, p <; 0.001). For stroke patients the fMRI results showed a very large variability, with no common activation pattern for either of the imagery tasks. Corroborating this fact, EEG results concerning feature selection for minimizing the classification error (using the Davies-Bouldin index) have also found no common activation pattern, although a well-defined set of meaningful electrodes and frequencies was found for some subjects. In terms of classification performance using EEG data, this work has detected a group of subjects with classifier rate of success up to 60%, which is promising in view of the cognitive complexity of the adopted tasks.