José Raimundo de Oliveira

Automatic feature selection for BCI: An analysis using the davies-bouldin index and extreme learning machines

In this work, we present a novel framework for automatic feature selection in brain-computer interfaces (BCIs). The proposal, which manipulates features generated in the frequency domain by an estimate of the power spectral density of the EEG signals, is based on feature optimization (with both binary and real coding) using a state-of-the-art artificial immune network, the cob-aiNet. In order to analyze the performance of the proposed framework, two approaches are adopted: a direct use of the Davies-Bouldin index and the use of metrics associated with the operation of an extreme learning machine (ELM) in the role of a classifier. The results reveal that the proposal has the potential of improving the performance of a BCI system, and also provide elements for an analysis of the spectral content of EEG signals and of the performance of ELMs in motor imagery paradigms.

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.

Information Generation and Lagrangian Coherent Structures in Multiscroll Attractors

Abstract The present work aims to apply a recently alternative approach to estimate the Lyapunov exponents that is suitable for such piecewise linear model in order of characterizing - with the aid of the metric entropy - the degree of information generated by several kinds of multiscroll attractors. Another analytical path is followed with the extraction of the corresponding Lagrangian coherent structures, which allows the determination of the dynamical system separatrices and also of the folding/stretching behavior that results in chaos. Overall, the reported study can be understood as an investigation, from distinct theoretical standpoints, of key aspects regarding the dynamic behavior of systems capable of engendering multiscroll structures.

A Microprocessor-Based Laboratory for Control Systems Analysis and Design 1

Abstract This paper discusses the structure of a new laboratory course in analysis and design of control systems. The laboratory has been implemented in the Faculty of Electrical Engineering at Unicamp and aims at providing an integrated environment for the experimental teaching of control systems with emphasis on the employment of digital technology. The distinguishing feature of the laboratory is the use of local microprocessor-based controllers connected to IBM-like personal computers equipped with analysis and design tools as for example Matlab/Simulink. After concluding the design, the student transmits the structure and parameters of the digital controller to the appropriate laboratory station, where each microprocessor controls a laboratory scale system. Implementation aspects of an experimental station are discussed in the paper.

Cooperative navigation and inter-vehicle communication using IEEE 802.15.4 and Zigbee

Abstract Following the technologies evolution of all kind of vehicles and parts of vehicles, it came together the increasing need for communication and interaction between these parts. Thus, it could be testified in few years the evolution of protocols, standards, methodologies and embedded systems created in order to maximize the security and the efficiency of all kinds of vehicles. Now there is a more complex task to solve that is to maximize the security and efficiency on vehicle systems and due to it there are some challenges to transpose like information exchange between vehicles and the right use of this information with local and global interactions.

Utilização do Controlador Neural por Linearização Feedback na Identificação e Controle da Velocidade de um Veiculo Experimental

This paper describe obtained results using the neural control by feedback linearization for the system identification and control of the speed of experimental car. It is known that the not controlled final speed of a experimental car is non linear due to some noise, obstacles or disturbances of the surface in which it moves. Thus, the objective of the use of the neural controller is to return the system of speed more robust to the parametric variations and mainly to compensate the non linear effects of the dependent gain of the margin of operation inherent of the speed systems. Here are discussed the experimental results that show a significant error reduction in steady-state and a uniformization of the permanent response of the closed-loop system.

A polygonal immune-inspired framework for broadband patch antenna design

In this work, we present a novel paradigm for the bottom-up project of patch antennas. This paradigm is based on a polygonal immune-inspired framework, being the chosen artificial immune system the CLONALG algorithm. In order to employ this new strategy, it was necessary to build a software platform to properly use the electromagnetic CST solver and provide a source engine to evolve antenna designs. We believe this development to be a contribution per se. The presented results show that the method was able to obtain low profile antennas with broadband characteristics by the exploration of unconventional patch shapes.