Evolvable hardware applied to voice recognition

This paper presents some results of the application on Evolvable Hardware (EHW) in the area of voice recognition. Evolvable Hardware is able to change inner connections, using genetic learning techniques, adapting its own functionality to external condition changing. This technique became feasible by the improvement of the Programmable Logic Devices. Nowadays, it is possible to have, in a single device, the ability to change, on-line and in real-time, part of its own circuit. This work proposes a reconfigurable architecture of a system that is able to receive voice commands to execute special tasks as, to help handicapped persons in their daily home routines. The idea is to collect several voice samples, process them through algorithms based on Mel - Ceptrais theory to obtain their numerical coefficients for each sample, which, compose the universe of search used by genetic algorithm. The voice patterns considered, are limited to seven sustained Portuguese vowel phonemes (a, eh, e, i, oh, o, u).

Common architecture for discrete wavelet transform analysis and synthesis with sequential and constant processing elements

This paper adresses the problem on processing biological data such as cardiac beats, audio and ultrasonic range, calculating wavelet coefficients in real time, with processor clock running at frequency of present ASIC's and FPGA. The Paralell Filter Architecture for DWT has been improved, calculating wavelet coefficients in real time with hardware reduced to 60%. The new architecture, which also processes IDWT, is implemented with the Radix-2 or the Booth-Wallace Constant multipliers. Including series memory register banks, one integrated circuit Signal Analyzer, ultrasonic range, is presented.

Hausdorff dimension for non-hyperbolic repellers II: Da diffeomorphisms

We study non-hyperbolic repellers of diffeomorphisms derived from transitive Anosov diffeomorphisms with unstable dimension 2 through a Hopf bifurcation. Using some recent abstract results about non-uniformly expanding maps with holes, by ourselves and by Dysman, we show that the Hausdorff dimension and the limit capacity (box dimension) of the repeller are strictly less than the dimension of the ambient manifold.

Basin problem for Hénon-like attractors in arbitrary dimensions

We prove that Hénon-like strange attractors of diffeomorphisms in any dimensions, such as considered in [2],[7], and [9] support a unique Sinai-Ruelle-Bowen (SRB) measure and have the no-hole property: Lebesgue almost every point in the basin of attraction is generic for the SRB measure. This extends two-dimensional results of Benedicks-Young [4] and Benedicks-Viana [3], respectively.

Identification of structural parameters for active vibration control

The study of algorithms for active vibration control in flexible structures became an area of enormous interest for some researchers due to the innumerable requirements for better performance in mechanical systems, as for instance, aircrafts and aerospace structures. Intelligent systems, constituted for a base structure with sensors and actuators connected, are capable to guarantee the demanded conditions, through the application of diverse types of controllers. For the project of active controllers it is necessary, in general, to know a mathematical model that enable the representation in the space of states, preferential in modal coordinates to permit the truncation of the system and reduction in the order of the controllers. For practical applications of engineering, some mathematical models based in discrete-time systems cannot represent the physical problem, therefore, techniques of identification of system parameters must be used. The techniques of identification of parameters determine the unknown values through the manipulation of the input (disturbance) and output (response) signals of the system. Recently, some methods have been proposed to solve identification problems although, none of them can be considered as being universally appropriate to all the situations. This paper is addressed to an application of linear quadratic regulator controller in a structure where the damping, stiffness and mass matrices were identified through Chebyshev's polynomial functions.

3-Dimensional hopf bifurcation via averaging theory

We consider the Lorenz system ẋ = σ(y - x), ẏ = rx - y - xz and ż = -bz + xy; and the Rössler system ẋ = -(y + z), ẏ = x + ay and ż = b - cz + xz. Here, we study the Hopf bifurcation which takes place at q± = (±√br - b,±√br - b, r - 1), in the Lorenz case, and at s± = (c+√c2-4ab/2, -c+√c2-4ab/2a, c±√c2-4ab/2a) in the Rössler case. As usual this Hopf bifurcation is in the sense that an one-parameter family in ε of limit cycles bifurcates from the singular point when ε = 0. Moreover, we can determine the kind of stability of these limit cycles. In fact, for both systems we can prove that all the bifurcated limit cycles in a neighborhood of the singular point are either a local attractor, or a local repeller, or they have two invariant manifolds, one stable and the other unstable, which locally are formed by two 2-dimensional cylinders. These results are proved using averaging theory. The method of studying the Hopf bifurcation using the averaging theory is relatively general and can be applied to other 3- or n-dimensional differential systems.

Towards intelligent manufacturing

This article describes the application of an Artificial Intelligence Planner in a robotized assembly cell that can be integrated to a Flexible Manufacturing System. The objective is to allow different products to be automatically assembled in a single production line with no pre-established assembly plans. The planner function is to generate action plans to the robot, in real time, from two input information: the initial state (disposition of parts of the product in line) and the final state (configuration of the assembled product). Copyright © 2007 IFAC.

Infuěncia do relevo na produtividade e custos do harvester

Among the several variables that influence timber harvesting is the slope, which influences the productivity of forest machines. In this experiment the harvester was evaluated technically and economically while cutting and processing eucalyptus activity on different slope classes. The technical analysis included a study of time and movements by the method of continuous time; productivity was determined by the volume in cubic meters of wood processing. The economic analysis included the parameters of operational cost, production cost and energy consumption. The analysis of the data showed that productivity decreased according to the increase of the percent slope inclination, resulting in an effective work hour productivity increase from 18.72 to 39.71 m 3sc, with a mean of operating cost of US$ 78.78 per work hour.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

On the periodic solutions of a class of duffing differential equations

In this work we study the periodic solutions, their stability and bifurcation for the class of Duffing differential equation mathematical equation represented where C > 0, ε > 0 and Λ are real parameter, A(t), b(t) and h(t) are continuous T periodic functions and ε is sufficiently small. Our results are proved using the averaging method of first order.

Error estimates for a neumann problem in highly oscillating thin domains

In this work we analyze the convergence of solutions of the Poisson equation with Neumann boundary conditions in a two-dimensional thin domain with highly oscillatory behavior. We consider the case where the height of the domain, amplitude and period of the oscillations are all of the same order, and given by a small parameter e > 0. Using an appropriate corrector approach, we show strong convergence and give error estimates when we replace the original solutions by the first-order expansion through the Multiple-Scale Method.

Piecewise linear perturbations of a linear center

This paper is mainly devoted to the study of the limit cycles that can bifurcate from a linear center using a piecewise linear perturbation in two zones. We consider the case when the two zones are separated by a straight line Σ and the singular point of the unperturbed system is in Σ. It is proved that the maximum number of limit cycles that can appear up to a seventh order perturbation is three. Moreover this upper bound is reached. This result confirms that these systems have more limit cycles than it was expected. Finally, center and isochronicity problems are also studied in systems which include a first order perturbation. For the latter systems it is also proved that, when the period function, defined in the period annulus of the center, is not monotone, then it has at most one critical period. Moreover this upper bound is also reached.

Controle ótimo H 'INFINITO' com modificação de zeros para o problema de rastreamento em sistemas discretos usando LMI

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Uma abordagem para problemas e controle ótimo via métodos de Runge-Kutta e análise de erro

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Controle de movimentos de pacientes paraplégicos utilizando modelos fuzzy T-S

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)