ONNIS-GI: uma rede neural oscilatória para segmentação de imagens implementada em arquitetura maciçamente paralela

A presente tese apresenta a concepção de uma rede neural oscilatória e sua realização em arquitetura maciçamente paralela, a qual é adequada à implementação de chips de visão digitais para segmentação de imagens. A rede proposta, em sua versão final, foi denominada ONNIS-GI (Oscillatory Neural Network for Image Segmentation with Global Inhibition) e foi inspirada em uma rede denominada LEGION (Locally Excitatory Globally Inhibitory Oscillator Network), também de concepção recente. Inicialmente, é apresentada uma introdução aos procedimentos de segmentação de imagens, cujo objetivo é o de situar e enfatizar a importância do tema abordado dentro de um contexto abrangente, o qual inclui aplicações de visão artificial em geral. Outro aspecto abordado diz respeito à utilização de redes neurais artificiais em segmentação de imagens, enfatizando as denominadas redes neurais oscilatórias, as quais têm apresentado resultados estimulantes nesta área. A implementação de chips de visão, integrando sensores de imagens e redes maciçamente paralelas de processadores, é também abordada no texto, ressaltando o objetivo prático da nova rede neural proposta. No estudo da rede LEGION, são apresentados resultados de aplicações originais desenvolvidas em segmentação de imagens, nos quais é verificada sua propriedade de separação temporal dos segmentos. A versão contínua da rede, um arranjo paralelo de neurônios baseados em equações diferenciais, apresenta elevada complexidade computacional para implementação em hardware digital e muitos parâmetros, com procedimento de ajuste pouco prático. Por outro lado, sua arquitetura maciçamente paralela apresenta-se particularmente adequada à implementação de chips de visão analógicos com capacidade de segmentação de imagens. Com base nos bons resultados obtidos nas aplicações desenvolvidas, é proposta uma nova rede neural, em duas versões, ONNIS e ONNIS-GI, as quais suplantam a rede LEGION em diversos aspectos relativos à implementação prática. A estrutura dos elementos de processamento das duas versões da rede, sua implementação em arquitetura maciçamente paralela e resultados de simulações e implementações em FPGA são apresentados, demonstrando a viabilidade da proposta. Como resultado final, conclui-se que a rede ONNIS-GI apresenta maior apelo de ordem prática, sendo uma abordagem inovadora e promissora na solução de problemas de segmentação de imagens, possuindo capacidade para separar temporalmente os segmentos encontrados e facilitando a posterior identificação dos mesmos. Sob o ponto de vista prático, a nova rede pode ser utilizada para implementar chips de visão digitais com arquitetura maciçamente paralela, explorando a velocidade de tais topologias e apresentando também flexibilidade para implementação de procedimentos de segmentação de imagens mais sofisticados.

Application of multivariable control using artificial neural networks in a debutanizer distillation column

LOPES, Jose Soares Batista et al. Application of multivariable control using artificial neural networks in a debutanizer distillation column.In: INTERNATIONAL CONGRESS OF MECHANICAL ENGINEERING - COBEM, 19, 5-9 nov. 2007, Brasilia. Anais... Brasilia, 2007

Controle preditivo neural aplicado à processos petroquímicos

A pesquisa tem como objetivo desenvolver uma estrutura de controle preditivo neural, com o intuito de controlar um processo de pH, caracterizado por ser um sistema SISO (Single Input - Single Output). O controle de pH é um processo de grande importância na indústria petroquímica, onde se deseja manter constante o nível de acidez de um produto ou neutralizar o afluente de uma planta de tratamento de fluidos. O processo de controle de pH exige robustez do sistema de controle, pois este processo pode ter ganho estático e dinâmica nãolineares. O controlador preditivo neural envolve duas outras teorias para o seu desenvolvimento, a primeira referente ao controle preditivo e a outra a redes neurais artificiais (RNA s). Este controlador pode ser dividido em dois blocos, um responsável pela identificação e outro pelo o cálculo do sinal de controle. Para realizar a identificação neural é utilizada uma RNA com arquitetura feedforward multicamadas com aprendizagem baseada na metodologia da Propagação Retroativa do Erro (Error Back Propagation). A partir de dados de entrada e saída da planta é iniciado o treinamento offline da rede. Dessa forma, os pesos sinápticos são ajustados e a rede está apta para representar o sistema com a máxima precisão possível. O modelo neural gerado é usado para predizer as saídas futuras do sistema, com isso o otimizador calcula uma série de ações de controle, através da minimização de uma função objetivo quadrática, fazendo com que a saída do processo siga um sinal de referência desejado. Foram desenvolvidos dois aplicativos, ambos na plataforma Builder C++, o primeiro realiza a identificação, via redes neurais e o segundo é responsável pelo controle do processo. As ferramentas aqui implementadas e aplicadas são genéricas, ambas permitem a aplicação da estrutura de controle a qualquer novo processo

A Learning Function for Parameter Reduction in Spiking Neural Networks with Radial Basis Function

Spiking neural networks - networks that encode information in the timing of spikes - are arising as a new approach in the artificial neural networks paradigm, emergent from cognitive science. One of these new models is the pulsed neural network with radial basis function, a network able to store information in the axonal propagation delay of neurons. Learning algorithms have been proposed to this model looking for mapping input pulses into output pulses. Recently, a new method was proposed to encode constant data into a temporal sequence of spikes, stimulating deeper studies in order to establish abilities and frontiers of this new approach. However, a well known problem of this kind of network is the high number of free parameters - more that 15 - to be properly configured or tuned in order to allow network convergence. This work presents for the first time a new learning function for this network training that allow the automatic configuration of one of the key network parameters: the synaptic weight decreasing factor.

Algoritmos inteligentes para auto-correção, auto-verificação e auto-validação de medidas em sensores

This work presents a set of intelligent algorithms with the purpose of correcting calibration errors in sensors and reducting the periodicity of their calibrations. Such algorithms were designed using Artificial Neural Networks due to its great capacity of learning, adaptation and function approximation. Two approaches willbe shown, the firstone uses Multilayer Perceptron Networks to approximate the many shapes of the calibration curve of a sensor which discalibrates in different time points. This approach requires the knowledge of the sensor s functioning time, but this information is not always available. To overcome this need, another approach using Recurrent Neural Networks was proposed. The Recurrent Neural Networks have a great capacity of learning the dynamics of a system to which it was trained, so they can learn the dynamics of a sensor s discalibration. Knowingthe sensor s functioning time or its discalibration dynamics, it is possible to determine how much a sensor is discalibrated and correct its measured value, providing then, a more exact measurement. The algorithms proposed in this work can be implemented in a Foundation Fieldbus industrial network environment, which has a good capacity of device programming through its function blocks, making it possible to have them applied to the measurement process

Otimização de superfícies seletivas de frequência com elementos pré-fractais utilizando rede neural MLP e algoritmos de busca populacional

This thesis describes design methodologies for frequency selective surfaces (FSSs) composed of periodic arrays of pre-fractals metallic patches on single-layer dielectrics (FR4, RT/duroid). Shapes presented by Sierpinski island and T fractal geometries are exploited to the simple design of efficient band-stop spatial filters with applications in the range of microwaves. Initial results are discussed in terms of the electromagnetic effect resulting from the variation of parameters such as, fractal iteration number (or fractal level), fractal iteration factor, and periodicity of FSS, depending on the used pre-fractal element (Sierpinski island or T fractal). The transmission properties of these proposed periodic arrays are investigated through simulations performed by Ansoft DesignerTM and Ansoft HFSSTM commercial softwares that run full-wave methods. To validate the employed methodology, FSS prototypes are selected for fabrication and measurement. The obtained results point to interesting features for FSS spatial filters: compactness, with high values of frequency compression factor; as well as stable frequency responses at oblique incidence of plane waves. This thesis also approaches, as it main focus, the application of an alternative electromagnetic (EM) optimization technique for analysis and synthesis of FSSs with fractal motifs. In application examples of this technique, Vicsek and Sierpinski pre-fractal elements are used in the optimal design of FSS structures. Based on computational intelligence tools, the proposed technique overcomes the high computational cost associated to the full-wave parametric analyzes. To this end, fast and accurate multilayer perceptron (MLP) neural network models are developed using different parameters as design input variables. These neural network models aim to calculate the cost function in the iterations of population-based search algorithms. Continuous genetic algorithm (GA), particle swarm optimization (PSO), and bees algorithm (BA) are used for FSSs optimization with specific resonant frequency and bandwidth. The performance of these algorithms is compared in terms of computational cost and numerical convergence. Consistent results can be verified by the excellent agreement obtained between simulations and measurements related to FSS prototypes built with a given fractal iteration

Especificação de um bloco funcional implementando rede neural para redes industriais foundations fieldbus

This work proposes the specification of a new function block according to Foundation Fieldbus standards. The new block implements an artificial neural network, which may be useful in process control applications. The specification includes the definition of a main algorithm, that implements a neural network, as well as the description of some accessory functions, which provide safety characteristics to the block operation. Besides, it also describes the block attributes emphasizing its parameters, which constitute the block interfaces. Some experimental results, obtained from an artificial neural network implementation using actual standard functional blocks on a laboratorial FF network, are also shown, in order to demonstrate the possibility and also the convenience of integrating a neural network to Fieldbus devices

Contribuição para o estudo do embarque de uma rede neural artificial em field programmable gate array (FPGA)

This study shows the implementation and the embedding of an Artificial Neural Network (ANN) in hardware, or in a programmable device, as a field programmable gate array (FPGA). This work allowed the exploration of different implementations, described in VHDL, of multilayer perceptrons ANN. Due to the parallelism inherent to ANNs, there are disadvantages in software implementations due to the sequential nature of the Von Neumann architectures. As an alternative to this problem, there is a hardware implementation that allows to exploit all the parallelism implicit in this model. Currently, there is an increase in use of FPGAs as a platform to implement neural networks in hardware, exploiting the high processing power, low cost, ease of programming and ability to reconfigure the circuit, allowing the network to adapt to different applications. Given this context, the aim is to develop arrays of neural networks in hardware, a flexible architecture, in which it is possible to add or remove neurons, and mainly, modify the network topology, in order to enable a modular network of fixed-point arithmetic in a FPGA. Five synthesis of VHDL descriptions were produced: two for the neuron with one or two entrances, and three different architectures of ANN. The descriptions of the used architectures became very modular, easily allowing the increase or decrease of the number of neurons. As a result, some complete neural networks were implemented in FPGA, in fixed-point arithmetic, with a high-capacity parallel processing

Análise de um controlador baseado no Jacobiano estimado da planta através de uma rede neural

This work presents an analysis of the control law based on an indirect hybrid scheme using neural network, initially proposed for O. Adetona, S. Sathanathan and L. H. Keel. Implementations of this control law, for a level plant of second order, was resulted an oscillatory behavior, even if the neural identifier has converged. Such results had motivated the investigation of the applicability of that law. Starting from that, had been made stability mathematical analysis and several implementations, with simulated plants and with real plants, for analyze the problem. The analysis has been showed the law was designed being despised some components of dynamic of the plant to be controlled. Thus, for plants that these components have a significant influence in its dynamic, the law tends to fail

Multidimensional polynomial powers of sigmoid (PPS) Wavelet neural networks

Wavelet functions have been used as the activation function in feedforward neural networks. An abundance of R&D has been produced on wavelet neural network area. Some successful algorithms and applications in wavelet neural network have been developed and reported in the literature. However, most of the aforementioned reports impose many restrictions in the classical backpropagation algorithm, such as low dimensionality, tensor product of wavelets, parameters initialization, and, in general, the output is one dimensional, etc. In order to remove some of these restrictions, a family of polynomial wavelets generated from powers of sigmoid functions is presented. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in pattern recognition tasks. As an example of application for the method proposed, it is studied the exclusive-or (XOR) problem.

A novel neural model to electrical load forecasting in transformers

The paper describes a novel neural model to electrical load forecasting in transformers. The network acts as identifier of structural features to forecast process. So that output parameters can be estimated and generalized from an input parameter set. The model was trained and assessed through load data extracted from a Brazilian Electric Utility taking into account time, current, tension, active power in the three phases of the system. The results obtained in the simulations show that the developed technique can be used as an alternative tool to become more appropriate for planning of electric power systems.

An efficient Hopfield network to solve economic dispatch problems with transmission system representation

Economic dispatch (ED) problems have recently been solved by artificial neural network approaches. Systems based on artificial neural networks have high computational rates due to the use of a massive number of simple processing elements and the high degree of connectivity between these elements. The ability of neural networks to realize some complex non-linear function makes them attractive for system optimization. All ED models solved by neural approaches described in the literature fail to represent the transmission system. Therefore, such procedures may calculate dispatch policies, which do not take into account important active power constraints. Another drawback pointed out in the literature is that some of the neural approaches fail to converge efficiently toward feasible equilibrium points. A modified Hopfield approach designed to solve ED problems with transmission system representation is presented in this paper. The transmission system is represented through linear load flow equations and constraints on active power flows. The internal parameters of such modified Hopfield networks are computed using the valid-subspace technique. These parameters guarantee the network convergence to feasible equilibrium points, which represent the solution for the ED problem. Simulation results and a sensitivity analysis involving IEEE 14-bus test system are presented to illustrate efficiency of the proposed approach. (C) 2004 Elsevier Ltd. All rights reserved.

Artificial neural networks and clustering techniques applied in the reconfiguration of distribution systems

One objective of the feeder reconfiguration problem in distribution systems is to minimize the power losses for a specific load. For this problem, mathematical modeling is a nonlinear mixed integer problem that is generally hard to solve. This paper proposes an algorithm based on artificial neural network theory. In this context, clustering techniques to determine the best training set for a single neural network with generalization ability are also presented. The proposed methodology was employed for solving two electrical systems and presented good results. Moreover, the methodology can be employed for large-scale systems in real-time environment.

Sensitivity analysis by neural networks applied to power systems transient stability

This work presents a procedure for transient stability analysis and preventive control of electric power systems, which is formulated by a multilayer feedforward neural network. The neural network training is realized by using the back-propagation algorithm with fuzzy controller and adaptation of the inclination and translation parameters of the nonlinear function. These procedures provide a faster convergence and more precise results, if compared to the traditional back-propagation algorithm. The adaptation of the training rate is effectuated by using the information of the global error and global error variation. After finishing the training, the neural network is capable of estimating the security margin and the sensitivity analysis. Considering this information, it is possible to develop a method for the realization of the security correction (preventive control) for levels considered appropriate to the system, based on generation reallocation and load shedding. An application for a multimachine power system is presented to illustrate the proposed methodology. (c) 2006 Elsevier B.V. All rights reserved.