Identificação da região periorbital utilizando a técnica SIFT em conjunto com rede neural híbrida

Nesta dissertação, foi utilizada a técnica SIFT (Scale Invariant Feature Transform) para o reconhecimento de imagens da área dos olhos (região periorbital). Foi implementada uma classificação das imagens em subgrupos internos ao banco de dados, utilizando-se das informações estatísticas provenientes dos padrões invariantes produzidos pela técnica SIFT. Procedeu-se a uma busca categorizada pelo banco de dados, ao invés da procura de um determinado padrão apresentado, através da comparação deste com cada padrão presente no banco de dados. A tais padrões foi aplicada uma abordagem estatística, através da geração da matriz de covariâncias dos padrões gerados, sendo esta utilizada para a categorização, tendo por base uma rede neural híbrida. A rede neural classifica e categoriza o banco de dados de imagens, criando uma topologia de busca. Foram obtidos resultados corretos de classificação de 76,3% pela rede neural híbrida, sendo que um algoritmo auxiliar determina uma hierarquia de busca, onde, ocorrendo uma errônea classificação, a busca segue em grupos de pesquisas mais prováveis.

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.

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

Análise de desempenho da rede neural artificial do tipo multilayer perceptron na era multicore

Artificial neural networks are usually applied to solve complex problems. In problems with more complexity, by increasing the number of layers and neurons, it is possible to achieve greater functional efficiency. Nevertheless, this leads to a greater computational effort. The response time is an important factor in the decision to use neural networks in some systems. Many argue that the computational cost is higher in the training period. However, this phase is held only once. Once the network trained, it is necessary to use the existing computational resources efficiently. In the multicore era, the problem boils down to efficient use of all available processing cores. However, it is necessary to consider the overhead of parallel computing. In this sense, this paper proposes a modular structure that proved to be more suitable for parallel implementations. It is proposed to parallelize the feedforward process of an RNA-type MLP, implemented with OpenMP on a shared memory computer architecture. The research consistes on testing and analizing execution times. Speedup, efficiency and parallel scalability are analyzed. In the proposed approach, by reducing the number of connections between remote neurons, the response time of the network decreases and, consequently, so does the total execution time. The time required for communication and synchronization is directly linked to the number of remote neurons in the network, and so it is necessary to investigate which one is the best distribution of remote connections

Uma análise da aplicação do modelo de Rede Neural RePART em Comitês de classificadores

RePART (Reward/Punishment ART) is a neural model that constitutes a variation of the Fuzzy Artmap model. This network was proposed in order to minimize the inherent problems in the Artmap-based model, such as the proliferation of categories and misclassification. RePART makes use of additional mechanisms, such as an instance counting parameter, a reward/punishment process and a variable vigilance parameter. The instance counting parameter, for instance, aims to minimize the misclassification problem, which is a consequence of the sensitivity to the noises, frequently presents in Artmap-based models. On the other hand, the use of the variable vigilance parameter tries to smoouth out the category proliferation problem, which is inherent of Artmap-based models, decreasing the complexity of the net. RePART was originally proposed in order to minimize the aforementioned problems and it was shown to have better performance (higer accuracy and lower complexity) than Artmap-based models. This work proposes an investigation of the performance of the RePART model in classifier ensembles. Different sizes, learning strategies and structures will be used in this investigation. As a result of this investigation, it is aimed to define the main advantages and drawbacks of this model, when used as a component in classifier ensembles. This can provide a broader foundation for the use of RePART in other pattern recognition applications

Rede neural não supervisionada baseada em transformada Karhunen-Loève para processamento, compressão e reconhecimento de imagens

The merit of the Karhunen-Loève transform is well known. Since its basis is the eigenvector set of the covariance matrix, a statistical, not functional, representation of the variance in pattern ensembles is generated. By using the Karhunen-Loève transform coefficients as a natural feature representation of a character image, the eigenvector set can be regarded as an feature extractor for a classifier.

Projeto E análise de uma rede neural para resolver problemas de programação dinâmica

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. Neural networks with feedback connections provide a computing model capable of solving a large class of optimization problems. This paper presents a novel approach for solving dynamic programming problems using artificial neural networks. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points which represent solutions (not necessarily optimal) for the dynamic programming problem. Simulated examples are presented and compared with other neural networks. The results demonstrate that proposed method gives a significant improvement.

Avaliação estatística de métodos de poda aplicados em neurônios intermediários da rede neural MLP

There are several papers on pruning methods in the artificial neural networks area. However, with rare exceptions, none of them presents an appropriate statistical evaluation of such methods. In this article, we proved statistically the ability of some methods to reduce the number of neurons of the hidden layer of a multilayer perceptron neural network (MLP), and to maintain the same landing of classification error of the initial net. They are evaluated seven pruning methods. The experimental investigation was accomplished on five groups of generated data and in two groups of real data. Three variables were accompanied in the study: apparent classification error rate in the test group (REA); number of hidden neurons, obtained after the application of the pruning method; and number of training/retraining epochs, to evaluate the computational effort. The non-parametric Friedman's test was used to do the statistical analysis.

Análise da incerteza na representação de classes de cobertura do solo urbano resultantes da aplicação de uma rede neural artificial

The great diversity of materials that characterizes the urban environment determines a structure of mixed classes in a classification of multiespectral images. In that sense, it is important to define an appropriate classification system using a non parametric classifier, that allows incorporating non spectral (such as texture) data to the process. They also allow analyzing the uncertainty associated to each class from the output alues of the network calculated in relation to each class. Considering these properties, an experiment was carried out. This experiment consisted in the application of an Artificial Neural Network aiming at the classification of the urban land cover of Presidente Prudente and the analysis of the uncertainty in the representation of the mapped thematic classes. The results showed that it is possible to discriminate the variations in the urban land cover through the application of an Artificial Neural Network. It was also possible to visualize the spatial variation of the uncertainty in the attribution of classes of urban land cover from the generated representations. The class characterized by a defined pattern as intermediary related to the impermeability of the urban soil presented larger ambiguity degree and, therefore, larger mixture.

Análise da incerteza na representação de classes temáticas resultantes da aplicação de uma rede neural artificial

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Detecção e classificação de curto-circuitos em sistemas de distribuição usando rede neural artificial ARTMAP nebulosa

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)