877 resultados para Redes Neurais Artificiais


Relevância:

100.00% 100.00%

Publicador:

Resumo:

The Artificial Neural Networks (ANN), which is one of the branches of Artificial Intelligence (AI), are being employed as a solution to many complex problems existing in several areas. To solve these problems, it is essential that its implementation is done in hardware. Among the strategies to be adopted and met during the design phase and implementation of RNAs in hardware, connections between neurons are the ones that need more attention. Recently, are RNAs implemented both in application specific integrated circuits's (Application Specific Integrated Circuits - ASIC) and in integrated circuits configured by the user, like the Field Programmable Gate Array (FPGA), which have the ability to be partially rewritten, at runtime, forming thus a system Partially Reconfigurable (SPR), the use of which provides several advantages, such as flexibility in implementation and cost reduction. It has been noted a considerable increase in the use of FPGAs for implementing ANNs. Given the above, it is proposed to implement an array of reconfigurable neurons for topologies Description of artificial neural network multilayer perceptrons (MLPs) in FPGA, in order to encourage feedback and reuse of neural processors (perceptrons) used in the same area of the circuit. It is further proposed, a communication network capable of performing the reuse of artificial neurons. The architecture of the proposed system will configure various topologies MLPs networks through partial reconfiguration of the FPGA. To allow this flexibility RNAs settings, a set of digital components (datapath), and a controller were developed to execute instructions that define each topology for MLP neural network.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Lung cancer is the most common of malignant tumors, with 1.59 million new cases worldwide in 2012. Early detection is the main factor to determine the survival of patients affected by this disease. Furthermore, the correct classification is important to define the most appropriate therapeutic approach as well as suggest the prognosis and the clinical disease evolution. Among the exams used to detect lung cancer, computed tomography have been the most indicated. However, CT images are naturally complex and even experts medical are subject to fault detection or classification. In order to assist the detection of malignant tumors, computer-aided diagnosis systems have been developed to aid reduce the amount of false positives biopsies. In this work it was developed an automatic classification system of pulmonary nodules on CT images by using Artificial Neural Networks. Morphological, texture and intensity attributes were extracted from lung nodules cut tomographic images using elliptical regions of interest that they were subsequently segmented by Otsu method. These features were selected through statistical tests that compare populations (T test of Student and U test of Mann-Whitney); from which it originated a ranking. The features after selected, were inserted in Artificial Neural Networks (backpropagation) to compose two types of classification; one to classify nodules in malignant and benign (network 1); and another to classify two types of malignancies (network 2); featuring a cascade classifier. The best networks were associated and its performance was measured by the area under the ROC curve, where the network 1 and network 2 achieved performance equal to 0.901 and 0.892 respectively.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Forecast is the basis for making strategic, tactical and operational business decisions. In financial economics, several techniques have been used to predict the behavior of assets over the past decades.Thus, there are several methods to assist in the task of time series forecasting, however, conventional modeling techniques such as statistical models and those based on theoretical mathematical models have produced unsatisfactory predictions, increasing the number of studies in more advanced methods of prediction. Among these, the Artificial Neural Networks (ANN) are a relatively new and promising method for predicting business that shows a technique that has caused much interest in the financial environment and has been used successfully in a wide variety of financial modeling systems applications, in many cases proving its superiority over the statistical models ARIMA-GARCH. In this context, this study aimed to examine whether the ANNs are a more appropriate method for predicting the behavior of Indices in Capital Markets than the traditional methods of time series analysis. For this purpose we developed an quantitative study, from financial economic indices, and developed two models of RNA-type feedfoward supervised learning, whose structures consisted of 20 data in the input layer, 90 neurons in one hidden layer and one given as the output layer (Ibovespa). These models used backpropagation, an input activation function based on the tangent sigmoid and a linear output function. Since the aim of analyzing the adherence of the Method of Artificial Neural Networks to carry out predictions of the Ibovespa, we chose to perform this analysis by comparing results between this and Time Series Predictive Model GARCH, developing a GARCH model (1.1).Once applied both methods (ANN and GARCH) we conducted the results' analysis by comparing the results of the forecast with the historical data and by studying the forecast errors by the MSE, RMSE, MAE, Standard Deviation, the Theil's U and forecasting encompassing tests. It was found that the models developed by means of ANNs had lower MSE, RMSE and MAE than the GARCH (1,1) model and Theil U test indicated that the three models have smaller errors than those of a naïve forecast. Although the ANN based on returns have lower precision indicator values than those of ANN based on prices, the forecast encompassing test rejected the hypothesis that this model is better than that, indicating that the ANN models have a similar level of accuracy . It was concluded that for the data series studied the ANN models show a more appropriate Ibovespa forecasting than the traditional models of time series, represented by the GARCH model

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Dissertação (mestrado)—Universidade de Brasília, Faculdade de Tecnologia, Departamento de Engenharia Mecânica, 2016.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

This work aims to obtain a low-cost virtual sensor to estimate the quality of LPG. For the acquisition of data from a distillation tower, software HYSYS ® was used to simulate chemical processes. These data will be used for training and validation of an Artificial Neural Network (ANN). This network will aim to estimate from available simulated variables such as temperature, pressure and discharge flow of a distillation tower, the mole fraction of pentane present in LPG. Thus, allowing a better control of product quality

Relevância:

100.00% 100.00%

Publicador:

Resumo:

O presente estudo teve como objetivo comparar a eficiência dos dados dos sensores Aster e ETM+/Landsat 7 na classificação do uso e cobertura da terra, com ênfase nos níveis de degradação das pastagens na Zona da Mata Mineira, através da utilização de redes neurais artificiais. Foram testadas três composições de uma imagem do sensor Aster e uma do ETM+/Landsat 7, para definição das melhores feições discriminantes para o classificador. As classes de uso e cobertura consideradas foram: floresta, café, área urbana/solo exposto e três níveis de degradação das pastagens (moderado, forte e muito forte). Utilizou-se o simulador de redes neurais Java Neural Network Simulator e o algoritmo empregado foi o back-propagation. Dentre as composições de imagens testadas o melhor resultado foi alcançado com a utilização das 9 bandas do Aster (30m) como variáveis discriminantes, que também permitiu uma melhor discriminação dos níveis de degradação das pastagens considerados. Este resultado é atribuído à melhor resolução espectral desta composição de imagem quando comparada às demais. Dentre as classes consideradas, a pastagem no nível de degradação muito forte foi a que apresentou o maior erro de classificação, em todas as composições, sendo bastante confundida com a pastagem no nível de degradação forte.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Este trabalho relata o desenvolvimento de uma aplicação capaz de reconhecer um vocabulário restrito de comandos de direcionamento pronunciados de forma isolada e independentes do locutor. Os métodos utilizados para efetivar o reconhecimento foram: técnicas clássicas de processamento de sinais e redes neurais artificiais. No processamento de sinais visou-se o pré-processamento das amostras para obtenção dos coeficientes cepstrais. Enquanto que para o treinamento e classificação foram utilizadas duas redes neurais distintas, as redes: Backpropagation e Fuzzy ARTMAP. Diversas amostras foram coletadas de diferentes usuários no sentido de compor um banco de dados flexível para o aprendizado das redes neurais, que garantisse uma representação satisfatória da grande variabilidade que apresentam as pronúncias entre as vozes dos usuários. Com a aplicação de tais técnicas, o reconhecimento demostrou-se eficaz, distinguindo cada um dos comandos com bons índices de acerto, uma vez que o sistema é independente do locutor.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Esse trabalho comparou, para condições macroeconômicas usuais, a eficiência do modelo de Redes Neurais Artificiais (RNAs) otimizadas por Algoritmos Genéticos (AGs) na precificação de opções de Dólar à Vista aos seguintes modelos de precificação convencionais: Black-Scholes, Garman-Kohlhagen, Árvores Trinomiais e Simulações de Monte Carlo. As informações utilizadas nesta análise, compreendidas entre janeiro de 1999 e novembro de 2006, foram disponibilizadas pela Bolsa de Mercadorias e Futuros (BM&F) e pelo Federal Reserve americano. As comparações e avaliações foram realizadas com o software MATLAB, versão 7.0, e suas respectivas caixas de ferramentas que ofereceram o ambiente e as ferramentas necessárias à implementação e customização dos modelos mencionados acima. As análises do custo do delta-hedging para cada modelo indicaram que, apesar de mais complexa, a utilização dos Algoritmos Genéticos exclusivamente para otimização direta (binária) dos pesos sinápticos das Redes Neurais não produziu resultados significativamente superiores aos modelos convencionais.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

O objetivo principal deste trabalho é propor uma metodologia de classificação de imagens de sensoriamento remoto que integre a importância de atributos de textura na seleção de feições, através da utilização de freqüências espaciais de cada classe textural e sua direção, com a eficiência das redes neurais artificiais para classificá-las. O processo é composto por uma etapa de filtragem baseada nos filtros de Gabor, seguida de uma fase de classificação através de uma rede neural Multi-Layer Perceptron com algoritmo BackPropagation. A partir da transformada de Fourier são estimados os parâmetros a serem utilizados na constituição dos filtros de Gabor, adequados às freqüências espaciais associadas a cada classe presente na imagem a ser classificada. Desta forma, cada filtro gera uma imagem filtrada. O conjunto de filtros determina um conjunto de imagens filtradas (canais texturais). A classificação pixel a pixel é realizada pela rede neural onde cada pixel é definido por um vetor de dimensionalidade igual ao número de filtros do conjunto. O processo de classificação através da rede neural Multi-Layer Perceptron foi realizado pelo método de classificação supervisionada. A metodologia de classificação de imagens de sensoriamento remoto proposta neste trabalho foi testada em imagens sintética e real de dimensões 256 x 256 pixels. A análise dos resultados obtidos é apresentada sob a forma de uma Matriz de Erros, juntamente com a discussão dos mesmos.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Este trabalho apresenta o estudo, investigação e realização de experimentos práticos, empregados na resolução do problema de reconhecimento de regiões promotoras em organismos da família Mycoplasmataceae. A partir disso, é proposta uma metodologia para a solução deste problema baseada nas Redes Neurais Artificiais. Os promotores são considerados trechos de uma seqüência de DNA que antecedem um gene, podem ser tratados como marcadores de uma seqüência de letras que sinalizam a uma determinada enzima um ponto de ligação. A posição onde se situa o promotor antecede o ponto de início do processo de transcrição, onde uma seqüência de DNA é transformada em um RNA mensageiro e, este potencialmente, em uma proteína. As Redes Neurais Artificiais representam modelos computacionais, inspirados no funcionamento de neurônios biológicos, empregadas com sucesso como classificadores de padrões. O funcionamento básico das Redes Neurais está ligado ao ajuste de parâmetros que descrevem um modelo representacional. Uma revisão bibliográfica de trabalhos relacionados, que empregam a metodologia de Redes Neurais ao problema proposto, demonstrou a sua viabilidade. Entretanto, os dados relativos à família Mycoplasmataceae apresentam determinadas particularidades de difícil compreensão e caracterização, num espaço restrito de amostras comprovadas. Desta forma, esta tese relata vários experimentos desenvolvidos, que buscam estratégias para explorar o conteúdo de seqüências de DNA, relativas à presença de promotores. O texto apresenta a discussão de seis experimentos e a contribuição de cada um para consolidação de um framework que agrega soluções robustas consideradas adequadas à solução do problema em questão.

Relevância:

100.00% 100.00%

Publicador:

Resumo:

One of the main activities in the petroleum engineering is to estimate the oil production in the existing oil reserves. The calculation of these reserves is crucial to determine the economical feasibility of your explotation. Currently, the petroleum industry is facing problems to analyze production due to the exponentially increasing amount of data provided by the production facilities. Conventional reservoir modeling techniques like numerical reservoir simulation and visualization were well developed and are available. This work proposes intelligent methods, like artificial neural networks, to predict the oil production and compare the results with the ones obtained by the numerical simulation, method quite a lot used in the practice to realization of the oil production prediction behavior. The artificial neural networks will be used due your learning, adaptation and interpolation capabilities

Relevância:

100.00% 100.00%

Publicador:

Resumo:

Post dispatch analysis of signals obtained from digital disturbances registers provide important information to identify and classify disturbances in systems, looking for a more efficient management of the supply. In order to enhance the task of identifying and classifying the disturbances - providing an automatic assessment - techniques of digital signal processing can be helpful. The Wavelet Transform has become a very efficient tool for the analysis of voltage or current signals, obtained immediately after disturbance s occurrences in the network. This work presents a methodology based on the Discrete Wavelet Transform to implement this process. It uses a comparison between distribution curves of signals energy, with and without disturbance. This is done for different resolution levels of its decomposition in order to obtain descriptors that permit its classification, using artificial neural networks