910 resultados para Integrated Expert Systems


Relevância:

80.00% 80.00%

Publicador:

Resumo:

This paper presents a methodology and a specialist tool for failure probability analysis of induction type watt-hour meters, considering the main variables related to their measurement degradation processes. The database of the metering park of a distribution company, named Elektro Electricity and Services Co., was used for determining the most relevant variables and to feed the data in the software. The modeling developed to calculate the watt-hour meters probability of failure was implemented in a tool through a user friendly platform, written in Delphi language. Among the main features of this tool are: analysis of probability of failure by risk range; geographical localization of the meters in the metering park, and automatic sampling of induction type watt-hour meters, based on a risk classification expert system, in order to obtain information to aid the management of these meters. The main goals of the specialist tool are following and managing the measurement degradation, maintenance and replacement processes for induction watt-hour meters. © 2011 IEEE.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

The automatic characterization of particles in metallographic images has been paramount, mainly because of the importance of quantifying such microstructures in order to assess the mechanical properties of materials common used in industry. This automated characterization may avoid problems related with fatigue and possible measurement errors. In this paper, computer techniques are used and assessed towards the accomplishment of this crucial industrial goal in an efficient and robust manner. Hence, the use of the most actively pursued machine learning classification techniques. In particularity, Support Vector Machine, Bayesian and Optimum-Path Forest based classifiers, and also the Otsu's method, which is commonly used in computer imaging to binarize automatically simply images and used here to demonstrated the need for more complex methods, are evaluated in the characterization of graphite particles in metallographic images. The statistical based analysis performed confirmed that these computer techniques are efficient solutions to accomplish the aimed characterization. Additionally, the Optimum-Path Forest based classifier demonstrated an overall superior performance, both in terms of accuracy and speed. © 2012 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Secondary phases such as Laves and carbides are formed during the final solidification stages of nickel based superalloy coatings deposited during the gas tungsten arc welding cold wire process. However, when aged at high temperatures, other phases can precipitate in the microstructure, like the γ″ and δ phases. This work presents a new application and evaluation of artificial intelligent techniques to classify (the background echo and backscattered) ultrasound signals in order to characterize the microstructure of a Ni-based alloy thermally aged at 650 and 950 °C for 10, 100 and 200 h. The background echo and backscattered ultrasound signals were acquired using transducers with frequencies of 4 and 5 MHz. Thus with the use of features extraction techniques, i.e.; detrended fluctuation analysis and the Hurst method, the accuracy and speed in the classification of the secondary phases from ultrasound signals could be studied. The classifiers under study were the recent optimum-path forest (OPF) and the more traditional support vector machines and Bayesian. The experimental results revealed that the OPF classifier was the fastest and most reliable. In addition, the OPF classifier revealed to be a valid and adequate tool for microstructure characterization through ultrasound signals classification due to its speed, sensitivity, accuracy and reliability. © 2013 Elsevier B.V. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Breast cancer is the most common cancer among women. In CAD systems, several studies have investigated the use of wavelet transform as a multiresolution analysis tool for texture analysis and could be interpreted as inputs to a classifier. In classification, polynomial classifier has been used due to the advantages of providing only one model for optimal separation of classes and to consider this as the solution of the problem. In this paper, a system is proposed for texture analysis and classification of lesions in mammographic images. Multiresolution analysis features were extracted from the region of interest of a given image. These features were computed based on three different wavelet functions, Daubechies 8, Symlet 8 and bi-orthogonal 3.7. For classification, we used the polynomial classification algorithm to define the mammogram images as normal or abnormal. We also made a comparison with other artificial intelligence algorithms (Decision Tree, SVM, K-NN). A Receiver Operating Characteristics (ROC) curve is used to evaluate the performance of the proposed system. Our system is evaluated using 360 digitized mammograms from DDSM database and the result shows that the algorithm has an area under the ROC curve Az of 0.98 ± 0.03. The performance of the polynomial classifier has proved to be better in comparison to other classification algorithms. © 2013 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

An important tool for the heart disease diagnosis is the analysis of electrocardiogram (ECG) signals, since the non-invasive nature and simplicity of the ECG exam. According to the application, ECG data analysis consists of steps such as preprocessing, segmentation, feature extraction and classification aiming to detect cardiac arrhythmias (i.e.; cardiac rhythm abnormalities). Aiming to made a fast and accurate cardiac arrhythmia signal classification process, we apply and analyze a recent and robust supervised graph-based pattern recognition technique, the optimum-path forest (OPF) classifier. To the best of our knowledge, it is the first time that OPF classifier is used to the ECG heartbeat signal classification task. We then compare the performance (in terms of training and testing time, accuracy, specificity, and sensitivity) of the OPF classifier to the ones of other three well-known expert system classifiers, i.e.; support vector machine (SVM), Bayesian and multilayer artificial neural network (MLP), using features extracted from six main approaches considered in literature for ECG arrhythmia analysis. In our experiments, we use the MIT-BIH Arrhythmia Database and the evaluation protocol recommended by The Association for the Advancement of Medical Instrumentation. A discussion on the obtained results shows that OPF classifier presents a robust performance, i.e.; there is no need for parameter setup, as well as a high accuracy at an extremely low computational cost. Moreover, in average, the OPF classifier yielded greater performance than the MLP and SVM classifiers in terms of classification time and accuracy, and to produce quite similar performance to the Bayesian classifier, showing to be a promising technique for ECG signal analysis. © 2012 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

This paper presents a novel segmentation method for cuboidal cell nuclei in images of prostate tissue stained with hematoxylin and eosin. The proposed method allows segmenting normal, hyperplastic and cancerous prostate images in three steps: pre-processing, segmentation of cuboidal cell nuclei and post-processing. The pre-processing step consists of applying contrast stretching to the red (R) channel to highlight the contrast of cuboidal cell nuclei. The aim of the second step is to apply global thresholding based on minimum cross entropy to generate a binary image with candidate regions for cuboidal cell nuclei. In the post-processing step, false positives are removed using the connected component method. The proposed segmentation method was applied to an image bank with 105 samples and measures of sensitivity, specificity and accuracy were compared with those provided by other segmentation approaches available in the specialized literature. The results are promising and demonstrate that the proposed method allows the segmentation of cuboidal cell nuclei with a mean accuracy of 97%. © 2013 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Besides optimizing classifier predictive performance and addressing the curse of the dimensionality problem, feature selection techniques support a classification model as simple as possible. In this paper, we present a wrapper feature selection approach based on Bat Algorithm (BA) and Optimum-Path Forest (OPF), in which we model the problem of feature selection as an binary-based optimization technique, guided by BA using the OPF accuracy over a validating set as the fitness function to be maximized. Moreover, we present a methodology to better estimate the quality of the reduced feature set. Experiments conducted over six public datasets demonstrated that the proposed approach provides statistically significant more compact sets and, in some cases, it can indeed improve the classification effectiveness. © 2013 Elsevier Ltd. All rights reserved.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Most railways in Latin America were built by private firms, often foreign owned. Over time, owing to a combination of nationalizations and competition from road transport, virtually all railways passed into government hands; the railroad industry became more and more of a white elephant for the Government because of the ever-increasing subsidies it swallowed up, its dwindling role in national economies, and a conviction that Governments should not be involved in productive activities. Consequently, the late 1980s saw the start of a trend towards denationalization of railways, with the latter being turned over to private, often foreign, interests. In this way, the railway industry in Latin America has come full circle in the space of 150 years. So far, there has not been any assessment of the recent privatization of railways in Latin America. However, the conclusion would probably be that: (i) privatization has on the whole been successful, and (ii) the results achieved would have been more positive still, had some things been done slightly differently. One problem is that the bidding process has failed to take into account the positive externalities associated with railways, such as the contribution they make to reducing road maintenance costs and environmental damage caused by road transport. Another unresolved issue is whether to put the entire railway system up for tender, or to invite separate bids for infrastructure and services. Economies of scale operate in the railway industry, favouring the existence of a number of rail companies. In the past, the railway companies of neighbouring countries such as Argentina and Paraguay, and Bolivia and Chile, enjoyed ties at director level, but these came to an end with the nationalization of railways. Now that the era of State involvement is itself drawing to a close, we can expect to see the formation of integrated railway systems, one of which might extend from Quijarro, on the border between Bolivia and Brazil, to Puerto Montt in the south of Chile.

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Pós-graduação em Agronomia (Ciência do Solo) - FCAV

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Nas regiões de clima tropical, o monocultivo da banana vem causando conseqüências ambientais desastrosas e, muitas vezes, impedindo uma exploração continuada de uma mesma área. A redução do rendimento é devido principalmente as limitações físico-químicas do solo e a rápida degradação do sistema radicular, agravada pela ação de parasitas do solo (nematóides, fungos, etc.). Em virtude destas limitações, várias iniciativas vem sendo buscadas para a minimização das perdas agronômicas e ambientais, destacando-se o melhoramento e a modificação genética, e a associação deste cultivo com espécies leguminosas. Porém uma das grandes dificuldades de avaliarmos os novos sistemas de cultivo alternativos concentra-se na falta de referenciais agronômicos relacionados principalmente com o funcionamento de sistemas de cultivos associados, especialmente relacionados aos fatores e condições que interferem diretamente na definição do rendimento da espécie principal. O presente estudo testou , em campo experimental, o uso de plantas de serviço associada a bananeira e seus efeitos na produção de biomassa durante seu o ciclo vegetativo. Isto porque é durante esta fase que a bananeira constrói sua capacidade de reservas de fotoassimilados e, consequentemente, define o potencial de produção e enchimento dos frutos. Além do monocultivo, definiu-se mais duas parcelas associadas com o feijão-de- porco: 1) o plantio simultâneo das duas espécies e; 2) o plantio de feijão-de-porco e, após 2 meses, a introdução da banana. Além de acompanhamento semanal das parcelas, realizou-se, bimensalmente, coletas destrutivas de dados sobre produção de matéria seca, superfície foliar e análise nutricional das plantas. Após a análise agronômica da fase vegetativa, aplicou-se a modelização dos sistemas de cultivo estudados e comparou-se os possíveis cenários sobre o rendimento final da bananeira, além de outros indicadores sobre os fatores de crescimento das plantas. Após o acompanhamento dos 7 primeiros meses do ciclo vegetativo, concluiu-se que a data de estabelecimento da associação foi determinante para o sucesso do cultivo associado. Podemos destacar que a associação entre a bananeira e o feijão-de-porco não causou limitações na produção de biomassa (4,2 ton/ha), quando comparada com o monocultivo (4,5 ton/ha). A redução do número de capinas também foi um indicador animador deste sistema de cultivo alternativo. Por outro lado, quando a bananeira foi plantada 60 dias após a leguminosa, a mesma representou uma séria limitação na produção de biomassa (2,7 ton/ha). Esta limitação deveu-se ao estado de forte competição devido a agressividade com que o feijão-de-porco recobria toda a parcela e alcançando uma altura (74 cm) superior que a muda de banana (29 cm). Em relação a primeira parte da metodologia aplicada - o diagnóstico agronômico -, a mesma foi eficiente para a avaliação do ciclo vegetativo da associação estudada, ficando a necessidade da continuidade do acompanhamento do ciclo reprodutivo, para a confirmação dos resultados em termos de formação e produção de frutos. Na fase de modelização, chegou-se a uma leitura dos resultados próxima dos resultados obtidos no campo. Em termos de rendimento em frutos, o monocultivo com adubação (400 kg/ha de nitrogênio) e irrigação (133 mm) teve um aumento na ordem de 50% no rendimento final (28 ton/ha) Quando comparada com a parcela nas condições reais do experimento (19,6 ton/ha). Já o rendimento em frutos da associação, apresentou o mesmo resultado com e sem adubação e irrigação (16 ton/ha). No tocante a contrução dos cenários, confirmou-se novamente algumas das vantagens da associação, principalmente na redução da adubação nitrogenada aplicada nos sistemas convencionais de cultivo. Finalmente, podemos imaginar a construção de várias formas de testar e otimizar o uso destes sistemas associados (cenários). Porém, confirma-se que a construção de novos referenciais agronômicos sobre sistemas de cultivo mais complexos (os cultivos associados) torna-se ainda muito necessário para a realização de avaliações mais precisas sobre estas alternativas. E, com estes novos referenciais técnicos, podemos imaginar, a médio e longo prazo, alguns dos benefícios das leguminosas sobre as propriedades físico-químicas do solo cultivado (cobertura viva, adubo verde, redução de adventícias, etc) e sobre a manutenção do rendimento dos cultivos (adubação verde).

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relevância:

80.00% 80.00%

Publicador:

Resumo:

Nesta tese é proposta uma metodologia para identificação automática de topologias de linhas telefônicas compostas de uma ou mais seções de linha, as quais são utilizadas em sistemas de linhas digitais de assinante (DSL, do inglês digital subscriber line). Métodos com esta finalidade são fundamentais para a qualificação da linha com o objetivo de instalação do serviço DSL, em especial na atualização para serviços como o VDSL2 ou para adoção de "vetorização". Com o intuito de ser relevante para as operadoras na qualificação de uma rede inteira, composta de milhões de linhas, é fundamental que, além de precisão, métodos de qualificação tenham baixo custo computacional. Os métodos desenvolvidos são baseados nessa premissa e fazem análise da resposta ao impulso e da resposta à reflectometria no domínio do tempo de uma dada linha. Esses sinais são analisados utilizando-se um método de detecção de bordas, baseado em transformada wavelet, para identificar e extrair características de sinal que contenham informação sobre a topologia da linha. Dependendo das características disponíveis, é utilizado um dos três sistemas especialistas desenvolvidos para interpretação dessas informações e identificação da topologia. Estas metodologias são avaliadas através de um conjunto de teste de linhas reais medidas em laboratório. Seus resultados são comparados com os resultados de dois outros métodos implementados a partir da literatura. Os resultados obtidos mostram que os métodos propostos são eficientes na estimação de informações da topologia da linha e possuem reduzido custo computacional quando comparados às implementações das outras técnicas avaliadas.