Uso de equações de diferenças na obtenção de filtros para redução de ruído em sinais de voz no domínio wavelet

Pós-graduação em Engenharia Elétrica - FEIS

Um sistema para extração automática de keyframes a partir de fluxos de vídeo direcionado à reconstrução tridimensional de cenários virtuais

Pós-graduação em Televisão Digital: Informação e Conhecimento - FAAC

Desenvolvimento de redes neurais para previsão de cargas elétricas de sistemas de energia elétrica

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Estoque de biomassa e carbono florestal em unidades de paisagem na Amazônia: uma análise a partir da abordagem metodológica ecologia da paisagem

O presente trabalho tem por objetivo central demonstrar a variabilidade existente na floresta no que tange aos estoques de biomassa e carbono florestal acima do solo, a partir da identificação e caracterização, com base em técnicas de sensoriamento remoto, de unidades de paisagem em uma área situada no município de Belterra, região oeste do Estado do Pará, a partir da matriz teórico-conceitual da abordagem Ecologia da Paisagem. Para o alcance de tal proposição, a metodologia empregada partiu da revisão da literatura sobre o tema, aquisição de dados cartográficos e orbitais, uso de técnicas de sensoriamento remoto, coleta de dados em campo, tratamento e análise estatística. O trabalho está dividido em quatro capítulos, seguidos pelas considerações gerais da obra. Partindo da matriz teórico-metodológica da Ecologia da Paisagem, analisa-se a dinâmica socioambiental do município de Belterra, que atualmente experimenta a expansão das atividades agrícolas, com destaque para a agricultura mecanizada da soja. A partir da análise multitemporal de imagens Landsat do município pôde-se avaliar a distribuição da cobertura florestal existente no mesmo, bem como o padrão espacial de distribuição das principais unidades de paisagem identificadas. Considerando esse recorte, realizou-se a coleta de dados em campo via inventário florestal em quatro tipologias florestais (floresta de alto platô, floresta de baixo platô, vegetação secundária e tensão ecológica) para obtenção de parâmetros morfométricos da vegetação e posterior quantificação dos estoques de biomassa e carbono contidos em cada unidade, bem como observar o comportamento estrutural da floresta nas mesmas. A adoção da paisagem como escala espacial de análise mostrou-se bastante satisfatória na quantificação dos estoques de biomassa e carbono florestal ao permitir considerar a influência da dinâmica socioeconômica na redução desses estoques. Além disso, possibilitou constatar que o reconhecimento da heterogeneidade da cobertura florestal é um elemento fundamental para a obtenção de estimativas de carbono de acordo com as características estruturais da vegetação, que varia de acordo com a topografia do terreno, com as espécies existentes e com as características geográficas, o que envolve a tipologia climática, as características geomorfológicas, pedológicas e geológicas da área.

Aplicações da teoria de nós no estudo da estrutura de proteínas

Pós-graduação em Ciência e Tecnologia de Materiais - FC

Comparing support vector machines and artificial neural networks in the recognition of steering angle for driving of mobile robots through paths in plantations

The use of mobile robots turns out to be interesting in activities where the action of human specialist is difficult or dangerous. Mobile robots are often used for the exploration in areas of difficult access, such as rescue operations and space missions, to avoid human experts exposition to risky situations. Mobile robots are also used in agriculture for planting tasks as well as for keeping the application of pesticides within minimal amounts to mitigate environmental pollution. In this paper we present the development of a system to control the navigation of an autonomous mobile robot through tracks in plantations. Track images are used to control robot direction by pre-processing them to extract image features. Such features are then submitted to a support vector machine and an artificial neural network in order to find out the most appropriate route. A comparison of the two approaches was performed to ascertain the one presenting the best outcome. The overall goal of the project to which this work is connected is to develop a real time robot control system to be embedded into a hardware platform. In this paper we report the software implementation of a support vector machine and of an artificial neural network, which so far presented respectively around 93% and 90% accuracy in predicting the appropriate route. (C) 2013 The Authors. Published by Elsevier B.V. Selection and peer review under responsibility of the organizers of the 2013 International Conference on Computational Science

Reconhecimento de voz para aplicações em automação implementado em FPGA

In many movies of scientific fiction, machines were capable of speaking with humans. However mankind is still far away of getting those types of machines, like the famous character C3PO of Star Wars. During the last six decades the automatic speech recognition systems have been the target of many studies. Throughout these years many technics were developed to be used in applications of both software and hardware. There are many types of automatic speech recognition system, among which the one used in this work were the isolated word and independent of the speaker system, using Hidden Markov Models as the recognition system. The goals of this work is to project and synthesize the first two steps of the speech recognition system, the steps are: the speech signal acquisition and the pre-processing of the signal. Both steps were developed in a reprogrammable component named FPGA, using the VHDL hardware description language, owing to the high performance of this component and the flexibility of the language. In this work it is presented all the theory of digital signal processing, as Fast Fourier Transforms and digital filters and also all the theory of speech recognition using Hidden Markov Models and LPC processor. It is also presented all the results obtained for each one of the blocks synthesized e verified in hardware

Aplicação de técnicas de geoprocessamento para a avaliação da expansão urbana no municípo de Duque de Caxias (RJ) como subsídio ao monitoramento de dutos: trecho da faixa de dutos Rio de Janeiro - Belo Horizonte

Different forms of human pressure may occur in the pipeline ranges, due to the large extensions and various configurations of land use, which can pass through the pipelines. Due to the dynamics of these pressures, it is necessary to monitor temporal changes of land use and cover the surface. Under this theme, appears as extremely important to use products and techniques of remote sensing, as they allow the identification of objects of the land surface that may compromise the security and monitoring of the pipeline, and allows the extraction of information conditions on land use at different periods of time. Based on the above, this paper aims to examine in a temporal approach, the process of urban expansion in the municipality of Duque de Caxias, located on the outskirts of the metropolitan area of the state of Rio de Janeiro, as well as settlement patterns characteristic of areas that the changes occurred in the period 1987 to 2010. We used the technique of visual analysis to perform the change detection and the technique of image classification, aimed at monitoring human pressure over a stretch of track pipeline Rio de Janeiro - Belo Horizonte, located in the state of Rio de Janeiro. The stages of work involved the characterization of the study area, urban sprawl and the existing settlement patterns, through the analysis of bibliographic data. The processing of Landsat 5 images and the application of the technique of change detection were performed in three scenes for the years 1987, 1998 and 2010, while the classification process was performed on the image RapidEye for the year 2010. Can be noted an increase in urban area of approximately 22.38% and the change of land cover from natural to built. This growth is concentrated outside to the area of direct influence of the duct, occurring in the area of indirect influence of the enterprise. Regarding the settlement patterns of growth areas, it was observed that these are predominantly

Algorithms for automatic segmentation of bovine embryos produced

In vitro production has been employed in bovine embryos and quantification of lipids is fundamental to understand the metabolism of these embryos. This paper presents a unsupervised segmentation method for histological images of bovine embryos. In this method, the anisotropic filter was used in the differents RGB components. After pre-processing step, the thresholding technique based on maximum entropy was applied to separate lipid droplets in the histological slides in different stages: early cleavage, morula and blastocyst. In the postprocessing step, false positives are removed using the connected components technique that identify regions with excess of dye near pellucid zone. The proposed segmentation method was applied in 30 histological images of bovine embryos. Experiments were performed with the images and statistical measures of sensitivity, specificity and accuracy were calculated based on reference images (gold standard). The value of accuracy of the proposed method was 96% with standard deviation of 3%.

Estimation of croplands using indicator kriging and fuzzy classification

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Classification of intact açai (Euterpe oleracea Mart.) and jucara (Euterpe edulis Mart) fruits based on dry matter content by means of near infrared spectroscopy

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Determinação de sólidos solúveis e firmeza em frutos íntegros de pessegueiro por meio da espectroscopia do infravermelho próximo (NIR)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Gestar: formação de professores em serviço e a abordagem da geometri

This present article aims to present some results of a PhD research in which intended to answer the following investigation question: In which extent a Program of Teacher Education in service in the early years of elementary school, GESTAR, contributed to the development of positive attitudes about Geometry? The participants were twelve teachers from two schools in the State of Mato Grosso. The instruments for data collection were a range of attitudes towards Geometry (EARG) developed and experimented by Viana and Brito (2004). The results showed a meaningful change in Geometry of the data pre and post-experiment.

Um estudo sobre limites duais para o problema integrado de dimensionamento de lotes e sequenciamento da produção

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Matrix-vector multiplication and triangular linear solver using GPGPU for symmetric positive definite matrices derived from elliptic equations

The modern GPUs are well suited for intensive computational tasks and massive parallel computation. Sparse matrix multiplication and linear triangular solver are the most important and heavily used kernels in scientific computation, and several challenges in developing a high performance kernel with the two modules is investigated. The main interest it to solve linear systems derived from the elliptic equations with triangular elements. The resulting linear system has a symmetric positive definite matrix. The sparse matrix is stored in the compressed sparse row (CSR) format. It is proposed a CUDA algorithm to execute the matrix vector multiplication using directly the CSR format. A dependence tree algorithm is used to determine which variables the linear triangular solver can determine in parallel. To increase the number of the parallel threads, a coloring graph algorithm is implemented to reorder the mesh numbering in a pre-processing phase. The proposed method is compared with parallel and serial available libraries. The results show that the proposed method improves the computation cost of the matrix vector multiplication. The pre-processing associated with the triangular solver needs to be executed just once in the proposed method. The conjugate gradient method was implemented and showed similar convergence rate for all the compared methods. The proposed method showed significant smaller execution time.