Sistema de controle de escoamento de gás natural em dutos de distribuição com detecção de vazamentos utilizando redes neurais

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Localização de falhas em linhas de transmissão utilizando decomposição harmônica e redes neurais artificiais

Este trabalho propõe a utilização de uma nova metodologia para a localização de falhas em linhas de transmissão (LT). Esta metodologia consiste na utilização da decomposição harmônica da corrente de fuga de uma linha e na aplicação de uma Rede Neural Artificial (RNA) capaz de distinguir padrões da condição normal de funcionamento e padrões de situações de falhas de uma LT. Foi utilizado um modelo Pi capaz de absorver dados reais de tensão e corrente de três fases e de alterar valores de R, L e C segundo modificações ambientais. Neste modelo foram geradas falhas em todas as torres com diferentes valores de capacitância. A saída fornecida pelo modelo é a decomposição da corrente de fuga do trecho considerado. Os dados de entrada e saída do modelo foram utilizados no treinamento da RNA desenvolvida. A aquisição de dados reais de tensão e corrente foi feita através de analisadores de parâmetros de qualidade de energia elétrica instalados nas extremidades de um trecho de LT, Guamá-Utinga, pertencente à Centrais Elétricas do Norte do Brasil ELETRONORTE. O cálculo dos parâmetros construtivos foi feito através do método matricial e melhorado através da utilização do Método de Elementos Finitos (MEF). A RNA foi desenvolvida com o auxílio do software Matlab. Para treinamento da RNA foi utilizado o algoritmo de Retropropagação Resiliente que apresentou um bom desempenho. A RNA foi treinada com dois conjuntos de dados de treinamento para analisar possíveis diferenças entre as saídas fornecidas pelos dois grupos. Nos dois casos apresentou resultados satisfatórios, possibilitando a localização de falhas no trecho considerado.

Aplicação de redes neurais artificiais na classificação de padrões filogeográficos com base na variabilidade genômica do DNA mitocondrial

Historicamente, o processo de formação das populações da Amazônia, assim como de todo território brasileiro, envolveu três grupos étnicos principais: o ameríndio, o europeu e o africano. Como conseqüência, estas populações possuem em geral constituição miscigenada do ponto de vista social e biológico. Desde o final do século passado, estudos do DNA mitocondrial (mtDNA) tem sido desenvolvidos com o propósito de estimar a mistura interétnica presente nestas populações. Para isto, é de fundamental importância a classificação de uma determinada linhagem de mtDNA em um dos mais de 250 haplogrupos/subclados propostos na literatura. Com o objetivo de desenvolver um sistema automatizado, preciso e acurado de classificação de seqüências (linhagens) de mtDNA, o presente trabalhou lançou mão da técnica de Redes Neurais Artificiais (RNA’s) tendo como base os estudos de filogeografia. Para esta classificação, foram desenvolvidas quatro redes neurais artificiais diretas, com múltiplas camadas e algoritmo de aprendizagem de retropropagação. As entradas de cada rede equivalem às posições nucleotídicas polimórficas da região hipervariável do DNA mitocondrial, as quais retornam como saída a classificação específica de cada linhagem. Posterior ao treinamento, todas as redes apresentaram índices de acerto de 100%, demonstrando que a técnica de Rede Neural Artificial pode ser utilizada, com êxito, na classificação de padrões filogeográficos com base no DNA mitocondrial.

Uso de redes neurais com adaptação de pesos por modos deslizantes para controle de sistemas e aplicações em máquinas elétricas

Pós-graduação em Engenharia Elétrica - FEIS

The effect of power-ultrasound on the pretreatment of acidified aqueous solutions of banana flower-stalk: Structural, chemical and statistical analysis

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Utilização de redes neurais artificiais aplicadas na discriminação de padrões de doenças florestais

Pós-graduação em Ciência Florestal - FCA

Utilização dos parâmetros físico-químicos e redes neurais artificiais na identificação dos méis de abelhas (Apis mellifera L.) produzidos no verão e inverno na microrregião de Campos de Jordão, São Paulo

The objective of this work was to typify, through physicochemical parameters, honey from Campos do Jordão’s microrregion, and verify how samples are grouped in accordance with the climatic production seasonality (summer and winter). It were assessed 30 samples of honey from beekeepers located in the cities of Monteiro Lobato, Campos do Jordão, Santo Antonio do Pinhal e São Bento do Sapucaí-SP, regarding both periods of honey production (November to February; July to September, during 2007 and 2008; n = 30). Samples were submitted to physicochemical analysis of total acidity, pH, humidity, water activity, density, aminoacids, ashes, color and electrical conductivity, identifying physicochemical standards of honey samples from both periods of production. Next, we carried out a cluster analysis of data using k-means algorithm, which grouped the samples into two classes (summer and winter). Thus, there was a supervised training of an Artificial Neural Network (ANN) using backpropagation algorithm. According to the analysis, the knowledge gained through the ANN classified the samples with 80% accuracy. It was observed that the ANNs have proved an effective tool to group samples of honey of the region of Campos do Jordao according to their physicochemical characteristics, depending on the different production periods.

Modelagem da irradiação direta na incidência normal em Botucatu: aprendizado de máquina, estatístico e linke

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

THE SLOAN DIGITAL SKY SURVEY CO-ADD: A GALAXY PHOTOMETRIC REDSHIFT CATALOG

We present and describe a catalog of galaxy photometric redshifts (photo-z) for the Sloan Digital Sky Survey (SDSS) Co-add Data. We use the artificial neural network (ANN) technique to calculate the photo-z and the nearest neighbor error method to estimate photo-z errors for similar to 13 million objects classified as galaxies in the co-add with r < 24.5. The photo-z and photo-z error estimators are trained and validated on a sample of similar to 83,000 galaxies that have SDSS photometry and spectroscopic redshifts measured by the SDSS Data Release 7 (DR7), the Canadian Network for Observational Cosmology Field Galaxy Survey, the Deep Extragalactic Evolutionary Probe Data Release 3, the VIsible imaging Multi-Object Spectrograph-Very Large Telescope Deep Survey, and the WiggleZ Dark Energy Survey. For the best ANN methods we have tried, we find that 68% of the galaxies in the validation set have a photo-z error smaller than sigma(68) = 0.031. After presenting our results and quality tests, we provide a short guide for users accessing the public data.

Machine learning methods for prediction of disulphide bonding states of cysteine residues in proteins

The goal of this thesis work is to develop a computational method based on machine learning techniques for predicting disulfide-bonding states of cysteine residues in proteins, which is a sub-problem of a bigger and yet unsolved problem of protein structure prediction. Improvement in the prediction of disulfide bonding states of cysteine residues will help in putting a constraint in the three dimensional (3D) space of the respective protein structure, and thus will eventually help in the prediction of 3D structure of proteins. Results of this work will have direct implications in site-directed mutational studies of proteins, proteins engineering and the problem of protein folding. We have used a combination of Artificial Neural Network (ANN) and Hidden Markov Model (HMM), the so-called Hidden Neural Network (HNN) as a machine learning technique to develop our prediction method. By using different global and local features of proteins (specifically profiles, parity of cysteine residues, average cysteine conservation, correlated mutation, sub-cellular localization, and signal peptide) as inputs and considering Eukaryotes and Prokaryotes separately we have reached to a remarkable accuracy of 94% on cysteine basis for both Eukaryotic and Prokaryotic datasets, and an accuracy of 90% and 93% on protein basis for Eukaryotic dataset and Prokaryotic dataset respectively. These accuracies are best so far ever reached by any existing prediction methods, and thus our prediction method has outperformed all the previously developed approaches and therefore is more reliable. Most interesting part of this thesis work is the differences in the prediction performances of Eukaryotes and Prokaryotes at the basic level of input coding when ‘profile’ information was given as input to our prediction method. And one of the reasons for this we discover is the difference in the amino acid composition of the local environment of bonded and free cysteine residues in Eukaryotes and Prokaryotes. Eukaryotic bonded cysteine examples have a ‘symmetric-cysteine-rich’ environment, where as Prokaryotic bonded examples lack it.

A New Prediction Model for Slope Stability Analysis

The instability of river bank can result in considerable human and land losses. The Po river is the most important in Italy, characterized by main banks of significant and constantly increasing height. This study presents multilayer perceptron of artificial neural network (ANN) to construct prediction models for the stability analysis of river banks along the Po River, under various river and groundwater boundary conditions. For this aim, a number of networks of threshold logic unit are tested using different combinations of the input parameters. Factor of safety (FS), as an index of slope stability, is formulated in terms of several influencing geometrical and geotechnical parameters. In order to obtain a comprehensive geotechnical database, several cone penetration tests from the study site have been interpreted. The proposed models are developed upon stability analyses using finite element code over different representative sections of river embankments. For the validity verification, the ANN models are employed to predict the FS values of a part of the database beyond the calibration data domain. The results indicate that the proposed ANN models are effective tools for evaluating the slope stability. The ANN models notably outperform the derived multiple linear regression models.

Investigation on the evolution of an indoor robotic localization system based on wireless networks

This work addresses the evolution of an artificial neural network (ANN) to assist in the problem of indoor robotic localization. We investigate the design and building of an autonomous localization system based on information gathered from wireless networks (WN). The article focuses on the evolved ANN, which provides the position of a robot in a space, as in a Cartesian coordinate system, corroborating with the evolutionary robotic research area and showing its practical viability. The proposed system was tested in several experiments, evaluating not only the impact of different evolutionary computation parameters but also the role of the transfer functions on the evolution of the ANN. Results show that slight variations in the parameters lead to significant differences on the evolution process and, therefore, in the accuracy of the robot position.

Oxygen isotopes, IRD and SST reconstruction for the interval MIS31-19 of IODP Site 306-U1314

Early and Mid-Pleistocene climate, ocean hydrography and ice sheet dynamics have been reconstructed using a high-resolution data set (planktonic and benthic d18O time series, faunal-based sea surface temperature (SST) reconstructions and ice-rafted debris (IRD)) record from a high-deposition-rate sedimentary succession recovered at the Gardar Drift formation in the subpolar North Atlantic (Integrated Ocean Drilling Program Leg 306, Site U1314). Our sedimentary record spans from late in Marine Isotope Stage (MIS) 31 to MIS 19 (1069-779 ka). Different trends of the benthic and planktonic oxygen isotopes, SST and IRD records before and after MIS 25 (~940 ka) evidence the large increase in Northern Hemisphere ice-volume, linked to the cyclicity change from the 41-kyr to the 100-kyr that occurred during the Mid-Pleistocene Transition (MPT). Beside longer glacial-interglacial (G-IG) variability, millennial-scale fluctuations were a pervasive feature across our study. Negative excursions in the benthic d18O time series observed at the times of IRD events may be related to glacio-eustatic changes due to ice sheets retreats and/or to changes in deep hydrography. Time series analysis on surface water proxies (IRD, SST and planktonic d18O) of the interval between MIS 31 to MIS 26 shows that the timing of these millennial-scale climate changes are related to half-precessional (10 kyr) components of the insolation forcing, which are interpreted as cross-equatorial heat transport toward high latitudes during both equinox insolation maxima at the equator.

Distribution of planktonic foraminifera during the Mid-Pleistocene of ODP Site 181-1123

Planktonic foraminiferal assemblages and artificial neural network estimates of sea-surface temperature (SST) at ODP Site 1123 (41°47.2'S, 171°29.9'W; 3290 m deep), east of New Zealand, reveal a high-resolution history of glacial-interglacial (G-I) variability at the Subtropical Front (STF) for the last 1.2 million years, including the Mid-Pleistocene climate transition (MPT). Most G-I cycles of ~100 kyr duration have short periods of cold glacial and warm deglacial climate centred on glacial terminations, followed by long temperate interglacial periods. During glacial-deglacial transitions, maximum abundances of subantarctic and subtropical taxa coincide with SST minima and maxima, and lead ice volume by up to 8 kyrs. Such relationships reflect the competing influence of subantarctic and subtropical surface inflows during glacial and deglacial periods, respectively, suggesting alternate polar and tropical forcing of southern mid-latitude ocean climate. The lead of SSTs and subtropical inflow over ice volume points to tropical forcing of southern mid-latitude ocean-climate during deglacial warming. This contrasts with the established hypothesis that southern hemisphere ocean climate is driven by the influence of continental glaciations. Based on wholesale changes in subantarctic and subtropical faunas, the last 1.2 million years are subdivided into 4-distinct periods of ocean climate. 1) The pre-MPT (1185-870 ka) has high amplitude 41-kyr fluctuations in SST, superimposed on a general cooling trend and heightened productivity, reflecting long-term strengthening of subantarctic inflow under an invigorated Antarctic Circumpolar Current. 2) The early MPT (870-620 ka) is marked by abrupt warming during MIS 21, followed by a period of unstable periodicities within the 40-100 kyr orbital bands, decreasing SST amplitudes, and long intervals of temperate interglacial climate punctuated by short glacial and deglacial phases, reflecting lower meridional temperature gradients. 3) The late MPT (620-435 ka) encompasses an abrupt decrease in the subantarctic inflow during MIS 15, followed by a period of warm equable climate. Poorly defined, low amplitude G-I variations in SSTs during this interval are consistent with a relatively stable STF and evenly balanced subantarctic and subtropical inflows, possibly in response to smaller, less dynamic polar icesheets. 4) The post-MPT (435-0 ka) is marked by a major climatic deterioration during MIS 12, and a return to higher amplitude 100 kyr-frequency SST variations, superimposed on a long term trend towards cooler SSTs and increased mixed-layer productivity as the subantarctic inflow strengthened and polar icesheets expanded.