A análise de imagens é uma das formas de avaliar o desenvolvimento das plantas, tanto para correlacionar aspectos biofísicos dos mesmos, como para a detecção de doenças. Através das imagens podem ser calculados índices vegetativos que se correlacionem com os teores de nutrientes nas folhas. Com essa perspectiva, o presente trabalho objetivou avaliar quais indices vegetativos melhor se correlacionariam com a taxa de fósforo nas folhas de tomateiros. Foi realizado o cultivo de uma cultivar de minitomate, com cinco doses de fósforo (0, 25, 50, 75 e 100%) do P recomendado (na formulação da solução nutritiva). Em diferentes etapas do desenvolvimento da planta foram coletadas amostras das folhas para obtenção das imagens, através de escâner e máquina fotográfica, e diagnose foliar. Foram determinadas as biorrespostas das plantas ao longo do tempo. Uma rede neural artificial foi desenvolvida para estimar os teores de fósforo foliares no minitomate grape. A análise do desenvolvimento da planta permitiu concluir que a dose 100% de P2O5 utilizada no experimento foi suficiente para suprir a demanda nutricional do minitomateiro. Aos 64 dias após o transplantio (DAT) foi observada a maior queda nos teores de fósforo nas folhas, coincidindo com o amadurecimento dos frutos. Propõe-se, para a cultivar estudada, que a dignose foliar seja feita aos 50 DAT. Os índices vegetativos obtidos pela análise de imagem e selecionados pela análise de componentes principais (ICVE e Bn, tanto da parte abaxial quanto adaxial) podem ser utilizados para estimar a diagnose foliar de P na cultivar de minitomate grape. A avaliação dos índices vegetativos indicou que a obtenção de imagens com o escâner é mais adequado do que com a câmera fotográfica. Para a cultivar estudada, verificou-se que na dosagem de 100% de P2O5 teor de P nas folhas fica abaixo de 4,0 g kg-1. Em relação à rede neural desenvolvida, ao categorizar os valores de P de acordo com a literatura, a mesma obteve uma taxa de acerto de 90%. / The analysis of images is one of the ways to evaluate the development of plants, both to correlate biophysical aspects of the same, as for the detection of diseases. Through the images can be calculated vegetative indexes that correlate with the contents of nutrients in the leaves. With this perspective, the present studied aimed to evaluate which vegetative indexes would best correlate with the phosphorus rate in tomato leaves. A minitomato grape cultivar with five phosphorus doses (0, 25, 50, 75 and 100%) of the recommended P (in the formulation of the nutrient solution) was carried out. At different stages of plant development, leaf samples were collected to obtain the images, with scanner and camera, and foliar diagnosis. The bio-responses of plants were determined over time. An artificial neural network was developed to estimate leaf phosphorus levels in the grape minitomate. The analysis of the development of the plant allowed to conclude that the dose 100% of P2O5 used in the experiment was enough to supply the nutritional demand of the minitomateiro. At 64 days after transplanting (DAT), the highest drop in phosphorus content in the leaves was observed, coinciding with the ripening of the fruits. It is proposed, for the studied cultivar, that the leaf dignity should be made at 50 DAT. The vegetative indexes obtained by the image analysis and selected by the principal components analysis (ICVE and Bn, both abaxial and adaxial) can be used to estimate the leaf diagnosis of P in the minitomate grape cultivar. The evaluation of vegetative indexes indicated that obtaining images with the scanner is more appropriate than with the photographic camera. For the cultivar studied, it was verified that in the dosage of 100% of P2O5 content of P in the leaves is below 4.0 g kg-1. In relation to the developed neural network, when categorizing the P values according to the literature, it obtained a 90% correctness rate.

Most research behind the use of Machine Learning models in the field of Human Activity Recognition focuses mainly on the classification of daily human activities and aerobic exercises. In this study, we focus on the use of 1 accelerometer and 2 gyroscope sensors to build a Deep Learning classifier to recognise 5 different strength exercises, as well as a null class. The strength exercises tested in this research are as followed: Bench press, bent row, deadlift, lateral rises and overhead press. The null class contains recordings of daily activities, such as sitting or walking around the house. The model used in this paper consists on the creation of consecutive overlapping fixed length sliding windows for each exercise, which are processed separately and act as the input for a Deep Convolutional Neural Network. In this study we compare different sliding windows lengths and overlap percentages (step sizes) to obtain the optimal window length and overlap percentage combination. Furthermore, we explore the accuracy results between 1D and 2D Convolutional Neural Networks. Cross validation is also used to check the overall accuracy of the classifiers, where the database used in this paper contains 5 exercises performed by 3 different users and a null class. Overall the models were found to perform accurately for window’s with length of 0.5 seconds or greater and provided a solid foundation to move forward in the creation of a more robust fully integrated model that can recognize a wider variety of exercises.

Orientador: Aparecido Augusto de Carvalho / Resumo: O desvio lateral da coluna e a escoliose alteram o equilíbrio corporal de uma pessoa e a distribuição de seu peso nos pés. Atualmente com o auxílio do baropodômetro é possível medir a distribuição do peso corporal nos pés, trazendo inovação no que concerne sobre os impactos da escoliose nos mesmos. As alterações da coluna vertebral não são visíveis pelo baropodômetro, logo apenas mensurando a pressão dos pés não é possível determinar uma escoliose e seus possíveis ângulos. Dessa forma, adota-se o objetivo de realizar três redes neurais para classificação de escolioses com dados obtidos pelo baropodômetro do Laboratório de Instrumentação e Engenharia Biomédica (LIEB). No desenvolvimento das redes foram observadas vinte e cinco mil redes neurais feitas para cada proposta, sendo a rede neural A dividida em dois grupos que classificam o desvio lateral A1 (0º a 9º) e a escoliose A2 (10º a 20º) , a rede B foi dividida em dois grupos, B1 (10º a 13º) e B2 (14º a 20º) e a rede C1 que abrange o grupos A1, B1 e B2. A rede A (1,2) obteve uma acurácia média de 70,06%, a rede B (1,2) teve uma a acurácia média em 73,6% e a rede C (1,2,3) classificou em média 56,5% dos dados corretamente. Com os resultados obtidos conclui-se que uma classificação entre três grupos é inviável e a rede A e B podem ser utilizadas como métodos para acompanhamento de evolução ao longo do tempo. / Abstract: The lateral deviation of the spine and scoliosis alter a person's body balance and the distribution of his weight in the feet. Nowadays, with the help of the baropodometer, it is possible to measure the distribution of body weight in the feet, bringing innovation in what concerns the impact of scoliosis on them. The changes in the spine are not visible by the baropodometer, so just by measuring the pressure of the feet it is not possible to determine a scoliosis and its possible angles. Thus, we adopted the objective of performing three neural networks to classify scoliosis with data obtained by the Baropodometer of the Laboratory of Instrumentation and Biomedical Engineering (LIEB). In the development of the networks twenty-five thousand neural networks were made for each proposal, the neural network A being divided into two groups that classified the lateral deviation A1 (0º to 9º) and the scoliosis A2 (10º to 20º), the network B was divided into two groups, B1 (10º to 13º) and B2 (14º to 20º), and the C1 network encompassing groups A1, B1 and B2. The network A (1,2) obtained an average accuracy of 70,06%, the network B (1,2) had an average accuracy of 73.6% and the network C (1,2,3) classified on average 56, 5% of the data correctly. With the results obtained it is concluded that a classification between three groups is not feasible and the network A and B can be used as methods to monitor evolution over time. / Mestre

We specify a class of non-linear and non-Gaussian models for which we estimate and forecast the conditional distributions with daily frequency. We use these forecasts to calculate VaR measures for three different equity markets (US, GB and Japan). These forecasts are evaluated on the basis of different statistical performance measures as well as on the basis of their economic costs that go along with the forecasted capital requirements. The results indicate that different performance measures generate different rankings of the models even within one financial market. We also find that for the three markets the improvement in the forecast by non-linear models over linear ones is negligible, while non-gaussian models significantly dominate the gaussian models. / Series: Report Series SFB "Adaptive Information Systems and Modelling in Economics and Management Science"

Úlceras cutâneas constituem um problema de saúde pública no mundo atual. A eficiência do seu tratamento é observada pela redução das áreas total, de fibrina (amarelo) e de granulação (vermelho) da úlcera, calculados manualmente e/ou por imagens, processos demorados e posteriores à consulta médica. O trabalho propõe uma nova técnica não-invasiva e automatizada de acompanhamento das úlceras por redes neurais artificiais (RNAs). Foram utilizadas imagens digitais do banco de imagens do ADUN (Ambulatório da Dermatologia de Úlceras Neurovasculares) do Hospital das Clínicas da FMRP-USP (Faculdade de Medicina de Ribeirão Preto da Universidade de São Paulo), escolhidas aleatoriamente, sendo 50 imagens para treinamento da RNA e 250 para o teste da RNA. Para validação da RNA foram criados os grupos: 1 (n=15 imagens poligonais com áreas e cores definidas previamente); 2 (n=15 imagens poligonais com áreas e cores definidas previamente, submetidas a variações de iluminação, brilho, contraste, saturação); 3 (n=15 imagens poligonais constituídas de texturas de fibrina e de granulação); 4 (n=15 imagens de úlceras cutâneas reais preenchidas totalmente em cor preta sua superfície). Para avaliar a sua aplicação clínica foram utilizadas 50 imagens padronizadas submetidas aos cálculos das áreas pela RNA. Os resultados da RNA foram comparados aos do programa Image J (segmentação manual) e/ou às medidas-padrão. Estatisticamente os programas foram considerados similares quando p > 0,05 pelo Teste t Student. Quando p < 0,05 e r positivo, considerou-se o coeficiente de correlação de Pearson. A base de imagens de úlceras cutâneas foi eficiente para a aquisição das imagens, para a criação e execução dos algoritmos de extração de cores, de treinamento e de teste da RNA. A rede neural artificial desenvolvida apresentou desempenho similar ao Image J e às medidas-padrão adotadas para a segmentação das figuras do grupo 1, sendo p > 0,05 para as áreas total, de fibrina e de granulação. Na avaliação de interferência de ruídos (grupo 2), foi verificado que tais fatores não interferiram na segmentação da área dos polígonos (p > 0,05), pela RNA e pelo Image J. Entretanto, apesar de interferirem na segmentação de cores de granulação, sendo p < 0,05, o coeficiente de correlação RNA/Image J foi de 0,90 com p < 0,0001. No grupo 3, os cálculos das áreas foram semelhantes pela RNA e pelo Image J (p > 0,05). Quando comparadas às áreas calculadas pelos programas às medidas-padrão, o coeficiente de correlação foi significante (p < 0,0001) para todas as áreas. A segmentação das áreas das úlceras do grupo 4 pela RNA foi validada quando comparada à segmentação manual pelo Image J (p> 0,05). A aplicação clínica da RNA sobre o banco de imagens foi semelhante ao Image J para a segmentação das áreas (p > 0,05). Enfim, a rede neural artificial desenvolvida no Matlab 7.0 mostrou desempenho eficaz e validado na segmentação das úlceras de perna quanto à automatização do cálculo das áreas total, de fibrina e de granulação, semelhante à oferecida manualmente pelo programa Image J. Além disso, mostrou-se de grande aplicação clínica devido a facilidade de sua utilização através da interface web criada, sua praticidade, não interferência do usuário (automatização), propriedades essas que a consolida como uma metodologia adequada para o acompanhamento dinâmico-terapêutico da evolução das úlceras cutâneas. / Cutaneous ulcers are a public health problem worldwide. The efficiency of their treatment is observed through the reduction on the total affected areas, slough (yellow) and granulation (red) of the ulcer, manually calculated and/or through images, which are delayed processes usually performed after medical consultation. This work proposes a new non-invasive and automated technique to follow-up ulcers through artificial neural networks (ANN). Digital images from the ADUN (Neurovascular Ulcers Dermatology Ambulatory) image bank - FMRP General Hospital (Ribeirão Preto Medical School - University of São Paulo) were used and randomly selected as follows: 50 images for ANN training and 250 for the ANN test. For the ANN validation, the following groups were created: 1 (n=15 polygonal images with areas and colors previously defined); 2 (n=15 polygonal images with areas and colors previously defined submitted to illumination, brightness, contrast and saturation variation); 3 (n=15 polygonal images composed of slough and granulation textures); 4 (n=15 images of actual cutaneous ulcers with their surface fully filled in black). To evaluate its clinical application, 50 standard images were used and submitted to calculation of areas using ANN. The ANN results were compared to those obtained with the Image J software (manual segmentation) and/or to standard measures. The programs were statistically considered similar when p > 0.05 through the t Student test. When p < 0.05 and r is positive, the Pearson correlation coefficient was considered. The cutaneous ulcer image bank was efficient for the acquisition of images, for the creation and execution of color extraction algorithms, ANN training and tests. The artificial neural network developed presented performance similar to that obtained with the Image J software and to standard measures adopted for the segmentation of figures from group 1, with p > 0.05 for total areas, slough and granulation. In the noise interference assessment (group 2), it was verified that such factors did not interfere in the polygons area segmentation (p > 0.05) through both ANN and Image J. However, although interfering in the color and granulation segmentation, with p < 0.05, the ANN/Image J correlation coefficient was of 0.90, with p < 0.0001. In group 3, the calculations of areas were similar through both ANN and Image J (p > 0.05). When compared to standard measures, the correlation coefficient was significant (p < 0.0001) for all areas. The segmentation of ulcer areas of group 4 through ANN was validated when compared to manual segmentation through Image J (p> 0.05). The clinical application of ANN on the image bank was similar to Image J for the segmentation of areas (p > 0.05). Finally, the Artificial Neural Network developed in Matlab 7.0 environment showed good performance and was validated in the segmentation of leg ulcers in relation to the automation of the calculation of total areas, slough and granulation, which was similar to that obtained with the Image J software. Moreover, it presented a large clinical application due to the easiness of its application through the web interface created and the non interference of the user (automation), properties that consolidate this technique as a suitable methodology for the dynamic-therapeutic follow-up of the evolution of cutaneous ulcers.

A Barragem de Itaipu é uma obra de engenharia de grande importância. Localizada na fronteira entre o Brasil e o Paraguai no Rio Paraná e com coordenadas geográficas aproximadas 25°24\'29\"S, 54°35\'21\"O, ela fornece energia elétrica a estes dois países e deve ser constantemente monitorada de modo a manter níveis de qualidade e segurança. Mais de dois mil instrumentos foram instalados e fornecem dados contínuos sobre diversas características da fundação e estrutura da barragem, incluindo mais de 650 piezômetros. A avaliação de níveis piezométricos em barragens é importante, pois refletem os valores de subpressão que atuam na estrutura da barragem. A utilização de novos métodos em tais análises pode permitir agilidade na tomada de decisões por parte da equipe de segurança de barragens. Dependendo do método aplicado, uma melhor compreensão do fenômeno no tempo e espaço pode ser obtida. Este estudo aplica Redes Neurais Artificiais (RNA) para simular o comportamento dos piezômetros instalados em uma descontinuidade geológica na fundação da Barragem de Itaipu. Ele considera diferentes tipos de dados de entrada em uma Rede Neural Multicamadas e determina a melhor arquitetura de RNA que mais se aproxima da situação real. / Itaipu Dam is an engineering work of high importance. Located at the border between Brazil and Paraguay in the Paraná River and with approximated geographical coordinates 25°24\'29\"S, 54°35\'21\"W, it provides electrical energy to these two countries and has to be constantly monitored in order to maintain its levels of quality and security. Over two thousand instruments have been installed and they provide continuous data about several characteristics of the dam foundation and structure, including more than 650 piezometers. The evaluation of piezometric levels in dams is important for it reflects the values of the uplift pressure that acts on the structure of the dam. The utilization of new methods in such an analysis can provide agility to decisions-taking by the security team of the dam. Depending on the method applied, a better comprehension of the phenomenon in time and space may be achieved. This study employs Artificial Neural Networks (ANN) to simulate the behavior of the piezometers installed in a geological discontinuity in the foundation of Itaipu Dam. It considers different types of entry data in a Multilayer Neural Network and determines the best ANN architecture that is closest to the real situation.

O presente trabalho de pesquisa enfoca a problemática da previsão de demandas com vistas à operação dos sistemas de abastecimento de água em tempo real, utilizando-se dados de consumo horários de água das cidades de São Carlos e Araraquara, SP, para que se identifique o modelo que produza os melhores ajustes. Foram estudadas as redes neurais artificiais Perceptron de Múltiplas Camadas (RNAs MLP), a Rede Neural Dinâmica (DAN2) e duas RNAs híbridas, sendo que estas últimas consistem em associar previsão por séries de Fourier com a RNA MLP e a DAN2, sendo denominadas respectivamente RNA-H e DAN2-H. As entradas fornecidas para os modelos de previsão foram escolhidas com base na revisão bibliográfica e por meio de análise de correlação, considerando os dados de consumo e as variáveis meteorológicas, tais como temperatura, umidade relativa do ar e ocorrência de chuva. Os melhores modelos de previsão utilizaram a DAN2, a qual se mostrou de manuseio mais fácil em relação às redes neurais de múltiplas camadas, pois dispensa o processo de tentativas e erros para se determinar a melhor arquitetura para os dados fornecidos ao modelo. Os melhores modelos de previsão para a próxima hora produziram um erro médio absoluto de 2,25 L/s (DAN2-H) para um subssetor de Araraquara, representado cerca de 8% do consumo médio, e 2,3 L/s (DAN2) para um setor de São Carlos, equivalente a 4% do consumo médio. / The present work focuses the problem of water demand forecasting for real time operation of WSS. The study was conducted using hourly consumption data from water distribution system from the cities of São Carlos, Araraquara, SP, to identify the model that fits better. It were studied the artificial neural network Multilayer Perceptron (ANN MLP), the Dynamic Neural Network (DAN2) and two hybrid ANN. The hybrid ANN is an association of the water demand prevision by series of Fourier with the ANN MLP and DAN2, which were called respectively ANN-H and DAN2-H. The inputs provided to the forecasting models were chosen based on literature review and correlation analysis, considering consumption data and meteorological variables, such as temperature, air relative humidity and rain occurrence. The best forecasting models were based on DAN2, which showed easy handling compared to other neural network with multiple layers, because it dispenses the trial and error procedure to find the best architecture for a given data. The best forecasting model for the next hour produced an absolute medium error of 2.25 L/s (DAN2-H) for a subsector from Araraquara, representing about 8% of the average consumption, and 2.30 L/s (DAN2) for a sector from São Carlos, which correspond to 4% of its average consumption.

Cardiovascular diseases are the largest mortality factor globally, and early diagnosis is essential for a proper medical response. Cardiac computed tomography can be used to acquire images for their diagnosis, but without radiation dose reduction the radiation emitted to the patient becomes a significant risk factor. By reducing the dose, the image quality is often compromised, and determining a diagnosis becomes difficult. This project proposes image quality enhancement with deep learning. A cycle-consistent generative adversarial neural network was fed low- and high-quality images with the purpose to learn to translate between them. By using a cycle-consistency cost it was possible to train the network without paired data. With this method, a low-quality image acquired from a computed tomography scan with dose reduction could be enhanced in post processing. The results were mixed but showed an increase of ventricular contrast and artifact mitigation. The technique comes with several problems that are yet to be solved, such as structure alterations, but it shows promise for continued development.

Two dimensional (2D) materials with interesting fundamental physics and potential applications attract tremendous efforts to study. The versatile properties of 2D materials can be further tailored by tuning the electronic structure with the layer-stacking arrangement, of which the main adjustable parameters include the thickness and the in-plane twist angle between layers. The Angle-Resolved Photoemission Spectroscopy (ARPES) has become a canonical tool to study the electronic structure of crystalline materials. The recent development of ARPES with sub-micrometre spatial resolution (micro-ARPES) has made it possible to study the electronic structure of materials with mesoscopic domains. In this thesis, we use micro-ARPES to investigate the spatially-resolved electronic structure of a series of few-layer materials: 1. We explore the electronic structure of the domains with different number of layers in few-layer graphene on copper substrate. We observe a layer- dependent substrate doping effect in which the Fermi surface of graphene shifts with the increase of number of layers, which is then explained by a multilayer effective capacitor model. 2. We systematically study the twist angle evolution of the energy band of twisted few-layer graphene over a wide range of twist angles (from 5° to 31°). We directly observe van Hove Singularities (vHSs) in twisted bilayer graphene with wide tunable energy range over 2 eV. In addition, the formation of multiple vHSs (at different binding energies) is observed in trilayer graphene. The large tuning range of vHS binding energy in twisted few-layer graphene provides a promising material base for optoelectrical applications with broad-band wavelength selectivity. 3. To better extract the energy band features from ARPES data, we propose a new method with a convolutional neural network (CNN) that achieves comparable or better results than traditional derivative based methods. Besides ARPES study, this thesis also includes the study of surface reconstruction for the layered material Bi2O2Se with the analysis of Scanning Tunnelling Microscopy (STM) images. To explain the origin of the pattern, we propose a tile model that produces the identical statistics with the experiment.

With the increased deterioration of infrastructure in this country, it has become important to find ways to maintain the strength and integrity of a structure over its design life. Being able to control the amount a structure displaces or vibrates during a seismic event, as well as being able to model this nonlinear behavior, provides a new challenge for structural engineers. This research proposes a wavelet-based adaptive neuro- fuzzy inference system for use in system identification and structural control of civil engineering structures. This algorithm combines aspects of fuzzy logic theory, neural networks, and wavelet transforms to create a new system that effectively reduces the number of sensors needed in a structure to capture its seismic response and the amount of computation time needed to model its nonlinear behavior. The algorithm has been tested for structural control using a three-story building equipped with a magnetorheological damper for system identification, an eight-story building, and a benchmark highway bridge. Each of these examples has been tested using a variety of earthquakes, including the El-Centro, Kobe, Hachinohe, Northridge, and other seismic events.