Introdução. O estudo e compreensão dos efeitos da poluição atmosférica podem contribuir para o planejamento de estratégias de controle de emissões de poluentes e na tomada de decisões em relação à saúde pública. Modelos de previsão da poluição do ar são importantes, na medida em que podem antecipar precauções e providências de ações públicas. Objetivo. Elaborar e analisar modelos de previsão do ozônio troposférico para a Região Metropolitana de São Paulo (RMSP). Métodos. Foram ajustados modelos de previsão de ozônio utilizando redes neurais artificiais (RNAs), denominadas técnicas de inteligência artificial. Os dados de entrada do modelo foram os meteorológicos, obtidos do CPTEC - Centro de Previsão de Tempo e Estudos Climáticos e do INMET - Instituto Nacional de Meteorologia e os dados do poluente ozônio monitorados pela CETESB - Companhia Ambiental do Estado de São Paulo. Foram considerados, para o ozônio, o padrão nacional de qualidade do ar (1 hora) e o padrão estadual de qualidade do ar (8 horas). Os dados foram distribuídos entre as médias do período da manhã (07h às 12h) e as médias do período da tarde (13h às 18h), obtendo-se como saída as concentrações máximas de ozônio para o período da tarde. O período analisado foi de 2008 a 2014. Resultados. Foram realizados 311 testes distribuídos de acordo com o padrão de qualidade do ar do ozônio (O3-1h ou O3-8h) e a origem dos dados meteorológicos (CPTEC ou INMET). Os valores de ozônio observados e estimados mostraram-se muito bem correlacionados. Para os ajustes usando o banco de dados do CPTEC, os melhores resultados das estatísticas de verificação para O3-1h foram: A=90 por cento ; B=0,41; FAR=47 por cento ; POD=22 por cento ; r=0,60. Sendo A a porcentagem de acertos nas previsões de eventos e não eventos; B indica, na média, se as previsões estão subestimadas ou superestimadas; FAR é a porcentagem de concentrações que foram previstas altas e que não ocorreram; POD é a capacidade de prever altas concentrações ( por cento ) e r é o coeficiente de correlação entre o valor observado e o valor estimado. Para O3-8h: A=96 por cento ; B=0,1; FAR=14 por cento ; POD=6,5 por cento ; r=0,72. Considerando-se o banco de dados do INMET, os melhores resultados para O3-1h foram: A=93 por cento ; B=0,54; FAR=29 por cento ; POD=38 por cento , r=0,84. Para O3-8h: A=95 por cento ; B=0,76; FAR=47 por cento ; POD=40 por cento ; r=0,85. As variáveis temperatura e vento meridional foram as mais importantes nos modelos. Conclusões. No geral, os modelos simulados com os dados meteorológicos do INMET apresentaram melhores resultados que os apresentados pelos dados do CPTEC, tanto para O3-1h, quanto para O3-8h. O modelo simulado com os dados do INMET, considerando O3-8h, apresentou melhor previsibilidade. Os modelos ajustados por redes neurais mostraram-se como boas alternativas de instrumentos para prever a concentração de ozônio na RMSP. / Introduction. The study and understanding of the effects of air pollution can contribute to the planning of pollutant emission control strategies and decision-making in relation to public health. Air pollution forecasting models are important, as they can anticipate precautions and actions of public action. Objetive. Develop and analyze tropospheric ozone forecasting models for the São Paulo Metropolitan Area (SPMA). Methods. Ozone forecasting models were adjusted using artificial neural networks (ANNs), called artificial intelligence techniques. The model input data were the weather, obtained from CPTEC - Weather and Climate Studies Prediction Center and INMET - National Meteorology Institute and the pollutant ozone data monitored by CETESB - São Paulo State Environmental Company. Were considered for ozone, the national standard of air quality (1 hour) and the state standard of air quality (8 hours). Data were distributed among the averages of the morning (07h to 12h) and the average of the afternoon (13h to 18h), obtaining as output the maximum concentrations of ozone to the afternoon. The study period was from 2008 to 2014. Results. Were conducted 311 tests distributed according to the standard of ozone air quality (O3-1h or O3-8h) and the source of meteorological data (CPTEC or INMET). The observed and estimated ozone values were shown to be very well correlated. For the settings using the CPTEC database, the best results of the verification statistics for O3-1h were: A= 90 per cent ; B=0.41; FAR=47 per cent ; POD=22 per cent ; r=0.60. Where A is the percentage of correct answers of forecasts in the events and not events; B indicates, on average, if the predictions are underestimated or overestimated; FAR is the percentage concentrations that were predicted high and that did not occur; POD is the ability to predict high concentrations ( per cent ) and r is the correlation coefficient between the observed value and the estimated value. To O3-8h: A=96 per cent ; B=0.1; FAR=14 per cent ; POD=6.5 per cent ; r=0.72. Considering the INMET database, the best results for O3-1h were: A=93 per cent ; B=0.54; FAR=29 per cent ; POD=38 per cent , r=0.84. To O3-8h: A=95 per cent ; B=0.76; FAR=47 per cent ; POD=40 per cent ; r=0.85. The variables temperature and meridional wind were the most importante in the models. Conclusions. Overall, the simulated models with meteorological INMET data showed better results than those presented by the CPTEC data for both O3-1h, and for O3-8h. The simulated model with INMET data, considering O3-8h, presented better predictability. The models adjusted by neural networks showed up as good instruments to predict the ozone concentration in the SPMA.

O presente trabalho tem como objetivo principal o desenvolvimento de um sistema de identificação do surgimento de vazamentos (rupturas) em dutos, através da análise do sinal de sensores de pressão de resposta rápida (frequência de corte superior a 1 kHz). O reconhecimento do sinal de vazamento se realiza através de uma rede neural artificial feed-foward do tipo Perceptron Multi Camadas, previamente treinada. Neste trabalho, a implementação para tal operação foi feita off-line, mas devido ao baixo custo computacional pode ser facilmente implementada em eletrônica embarcada, em tempo real (on-line). Os resultados experimentais foram obtidos no oleoduto piloto do NETeF - Núcleo de Engenharia Térmica e Fluidos da USP - Universidade de São Paulo, com uma seção de testes com 1500 metros e diâmetro de 51,2 mm. Especificamente, os resultados foram obtidos com escoamento monofásico de água. Os resultados mostram-se promissores, visto que o sistema de redes neurais artificiais foi capaz de discriminar 2 universos linearmente separáveis, para sinais de vazamento e de não vazamento, para diversas vazões e localizações de vazamentos simulados. / The present dissertation deals with the development of a system to identify abrupt leaks (ruptures) in pipelines, by analyzing the signal of fast response pressure sensors (cutoff frequency over then 1kHz). The recognition of the leak signal is established by an artificial neural network feed-forward Perceptron Multi Layer, previously trained. In the present work the implementation was performed off-line, but due to low computational costs, the neural network can be easily implemented in real time embedded electronics (online). The experimental results were obtained in a 1500 meter-long and 51.2 millimeter-diameter pilot pipeline at the Center of Thermal Engineering and Fluids. Specifically, the results were obtained with single-phase flow of water. The results have proven to be promising, as the trained neural network was capable of classifying the 2 types of signals into 2 linearly separable regions, for leakage signals and no leakage signals, for various flow rates and locations of simulated leaks.

A área de dinâmica de aeronaves atingiu um alto nível de desenvolvimento e devido à crescente disponibilidade de computadores cada vez mais rápidos e com maior capacidade de processamento; a aplicação de técnicas numéricas de identificação nesta área também teve grande avanço. Este trabalho apresenta uma metodologia para predição de respostas de aeronaves dentro de envelopes de vôo pré-estabelecidos usando redes neurais recorrentes e uma metodologia para estimação das suas derivadas aerodinâmicas usando redes neurais feedforward. Para obter os conjuntos de dados para treinar as redes neurais, foi implementado um modelo não linear de dinâmica de vôo e simulado o comportamento de uma aeronave de combate em nove pontos de um envelope de vôo. Foram usadas as respostas simuladas correspondentes a quatro pontos para treinar a rede neural e depois disto, esta capturou satisfatoriamente a dinâmica da aeronave, identificando com grande sucesso as respostas do movimento longitudinal da aeronave por todo o envelope de vôo considerado. Após a simulação e identificação das respostas da aeronave dentro do envelope de vôo, é apresentada a resolução do problema inverso, ou seja, usando velocidades escalares e angulares da aeronave juntamente com seus dados geométricos como entradas para a rede neural feedforward, é obtido um modelo neural estimador de derivadas aerodinâmicas. Para mostrar a capacidade deste modelo neural estimador, este é aplicado na estimação das derivadas da aeronave simulada e também aplicado na estimação das derivadas aerodinâmicas da aeronave militar a jato Xavante AT-26 da Força Aérea Brasileira. Estas metodologias propostas reduzem custo de obtenção das derivadas aerodinâmicas e mostram a eficácia das redes neurais em estimar as respostas de aeronaves dentre de um envelope de vôo pré-definido. / The area of aircraft dynamics has reached a high level of development and due to the increasing availability of computers continuously faster and with bigger processing capacity, the application of numerical identification techniques in this area also had great advance. This work presents two methodologies, one for prediction of aircraft responses within a pre-established flight envelope using recurrent neural networks and another one for estimation of its aerodynamic derivatives using feedforward neural networks. To get data sets to train the neural networks, a combat aircraft flight dynamics non-linear model was implemented and simulated in nine points of the flight envelope to obtain its behavior. The simulated responses corresponding to a four points of the flight envelope were used to train the neural network and after that, it was possible to verify that this net satisfactorily captured the dynamics of the aircraft, identifying with great success the longitudinal motion responses of the aircraft at all the considered flight envelope positions. After the simulation and identification of the aircraft responses inside the flight envelope, the solution of the inverse problem is presented, i.e., using scalar and angular aircraft velocities together with its geometric data as input to the feedforward neural network, a neural estimator model of aerodynamic derivatives is obtained. In order to show the capacity of this neural estimator model, this model is applied to the estimation of the derivatives of the simulated aircraft as well as to the estimation of the aerodynamic derivatives of a brazilian air force military jet aircraft, the Xavante AT-26. These proposed methodologies reduce the cost of obtaining the aerodynamic derivatives and show the estimation effectiveness of the neural networks to estimate the responses of an aircraft inside a pre-defined flight envelope.

Dados reais apontam um expressivo aumento do consumo de combustível no Brasil e no mundo, além de um crescimento acelerado da população urbana. Ambos os processos vem ocorrendo sem um controle adequado no país e, como conseqüência, têm surgido grandes deseconomias urbanas, tais como: congestionamentos, poluição ambiental, consumo exagerado de combustíveis e uso inadequado do espaço viário. Neste contexto, quaisquer iniciativas no intuito de frear estas deseconomias são relevantes e oportunas, tanto que pesquisas nacionais e internacionais vêm sendo realizadas buscando entender melhor os fatores que mais interferem na energia gasta com transportes. O objetivo deste trabalho é investigar a relação entre o consumo de energia com transportes e algumas variáveis espaciais e sócio-econômicas dos municípios do estado de São Paulo com população superior a 50 mil habitantes. A caracterização dos padrões de forma das áreas urbanizadas foi viabilizada graças aos recursos de um Sistema de Informações Geográficas, que possibilitaram determinar com relativa precisão as variáveis espaciais das manchas urbanas a partir de imagens de satélite georeferenciadas. Uma vez levantados todos os dados possíveis, procedeu-se a uma análise através do emprego de Redes Neurais Artificiais, ferramenta que possibilita identificar e classificar as variáveis de acordo com suas importâncias relativas no consumo de energia, que é a variável dependente do modelo. Os resultados encontrados para as cidades paulistas pesquisadas confirmam a tendência internacional, sobretudo no que concerne à grande relevância da densidade populacional urbana, juntamente com outras características sócio-econômicas, sobre o consumo de energia com transportes. Variáveis como a população urbana, a densidade populacional e o nível de empregos no comércio revelaram-se como as de maior importância relativa no contexto analisado. / The world has been experiencing in recent years an unprecedented increase in the amount of fuel consumed for transportation purposes, in addition to a fast growth of the urban population. Those conditions were also found in Brazil, where they have produced several problems for urban areas, such as: traffic congestion, environmental pollution, high fuel consumption, and an improper use of the urban space. In such a context, any attempt to reduce those problems and their consequences is relevant and opportune. That is the reason why a considerable research effort is being directed to the issue at both national and international levels, in order to better understand the factors that most significantly contribute for the high levels of energy use for transportation.The aim of this work is to investigate the relationship between energy consumption for transportation and a few selected variables related to urban form and socioeconomic characteristics of urbanized areas with more then 50,000 inhabitants located in the state of São Paulo. The boundaries of the urbanized areas were obtained from satellite images georeferenced in a Geographic Information System environment, which also offered the tools for the analysis of some spatial attributes. After the spatial and socioeconomic data were combined in a single database, they were then analyzed using Artificial Neural Network models, in order to identify variables that are relevant to energy consumption for transportation, along with their relative weights.The results found with the Brazilian cities selected for the current study confirmed the trend observed in several countries worldwide, in which urban density played an important role influencing energy use for transportation. In the case studied here, other relevant input variables that considerably influenced the energy consumed for transportation were population and employment level.

The high complexity existent in businesses has required managers to rely on accurate and up to date information. Over the years, many tools have been created to give support to decision makers, such as discrete event simulation and artificial neural networks. Both tools have been applied to improve business performance; however, most of the time they are used separately. This research aims to interpret artificial neural network models that are applied to the data generated by a simulation model and determine which inputs have the most impact on the output of a business. This would allow prioritization of the variables for maximized system performance. A connection weight approach will be used to interpret the artificial neural network models. The research methodology consisted of three main steps: 1) creation of an accurate simulation model, 2) application of artificial neural network models to the output data of the simulation model, and 3) interpretation of the artificial neural network models using the connection weight approach. In order to test this methodology, a study was performed in the raw material receiving process of a manufacturing facility aiming to determine which variables impact the most the total time a truck stays in the system waiting to unload its materials. Through the research it was possible to observe that artificial neural network models can be useful in making good prediction about the system they model. Moreover, through the connection weight approach, artificial neural network models were interpreted and helped determine the variables that have the greatest impact on the modeled system. As future research, it would be interesting to use this methodology with other data mining algorithms and understand which techniques have the greatest capabilities of determining the most meaningful variables of a model. It would also be relevant to use this methodology as a resource to not only prioritize, but optimize a simulation model.

Developing advanced semantic models is important in building computational systems that can not only understand language but also convey ideas and concepts to others. Semantic models can allow a creative image-producing-agent to autonomously produce artifacts that communicate an intended meaning. This notion of communicating meaning through art is often considered a necessary part of eliciting an aesthetic experience in the viewer and can thus enhance the (perceived) creativity of the agent. Computational creativity, a subfield of artificial intelligence, deals with designing computational systems and algorithms that either automatically create original and functional products, or that augment the ability of humans to do so. We present work on DARCI (Digital ARtist Communicating Intention), a system designed to autonomously produce original images that convey meaning. In order for DARCI to automatically express meaning through the art it creates, it must have its own semantic model that is perceptually grounded with visual capabilities.The work presented here focuses on designing, building, and incorporating advanced semantic and perceptual models into the DARCI system. These semantic models give DARCI a better understanding of the world and enable it to be more autonomous, to better evaluate its own artifacts, and to create artifacts with intention. Through designing, implementing, and studying DARCI, we have developed evaluation methods, models, frameworks, and theories related to the creative process that can be generalized to other domains outside of visual art. Our work on DARCI has even influenced the visual art community through several collaborative efforts, art galleries, and exhibits. We show that the DARCI system is successful at autonomously producing original art that is meaningful to human viewers. We also discuss insights that our efforts have contributed to the field of computational creativity.

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder characterized by difficulty paying attention, impulsivity, and hyperactivity. Diagnosis of ADHD rose 42% from 2003–2004 to 2011–2012. In 2011, 3.5 million children were treated with drugs. Optimizing therapy can take a year, and may not be completely effective. A clinical trial is currently being conducted of a device/drug combination using the computer game Minecraft, to determine how certain activities affect executive function, working memory, and restraint in patients diagnosed with ADHD. The human subjects’ responses are being modeled using artificial neural networks (ANNs), an artificial intelligence method that can be utilized to interpret highly complex data. We propose using ANNs to optimize drug and Minecraft therapy for individual patients based on the initial NICHQ Vanderbilt assessment scores. We are applying ANNs in the development of computational models for executive function deficiencies in ADHD. These models will then be used to develop a therapeutic video game as a drug/device combination with stimulants for the treatment of ADHD symptoms in Fragile X Syndrome. As a first step towards the design of virtual subjects with executive function deficits, computational models of the core executive functions working memory and fluid intelligence were constructed. These models were combined to create healthy control and executive function-deficient virtual subjects, who performed a Time Management task simulation that required the use of their executive functions to complete. The preliminary working memory model utilized a convolutional neural network to identify handwritten digits from the MNIST dataset, and the fluid intelligence model utilized a basic recurrent neural network to produce sequences of integers in the range 1-9 that can be multiplied together to produce the number 12. A simplified Impulsivity function was also included in the virtual subject as a first step towards the future inclusion of the core executive function inhibition.

No description available.

在此論文中，我們提出一個用來解釋線性規劃問題的類神經網路系統。這 個系統，我們取名為 LP-ANN 系統，它引用了能量函數(Energy Function)的概念及懲罰(Penalty)的方法。從這兩個概念，我們提出了一 個處理非負限制式的新想法。基本上，這個 LP-ANN 系統是以數位電腦來 做模擬，而不以類比式的電子電路來做模擬。這個系統可以判斷所給的線 性規劃問題是否有最佳解。如果有的話，再進一步找出一個符合可接受準 確度範圍內的最佳解。最後，以1200個任意產生的線性規劃問題來測試系 統的模擬結果也在本篇論文中詳述。

The use of composite structures in engineering applications has proliferated over the past few decades due to its distinct advantages namely: high structural performance, corrosion resistance, and high strength/weight ratio. However, they also come with a set of disadvantages, i.e. they are prone to fibre breakage, matrix cracking and delaminations. These types of damage are often invisible and if undetected, could lead to catastrophic failures of structures. Although there are systems to detect such damage, the criticality assessment and prognosis of the damage is often much more difficult to achieve. The research study conducted here resulted in the development of a Structural Health Monitoring (SHM) system for a 2D polymeric composite T-joint, used in maritime structures. The SHM system was found to be capable of not only detecting the presence of multiple delaminations in a composite structure, but also capable of determining the location and extent of all t he delaminations present in the T-joint structure, regardless of the load (angle and magnitude) acting on the structure. The system developed relies on the examination of the strain distribution of the structure under operational loading. This SHM system necessitated the development of a novel pre-processing algorithm - Damage Relativity Assessment Technique (DRAT) along with a pattern recognition tool, Artificial Neural Network (ANN), to predict and estimate the damage. Another program developed - the Global Neural network Algorithm for Sequential Processing of Internal sub Networks (GNAISPIN) uses multiple ANNs to render the SHM system independent to variations in structural loading and capable of estimating multiple delaminations in composite T-joint structures. Upto 82% improvement in detection accuracy was observed when GNAISPIN was invoked. The Finite Element Analysis (FEA) was also conducted by placing delaminations of different sizes at various locations in two structures, a composite beam and a T-joint. Glass Fibre Reinforced Polymer T-joints were then manufactured and tested, thereby verifying the accuracy of the FEA results experimentally. The resulting strain distribution from the FEA was pre-processed by the DRAT and used to trai n the ANN to predict and estimate damage in the structures. Finally, on testing the SHM system developed with strain signatures of composite T-joint structures, subjected to variable loading, embedded with all possible damage configurations (including multiple damage scenarios), an overall damage (location & extent) prediction accuracy of 94.1% was achieved. These results are presented and discussed in detail in this study.