Orientador: Anna Diva Plasencia Lotufo / Resumo: Os sistemas de energia elétrica estão passando por transformações. Aos poucos, técnicas de sistemas de informação estão sendo incorporadas aos sistemas atuais de energia. Basicamente este é o conceito de smart grid. Esta incorporação visa aumentar a eficiência dos sistemas de energia elétrica, pois os diversos agentes envolvidos em todo o sistema terão à disposição informações mais completas, precisas e de forma praticamente instantânea. Como consequência, haverá um aumento significativo de dados disponíveis para serem empregados de variadas formas. Um exemplo do uso de dados é a previsão de demanda de energia elétrica. De uma forma geral, previsões servem como suporte para suprir demandas, estimar custos ou justificar investimentos futuros. No campo de previsão de demanda de cargas elétricas existem diversos modelos na literatura, a grande maioria se concentra em níveis mais agregados, que atendem a grandes consumidores em que o fornecimento de energia é feito, por exemplo, por uma subestação. Uma smart grid também coloca à disposição as informações de consumo de energia em níveis cada vez menos agregados, como uma residência ou um prédio comercial. Realizar previsões neste nível é um desafio, pois essas demandas são muito influenciadas pelo comportamento humano. Diferentemente dos níveis mais agregados, modelos de previsão para níveis menos agregados, ou desagregados, ainda são poucos. O objetivo deste trabalho é fazer a previsão de cargas elétricas não residenciais mistas ... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: Electrical power systems are in transformation nowadays. Gradually, information system technology are being introduced to the energy systems. Basically, this is the concept of smart grid. This new concept aims to improve the efficiency of the energy systems, once the evolved agents will provide complete and precise information instantaneously. This way, a significant increase in data will be available to be employed in several forms. One example in using these data is electric energy demand forecasting. In general, predictions are support to provide electric load demand, estimate costs or justify future investments. Concerning electric load demand, there are several models in the literature, and the majority is concentrated in aggregated levels, attending large consumers, where, for example, the energy supply is provided by a substation. Considering the smart grid, there are consumption information in less aggregated levels as for example residences or commercial buildings. Therefore, realizing predictions in these levels (less aggregated) is a challenge, once the demand is influenced by the human behavior. The models for predicting loads in aggregated levels are common, in the contrary of less aggregated that are few. This work aims to predict short term mixed nonresidential electric loads using data from a Brazilian University. Firstly, Fuzzy ARTMAP Neural Network is chosen to execute the predictions, and afterwards a hybrid methodology containing Fuzzy ARTMAP and Square Mi... (Complete abstract click electronic access below) / Doutor

The significant amount of data contained in digital images present barriers to methods of learning from the information they hold. Noise and the subjectivity of image evaluation further complicate such automated processes. In this thesis, we examine a particular area in which these difficulties are experienced. We attempt to control the parameters of a multi-step algorithm that processes visual information. A framework for approaching the parameter selection problem using reinforcement learning agents is presented as the main contribution of this research. We focus on the generation of state and action space, as well as task-dependent reward. We first discuss the automatic determination of fuzzy membership functions as a specific case of the above problem. Entropy of a fuzzy event is used as a reinforcement signal. Membership functions representing brightness have been automatically generated for several images. The results show that the reinforcement learning approach is superior to an existing simulated annealing-based approach. The framework has also been evaluated by optimizing ten parameters of the text detection for semantic indexing algorithm proposed by Wolf et al. Image features are defined and extracted to construct the state space. Generalization to reduce the state space is performed with the fuzzy ARTMAP neural network, offering much faster learning than in the previous tabular implementation, despite a much larger state and action space. Difficulties in using a continuous action space are overcome by employing the DIRECT method for global optimization without derivatives. The chosen parameters are evaluated using metrics of recall and precision, and are shown to be superior to the parameters previously recommended. We further discuss the interplay between intermediate and terminal reinforcement.

La surveillance des systèmes mécatroniques, en particulier, ceux intégrés sur les véhicules d'aujourd'hui est de plus en plus difficile. Les interconnexions de ces systèmes en vue de l'accroissement des performances et du confort de véhicule augmentent la complexité de l'information nécessaire à la prise de décision en temps réel. Cette thèse est consacrée à la problématique de détection et d'isolation (FDI, Fault Detection & Isolation) de pannes automobiles en utilisant des systèmes de recherche et d'évaluation de l'information par des approches monocritères. Les variables pertinentes pour la détection rapide des pannes sont sélectionnées d'une manière automatique en utilisant deux approches différentes : I. La première consiste à introduire la notion de conflit entre toutes les variables mesurables du système mécatronique et les analyser à partir des projections dans des espaces de classification hyper-rectangles. II. La deuxième approche consiste à utiliser la complexité de Kolmogorov comme outil de classification des signatures de pannes. L'estimation de la complexité de Kolmogorov par des algorithmes de compression sans perte d'information permet de définir un dictionnaire de pannes et de donner un score de criticité par rapport au bon fonctionnement du véhicule. Les deux approches proposées ont été appliquées avec succès sur plusieurs types de données automobiles dans le cadre du projet ANR-DIAPA

This thesis proposes an object localization and image retrieval framework, which trains a discriminative feature set for each object class. For this purpose, a hierarchical learning architecture, together with a Neighborhood Tree is introduced for object labeling. Initially, a large variety of features are extracted from the regions of the pre-segmented images. These features are, then, fed to the training module, which selects the &quot / best set of representative features&quot / , suppressing relatively less important ones for each class. During this study, we attack various problems of the current image retrieval and classification systems, including feature space design, normalization and curse of dimensionality. Above all, we elaborate the semantic gap problem in comparison to human visual system. The proposed system emulates the eye-brain channel in two layers. The first layer combines relatively simple classifiers with low level, low dimensional features. Then, the second layer implements Adaptive Resonance Theory, which extracts higher level information from the first layer. This two-layer architecture reduces the curse of dimensionality and diminishes the normalization problem. The concept of Neighborhood Tree is introduced for identifying the whole object from the over-segmented image regions. The Neighborhood Tree consists of the nodes corresponding to the neighboring regions as its children and merges the regions through a search algorithm. Experiments are performed on a set of images from Corel database, using MPEG-7, Haar and Gabor features in order to observe the power and the weakness of the proposed system. The &quot / Best Representative Features&quot / are found in the training phase using Fuzzy ARTMAP [1], Feature-based AdaBoost [2], Descriptor-based AdaBoost, Best Representative Descriptor [3], majority voting and the proposed hierarchical learning architecture. During the experiments, it is observed that the proposed hierarchical learning architecture yields better retrieval rates than the existing algorithms available in the literature.

Orientador: Carlos Roberto Minussi / Banca: Francisco Villarreal Alvarado / Banca: Maria do Carmo Gomes da Silveira / Banca: Luciana Cambraia Leite / Banca: Ricardo Menezes Salgado / Resumo: Esta pesquisa visa o desenvolvimento de um método para análise da estabilidade transitória de sistemas de energia eletrica multimaquinas, por meio de uma rede neural ART-ARTMAP Fuzzy Euclidiana Modificada com Treinamento Continuado. Esta arquitetura apresenta tres diferenciais em e relação a outras já utilizadas para abordar tal problema: (1) a rede iniciada com apenas um neuronio ativado e vai se expandindo durante todo o o treinamento/análise, (2) possui um módulo de treinamento continuado e (3) a o possui um módulo de deteção de intruso. No primeiro diferencial, a redeé iniciada com um neuronio e vai se expandindo de acordo com a aquisição de conhecimento, isto faz com que esta se torne muito mais rápida e que o gasto computacional se torne mínimo. Com o módulo de treinamento continuado, a rede neural consegue armazenar novos dados sem a necessidade de realizar o retreinamento. Já o módulo de detecção de intruso faz com que, ao ser apresentada a rede uma configuração "estranha", a rede execute um treinamento específico para que esta configuração, com um número mínimo de entradas, seja incorporada definitivamente à rede neural. A aplicação para a rede proposta nesta pesquisa, foi a análise de estabilidade transitória, considerando-se o modelo clássico (estabilidade de primeira oscilação), para um sistema composto por 10 máquinas síncronas, 45 barras e 73 linhas de transmissão / Abstract: This doctoral research aims to develop a method to analyze the transient stability of multimachine eletric power systems, through a neural network Modified Euclidean Fuzzy ART-ARTMAP with Continuous Training. The architecture presented has three differences in relation to others used to deal with this problem: (1) the network starts with only one neuron activated and expands throughout the training/analysis, (2) has a continuous training module and (3) has an intrusion detection module. The first difference, is the fact that it starts with a neuron and expands according to knowledge acquisition of the network, and causes it to become much faster and the computational expenses becomes minimum. With continuous training mod- ule, the neural network can store the new data without the need for the retraining. The intrusion detection module causes, when presented to the network a strange configuration, the network to carry out a specific training for this configuration with a minimum total of inputs so that the configu- ration is definitely incorporated to the neural network. The application for this network, in this research, was to analyze the transient stability consid- ering the classical model (stability of first oscillation) to a system composed of 10 synchronous machines, 45 buses and 73 transmission lines / Doutor

Made available in DSpace on 2014-06-11T19:30:50Z (GMT). No. of bitstreams: 0 Previous issue date: 2010-10-22Bitstream added on 2014-06-13T20:00:53Z : No. of bitstreams: 1 moreno_al_dr_ilha.pdf: 923809 bytes, checksum: e8a55f496e6bf5bfbe0531f9211526e5 (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Esta pesquisa visa o desenvolvimento de um método para análise da estabilidade transitória de sistemas de energia eletrica multimaquinas, por meio de uma rede neural ART-ARTMAP Fuzzy Euclidiana Modificada com Treinamento Continuado. Esta arquitetura apresenta tres diferenciais em e relação a outras já utilizadas para abordar tal problema: (1) a rede iniciada com apenas um neuronio ativado e vai se expandindo durante todo o o treinamento/análise, (2) possui um módulo de treinamento continuado e (3) a o possui um módulo de deteção de intruso. No primeiro diferencial, a redeé iniciada com um neuronio e vai se expandindo de acordo com a aquisição de conhecimento, isto faz com que esta se torne muito mais rápida e que o gasto computacional se torne mínimo. Com o módulo de treinamento continuado, a rede neural consegue armazenar novos dados sem a necessidade de realizar o retreinamento. Já o módulo de detecção de intruso faz com que, ao ser apresentada a rede uma configuração estranha, a rede execute um treinamento específico para que esta configuração, com um número mínimo de entradas, seja incorporada definitivamente à rede neural. A aplicação para a rede proposta nesta pesquisa, foi a análise de estabilidade transitória, considerando-se o modelo clássico (estabilidade de primeira oscilação), para um sistema composto por 10 máquinas síncronas, 45 barras e 73 linhas de transmissão / This doctoral research aims to develop a method to analyze the transient stability of multimachine eletric power systems, through a neural network Modified Euclidean Fuzzy ART-ARTMAP with Continuous Training. The architecture presented has three differences in relation to others used to deal with this problem: (1) the network starts with only one neuron activated and expands throughout the training/analysis, (2) has a continuous training module and (3) has an intrusion detection module. The first difference, is the fact that it starts with a neuron and expands according to knowledge acquisition of the network, and causes it to become much faster and the computational expenses becomes minimum. With continuous training mod- ule, the neural network can store the new data without the need for the retraining. The intrusion detection module causes, when presented to the network a strange configuration, the network to carry out a specific training for this configuration with a minimum total of inputs so that the configu- ration is definitely incorporated to the neural network. The application for this network, in this research, was to analyze the transient stability consid- ering the classical model (stability of first oscillation) to a system composed of 10 synchronous machines, 45 buses and 73 transmission lines