Epilepsy is a neurological disease causing seizures in its victims and affects approximately 50 million people worldwide. Successful treatment is dependent upon correct identification of the origin of the seizures within the brain. To achieve this, electroencephalograms (EEGs) are used to measure a patient’s brainwaves. This EEG data must be manually analyzed to identify interictal spikes that emanate from the afflicted region of the brain. This process can take a neurologist more than a week and a half per patient. This thesis presents a method to extract and process the interictal spikes in a patient, and use them to reduce the amount of data for a neurologist to manually analyze. The effectiveness of multiple neural network implementations is compared, and a data reduction of 3-4 orders of magnitude, or upwards of 99%, is achieved.

Land cover classification using artificial neural networks Abstract This Diploma thesis deals with automatic classification of the satellite high spatial resolution image in the field of land cover. The first half of the work contains the theoretical information about remote sensing and classification methods. The biggest attention is given to the artificial neural networks. In practical part of Diploma thesis are these methods used for the classification of SPOT satellite image. Keywords: remote sensing, image classification, artificial neural networks, SPOT

The thesis introduces Artificial Neural Networks (ANN) to the field of financial durations. We begin by reviewing the findings about financial durations and models applied to analyze them. ANNs are then surveyed and one of the possible network architectures is selected for the forecasting. The selected ANN is a feed-forward network, with one hidden layer, a sigmoid activation function and a genetic algorithm for optimization. We use original and diurnally adjusted data for estimation and in contrast to other duration models, ANNs do not require data pre-processing. Therefore forecasts are estimated in one step without removing seasonalities for raw data. The estimates of the ANN are compared to estimates of the Autoregressive Conditional Duration (ACD) model, which serves as a benchmark for forecasting capabilities of the ANNs. The findings confirm that ANNs can be used to model durations with a similar accuracy as the ACD model. In the case of raw data the model slightly outperforms the ACD model, while the opposite is true for adjusted data, however the forecasting ability difference is not significant.

Cette thèse a été réalisée dans le cadre d'un projet industriel (BMCI), dont l'objectif est d'augmenter la disponibilité des équipements sur les navires. Dans cette thèse, nous proposons une approche qui met à contribution deux approches différentes, à savoir une approche à base de données pour la détection des défauts et une approche à base de connaissances d'experts pour l'isolation des défauts. Cette approche se veut générique et applicable à différents sous-systèmes du moteur ainsi qu'à divers moteurs et offre une ouverture pour une éventuelle application sur d'autres équipements. De plus, elle est tolérante vis-à-vis des éventuels changements au niveau de l'instrumentation disponible. Cette approche a été testée sur la détection et l'isolation des défauts les plus fréquents et aux conséquences graves auxquels les moteurs Diesel sont sujets. Tous les sous-systèmes du moteurs Diesel sont inclus et l'approche de diagnostic prend en considération les interactions existantes entre les sous-systèmes. L'approche de diagnostic a été testée sur un banc d'essai et sur le navire militaire Adroit de DCNS. Les défauts réalisés sur divers circuits du banc moteur et les défauts apparus en fonctionnement sur certains moteurs de l'Adroit, ont été majoritairement détectés et isolés avec succès. De plus, pour pallier à l'incertitude et au caractère flou des relations expertes utilisées dans la procédure d'isolation, une validation des relations de cause à effet a été réalisée, dans le cadre de cette thèse, par la réalisation d'un modèle analytique de simulation de défauts. / This thesis is carried out within an industrial framework (BMCI) which aims to enhance the availability of equipments on board ships. In this work, a data-based method for fault detection is combined with a knowledge-based method for fault isolation. The presented approach is generic and characterized by the ability to be applied to all the Diesel engine subsystems, to different kind of Diesel engines and can also be extended to other equipments. Moreover, this approach is tolerant regarding differences in instrumentation. This approach is tested upon the detection and isolation of the most hazardous and frequent faults which subject Diesel engines. This approach intends to make diagnosis upon the entire Diesel engine including all the subsystems and the existing interactions between the subsystems. The proposed approach is tested upon a test bench and upon the Diesel engines of the DCNS military vessel textquotedblleft Adroit". Most of the introduced faults on the test bench and the appeared faults on the Adroit engines have been successfully detected and isolated. In addition, to deal with uncertainties and fuzziness of the causal relationships given by maintenance experts, a model is developed. This model aims to validate these causal relationships used in the isolation part of the diagnosis approach.

[pt] O presente trabalho apresenta o desenvolvimento de um modelo neural para a inferência da qualidade do polietileno de baixa densidade (PEBD) a partir dos valores das variáveis de processo do sistema reacional. Para tal, fez- se uso de dados operacionais de uma empresa petroquímica, cujo pré-processamento incluiu a seleção de variáveis, limpeza e normalização dos dados selecionados e preparação dos padrões. A capacidade de inferência do modelo neural desenvolvido neste estudo foi comparada com a de dois modelos fenomenológicos existentes. Para tal, utilizou-se como medida de desempenho o valor do erro médio absoluto percentual dos modelos, tendo como referência valores experimentais do índice de fluidez. Neste contexto, o modelo neural apresentou-se como uma eficiente ferramenta de modelagem da qualidade do sistema reacional de produção do PEBD. / [en] This work comprises the development of a neural network- based model for quality inference of low density polyethylene (LDPE). Plant data corresponding to the process variables of a petrochemical company`s LDPE reactor were used for model development. The data were preprocessed in the following manner: first, the most relevant process variables were selected, then data were conditioned and normalized. The neural network- based model was able to accurately predict the value of the polymer melt index as a function of the process variables. This model`s performance was compared with that of two mechanistic models developed from first principles. The comparison was made through the models` mean absolute percentage error, which was calculated with respect to experimental values of the melt index. The results obtained confirm the neural network model`s ability to infer values of quality-related measurements of the LDPE reactor.

Les réseaux de neurones multicouches ont été proposés pour la première fois il y a plus de trois décennies, et diverses architectures et paramétrages ont été explorés depuis. Récemment, les unités de traitement graphique ont permis une formation très efficace sur les réseaux neuronaux et ont permis de former des réseaux beaucoup plus grands sur des ensembles de données plus importants, ce qui a considérablement amélioré le rendement dans diverses tâches d'apprentissage supervisé. Cependant, la généralisation est encore loin du niveau humain, et il est difficile de comprendre sur quoi sont basées les décisions prises. Pour améliorer la généralisation et la compréhension, nous réexaminons les problèmes de paramétrage du poids dans les réseaux neuronaux profonds. Nous identifions les problèmes les plus importants, à notre avis, dans les architectures modernes : la profondeur du réseau, l'efficacité des paramètres et l'apprentissage de tâches multiples en même temps, et nous essayons de les aborder dans cette thèse. Nous commençons par l'un des problèmes fondamentaux de la vision par ordinateur, le patch matching, et proposons d'utiliser des réseaux neuronaux convolutifs de différentes architectures pour le résoudre, au lieu de descripteurs manuels. Ensuite, nous abordons la tâche de détection d'objets, où un réseau devrait apprendre simultanément à prédire à la fois la classe de l'objet et l'emplacement. Dans les deux tâches, nous constatons que le nombre de paramètres dans le réseau est le principal facteur déterminant sa performance, et nous explorons ce phénomène dans les réseaux résiduels. Nos résultats montrent que leur motivation initiale, la formation de réseaux plus profonds pour de meilleures représentations, ne tient pas entièrement, et des réseaux plus larges avec moins de couches peuvent être aussi efficaces que des réseaux plus profonds avec le même nombre de paramètres. Dans l'ensemble, nous présentons une étude approfondie sur les architectures et les paramétrages de poids, ainsi que sur les moyens de transférer les connaissances entre elles / Multilayer neural networks were first proposed more than three decades ago, and various architectures and parameterizations were explored since. Recently, graphics processing units enabled very efficient neural network training, and allowed training much larger networks on larger datasets, dramatically improving performance on various supervised learning tasks. However, the generalization is still far from human level, and it is difficult to understand on what the decisions made are based. To improve on generalization and understanding we revisit the problems of weight parameterizations in deep neural networks. We identify the most important, to our mind, problems in modern architectures: network depth, parameter efficiency, and learning multiple tasks at the same time, and try to address them in this thesis. We start with one of the core problems of computer vision, patch matching, and propose to use convolutional neural networks of various architectures to solve it, instead of manual hand-crafting descriptors. Then, we address the task of object detection, where a network should simultaneously learn to both predict class of the object and the location. In both tasks we find that the number of parameters in the network is the major factor determining it's performance, and explore this phenomena in residual networks. Our findings show that their original motivation, training deeper networks for better representations, does not fully hold, and wider networks with less layers can be as effective as deeper with the same number of parameters. Overall, we present an extensive study on architectures and weight parameterizations, and ways of transferring knowledge between them

Student Number : 9801145J - MSc dissertation - School of Electrical and Information Engineering - Faculty of Engineering / In this document, a paper is presented that reports on the optimisation of a system that assists in time series prediction. Daily closing prices of a stock are used as the time series under which the system is being optimised. Concepts of machine learning, Artificial Neural Networks, Genetic Algorithms, and Agent-Based Modeling are used as tools for this task. Neural networks serve as the prediction engine and genetic algorithms are used for optimisation tasks as well as the simulation of a multi-agent based trading environment. The simulated trading environment is used to ascertain and optimise the best data, in terms of quality, to use as inputs to the neural network. The results achieved were positive and a large portion of this work concentrates on the refinement of the predictive capability. From this study it is concluded that AI methods bring a sound scientific approach to time series prediction, regardless of the phenomena that is being predicted.

As Redes Neurais Artificiais (RNAs) vêm sendo empregadas com cada vez mais sucesso em diversas áreas de pesquisa, no campo da engenharia e em outros campos diversos. Neste trabalho foram modeladas séries fluviométricas relativas às afluências a quatro reservatórios, localizados em quatro bacias hidrográficas distintas que compõem a Bacia Metropolitana de Fortaleza, Ceará, Brasil. Tais afluências apresentam peculiaridades relativas à ocorrência de magnitudes nulas, que dificultam sua modelagem através dos convencionais modelos estatísticos da família Box-Jenkins. Neste estudo foram trabalhadas duas abordagens distintas, a primeira univariada, em que cada série era modelada de forma individual, e a segunda multivariada, em que as séries fluviométricas eram modeladas simultaneamente. Os resultados obtidos, segundo ambas as modelagens, demonstram que a técnica apresenta potencial para a aplicação pretendida. Estudos futuros merecem ser desenvolvidos ainda no sentido de verificar a melhor maneira de se enquadrar a componente aleatória nas séries sintéticas produzidas via RNAs. / Artificial Neural Networks (ANNs) are being used more and more in many different fields of research, in engineering applications or other applications. This research deals with modeling of inflows to four reservoirs, located in different watersheds that belong to the Metropolitan Watershed of Fortaleza city, Brazil. These discharge sequences have particular characteristics in that they have frequent occurence of null discharges which makes it difficult to use traditional statistical models such as those Box-Jenkis family. Two different modeling approaches were adopted in this study, the first univariate, in which each time series was modeled individually, and the second multivariate, in which the four time series were modeled simultaneously. The results from the both approaches show that the technique has potential for use in water resources planning and management. Future studies are required to propose better means of incorporing the random component in the generation of synthetic time series through ANNs.

Este trabalho apresenta a aplicação de Redes Neurais Artificiais (RNAs) como um classificador de padrões para as operações do relé de distância. As grandezas analisadas referem-se aos valores trifásicos de tensões e correntes do sistema elétrico, incluindo a seqüência zero. Para a obtenção dos valores amostrais da linha de transmissão em condição faltosa, valores estes utilizados como entradas para as arquiteturas de RNAs em seus processos de treinamento e teste, utilizou-se do software Alternative Transients Program - ATP. Para se observar o desempenho do relé de distância implementado, duas formas de análise dos valores trifásicos foram adotadas. Uma utilizando-se como entrada os cinco valores amostrados em meio ciclo pós-falta do sinal analisado e a segunda, pelo emprego da magnitude dos fatores de tensões e correntes, incluindo a seqüência zero. A função da rede neural implementada é de capturar o conhecimento da correta atuação do relé de distância, para posteriormente atuar com melhores resultados frente às situações de operações que por ventura venham a ocorrer. Para criar, treinar (obtenção dos pesos associados como saída) e testar as arquiteturas de RNAs, utilizou-se do software Stuttgard Neural Network Simulator (SNNS). Dos resultados encontrados comenta-se o desempenho do relé de distância implementado frente às duas abordagens anteriormente descritas. Do uso de RNAs como um classificador de padrões, observa-se uma melhora no desempenho do sistema de proteção, alcançando-se uma definição de 96% do comprimento da linha de transmissão como sendo a zona de proteção primária do relé de distância digital. / This work demonstrates the use of Artificial Neural Networks (ANNs) theory as a pattern classifier for a distance relay operation. The approach utilizes the magnitudes of the three phase voltage and current phasors (including the zero sequence) as inputs. The Alternative Transients Program (ATP) software is used to generate data for the transmission line in a faulted condition both for the training process and the tests. Two different types of ANN architecture, concerning the input data, are taken into account. The main objective was to analyse the relay performance considering each of them. One approach utilises the five post-fault samples as inputs. The other one employs the magnitudes of the three phase voltage and current phasors (including the zero sequence) as inputs. The implemented neural network should capture the knowledge for the correct relay operation facing the different network conditions. A comparison of how well the schemes performed is carried out. The Stuttgard Neural Network Simulator (SNNS) was used to create the ANN diagram, train it and obtain the weights as an output. An improvement concerning the use of ANNs for distance protection purposes is found. Through the use of ANN as a pattern classifier, a reach of 96% of the transmission line length as the relay primary protection zone was implemented in this work.

Este trabalho consiste em apresentar um método alternativo para a identificação de fontes de correntes harmônicas comumente encontradas em sistemas elétricos residenciais. Desta identificação, soluções viáveis poderão ser aplicadas com o intuito de mitigar os níveis de emissão das correntes harmônicas geradas, principalmente, por cargas com características não lineares. Para a identificação empregou-se redes neurais artificiais (RNAs), sendo esta técnica inteligente, apresentada como uma alternativa aos métodos convencionais. Os resultados reportados neste contexto procuram validar a proposta apresentada com dados experimentais obtidos em ensaios laboratoriais. / This work presents an alternative method for the identification of current harmonic sources commonly encountered in residential electrical systems. For this purpose, feasible solutions can be applied to minimize the levels of harmonic currents emission caused by nonlinear loads. Artificial neural networks are employed as alternative to conventional methods. The experimental results will be reported in order to validate the proposal presented with the experimental data obtained in laboratory.