Encoding and consolidation of memories are two processes within the hippocampus, and connected cortical networks, that recruit different circuit level dynamics to effectively process and pass information from brain region to brain region. In the hippocampal CA1 pyramidal layer local field potential (LFP), these processes take the form of theta and sharp wave ripples (SPW-Rs) for encoding and consolidation, respectively. As an animal runs through an environment, neurons become active at specific locations in the environment (place cells) increasing their firing rate, functionally representing these specific locations. These firing rate increases are organized within the local theta oscillations and sequential activation of many place cells creates a map of the environment. Once the animal stops moving and begins consummatory behaviors, such as eating, drinking, or grooming, theta activity diminishes, and large irregular activity (LIA) begins to dominate the LFP. Spontaneously, with the LIA, the place cells active during the experience are replayed during SPW-Rs in the same spatial order they were encountered in the environment. Both theta and SPW-R oscillations and their associated neuronal firing are necessary for effective place recognition as well as learning and memory. As such, interruption or termination of SPW-R events results in decreased learning performance over days. During exploration, the associated theta and sequential place cell activity is thought to encode the experience. During quiet restfulness or slow wave sleep (SWS), SPW-R events, that replay experience specific place sequences, are thought to be the signal by which systems consolidation progresses and the hippocampus guides cortical synaptic reorganization. The granular retrosplenial cortex (gRSC) is an associational area that exhibits high frequency oscillations (HFOs) during both hippocampal theta and SPW-Rs, and is potentially a period when the gRSC interprets incoming content from the hippocampus during encoding and systems consolidation. However, the precise laminar organization of synaptic currents supporting HFOs, whether the local gRSC circuitry can support HFOs without patterned input, and the precise coupling of hippocmapla oscillations to gRSC HFOs across brain states remains unknown. We aimed to answer these questions using in vivo, awake electrophysiological recordings in head-fixed mice that were trained to run for water rewards in a 1D virtual environment. We show that gRSC synaptic currents supporting HFOs, across all awake brain states, are exclusively localized to layer 2/3 (L2/3), even when events are detected within layer 5 (L5). Using focal optogenetics, both L2/3 and L5 can generate induced HFOs given a strong enough broad stimulation. Spontaneous gRSC HFOs occurring outside of SPW-Rs are highly comodulated with medial entorhinal cortex (MEC) generated high gamma in hippocampal stratum lacunosum moleculare. gRSC HFOs may serve a necessary role in communication between the hippocampus during SPW-Rs states and between the hippocampus, gRSC, and MEC during theta states to support memory consolidation and memory encoding, respectively. / Doctor of Philosophy / As an animal moves through an environment, individual neurons in the hippocampus, known as place cells, increase and decrease their firing rate as the animal enters and exits specific locations in the environment. Within an environment, multiple neurons become active in different locations, this cooperation of spiking in various locations creates a place map of the environment. Now let's say when the animal moved from one corner of the environment to another, place cells 'A', 'C', 'B', 'E', and 'D' became active in that order. This means, at any given point in the environment, the animal is standing in a venn-diagram-esque overlap of place fields, or locations individual place cells represent. A key question that entranced researchers for many years was how do these neurons know when to be active to not impinge on their neighbor's locations? The answer to this question rested with population electrical activity, known as the local field potential (LFP), that place cell activity is paced to. During active navigation through an environment, place cells activity is coupled to the phase of a slow ~8 hertz (Hz) theta oscillation. Within one theta cycle, or peak to peak, multiple place cells are active, representing the venn diagram of location the animal is in. Importantly, this theta activity and encoding of place cell activity is largely seen during active running or rapid eye movement (REM) sleep. During slow wave sleep (SWS), after an animal has experienced a specific environment and has created a place map, place cells are reactivated in the same order the animal experienced them in. From our previous example, the content of this reactivation would be the place cells 'A', 'C', 'B', 'E', and 'D' which all would be reactivated in that same order. These reactivations or replays occur during highly synchronous and fast LFP oscillations known as sharp wave-ripples (SPW-Rs). SPW-Rs are thought to be a key LFP event that drives memory consolidation and the eventual conversion of short-term memory into long-term memory. However, for consolidation to occur, connected cortical regions need to be able to receive and interpret the information within SPW-Rs. The granular retrosplenial cortex (gRSC) is one proposed region that serves this role. During SPW-Rs the superficial gRSC has been shown to exhibit high frequency oscillations (HFOs), which potentially serve the purpose for interpreting SPW-R content. However, HFOs have been reported during hippocampal theta, suggesting HFOs serve multiple purposes in interregional communication across different states. In this study, we found that naturally occurring gRSC HFOs occur exclusively in layer 2/3 across all awake brain states. Using focal optogenetic excitation we were able to evoke HFOs in both layer 2/3 and 5. Spontaneous gRSC HFOs occurring without SPW-Rs were highly comodulated with medial entorhinal cortex (MEC) generated high gamma in hippocampal stratum lacunosum moleculare. gRSC HFOs may serve a general role in supporting hippocampo-cortical dialogue during SPW-R and theta brain states to support memory consolidation and encoding, respectively.

The work presented in this thesis aims to provide various tools to be used during design process to make maximum use of the increasing availability of accurate engine blade measurement data for high fidelity fluid mechanic simulations at a reasonable computational expense. A new method for uncertainty propagation for geometric error has been proposed for fluid mechanics codes using adjoint error correction. Inexpensive Monte Carlo (IMC) method targets small uncertainties and provides complete probability distribution for the objective function at a significantly reduced computational cost. A brief literature survey of the existing methods is followed by the formulation of IMC. An example algebraic model is used to demonstrate the IMC method. The IMC method is extended to fluid mechanic applications using Principal Component Analysis (PCA) for reduced order modelling. Implementation details for the IMC method are discussed using an example airfoil code. Finally, the IMC method has been implemented and validated for an industrial fluid mechanic code HYDRA. A consistent methodology has been developed for the automatic generation of the linear and adjoint codes by selective use of automatic differentiation (AD) technique. The method has the advantage of keeping the linear and the adjoint codes in-sync with the changes in the underlying nonlinear fluid mechanic solver. The use of various consistency checks have been demonstrated to ease the development and maintenance process of the linear and the adjoint codes. The use of AD has been extended for the calculation of the complete Hessian using forward-on-forward approach. The complete mathematical formulation for Hessian calculation using the linear and the adjoint solutions has been outlined for fluid mechanic solvers. An efficient implementation for the Hessian calculation is demonstrated using the airfoil code. A new application of the Independent Component Analysis (ICA) is proposed for manufacturing uncertainty source identification. The mathematical formulation is outlined followed by an example application of ICA for artificially generated uncertainty for the NACA0012 airfoil.

L'analyse en composantes indépendantes (ACI) est une méthode d'analyse statistique qui consiste à exprimer les données observées (mélanges de sources) en une transformation linéaire de variables latentes (sources) supposées non gaussiennes et mutuellement indépendantes. Dans certaines applications, on suppose que les mélanges de sources peuvent être groupés de façon à ce que ceux appartenant au même groupe soient fonction des mêmes sources. Ceci implique que les coefficients de chacune des colonnes de la matrice de mélange peuvent être regroupés selon ces mêmes groupes et que tous les coefficients de certains de ces groupes soient nuls. En d'autres mots, on suppose que la matrice de mélange est éparse par groupe. Cette hypothèse facilite l'interprétation et améliore la précision du modèle d'ACI. Dans cette optique, nous proposons de résoudre le problème d'ACI avec une matrice de mélange éparse par groupe à l'aide d'une méthode basée sur le LASSO par groupe adaptatif, lequel pénalise la norme 1 des groupes de coefficients avec des poids adaptatifs. Dans ce mémoire, nous soulignons l'utilité de notre méthode lors d'applications en imagerie cérébrale, plus précisément en imagerie par résonance magnétique. Lors de simulations, nous illustrons par un exemple l'efficacité de notre méthode à réduire vers zéro les groupes de coefficients non-significatifs au sein de la matrice de mélange. Nous montrons aussi que la précision de la méthode proposée est supérieure à celle de l'estimateur du maximum de la vraisemblance pénalisée par le LASSO adaptatif dans le cas où la matrice de mélange est éparse par groupe. / Independent component analysis (ICA) is a method of statistical analysis where the main goal is to express the observed data (mixtures) in a linear transformation of latent variables (sources) believed to be non-Gaussian and mutually independent. In some applications, the mixtures can be grouped so that the mixtures belonging to the same group are function of the same sources. This implies that the coefficients of each column of the mixing matrix can be grouped according to these same groups and that all the coefficients of some of these groups are zero. In other words, we suppose that the mixing matrix is sparse per group. This assumption facilitates the interpretation and improves the accuracy of the ICA model. In this context, we propose to solve the problem of ICA with a sparse group mixing matrix by a method based on the adaptive group LASSO. The latter penalizes the 1-norm of the groups of coefficients with adaptive weights. In this thesis, we point out the utility of our method in applications in brain imaging, specifically in magnetic resonance imaging. Through simulations, we illustrate with an example the effectiveness of our method to reduce to zero the non-significant groups of coefficients within the mixing matrix. We also show that the accuracy of the proposed method is greater than the one of the maximum likelihood estimator with an adaptive LASSO penalization in the case where the mixing matrix is sparse per group.

L'objectif de cette thèse est d'identifier et caractériser les boucles anatomiques et fonctionnelles cortico-sous-corticales chez l'Homme, à partir de données d'imagerie par résonance magnétique fonctionnelle (IRMf) au repos et de diffusion. Une boucle est un ensemble de régions corticales, sous-corticales et cérébelleuses, qui interagissent afin d'effectuer ou de préparer une tâche.Le premier axe de ce travail vise à identifier les réseaux fonctionnels cortico-sous-corticaux en IRMf au repos. Nous proposons une méthode statistique robuste séparant l'analyse corticale de l'analyse sous-corticale. Une analyse en composantes indépendantes spatiales est d'abord réalisée individuellement sur les régions corticales, et suivie d'une classification hiérarchique. Les régions sous-corticales associées sont ensuite extraites par un modèle linéaire général dont les régresseurs comportent la dynamique des régions corticales, suivi d'une analyse de groupe à effets aléatoires. La méthode est validée sur deux jeux de données différents. Un atlas immunohistochimique des structures sous-corticales permet ensuite de déterminer la fonction sensorimotrice, associative ou limbique des réseaux obtenus. Nous montrons enfin que l'anatomie est un support pour la fonction chez des sujets sains.Le dernier axe étudie le syndrome de Gilles de la Tourette, qu'on pense être dû à un dysfonctionnement des boucles cortico-sous-corticales. Nous caractérisons d'abord les boucles cortico-sous-corticales fonctionnelles grâce à des métriques d'intégration et de théorie des graphes, et des différences en termes de connectivité sont mises en évidence entre patients adultes et volontaires sains. Nous montrons également que les boucles cortico-sous-corticales fonctionnelles chez les patients sont soutenues par l'anatomie sous-jacente. / The objective of this thesis is to identify and characterize human anatomical and functional cortico-subcortical loops, using data from resting-state functional magnetic resonance imaging (fMRI) and diffusion MRI. A loop is a set of cortical, subcortical and cerebellar regions that interact to perform or prepare for a task.We first aim to identify cortico-subcortical functional networks from resting-state fMRI data. We propose a robust statistical method that separates the analysis of cortical regions from that of subcortical structures. A spatial independent component analysis is first performed on individual cortical regions, followed by a hierarchical classification. The associated subcortical regions are then extracted by using a general linear model, the regressors of which contain the dynamics of the cortical regions, followed by a random-effect group analysis. The proposed approach is assessed on two different data sets. An immunohistochemical subcortical atlas is then used to determine the sensorimotor, associative or limbic function of the resulting networks. We finally demonstrate that anatomy is a support for function in healthy subjects.The last part is devoted to the study of the Gilles de la Tourette syndrome, thought to be due to adysfunction of cortico-subcortical loops. Firstly, cortico-subcortical functional loops are characterized using metrics such as integration and graph theory measures, showing differences in terms of connectivity between adult patients and healthy volunteers. Secondly, we show that the cortico-subcortical functional loops in patients are supported by the underlying anatomy.

Este trabalho estuda o modelo de análise em componentes independentes (ICA) para misturas instantâneas, aplicado na separação de sinais de áudio. Três algoritmos de separação de misturas instantâneas são avaliados: FastICA, PP (Projection Pursuit) e PearsonICA; possuindo dois princípios básicos em comum: as fontes devem ser independentes estatisticamente e não-Gaussianas. Para analisar a capacidade de separação dos algoritmos foram realizados dois grupos de experimentos. No primeiro grupo foram geradas misturas instantâneas, sinteticamente, a partir de sinais de áudio pré-definidos. Além disso, foram geradas misturas instantâneas a partir de sinais com características específicas, também geradas sinteticamente, para avaliar o comportamento dos algoritmos em situações específicas. Para o segundo grupo foram geradas misturas convolutivas no laboratório de acústica do LPS. Foi proposto o algoritmo PP, baseado no método de Busca de Projeções comumente usado em sistemas de exploração e classificação, para separação de múltiplas fontes como alternativa ao modelo ICA. Embora o método PP proposto possa ser utilizado para separação de fontes, ele não pode ser considerado um método ICA e não é garantida a extração das fontes. Finalmente, os experimentos validam os algoritmos estudados. / This work studies Independent Component Analysis (ICA) for instantaneous mixtures, applied to audio signal (source) separation. Three instantaneous mixture separation algorithms are considered: FastICA, PP (Projection Pursuit) and PearsonICA, presenting two common basic principles: sources must be statistically independent and non-Gaussian. In order to analyze each algorithm separation capability, two groups of experiments were carried out. In the first group, instantaneous mixtures were generated synthetically from predefined audio signals. Moreover, instantaneous mixtures were generated from specific signal generated with special features, synthetically, enabling the behavior analysis of the algorithms. In the second group, convolutive mixtures were probed in the acoustics laboratory of LPS at EPUSP. The PP algorithm is proposed, based on the Projection Pursuit technique usually applied in exploratory and clustering environments, for separation of multiple sources as an alternative to conventional ICA. Although the PP algorithm proposed could be applied to separate sources, it couldnt be considered an ICA method, and source extraction is not guaranteed. Finally, experiments validate the studied algorithms.

Um Sistema Elétrico de Potência (SEP) está susceptível à presença de diversas fontes de distúrbios que prejudicam a Qualidade da Energia Elétrica (QEE). Desta forma, as suas tensões e/ou correntes podem conter m´múltiplos distúrbios com ocorrência simultânea. Este trabalho apresenta uma metodologia para decomposição do sinal medido em componentes que estimem as formas de onda dos distúrbios individuais quando da ocorrência de m´múltiplos distúrbios, com o posterior reconhecimento de cada um deles. A Análise de Componentes Independentes (ICA) é utilizada como principal ferramenta na etapa de decomposição dos distúrbios. A ICA é originalmente uma t´técnica aplicada em análise multivariada de dados, o que significa que ela necessita de medições realizadas por múltiplos sensores dispostos em diferentes posições de um sistema. No entanto, este trabalho propõe a sua aplicação tendo disponível apenas um sinal medido. Para tanto, são propostos dois métodos para produzir a diversidade necessária para a t´técnica funcionar adequadamente. É demonstrado que ambos os métodos equivalem a um banco de filtros lineares adaptativos capaz de realizar a separação não-supervisionada de múltiplos distúrbios independentes e que sejam espectralmente disjuntos. Por fim, é proposto um sistema de classificação que utiliza Redes Neurais Artificiais (RNAs) para identificar os distúrbios decompostos pela etapa anterior. A metodologia completa é avaliada por meio de testes utilizando dados sintéticos e reais, alcançando resultados altamente satisfatórios para decomposição de sinais contendo múltiplos distúrbios e taxas de acerto globais dos classificadores superiores a 97% / The power system is susceptible to the presence of several sources of disturbances that harm the power quality. In this sense, its voltages and/or currents may contain multiple disturbances with simultaneous occurrence. This work presents a methodology that decomposes the measured signal in components which estimate the waveforms of the individual disturbances followed by their recognition when a multiple disturbance situation occurs. The Independent Component Analysis (ICA) is the main tool in the disturbance decomposition stage. The ICA is originally a technique applied in multivariate data analysis, which means that it requires measurements from multiple sensors allocated in different positions of the system. However, this work proposes its application for a single measured signal available. For this, two methods were developed in order to provide the required diversity to the ICA technique. It is demonstrated that both methods are equivalent to an adaptive linear filter bank capable to perform an unsupervised separation of multiple independent disturbances, if they are spectrally disjoint. A classification system based on artificial neural networks is proposed to identify the disturbances decomposed by the previous stage. The complete system is tested using synthetic and actual data, presenting highly satisfactory results for the decomposition of signals containing multiple disturbances, and precision for the classification task above 97%

In dieser Arbeit werden - basierend auf dem Langsamkeitsprinzip - Modelle und Algorithmen für das auditorische System entwickelt. Verschiedene experimentelle Ergebnisse, sowie die erfolgreichen Ergebnisse im visuellen System legen nahe, dass, trotz der unterschiedlichen Beschaffenheit visueller und auditorischer sensorischer Signale, das Langsamkeitsprinzip auch im auditorischen System eine bedeutsame Rolle spielen könnte, und vielleicht auch im Kortex im Allgemeinen. Es wurden verschiedene Modelle für unterschiedliche Repräsentationen des auditorischen Inputs realisiert. Es werden die Beschränkungen der jeweiligen Ansätze aufgezeigt. Im Bereich der Signalverarbeitung haben sich das Langsamkeitsprinzip und dessen direkte Implementierung als Signalverarbeitungsalgorithmus, Slow Feature Analysis, über die biologisch inspirierte Modellierung hinaus als nützlich erwiesen. Es wird ein neuer Algorithmus für das Problem der nichtlinearen blinden Signalquellentrennung beschrieben, der auf einer Kombination von Langsamkeitsprinzip und dem Prinzip der statistischen Unabhängigkeit basiert, und der anhand von künstlichen und realistischen Audiosignalen getestet wird. Außerdem wird die Open Source Software Bibliothek Modular toolkit for Data Processing vorgestellt. / In this thesis we develop models and algorithms based on the slowness principle in the auditory domain. Several experimental results as well as the successful results in the visual domain indicate that, despite the different nature of the sensory signals, the slowness principle may play an important role in the auditory domain as well, if not in the cortex as a whole. Different modeling approaches have been used, which make use of several alternative representations of the auditory stimuli. We show the limitations of these approaches. In the domain of signal processing, the slowness principle and its straightforward implementation, the Slow Feature Analysis algorithm, has been proven to be useful beyond biologically inspired modeling. A novel algorithm for nonlinear blind source separation is described that is based on a combination of the slowness and the statistical independence principles, and is evaluated on artificial and real-world audio signals. The Modular toolkit for Data Processing open source software library is additionally presented.

Der Fokus dieser Dissertation liegt auf den Verbindungen zwischen ICA (Independent Component Analysis - Unabhängige Komponenten Analyse) und SFA (Slow Feature Analysis - Langsame Eigenschaften Analyse). Um einen Vergleich zwischen beiden Methoden zu ermöglichen wird CuBICA2, ein ICA Algorithmus basierend nur auf Statistik zweiter Ordnung, d.h. Kreuzkorrelationen, vorgestellt. Dieses Verfahren minimiert zeitverzögerte Korrelationen zwischen Signalkomponenten, um die statistische Abhängigkeit zwischen denselben zu reduzieren. Zusätzlich wird eine alternative SFA-Formulierung vorgestellt, die mit CuBICA2 verglichen werden kann. Im Falle linearer Gemische sind beide Methoden äquivalent falls nur eine einzige Zeitverzögerung berücksichtigt wird. Dieser Vergleich kann allerdings nicht auf mehrere Zeitverzögerungen erweitert werden. Für ICA lässt sich zwar eine einfache Erweiterung herleiten, aber ein ähnliche SFA-Erweiterung kann nicht im originären SFA-Sinne (SFA extrahiert die am langsamsten variierenden Signalkomponenten aus einem gegebenen Eingangssignal) interpretiert werden. Allerdings kann eine im SFA-Sinne sinnvolle Erweiterung hergeleitet werden, welche die enge Verbindung zwischen der Langsamkeit eines Signales (SFA) und der zeitlichen Vorhersehbarkeit desselben verdeutlich. Im Weiteren wird CuBICA2 und SFA kombiniert. Das Resultat kann aus zwei Perspektiven interpretiert werden. Vom ICA-Standpunkt aus führt die Kombination von CuBICA2 und SFA zu einem Algorithmus, der das Problem der nichtlinearen blinden Signalquellentrennung löst. Vom SFA-Standpunkt aus ist die Kombination eine Erweiterung der standard SFA. Die standard SFA extrahiert langsam variierende Signalkomponenten die untereinander unkorreliert sind, dass heißt statistisch unabhängig bis zur zweiten Ordnung. Die Integration von ICA führt nun zu Signalkomponenten die mehr oder weniger statistisch unabhängig sind. / Within this thesis, we focus on the relation between independent component analysis (ICA) and slow feature analysis (SFA). To allow a comparison between both methods we introduce CuBICA2, an ICA algorithm based on second-order statistics only, i.e.\ cross-correlations. In contrast to algorithms based on higher-order statistics not only instantaneous cross-correlations but also time-delayed cross correlations are considered for minimization. CuBICA2 requires signal components with auto-correlation like in SFA, and has the ability to separate source signal components that have a Gaussian distribution. Furthermore, we derive an alternative formulation of the SFA objective function and compare it with that of CuBICA2. In the case of a linear mixture the two methods are equivalent if a single time delay is taken into account. The comparison can not be extended to the case of several time delays. For ICA a straightforward extension can be derived, but a similar extension to SFA yields an objective function that can not be interpreted in the sense of SFA. However, a useful extension in the sense of SFA to more than one time delay can be derived. This extended SFA reveals the close connection between the slowness objective of SFA and temporal predictability. Furthermore, we combine CuBICA2 and SFA. The result can be interpreted from two perspectives. From the ICA point of view the combination leads to an algorithm that solves the nonlinear blind source separation problem. From the SFA point of view the combination of ICA and SFA is an extension to SFA in terms of statistical independence. Standard SFA extracts slowly varying signal components that are uncorrelated meaning they are statistically independent up to second-order. The integration of ICA leads to signal components that are more or less statistically independent.

CoordenaÃÃo de AperfeÃoamento de Pessoal de NÃvel Superior / Neste trabalho, à discutido o problema de reconhecimento de objetos utilizando imagens extraÃdas de um sensor industrial 3D. NÃs nos concentramos em 9 extratores de caracterÃsticas, dos quais 7 sÃo baseados nos momentos invariantes (Hu, Zernike, Legendre, Fourier-Mellin, Tchebichef, Bessel-Fourier e Gaussian-Hermite), um outro à baseado na Transformada de Hough e o Ãltimo na anÃlise de componentes independentes, e, 4 classificadores, Naive Bayes, k-Vizinhos mais PrÃximos, MÃquina de Vetor de Suporte e Rede Neural Artificial-Perceptron Multi-Camadas. Para a escolha do melhor extrator de caracterÃsticas, foram comparados os seus desempenhos de classificaÃÃo em termos de taxa de acerto e de tempo de extraÃÃo, atravÃs do classificador k-Vizinhos mais PrÃximos utilizando distÃncia euclidiana. O extrator de caracterÃsticas baseado nos momentos de Zernike obteve as melhores taxas de acerto, 98.00%, e tempo relativamente baixo de extraÃÃo de caracterÃsticas, 0.3910 segundos. Os dados gerados a partir deste, foram apresentados a diferentes heurÃsticas de classificaÃÃo. Dentre os classificadores testados, o classificador k-Vizinhos mais PrÃximos, obteve a melhor taxa mÃdia de acerto, 98.00% e, tempo mÃdio de classificaÃÃo relativamente baixo, 0.0040 segundos, tornando-se o classificador mais adequado para a aplicaÃÃo deste estudo. / In this work, the problem of recognition of objects using images extracted from a 3D industrial sensor is discussed. We focus in 9 feature extractors (where seven are based on invariant moments -Hu, Zernike, Legendre, Fourier-Mellin, Tchebichef, BesselâFourier and Gaussian-Hermite-, another is based on the Hough transform and the last one on independent component analysis), and 4 classifiers (Naive Bayes, k-Nearest Neighbor, Support Vector machines and Artificial Neural Network-Multi-Layer Perceptron). To choose the best feature extractor, their performance was compared in terms of classification accuracy rate and extraction time by the k-nearest neighbors classifier using euclidean distance. The feature extractor based on Zernike moments, got the best hit rates, 98.00 %, and relatively low time feature extraction, 0.3910 seconds. The data generated from this, were presented to different heuristic classification. Among the tested classifiers, the k-nearest neighbors classifier achieved the highest average hit rate, 98.00%, and average time of relatively low rank, 0.0040 seconds, thus making it the most suitable classifier for the implementation of this study.

Um Sistema Elétrico de Potência (SEP) está susceptível à presença de diversas fontes de distúrbios que prejudicam a Qualidade da Energia Elétrica (QEE). Desta forma, as suas tensões e/ou correntes podem conter m´múltiplos distúrbios com ocorrência simultânea. Este trabalho apresenta uma metodologia para decomposição do sinal medido em componentes que estimem as formas de onda dos distúrbios individuais quando da ocorrência de m´múltiplos distúrbios, com o posterior reconhecimento de cada um deles. A Análise de Componentes Independentes (ICA) é utilizada como principal ferramenta na etapa de decomposição dos distúrbios. A ICA é originalmente uma t´técnica aplicada em análise multivariada de dados, o que significa que ela necessita de medições realizadas por múltiplos sensores dispostos em diferentes posições de um sistema. No entanto, este trabalho propõe a sua aplicação tendo disponível apenas um sinal medido. Para tanto, são propostos dois métodos para produzir a diversidade necessária para a t´técnica funcionar adequadamente. É demonstrado que ambos os métodos equivalem a um banco de filtros lineares adaptativos capaz de realizar a separação não-supervisionada de múltiplos distúrbios independentes e que sejam espectralmente disjuntos. Por fim, é proposto um sistema de classificação que utiliza Redes Neurais Artificiais (RNAs) para identificar os distúrbios decompostos pela etapa anterior. A metodologia completa é avaliada por meio de testes utilizando dados sintéticos e reais, alcançando resultados altamente satisfatórios para decomposição de sinais contendo múltiplos distúrbios e taxas de acerto globais dos classificadores superiores a 97% / The power system is susceptible to the presence of several sources of disturbances that harm the power quality. In this sense, its voltages and/or currents may contain multiple disturbances with simultaneous occurrence. This work presents a methodology that decomposes the measured signal in components which estimate the waveforms of the individual disturbances followed by their recognition when a multiple disturbance situation occurs. The Independent Component Analysis (ICA) is the main tool in the disturbance decomposition stage. The ICA is originally a technique applied in multivariate data analysis, which means that it requires measurements from multiple sensors allocated in different positions of the system. However, this work proposes its application for a single measured signal available. For this, two methods were developed in order to provide the required diversity to the ICA technique. It is demonstrated that both methods are equivalent to an adaptive linear filter bank capable to perform an unsupervised separation of multiple independent disturbances, if they are spectrally disjoint. A classification system based on artificial neural networks is proposed to identify the disturbances decomposed by the previous stage. The complete system is tested using synthetic and actual data, presenting highly satisfactory results for the decomposition of signals containing multiple disturbances, and precision for the classification task above 97%