Purpose – The purpose of the study is to expand the knowledge of how wheel motor currents can be combined with machine learning to be used in a collision detection system for autonomous robots, in order to decrease the number of external sensors and open new design opportunities and lowering production costs. Method – The study is conducted with design science research where two artefacts are developed in a cooperation with Globe Tools Group. The artefacts are evaluated in how they categorize data given by an autonomous robot in the two categories collision and non-collision. The artefacts are then tested by generated data to analyse their ability to categorize. Findings – Both artefacts showed a 100 % accuracy in detecting the collisions in the given data by the autonomous robot. In the second part of the experiment the artefacts show that they have different decision boundaries in how they categorize the data, which will make them useful in different applications. Implications – The study contributes to an expanding knowledge in how machine learning and wheel motor currents can be used in a collision detection system. The results can lead to lowering production costs and opening new design opportunities. Limitations – The data used in the study is gathered by an autonomous robot which only did frontal collisions on an artificial lawn. Keywords – Machine learning, K-Nearest Neighbour, Multilayer Perceptron, collision detection, autonomous robots, Collison detection based on current. / Syfte – Studiens syfte är att utöka kunskapen om hur hjulmotorstömmar kan kombineras med maskininlärning för att användas vid kollisionsdetektion hos autonoma robotar, detta för att kunna minska antalet krävda externa sensorer hos dessa robotar och på så sätt öppna upp design möjligheter samt minska produktionskostnader Metod – Studien genomfördes med design science research där två artefakter utvecklades i samarbete med Globe Tools Group. Artefakterna utvärderades sedan i hur de kategoriserade kollisioner utifrån en given datamängd som genererades från en autonom gräsklippare. Studiens experiment introducerade sedan in data som inte ingick i samma datamängd för att se hur metoderna kategoriserade detta. Resultat – Artefakterna klarade med 100% noggrannhet att detektera kollisioner i den giva datamängden som genererades. Dock har de två olika artefakterna olika beslutsregioner i hur de kategoriserar datamängderna till kollision samt icke-kollisioner, vilket kan ge dom olika användningsområden Implikationer – Examensarbetet bidrar till en ökad kunskap om hur maskininlärning och hjulmotorströmmar kan användas i ett kollisionsdetekteringssystem. Studiens resultat kan bidra till minskade kostnader i produktion samt nya design möjligheter Begränsningar – Datamängden som användes i studien samlades endast in av en autonom gräsklippare som gjorde frontalkrockar med underlaget konstgräs. Nyckelord – Maskininlärning, K-nearest neighbor, Multi-layer perceptron, kollisionsdetektion, autonoma robotar

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.

The electro-oculogram (EOG) is the most widely used technique for recording eye movements in clinical settings. It is inexpensive, practical, and non-invasive. Use of EOG is usually restricted to horizontal recordings as vertical EOG contains eyelid artefact (Oster & Stern, 1980) and blinks. The ability to analyse two dimensional (2D) eye movements may provide additional diagnostic information on pathologies, and further insights into the nature of brain functioning. Simultaneous recording of both horizontal and vertical EOG also introduces other difficulties into calibration of the eye movements, such as different gains in the two signals, and misalignment of electrodes producing crosstalk. These transformations of the signals create problems in relating the two dimensional EOG to actual rotations of the eyes. The application of an artificial neural network (ANN) that could map 2D recordings into 2D eye positions would overcome this problem and improve the utility of EOG. To determine whether ANNs are capable of correctly calibrating the saccadic eye movement data from 2D EOG (i.e. performing the necessary inverse transformation), the ANNs were first tested on data generated from mathematical models of saccadic eye movements. Multi-layer perceptrons (MLPs) with non-linear activation functions and trained with back propagation proved to be capable of calibrating simulated EOG data to a mean accuracy of 0.33° of visual angle (SE = 0.01). Linear perceptrons (LPs) were only nearly half as accurate. For five subjects performing a saccadic eye movement task in the upper right quadrant of the visual field, the mean accuracy provided by the MLPs was 1.07° of visual angle (SE = 0.01) for EOG data, and 0.95° of visual angle (SE = 0.03) for infrared limbus reflection (IRIS®) data. MLPs enabled calibration of 2D saccadic EOG to an accuracy not significantly different to that obtained with the infrared limbus tracking data.

Spacecraft fulfill a myriad of critical functions on orbit, from defense and intelligence to science, navigation, and telecommunication. Spacecraft can also cost several hundred millions of dollars to design and launch, and given that physical access for maintenance remains difficult if not impossible to date, designing high reliability and survivability into these systems is an engineering and financial imperative. While reliability is recognized as an essential attribute for spacecraft, little analysis has been done pertaining to actual field reliability of spacecraft and their subsystems. This thesis consists of two parts. The first part fills the gap in the current understanding of spacecraft failure behavior on orbit through extensive statistical analysis and modeling of anomaly and failure data of Earth-orbiting spacecraft. The second part builds on these results to develop a novel theoretical basis (interdependent multi-layer network approach) and algorithmic tools for the analysis of survivability of spacecraft and space-based networks. Space-based networks (SBNs) allow the sharing of on-orbit resources, such as data storage, processing, and downlink. Results indicate and quantify the incremental survivability improvement of the SBN over the traditional monolith architecture. A trade-space analysis is then conducted using non-descriptive networkable subsystems/technologies to explore survivability characteristics of space-based networks and help guide design choices.

In this work, a multilayer security solution for digital communication systems is provided by considering the joint effects of physical-layer security channel codes with application-layer cryptography. We address two problems: first, the cryptanalysis of error-prone ciphertext; second, the design of a practical physical-layer security coding scheme. To our knowledge, the cryptographic attack model of the noisy-ciphertext attack is a novel concept. The more traditional assumption that the attacker has the ciphertext is generally assumed when performing cryptanalysis. However, with the ever-increasing amount of viable research in physical-layer security, it now becomes essential to perform the analysis when ciphertext is unreliable. We do so for the simple substitution cipher using an information-theoretic framework, and for stream ciphers by characterizing the success or failure of fast-correlation attacks when the ciphertext contains errors. We then present a practical coding scheme that can be used in conjunction with cryptography to ensure positive error rates in an eavesdropper's observed ciphertext, while guaranteeing error-free communications for legitimate receivers. Our codes are called stopping set codes, and provide a blanket of security that covers nearly all possible system configurations and channel parameters. The codes require a public authenticated feedback channel. The solutions to these two problems indicate the inherent strengthening of security that can be obtained by confusing an attacker about the ciphertext, and then give a practical method for providing the confusion. The aggregate result is a multilayer security solution for transmitting secret data that showcases security enhancements over standalone cryptography.

The Multi-Layer Perceptron (MLP) is one of the most widely applied and researched Artificial Neural Network model. MLP networks are normally applied to performing supervised learning tasks, which involve iterative training methods to adjust the connection weights within the network. This is commonly formulated as a multivariate non-linear optimization problem over a very high-dimensional space of possible weight configurations. Analogous to the field of mathematical optimization, training an MLP is often described as the search of an error surface for a weight vector which gives the smallest possible error value. Although this presents a useful notion of the training process, there are many problems associated with using the error surface to understand the behaviour of learning algorithms and the properties of MLP mappings themselves. Because of the high-dimensionality of the system, many existing methods of analysis are not well-suited to this problem. Visualizing and describing the error surface are also nontrivial and problematic. These problems are specific to complex systems such as neural networks, which contain large numbers of adjustable parameters, and the investigation of such systems in this way is largely a developing area of research. In this thesis, the concept of the error surface is explored using three related methods. Firstly, Principal Component Analysis (PCA) is proposed as a method for visualizing the learning trajectory followed by an algorithm on the error surface. It is found that PCA provides an effective method for performing such a visualization, as well as providing an indication of the significance of individual weights to the training process. Secondly, sampling methods are used to explore the error surface and to measure certain properties of the error surface, providing the necessary data for an intuitive description of the error surface. A number of practical MLP error surfaces are found to contain a high degree of ultrametric structure, in common with other known configuration spaces of complex systems. Thirdly, a class of global optimization algorithms is also developed, which is focused on the construction and evolution of a model of the error surface (or search spa ce) as an integral part of the optimization process. The relationships between this algorithm class, the Population-Based Incremental Learning algorithm, evolutionary algorithms and cooperative search are discussed. The work provides important practical techniques for exploration of the error surfaces of MLP networks. These techniques can be used to examine the dynamics of different training algorithms, the complexity of MLP mappings and an intuitive description of the nature of the error surface. The configuration spaces of other complex systems are also amenable to many of these techniques. Finally, the algorithmic framework provides a powerful paradigm for visualization of the optimization process and the development of parallel coupled optimization algorithms which apply knowledge of the error surface to solving the optimization problem.

Gegenstand dieser Arbeit ist die Modifizierung von Oberflächen durch die Abscheidung alternierender Schichtsysteme auf Kohlenstofffasern und die Abscheidung von Aluminiumoxid auf organischen Membranen. Im ersten Kapitel wird das Vorgehen zur Abscheidung von organischen und anorganischen Schichten auf Kohlenstofffasern mittels der Atomlagenabscheidung und der oberflächeninitiierten Gasphasenabscheidung betrachtet. Dabei wird als Erstes auf die Abscheidung von Einzellagen und deren Optimierung eingegangen sowie im Anschluss auf die Übertragung dieser Parameter auf die Abscheidung von alternierenden Multilagensystemen. Mittels elektronenmikroskopischen-Untersuchungen, Rasterelektronenmikroskopie und energiedispersiver Röntgenspektroskopie, wird die Abscheidung der Materialien untersucht. Weiterhin können mit Hilfe von thermogravimetrischen Analysen die Oxidationsbeständigkeit der beschichteten Kohlenstofffasern sowie die einzelnen Schichtdicken bestimmt werden. Im zweiten Kapitel wird auf die Beschichtung von organischen Membranen eingegangen. Das Hauptaugenmerk liegt dabei auf der Beschichtung von nicht-hierarchisch und hierarchisch strukturierten Membranen mit Aluminiumoxid. Dafür werden die Atomlagenabscheidung und die Grenzflächenreaktion der Gasphase mit der im Feststoff gebundenen Flüssigphase angewendet. Unter Anwendung dieser beiden Verfahren ist es gelungen, dünne und gleichmäßige Schichten auf den Membranen abzuscheiden. Die Charakterisierung erfolgte mittels Rasterelektronenmikroskopie und energiedispersiver Röntgenspektroskopie. Zum Schluss wurden Filtrationsexperimente zum Vergleich der Stabilität und Durchflussraten der beschichteten mit den unbeschichteten Membranen durchgeführt.

Ces travaux de thèse s’inscrivent dans la problématique de développement de transformateurs planar pour l’intégration de puissance, dans le contexte de l’avion plus électrique (More Electric Aircraft – MEA) où les contraintes de volume et de poids sont primordiales. Les composants magnétiques restent en effet un frein à l’intégration des systèmes d’Electronique de Puissance et les composants planar (transformateurs et inductances) offrent une alternative intéressante aux composants bobinés pour la réduction de la taille des convertisseurs.Dans ce manuscrit, des méthodes, un outil de dimensionnement et des prototypes de transformateurs planar (2 et 3 enroulements) en technologie feuillard et PCB sont développés pour des applications de convertisseur DC/DC aéronautique. Dans un premier temps, les modèles permettant le calcul des pertes, l'estimation de l'élévation de température et le calcul de l’inductance de fuite sont présentés et comparés afin de concevoir des outils de calculs pour la conception. Dans un deuxième temps, il est montré que la modification de la forme des angles des spires rectangulaires permet de réduire significativement les pertes cuivre HF. Sur la base de ces outils et résultats, des prototypes de transformateurs planar à 3 enroulements en PCB multicouches sont développés. De nombreux prototypes sont caractérisés et valident les modèles de dimensionnement proposés. Enfin, l’un de ces prototypes est intégré et testé dans un convertisseur de puissance DC/DC de 3.75kW mettant en évidence les gains obtenus. / These thesis works deal with the issue of the planar transformers development for power integration, in the context of the More Electric Aircraft (MEA), where the constraints of volume and weight are paramount. Magnetic components remain a hindrance to the integration of Power Electronics systems and planar components (transformers and inductors) offer an interesting alternative to wound components for reducing the size of converters.In these works, methods, a sizing tool and prototypes of planar transformers (2 and 3 windings) in strip and PCB technology are developed for aeronautical DC / DC converter applications. Firstly, the models allowing the calculation of the losses, the estimation of the temperature rise and the calculation of the leakage inductance are presented and compared in order to design calculation tools for engineers. In a second step, it is shown that the modification of the shape of the angles of rectangular turns makes it possible to significantly reduce the HF copper losses.Based on these tools and results, prototypes of 3-windings planar transformers in multilayer PCBs are developed. Many prototypes are characterized and validate the proposed designing models. Finally, one of these prototypes is integrated and tested in a DC / DC power converter of 3.75kW highlighting the gains obtained.

La prévision des séries temporelles est un problème qui est traité depuis de nombreuses années. On y trouve des applications dans différents domaines tels que : la finance, la médecine, le transport, etc. Dans cette thèse, on s’est intéressé aux méthodes issues de l’apprentissage artificiel : les réseaux de neurones et les SVM. On s’est également intéressé à l’intérêt des méta-méthodes pour améliorer les performances des prédicteurs, notamment l’approche locale. Dans une optique de diviser pour régner, les approches locales effectuent le clustering des données avant d’affecter les prédicteurs aux sous ensembles obtenus. Nous présentons une modification dans l’algorithme d’apprentissage des réseaux de neurones récurrents afin de les adapter à cette approche. Nous proposons également deux nouvelles techniques de clustering, la première basée sur les cartes de Kohonen et la seconde sur les arbres binaires. / Time series forecasting is a widely discussed issue for many years. Researchers from various disciplines have addressed it in several application areas : finance, medical, transportation, etc. In this thesis, we focused on machine learning methods : neural networks and SVM. We have also been interested in the meta-methods to push up the predictor performances, and more specifically the local models. In a divide and conquer strategy, the local models perform a clustering over the data sets before different predictors are affected into each obtained subset. We present in this thesis a new algorithm for recurrent neural networks to use them as local predictors. We also propose two novel clustering techniques suitable for local models. The first is based on Kohonen maps, and the second is based on binary trees.

Este trabalho fundamenta-se no conceito de máquina de comitê de redes neurais artificiais e tem por objetivo resolver o problema inverso de transferência radiativa em um meio unidimensional, homogêneo, absorvedor e espalhador isotrópico. A máquina de comitê de redes neurais artificiais agrega e combina o conhecimento adquirido por um certo número de especialistas aqui representados, individualmente, por cada uma das redes neurais artificiais (RNA) que compõem a máquina de comitê de redes neurais artificiais. O objetivo é atingir um resultado final melhor do que o obtido por qualquer rede neural artificial separadamente, selecionando-se apenas àquelas redes neurais artificiais que apresentam os melhores resultados na fase de generalização descartando-se as demais, o que foi feito neste trabalho. Aqui são utilizados dois modelos estáticos de máquinas de comitê, usando a média aritmética de conjunto, que se diferenciam entre si apenas na composição do combinador de saída de cada máquina de comitê. São obtidas, usando-se máquinas de comitê de redes neurais artificiais, estimativas para os parâmetros de transferência radiativa, isto é, a espessura óptica do meio, o albedo de espalhamento simples e as refletividades difusas. Finalmente, os resultados obtidos com ambos os modelos de máquina de comitê são comparados entre si e com aqueles encontrados usando-se apenas redes neurais artificiais do tipo perceptrons de múltiplas camadas (MLP), isoladamente. Aqui essas redes neurais artificiais são denominadas redes neurais especialistas, mostrando que a técnica empregada traz melhorias de desempenho e resultados a um custo computacional relativamente baixo. / This work is based on the concept of neural networks committee machine and has the objective to solve the inverse radiative transfer problem in one-dimensional, homogeneous, absorbing and isotropic scattering media. The artificial neural networks committee machine adds and combines the knowledge acquired by an exact number of specialists which are represented, individually, by each one of the artificial neural networks (ANN) that composes the artificial neural network committee machine. The aim is to reach a final result better than the one obtained by any of the artificial neural network separately, selecting only those artificial neural networks that presents the best results during the generalization phase and discarding the others, what was done in this present work. Here are used two static models of committee machines, using the ensemble arithmetic average, that differ between themselves only by the composition of the output combinator by each one of the committee machine. Are obtained, using artificial neural networks committee machines, estimates for the radiative transfer parameters, that is, medium optical thickness, single scattering albedo and diffuse reflectivities. Finally, the results obtained with both models of committee machine are compared between themselves and with those found using artificial neural networks type multi-layer perceptrons (MLP), isolated. Here that artificial neural networks are named as specialists neural networks, showing that the technique employed brings performance and results improvements with relatively low computational cost.