This thesis deals with analysis and processing of the Sleep Electroencephalogram (EEG) signals. The scope of this thesis can be split into several areas. The first area is application of the Independent Component Analysis (ICA) method for EEG signal analysis. A model of EEG signal formation is proposed and conditions under which this model is valid are examined. It is shown that ICA can be used to remove non-deterministic artifacts contained in the EEG signals. The second area of interest is analysis of stationarity of the Sleep EEG signal. Methods to identify stationary signal segments and to analyze statistical properties of these stationary segments are presented. The third area of interest focuses on spectral analysis of the Sleep EEG signals. Analyses are performed that shows the processes that form particular parts of EEG signals spectrum. Also, random signals that are an integral part of the EEG signals analysis are performed. The last area of interest focuses on elimination of the transition processes that are caused by the filtering of the short EEG signal segments.

This thesis compares hand-designed features with features learned by feature learning methods in video classification. The features learned by Principal Component Analysis whitening, Independent subspace analysis and Sparse Autoencoders were tested in a standard Bag of Visual Word classification paradigm replacing hand-designed features (e.g. SIFT, HOG, HOF). The classification performance was measured on Human Motion DataBase and YouTube Action Data Set. Learned features showed better performance than the hand-desined features. The combination of hand-designed features and learned features by Multiple Kernel Learning method showed even better performance, including cases when hand-designed features and learned features achieved not so good performance separately.

This thesis deals with the increasingly developing field of biometric systems which is the identification of faces. The thesis deals with the possibilities of face localization in pictures and their normalization, which is necessary due to external influences and the influence of different scanning techniques. It describes various techniques of localization of dominant features of the face such as eyes, mouth or nose. Not least, it describes different approaches to the identification of faces. Furthermore a it deals with an implementation of the Dominant Face Features Recognition application, which demonstrates chosen methods for localization of the dominant features (Hough Transform for Circles, localization of mouth using the location of the eyes) and for identification of a face (Linear Discriminant Analysis, Kernel Discriminant Analysis). The last part of the thesis contains a summary of achieved results and a discussion.

Les travaux présentés dans cette mémoire visent à développer de nouvelles méthodes qui exploitent les propriétés de cyclostationnarité pour traiter des signaux de force de réaction du sol enregistrées au cours de la marche et la course à pied. Nous nous intéressons à l’analyse de la locomotion humaine dans trois domaines d´études: une étude liée à la pathologie, une deuxième liée directement à l’âge et une troisième relative à la fatigue. En effet, la détection du risque de chute chez les personnes âgées pour fin de prévention contre la chute constitue un enjeu majeur, car cette chute entraine d’une part un nombre de décès important et d’autres part se traduit par un cout élevée de la santé publique. Par ailleurs, l’étude de la fatigue musculaire en particulier pour l’amélioration des performances des sportifs de haut niveau a fait l’objet de nombreux travaux de recherche & développement. La recherche et le développement de nouvelles méthodes et d’indicateurs dans le domaine de traitement de signal dans le but de caractériser la locomotive humaine, permettrait des avancées intéressantes dans les enjeux évoqués ci-dessus. La complexité des signaux GRF est définie par le système neuromusculaire qui génère ce signal. Une meilleure connaissance de ce système nécessite le développement des méthodes de séparation de sources et des outils avancés de traitement du signal pour mieux décrire le système considéré. En effet, nous montrons dans cette thèse que les signaux GRF peuvent être modélisés dans un cadre cyclostationnaire élargi. Les composantes de signal GRF (contribution active et passive) sont séparées par de nouvelles techniques de séparation de sources. Cette modélisation ouvre de nouvelles perspectives pour la décomposition et identification des sources individuelles. D'autre part, on exploite les caractères cyclostationnaire des signaux dans le cadre de la méthode d'analyse en composantes morphologique (MCA). Cet algorithme nous permet de séparer avec succès les composantes d’ordre 1 et d’ordre 2 des signaux considérés. Finalement, nous nous proposons un nouveau modèle utile pour l'étude et la caractérisation de cyclostationnarité. Il présente l'effet de la variation aléatoire de la pente sur le spectre du signal cyclique. Nous appelons ce modèle (modèle cyclostationnaire à pente aléatoire). Nous appliquons ce modèle pour l'étude des signaux biomécaniques où nous considérons la pente comme une mesure spécifique extraite des forces de réaction du sol. Les résultats montrent que la pente et les polynômes à coefficients aléatoires du pic passive peuvent jouer un rôle important et fournir des informations intéressantes concernant la fatigue et concernant la performance de marche et course à pied / The research work presented in this dissertation, involves the development of novel methodologies and methods, for the exploitation of cyclostationarity properties and for the treatment of ground reaction force signals, recorded during walking and running. We are especially interested in the analysis of human locomotion in three fields of interest: a study relating to pathology, a study directly related to age, and a study of muscle fatigue. Indeed, the detection of risk of falling among the elderly for the prevention of falls is of major concern. This is because falling on the one hand leads to a large number of deaths and secondly, resulting in higher costs of public health.Study the muscle fatigue in particular has occupied taken a big share out of this research due to the importance of such events like strenuous level of sports. Research and development of new methods and indicators in the field of signal processing for better characterizing the human locomotion, would allow interesting advances in the aforementioned issues. The complexity of GRF signals is defined by the neuromuscular system which generates this signal. Improved knowledge of this system requires developing source separation methods and advanced signal processing tools to better describe the system under consideration. Indeed, we will endeavor to show in this dissertation that GRF signals can be modeled within an enlarged cyclostationary framework. The GRF signal components (active and passive contribution) are separated by means of new source separation techniques. This modeling opens new perspectives for the decomposition and identification of individual sources. On the other hand, we exploit the cyclostationary characters of signals in the context of Morphological component analysis (MCA) method. Such algorithm enables us to successfully separate the first and second order components of the signals under consideration. Finally, we provide a new model useful for studying and characterizing cyclostationarity. It presents the impact of random slope variation on the cyclic spectrum of the signal. We call this model the random slope modulation (RSM). We apply this model for studying biomechanical signals where we consider the slope as a specic measure extracted from the vertical ground reaction forces. The results show that the slope and polynomial random coefficients of passive peaks can play important role and provide interesting information concerning fatigue and concerning running / walking performance

Les processus biologiques sont nombreux et leurs interactions complexes. Les mesures de cesphénomènes génèrent des biomarqueurs multiples. Ainsi, l’épidémiologie doit évoluer dans cecontexte de données complexes et de nature multidimensionnelle. Les maladies du systèmeimmunitaire et les troubles immunologiques qui leur sont associés constituent un bon exemplede pathologies où les questions clinico-épidémiologiques sont de plus en plus complexes,nécessitant des méthodes biostatistiques et épidémiologiques adaptées. Dans cette thèsed’Université, des méthodes permettant de prendre en compte les difficultés méthodologiquesgénérées par les données d’immunologie sont présentées autour de trois applicationscliniques. Notre approche consiste en l’utilisation de méthodes intégratives qui prennent encompte l’ensemble des mesures concernant une pathologie donnée. Nous montrons l’intérêtde l’analyse en composantes principales et de la classification hiérarchique ascendante pourrésumer et extraire l’information de données multiples de cytométrie en flux et celui desmodèles d’équations structurelles pour l’étude de relations complexes entre variables lors deprocessus multifactoriels. Enfin, via l’exemple d’un modèle de reconstitution immunitaireasymptotique utilisant une fonction exponentielle, nous illustrons l’importance de s’appuyersur la structure même des données et sur la compréhension des mécanismes biologiques quisous-tendent la variabilité de ces données dans la réflexion qui concourt au choix d’un modèlestatistique. Les méthodes et la réflexion proposées dans cette thèse sont transposables àd’autres domaines d’application avec des données multiples complexes. / Numerous biological processes with potentially complex interactions exist. Measurements ofthese processes allow to produce multiple biomarkers. Thus, there is a need for epidemiologyto evolve within the context of complex and multidimensional data. Immune system diseasesand associated immune disorders are an example of a field where clinical and epidemiologicalissues are increasingly complex, requiring appropriate statistical and epidemiologicalmethods. In this thesis, methods taking into account methodological difficulties generated byimmunology data are presented through three motivating examples. The general paradigm ofour approach is to take into account all measurements on a given pathology using integrativemethods. We propose principal component analysis and hierarchical clustering to summarizemultidimensional cytometry data and structural equation modelling for dealing with complexrelationships between variables in multifactorial processes. Then, through the example of anasymptotic model of immune reconstitution using an exponential function, we illustrate theimportance about the data’s structure and the biological mechanisms underlying its variabilitywhen building a mathematical model. The methods and the thinking advocated in this thesisare transposable to other research domains with complex data.

This thesis is carried out in collaboration with a private company, DANSiC AB This study is an extension of a research work started by DANSiC AB in 2019 to classify a source. This study is about classifying a source into two classes with the sensitivity of one source higher than the other as one source has greater importance. The data provided for this thesis is based on sensor measurements on different temperature cycles. The data is high-dimensional and is expected to have a drift in measurements. Principal component analysis (PCA) is used for dimensionality reduction. “Differential”, “Relative” and “Fractional” drift compensation techniques are used for compensating the drift in data. A comparative study was performed using three different classification algorithms, which are “Linear Discriminant Analysis (LDA)”, “Naive Bayes classifier (NB)” and “Random forest (RF)”. The highest accuracy achieved is 59%,Random forest is observed to perform better than the other classifiers. / <p>This work is done with DANSiC AB in collaboration with Linkoping University.</p>

Design space exploration (DSE) is used to improve and understand engineering designs. Such designs must meet objectives and structural requirements. Design improvement is non-trivial and requires new DSE methods. Turbomachinery manufacturers must continue to improve existing engines to keep up with global demand. Two challenges of turbomachinery DSE are: the time required to evaluate designs, and knowing which designs to evaluate. This research addressed these challenges by developing novel surrogate and principal component analysis (PCA) based DSE methods. Node and PCA-based surrogates were created to allow faster DSE of turbomachinery blades. The surrogates provided static stress estimation within 10% error. Surrogate error was related to the number of sampled finite element (FE) models used to train the surrogate and the variables used to change the designs. Surrogates were able to provide structural evaluations three to five orders of magnitude faster than FEA evaluations. The PCA-based surrogates were then used to create a PCA-based design workflow to help designers know which designs to evaluate. The workflow used either two-point correlation or stress and geometry coupling to relate the design variables to principal component (PC) scores. These scores were projections of the FE models onto the PCs obtained from PCA. Analysis showed that this workflow could be used in DSE to better explore and improve designs. The surrogate methods were then applied to vibratory stress. A computationally simplified analysis workflow was developed to allow for enough fluid and structural analyses to create a surrogate model. The simplified analysis workflow introduced 10% error but decreased the computational cost by 90%. The surrogate methods could not directly be applied to emulation of vibration due to the large spikes which occur near resonance. A novel, indirect emulation method was developed to better estimate vibratory responses Surrogates were used to estimate the inputs to calculate the vibratory responses. During DSE these estimations were used to calculate the vibratory responses. This method reduced the error between the surrogate and FEA from 85% to 17%. Lastly, a PCA-based multi-fidelity surrogate method was developed. This assumed the PCs of the high and low-fidelities were similar. The high-fidelity FE models had tens of thousands of nodes and the low-fidelity FE models had a few hundred nodes. The computational cost to create the surrogate was decreased by 75% for the same errors. For the same computational cost, the error was reduced by 50%. Together, the methods developed in this research were shown to decrease the cost of evaluating the structural responses of turbomachinery blade designs. They also provided a method to help the designer understand which designs to explore. This research paves the way for better, and more thoroughly understood turbomachinery blade designs.

Notre but était de mieux comprendre les mécanismes associés à la récupération en mémoire à court terme acoustique à l’aide de mesures électrophysiologiques. La tâche utilisée était une version modifiée de la tâche de Sternberg dans laquelle les participants devaient retenir deux, quatre ou six sons purs hors de la gamme musical bien tempérée, ne pouvant pas être facilement recodés verbalement. Après un intervalle de rétention silencieux, ils entendaient un son et devaient indiquer si celui-ci était présent ou absent dans l’ensemble mémoire. En utilisant plusieurs conditions de charge et en contrôlant pour les durées de stimulation, nous avons comparé les effets de position sérielle, ainsi que les effets de charge, sur les données comportementales et sur les données électrophysiologiques mesurées lors du balayage mnésique. Notamment, nous avons trouvé un effet de récence important peu importe le nombre d’items mémorisés, se traduisant par des temps de réponses courts et des taux de bonne réponse presque parfaits, ainsi que par l’augmentation de l’amplitude de la P3, une composante de potentiels reliés aux évènements (PRE). Les données liées aux autres positions sérielles étaient similaires, indépendamment de la charge mnésique, et montraient des performances moins bonnes et une P3 moins ample. Une méthode de décomposition du signal, l’analyse en composantes indépendantes (ACI) nous a permis d’observer et de décrire les différences électrophysiologiques, dans le temps, entre la récupération d’un son parfaitement retenu (le dernier) et celle d’un son peu retenu. Nos résultats suggèrent l’existence de deux sous-types de mémoire sensorielle. / We aimed to understand better the processes involved in acoustic short-term memory retrieval using electrophysiology. We used a modified Sternberg task in which participants had to encode two, four, or six pure non-musical tones (out of the well-tempered musical scale) that cannot be readily recoded verbally. After a silent retention interval, we presented them with a probe tone and they had to report its presence or absence in the memory set. By using multiple load conditions, and by controlling for stimulation duration, we compared the serial position effects, as well as the load effects, on behavioral and electrophysiological data during memory scanning. In particular, we found a recency effect, similar across loads, where shorter response times, near perfect accuracy, and an increased P3 amplitude in the event-related potential (ERP) data were observed. Serial position data for all other positions were similar regardless of the memory load and showed lower performances (response times and accuracy), as well as smaller P3 components. We also performed a signal decomposition analysis, the independent component analysis (ICA), which allowed us to observe and describe better the time courses of the electrophysiological data for the retrieval of a perfectly memorised tone (the last one), and a lesser memorised one (any other serial position). Our results suggest the existence of two subtypes of sensory memory.

Being able to accurately approximate outputs of computationally expensive simulations for arbitrary input parameters, also called missing points estimation, is central in many different areas of research and development with applications ranging from uncertainty propagation to control system design to name a few. This project investigates the potential of kernel transformations and nonlinear autoencoders as methods of improving the accuracy of the proper orthogonal decomposition method combined with regression. The techniques are applied on aerodynamic pressure CFD data around airplane wings in both two- and three-dimensional settings. The novel methods show potential in select situations, but cannot at this stage be generally considered superior. Their performances are similar although the procedure of design and training of a nonlinear autoencoder is less straight forward and more time demanding than using kernel transformations. The results demonstrate the regression bottleneck of the proper orthogonal decomposition method, which partially is improved with the new methods. Future studies should focus on adapting the autoencoder training strategy to the architecture and data as well as improving the regression stage of all methods.

The purpose of this project is to validate the adequacy of the Standard formula, used to calculate the Solvency Capital Requirement (SCR), with respect to a Swedish insurance company. The sub-modules evaluated are Equity risk (type 1) and Interest rate risk. The validation uses a quantitative assessment and the concept of Value at Risk (VaR). Additionally, investment strategies for risk free assets are evaluated through a scenario based analysis. The findings support that the Equity shock of 39%, as proposed in the Standard formula, is appropriate for a diversified portfolio of global equities. Furthermore, to some extent; the Equity shock is also sufficient for a diversified global portfolio with an overweight of Swedish equities. Additionally, the findings shows that the Standard formula for Interest rate risks occasionally underestimates the true Interest rate risk. Furthermore, it’s shown that there are some advantage of selecting an investment strategy that stabilizes the Own fund of an insurance company rather than a strategy that minimizes the SCR. / Syftet med detta arbete är att utvärdera Standardformeln, som används för att beräkna solvenskapitalkravet (SCR) under Solvens II, med avseende på dess lämplighet för ett svensk försäkringsbolag. Modulerna som utvärderas är aktierisk (typ 1) och ränterisk. Utvärderingen genomförs med kvantitativa metoder och utifrån konceptet Value at Risk (VaR). Dessutom utvärderas investeringsstrategier för riskfria tillgångar genom en scenariobaserad analys. Resultaten stödjer att den av Standardformeln föreskrivna aktiechocken på -39 % är tillräcklig för en diversifierad global aktieportfölj. Dessutom är aktiechocken även tillräcklig för en diversifierad global portfölj med en viss övervikt mot svenska aktier. Vidare visar resultaten att Standardformeln under vissa omständigheter underskattar ränterisken. Slutligen visar den scenariobaserade analysen att det är fördelaktigt att välja en investeringsstrategi som stabiliserar Own fund, hellre än en strategi som minimerar SCR.