Neural networks with algorithm back-propagation will be presented in this work. Theoretical background of the algorithm will be explained. The problems with training neural nets will be solving there. The work discuss some techniques of image preprocessing and image extraction features, which is one of main part in classification. Some part of work discuss few experiments with neural nets with chosen image features.

This thesis summarizes the information retrieval theory, the relational model basic and focuses on the data indexing in relational database systems. The thesis focuses on multimedia data searching. It includes description of automatic multimedia data content extraction and multimedia data indexing. Practical part discusses design and solution implementation for improving query effectivity for multidimensional vector similarity which describes multimedia data. Thesis final part discusses experiments with this solution.

La récente crise financière qui a débuté aux États-Unis en 2007 a révélé les faiblesses du système bancaire international se traduisant par l’effondrement de nombreuses institutions financières aux États-Unis et aussi par l’augmentation de la part des prêts non performants dans les bilans des banques européennes. Dans ce cadre, nous proposons d’abord d’estimer et de tester l’efficacité des modèles de prévisions des défaillances bancaires. L’objectif étant d’établir un système d’alerte précoce (EWS) de difficultés bancaires basées sur des variables financières selon la typologie CAMEL (Capital adequacy, Asset quality, Management quality, Earnings ability, Liquidity). Dans la première étude, nous avons comparé la classification et la prédiction de l’analyse discriminante canonique (CDA) et de la régression logistique (LR) avec et sans coûts de classification en combinant ces deux modèles paramétriques avec le modèle descriptif d’analyse en composantes principales (ACP). Les résultats montrent que les modèles (LR et CDA) peuvent prédire la faillite des banques avec précision. De plus, les résultats de l’ACP montrent l’importance de la qualité des actifs, de l’adéquation des fonds propres et de la liquidité en tant qu’indicateurs des conditions financières de la banque. Nous avons aussi comparé la performance de deux méthodes non paramétriques, les arbres de classification et de régression (CART) et le nouveau modèle régression multivariée par spline adaptative (MARS), dans la prévision de la défaillance. Un modèle hybride associant ’K-means clustering’ et MARS est également testé. Nous cherchons à modéliser la relation entre dix variables financières et le défaut d’une banque américaine. L’approche comparative a mis en évidence la suprématie du modèle hybride en termes de classification. De plus, les résultats ont montré que les variables d’adéquation du capital sont les plus importantes pour la prévision de la faillite d’une banque. Enfin, nous avons étudié les facteurs déterminants des prêts non performants des banques de l’Union Européenne durant la période 2012-2015 en estimant un modèle à effets fixe sur données de panel. Selon la disponibilité des données nous avons choisi un ensemble de variables qui se réfèrent à la situation macroéconomique du pays de la banque et d’autres variables propres à chaque banque. Les résultats ont prouvé que la dette publique, les provisions pour pertes sur prêts, la marge nette d’intérêt et la rentabilité des capitaux propres affectent positivement les prêts non performants, par contre la taille de la banque et l’adéquation du capital (EQTA et CAR) ont un impact négatif sur les créances douteuses. / The recent financial crisis that began in the United States in 2007 revealed the weaknesses of the international banking system resulting in the collapse of many financial institutions in the United States and also the increase in the share of non-performing loans in the balance sheets of European banks. In this framework, we first propose to estimate and test the effectiveness of banking default forecasting models. The objective is to establish an early warning system (EWS) of banking difficulties based on financial variables according to CAMEL’s ratios (Capital adequacy, Asset quality, Management quality, Earnings ability, Liquidity). In the first study, we compared the classification and the prediction of the canonical discriminant analysis (CDA) and the logistic regression (LR) with and without classification costs by combining these two parametric models with the descriptive model of principal components analysis (PCA). The results show that the LR and the CDA can predict bank failure accurately. In addition, the results of the PCA show the importance of asset quality, capital adequacy and liquidity as indicators of the bank’s financial conditions. We also compared the performance of two non-parametric methods, the classification and regression trees (CART) and the newly multivariate adaptive regression splines (MARS) models, in the prediction of failure. A hybrid model combining ’K-means clustering’ and MARS is also tested. We seek to model the relationship between ten financial variables (CAMEL’s ratios) and the default of a US bank. The comparative approach has highlighted the supremacy of the hybrid model in terms of classification. In addition, the results showed that the capital adequacy variables are the most important for predicting the bankruptcy of a bank. Finally, we studied the determinants of non-performing loans from European Union banks during the period 2012-2015 by estimating a fixed effects model on panel data. Depending on the availability of data we have chosen a set of variables that refer to the macroeconomic situation of the country of the bank and other variables specific to each bank. The results showed that public debt, loan loss provisions, net interest margin and return on equity positively affect non performing loans, while the size of the bank and the adequacy of capital (EQTA and CAR) have a negative impact on bad debts.

Avec l'essor des objets connectés pour fournir un suivi systématique, objectif et fiable aux sportifs et à leur entraineur, de plus en plus de paramètres sont collectés pour un même individu. Une alternative aux méthodes d'évaluation en laboratoire est l'utilisation de capteurs inertiels qui permettent de suivre la performance sans l'entraver, sans limite d'espace et sans procédure d'initialisation fastidieuse. Les données collectées par ces capteurs peuvent être vues comme des données fonctionnelles multivariées : se sont des entités quantitatives évoluant au cours du temps de façon simultanée pour un même individu statistique. Cette thèse a pour objectif de chercher des paramètres d'analyse de la locomotion du cheval athlète à l'aide d'un capteur positionné dans la selle. Cet objet connecté (centrale inertielle, IMU) pour le secteur équestre permet de collecter l'accélération et la vitesse angulaire au cours du temps, dans les trois directions de l'espace et selon une fréquence d'échantillonnage de 100 Hz. Une base de données a ainsi été constituée rassemblant 3221 foulées de galop, collectées en ligne droite et en courbe et issues de 58 chevaux de sauts d'obstacles de niveaux et d'âges variés. Nous avons restreint notre travail à la prédiction de trois paramètres : la vitesse par foulée, la longueur de foulée et la qualité de saut. Pour répondre aux deux premiers objectifs nous avons développé une méthode de clustering fonctionnelle multivariée permettant de diviser notre base de données en sous-groupes plus homogènes du point de vue des signaux collectés. Cette méthode permet de caractériser chaque groupe par son profil moyen, facilitant leur compréhension et leur interprétation. Mais, contre toute attente, ce modèle de clustering n'a pas permis d'améliorer les résultats de prédiction de vitesse, les SVM restant le modèle ayant le pourcentage d'erreur inférieur à 0.6 m/s le plus faible. Il en est de même pour la longueur de foulée où une précision de 20 cm est atteinte grâce aux Support Vector Machine (SVM). Ces résultats peuvent s'expliquer par le fait que notre base de données est composée uniquement de 58 chevaux, ce qui est un nombre d'individus très faible pour du clustering. Nous avons ensuite étendu cette méthode au co-clustering de courbes fonctionnelles multivariées afin de faciliter la fouille des données collectées pour un même cheval au cours du temps. Cette méthode pourrait permettre de détecter et prévenir d'éventuels troubles locomoteurs, principale source d'arrêt du cheval de saut d'obstacle. Pour finir, nous avons investigué les liens entre qualité du saut et les signaux collectés par l'IMU. Nos premiers résultats montrent que les signaux collectés par la selle seuls ne suffisent pas à différencier finement la qualité du saut d'obstacle. Un apport d'information supplémentaire sera nécessaire, à l'aide d'autres capteurs complémentaires par exemple ou encore en étoffant la base de données de façon à avoir un panel de chevaux et de profils de sauts plus variés / With the growth of smart devices market to provide athletes and trainers a systematic, objective and reliable follow-up, more and more parameters are monitored for a same individual. An alternative to laboratory evaluation methods is the use of inertial sensors which allow following the performance without hindering it, without space limits and without tedious initialization procedures. Data collected by those sensors can be classified as multivariate functional data: some quantitative entities evolving along time and collected simultaneously for a same individual. The aim of this thesis is to find parameters for analysing the athlete horse locomotion thanks to a sensor put in the saddle. This connected device (inertial sensor, IMU) for equestrian sports allows the collection of acceleration and angular velocity along time in the three space directions and with a sampling frequency of 100 Hz. The database used for model development is made of 3221 canter strides from 58 ridden jumping horses of different age and level of competition. Two different protocols are used to collect data: one for straight path and one for curved path. We restricted our work to the prediction of three parameters: the speed per stride, the stride length and the jump quality. To meet the first to objectives, we developed a multivariate functional clustering method that allow the division of the database into smaller more homogeneous sub-groups from the collected signals point of view. This method allows the characterization of each group by it average profile, which ease the data understanding and interpretation. But surprisingly, this clustering model did not improve the results of speed prediction, Support Vector Machine (SVM) is the model with the lowest percentage of error above 0.6 m/s. The same applied for the stride length where an accuracy of 20 cm is reached thanks to SVM model. Those results can be explained by the fact that our database is build from 58 horses only, which is a quite low number of individuals for a clustering method. Then we extend this method to the co-clustering of multivariate functional data in order to ease the datamining of horses’ follow-up databases. This method might allow the detection and prevention of locomotor disturbances, main source of interruption of jumping horses. Lastly, we looked for correlation between jumping quality and signals collected by the IMU. First results show that signals collected by the saddle alone are not sufficient to differentiate finely the jumping quality. Additional information will be needed, for example using complementary sensors or by expanding the database to have a more diverse range of horses and jump profiles

PhD (Business Management) / Department of Business Management / This thesis demonstrates the researcher’s efforts to put into practice the theoretical foundations of information systems research, in order to come up with a context-aware business intelligence framework (CABIF), for the South African higher education institutions. Using critical realism as the philosophical underpinning and mixed methods research design, a business intelligence (BI) survey was deployed within the South African public higher education institutions to measure the respondents’ satisfaction and importance of business intelligence characteristics. The 258 respondents’ satisfaction and importance of the 34 observed business intelligence variables, were subjected to principal components analysis and design science research to come up with the CABIF. The observable BI variables were drawn from four latent variables namely technology and business alignment; organizational and behavioural strategies; business intelligence domain; and technology strategies. The study yielded good values for all the observed satisfaction and importance business intelligence variables as indicated by the Kaiser- Meyer-Olkin (KMO) Measure of Sampling Adequacy and the Bartlett Test of Sphericity. The data set collected from the survey deployed at the South African public higher education institutions, was reliable and valid based on the Cronbach α values which were all above 0.9. The researcher then used the descriptive and prescriptive knowledge of design science research, and the meta-inferences of the results from the principal components analysis to produce five contexts of CABIF. The BI contexts developed were, the Basic Context; the Business Processes Context which was divided into Macro and Micro business process contexts; the Business Intelligence Context; and the Governance Context. These contexts were extrapolated within the University of Venda’s business processes and this researcher concluded that the CABIF developed, could be inferred within the South African higher education institutions. At the University of Venda, this researcher managed to draw up CABIF based business intelligence tools that spanned from leveraging the existing ICT infrastructure, student cohort analysis, viability of academic entities, strategic enrolment planning and forecasting government block grants. The correlations and regression measures of the technology acceptance variables of the business intelligence tools modelled using CABIF at University of Venda, revealed high acceptance ratio. Overall, this research provides a myriad of conceptual and practical insights into how contextualised aspects of BI directly or indirectly impact on the quality of managerial decision making within various core business contexts of South African higher education institutions.

Cette thèse transdisciplinaire réalisée en collaboration avec le laboratoire SPCTS (Sciences des Procédés Céramiques et Traitement de Surface) et l’EA 3842 (Homéostasie cellulaire et pathologies) de l’université de Limoges est un projet de recherche à l’interface entre la biologie et la chimie et a été consacrée à l’étude de l’influence des propriétés physico-chimiques de biocéramiques de phosphate de calcium sur leur comportement biologique in vitro.L’exploration des processus d’interaction entre matériaux et cellules reste une problématique scientifique de premier plan tant d’un point de vue fondamental qu’appliqué pour la mise au point de biomatériaux performants. L’objectif final est d’optimiser l’efficacité thérapeutique des céramiques phosphocalciques comme matériaux de substitution pour la régénération osseuse. La première partie de la thèse est une revue bibliographique générale présentant la problématique actuelle abordée en lien avec les besoins cliniques et les limitations des études actuelles. Les connaissances sur la biologie du tissu osseux sain ainsi que les aspects de régulation du processus de remodelage osseux ont également été abordés dans ce chapitre. Ce chapitre se termine par une synthèse bibliographique sur les biomatériaux et la régénération osseuse. Le chapitre 2 est relatif à la synthèse puis à la caractérisation physico-chimique des matériaux céramiques. Des céramiques de trois compositions chimiques : HA (hydroxyapatite : Ca10(PO4)6(OH)2 , SiHA (hydroxyapatite silicatée : Ca10(PO4)5,6(SiO4)0,42(OH)1,6 et CHA (hydroxyapatite carbonatée : Ca9,5(PO4)5,5(CO3)0,48(OH)1,08(CO3)0,23 , chacune avec deux microstructures différentes : dense ou poreuse, ont été élaborées et rigoureusement caractérisées (porosité, topographie de surface, mouillabilité, potentiel zêta, taille des grains, distribution et taille des pores, surface spécifique). Le chapitre 3 décrit l’approche expérimentale employée pour l’évaluation biologique des interactions matériaux/cellules explorées dans ce travail. Les analyses biologiques ont été réalisées avec deux lignées cellulaires différentes. La lignée cellulaire pré-ostéoblastique MC3T3-E1 et la lignée cellulaire de monocytes/macrophages, précurseurs des ostéoclastes RAW 264.7, (très importantes pour les aspects osseux, mais moins souvent explorées que les lignées ostéoblastiques dans la littérature). Enfin, le chapitre 4 reporte et commente les résultats biologiques obtenus dans ce travail. Tous les biomatériaux évalués dans cette étude sont biocompatibles, néanmoins, le biomatériau poreux CHA s’est avéré le plus prometteur des six variantes de biomatériaux testés. / This transdisciplinary thesis, carried out in collaboration with the SPCTS laboratory (sciences of ceramic processes and surface treatment) and EA 3842 (Cellular homoeostasis and pathologies) of the University of Limoges, is a research project at the interface between biology and chemistry and was devoted to the study of the influence of the physico-chemical properties of calcium phosphate bioceramics on their biological behavior in vitro.The exploration of the processes of interaction between materials and cells remains a major scientific issue, both from a fundamental and applied point of view for the development of highperformance biomaterials. The ultimate objective is to optimize the therapeutic efficiency of phosphocalcic ceramics as substitute materials for bone regeneration.The first part of the thesis is a general bibliographic review presenting the current issues tackled with the clinical needs and limitations of current studies. Knowledge of the biology of healthy bone tissue as well as the regulatory aspects of the bone remodeling process was also discussed in this chapter. It includes also a bibliographic overview of biomaterials and bone regeneration.Chapter 2 relates to the synthesis and the physico-chemical characterization of ceramic materials. HA (hydroxyapatite: Ca10 (PO4) 6 (OH) 2, SiHA (silicated hydroxyapatite: Ca10 (PO4) 5.6 (SiO4) 0.42 (OH) 1.6 and CHA (carbonated hydroxyapatite: Ca9.5 (PO4) 5.5 (CO3) 0.48 (OH) 1.08 (CO3) 0.23, ceramics each with two different microstructures : dense or porous, have been elaborated and thoroughly characterized (porosity, surface topography, wettability, zeta potential, grain size, pore size and distribution, specific surface area). Chapter 3 describes the experimental approach used for the biological evaluation of the interactions between materials and cells. Biological analyzes were performed with two different cell lines. The pre-osteoblastic MC3T3-E1 cell line and the RAW 264.7cell line of monocytes / macrophages, precursors of the steoclasts, (very important for the bone aspects, but less often explored than the osteoblastic lines in the literature). Finally, Chapter 4 reports and comments on the biological results obtained in this work. All biomaterials evaluated are biocompatible, nevertheless, the porous CHA biomaterial was the most promising of the six variants of biomaterials tested.

Fungus Gloeophyllum trabeum (Agaricomytes: Gloeophyllates) is a brown rot wood-decay fungus which produces a vast spectrum of volatile secondary metabolites. Scientific publications state, that one of the metabolites produced by G. trabeum, can be the substance (3Z,6Z,8E)-dodecatrien-1-ol. This chemical substance is also the main component of trail-following pheromone of Rhinotermitidae termite family. In this diploma thesis, I was trying to verify whether various species of G. trabeum are in fact capable of producing the substance (3Z,6Z,8E)-dodecatrien-1-ol. I was also focusing on the effects of saccharides, present in nutrient solutions, on quantitative and qualitative change in composition of volatile secondary metabolites produced by G. trabeum. The saccharides I used for my research were - maltose, fructose, sucrose, xylose, and mannose. The analysis was made by using comprehensive two-dimensional gas chromatography separation technique with time-of-flight mass spectrometric detection (GC×GC-TOFMS). During my research I discovered that one of obtained species of G. trabeum can produce substance (3Z,6Z,8E)-dodecatrien-1-ol, but only under specific conditions. It is produced when cultivating on Petri dishes on agar - cellulose growth media. The measurement was further validated by...

The development of Advanced Driver Assistance Systems and autonomous driving is one of the main research fields in the area of vehicle development today. Initially the research in this area focused on analyzing and predicting driving maneuvers on highways. Nowadays, a vast amount of research focuses on urban areas as well. Driving maneuvers in urban areas are more complex and therefore more difficult to predict than driving maneuvers on highways. The goals of predicting and understanding driving maneuvers are to reduce accidents, to improve traffic density, and to develop reliable algorithms for autonomous driving. Driving behavior during different driving maneuvers such as turning at intersections, emergency braking or lane changes are analyzed. This thesis focuses on the driving behavior around lane changes and thus the prediction of lane changes in the urban area is applied with an Echo State Network. First, existing methods with a special focus on input variables and results were evaluated to derive input variables with regard to lane change and no lane change sequences. The data for this first analyses were obtained from a naturalistic driving study. Based on theses results the final set of variables (steering angle, turn signal and gazes to the left and right) was chosen for further computations. The parameters of the Echo State Network were then optimized using the data of the naturalistic driving study and the final set of variables. Finally, left and right lane changes were predicted. Furthermore, the Echo State Network was compared to a feedforward neural network. The Echo State Network could predict left and right lane changes more successful than the feedforward neural network. / Fahrerassistenzsysteme und Algorithmen zum autonomen Fahren stellen ein aktuelles Forschungsfeld im Bereich der Fahrzeugentwicklung dar. Am Anfang wurden vor allem Fahrmanöver auf der Autobahn analysiert und vorhergesagt, mittlerweile hat sich das Forschungsfeld auch auf den urbanen Verkehr ausgeweitet. Fahrmanöver im urbanen Raum sind komplexer als Fahrmanöver auf Autobahnen und daher schwieriger vorherzusagen. Ziele für die Vorhersage von Fahrmanövern sind die Reduzierung von Verkehrsunfällen, die Verbesserung des Verkehrsflusses und die Entwicklung von zuverlässigen Algorithmen für das autonome Fahren. Um diese Ziele zu erreichen, wird das Fahrverhalten bei unterschiedlichen Fahrmanövern analysiert, wie z.B. beim Abbiegevorgang an Kreuzungen, bei der Notbremsung oder beim Spurwechsel. In dieser Arbeit wird der Spurwechsel im urbanen Straßenverkehr mit einem Echo State Network vorhergesagt. Zuerst wurden existierende Methoden zur Spurwechselvorhersage bezogen auf die Eingaben und die Ergebnisse bewertet, um danach die spurwechselbezogenen Variableneigenschaften bezüglich Spurwechsel- und Nicht-Spurwechselsequenzen zu analysieren. Die Daten, die Basis für diese ersten Untersuchungen waren, stammen aus einer Realfahrstudie. Basierend auf diesen Resultaten wurden die finalen Variablen (Lenkwinkel, Blinker und Blickrichtung) für weitere Berechnungen ausgewählt. Mit den Daten aus der Realfahrstudie und den finalen Variablen wurden die Parameter des Echo State Networks optimiert und letztendlich wurden linke und rechte Spurwechsel vorhergesagt. Zusätzlich wurde das Echo State Network mit einem vorwärtsgerichteten neuronalen Netz verglichen. Das Echo State Network konnte linke und rechte Spurwechsel erfolgreicher vorhersagen als das vorwärtsgerichtete neuronale Netz.

Human activities have increased the concentration of CO2 into the atmosphere, thus it has caused global warming. Construction equipment are semi-stationary machines and spend at least 30% of its life time during idling. The majority of the construction equipment is diesel powered and emits toxic emission into the environment. In this work, the idling will be investigated through adopting several statistical regressions models to quantify the fuel consumption of construction equipment during idling. The regression models which are studied in this work: Multivariate Linear Regression (ML-R), Support Vector Machine Regression (SVM-R), Gaussian Process regression (GP-R), Artificial Neural Network (ANN), Partial Least Square Regression (PLS-R) and Principal Components Regression (PC-R). Findings show that pre-processing has a significant impact on the goodness of the prediction of the explanatory data analysis in this field. Moreover, through mean centering and application of the max-min scaling feature, the accuracy of models increased remarkably. ANN and GP-R had the highest accuracy (99%), PLS-R was the third accurate model (98% accuracy), ML-R was the fourth-best model (97% accuracy), SVM-R was the fifth-best (73% accuracy) and the lowest accuracy was recorded for PC-R (83% accuracy). The second part of this project estimated the CO2 emission based on the fuel used and by adopting the NONROAD2008 model.  Keywords:

Orientador: Andréa Aparecida Zacharias / Resumo: Na atualidade, uma série de desastres inter-relacionados ganharam notoriedade no Brasil e no mundo, reunindo episódios que marcaram crescentes perdas, humanas e econômicas, associadas aos riscos e suas consequências. O processo de urbanização, juntamente com a impermeabilização do solo, retificação e assentamento em cursos d’água e encostas, contribuíram para o aumento do impacto de inundações, enchentes e vários outros processos advindos da ação antrópica que levam ao risco socioambiental. Somam-se nas últimas cinco décadas mais de dez mil mortes em desastres naturais no Brasil, a maioria destes relacionadas a inundações e queda de encostas. A magnitude de um desastre está vinculada com os fenômenos sociais, econômicos e demográficos, entre outros, e contribuem para aumentar a vulnerabilidade e exposição da população. O recorte espacial aqui analisado compreende a Região Administrativa do Lavapés, macrozona que envolve a área urbana do município de Bragança Paulista/SP. Bragança Paulista sofre, historicamente, uma série de problemas socioeconômicos e ambientais. Destaca-se o aumento na magnitude e frequência das enchentes devido à extensa cobertura impermeabilizada, pois grande parte da água que antes era infiltrada no solo, passa então a compor o volume que escoa superficialmente. O objetivo principal desta pesquisa funda-se sobre o estudo da espacialidade da vulnerabilidade socioambiental aos riscos hidrológicos, em específico as inundações, considerando a atuação dos fato... (Resumo completo, clicar acesso eletrônico abaixo) / Abstract: A series of interrelated disasters have currently gained prominence over the Brazil and worldwide, gathering episodes that have resulted in increasing losses, both human and economic, related to risks and their consequences. The urbanization process, along with degree of saturation, soil imperviousness, rectification and improper settlement on hillslopes and near to the rivers, have contributed to an increasing impact of floods and several human-induced processes that lead to socio-environmental risk. In the last five decades, there have been more than ten thousand deaths caused by natural disasters, most of them related to floods and landslide. The magnitude of a disaster is related to social, economic and demographic phenomena, among others, and contributes to increasing the population's vulnerability and exposure. We analyzed the Lavapés Administrative Region, a macrozone encompassing the urban area of Bragança Paulista/SP municipality. The city of Bragança Paulista have suffered, historically, a plenty of socioeconomic and environmental issues. The increasing intensity and frequency of the floods are noteworthy due to extensive impervious cover, since large water volumes that were previously infiltrating, now become part of the surface runoff. The main objective here relies on the spatial distribution of socio-environmental vulnerability related to hydrological risks, particularly floods, considering the triggering factors in urban areas. The methodological procedures are... (Complete abstract click electronic access below) / Mestre