Le but de cette thèse est de développer des méthodes pratiques plus performantes pour la détection d'instances de classes d'objets de la vie quotidienne dans les images. Nous présentons une famille de détecteurs qui incorporent trois types d'indices visuelles performantes – histogrammes de gradients orientés (Histograms of Oriented Gradients, HOG), motifs locaux binaires (Local Binary Patterns, LBP) et motifs locaux ternaires (Local Ternary Patterns, LTP) – dans des méthodes de discrimination efficaces de type machine à vecteur de support latent (Latent SVM), sous deux régimes de réduction de dimension – moindres carrées partielles (Partial Least Squares, PLS) et sélection de variables par élagage de poids SVM (SVM Weight Truncation). Sur plusieurs jeux de données importantes, notamment ceux du PASCAL VOC2006 et VOC2007, INRIA Person et ETH Zurich, nous démontrons que nos méthodes améliorent l'état de l'art du domaine. Nos contributions principales sont : – Nous étudions l'indice visuelle LTP pour la détection d'objets. Nous démontrons que sa performance est globalement mieux que celle des indices bien établies HOG et LBP parce qu'elle permet d'encoder à la fois la texture locale de l'objet et sa forme globale, tout en étant résistante aux variations d'éclairage. Grâce à ces atouts, LTP fonctionne aussi bien pour les classes qui sont caractérisées principalement par leurs structures que pour celles qui sont caractérisées par leurs textures. En plus, nous démontrons que les indices HOG, LBP et LTP sont bien complémentaires, de sorte qu'un jeux d'indices étendu qui intègre tous les trois améliore encore la performance. – Les jeux d'indices visuelles performantes étant de dimension assez élevée, nous proposons deux méthodes de réduction de dimension afin d'améliorer leur vitesse et réduire leur utilisation de mémoire. La première, basée sur la projection moindres carrés partielles, diminue significativement le temps de formation des détecteurs linéaires, sans réduction de précision ni perte de vitesse d'exécution. La seconde, fondée sur la sélection de variables par l'élagage des poids du SVM, nous permet de réduire le nombre d'indices actives par un ordre de grandeur avec une réduction minime, voire même une petite augmentation, de la précision du détecteur. Malgré sa simplicité, cette méthode de sélection de variables surpasse toutes les autres approches que nous avons mis à l'essai. – Enfin, nous décrivons notre travail en cours sur une nouvelle variété d'indice visuelle – les « motifs locaux quantifiées » (Local Quantized Patterns, LQP). LQP généralise les indices existantes LBP / LTP en introduisant une étape de quantification vectorielle – ce qui permet une souplesse et une puissance analogue aux celles des approches de reconnaissance visuelle « sac de mots », qui sont basées sur la quantification des régions locales d'image considérablement plus grandes – sans perdre la simplicité et la rapidité qui caractérisent les approches motifs locales actuelles parce que les résultats de la quantification puissent être pré-compilés et stockés dans un tableau. LQP permet une augmentation considérable de la taille du support local de l'indice, et donc de sa puissance discriminatoire. Nos expériences indiquent qu'elle a la meilleure performance de toutes les indices visuelles testés, y compris HOG, LBP et LTP. / The goal of this thesis is to develop better practical methods for detecting common object classes in real world images. We present a family of object detectors that combine Histogram of Oriented Gradient (HOG), Local Binary Pattern (LBP) and Local Ternary Pattern (LTP) features with efficient Latent SVM classifiers and effective dimensionality reduction and sparsification schemes to give state-of-the-art performance on several important datasets including PASCAL VOC2006 and VOC2007, INRIA Person and ETHZ. The three main contributions are as follows. Firstly, we pioneer the use of Local Ternary Pattern features for object detection, showing that LTP gives better overall performance than HOG and LBP, because it captures both rich local texture and object shape information while being resistant to variations in lighting conditions. It thus works well both for classes that are recognized mainly by their structure and ones that are recognized mainly by their textures. We also show that HOG, LBP and LTP complement one another, so that an extended feature set that incorporates all three of them gives further improvements in performance. Secondly, in order to tackle the speed and memory usage problems associated with high-dimensional modern feature sets, we propose two effective dimensionality reduction techniques. The first, feature projection using Partial Least Squares, allows detectors to be trained more rapidly with negligible loss of accuracy and no loss of run time speed for linear detectors. The second, feature selection using SVM weight truncation, allows active feature sets to be reduced in size by almost an order of magnitude with little or no loss, and often a small gain, in detector accuracy. Despite its simplicity, this feature selection scheme outperforms all of the other sparsity enforcing methods that we have tested. Lastly, we describe work in progress on Local Quantized Patterns (LQP), a generalized form of local pattern features that uses lookup table based vector quantization to provide local pattern style pixel neighbourhood codings that have the speed of LBP/LTP and some of the flexibility and power of traditional visual word representations. Our experiments show that LQP outperforms all of the other feature sets tested including HOG, LBP and LTP.

This study investigates key components for effective Indigenous adult language learning and resulting health and wellness benefits following a Dene research paradigm with Grounded Theory applications. Eight colleagues in the Master’s of Indigenous Language Revitalization (MILR) program at the University of Victoria participated in open ended discussions on their experiences in learning their Indigenous languages as adults. These Indigenous adults reclaiming their ancestral languages report experiencing benefits related to health and overall well-being. Physical fitness and healthy weight loss, emotional healing and a greater sense of identity all surfaced for my colleagues while working towards or achieving fluency in their languages. The main methods of successful language learning used were the Master-Apprentice Program, Total Physical Response and Accelerated Second Language Acquisition. Tips for learning the languages are included. / Graduate / 2021-04-13

The aim of the study is to examine the teachers’ working methods for reading and writing development among adult learners who are at the beginning of their literacy development, as the methods for reading and writing development can vary depending on research, activities and teachers. Semi-structured interviews and observations are used to answer the research questions, and the data that emerges is processed with a thematic analysis method. The results show that repetition and support, both by teachers as well as students, are integrated parts of study path 1. According to the findings, study part 1’s primary goal is to help students become functionally literate, which calls for a basic understanding of reading and writing. At the same time, methods for reading and writing development such as the sound method, the Witting method, the whole word method and visual support (which is compared to the Bornholm model in this study) are useful for the study path’s goal. Following this, the results based on the research methodologies are compared to the theoretical foundations and the prior research before being further analyzed from a critical perspective. In conclusion, it is possible to notice a degree of agreement amongst the interviewed teachers and how their methods and strategies are practiced during the observations with the aim of enhancing the reading and writing development among adult learners who are at the beginning of their literacy development. Song and imagery are employed as a tool to contextualize the sounds and the new words, whereas the sound method, the Witting method and the whole word method are recurring and more well-established techniques.

The purpose of this study was to compare the effects of Web-based learning (WBL) versus those of traditional instructor-based learning (IBL) on student knowledge and satisfaction based on student learning styles. Other goals were to determine if WBL is more effective for those with a particular learning style. The study examined a sample of undergraduate students who were enrolled in the college algebra offered as both oncampus instructor-based (traditional) and Web-based at the university of North Texas (UNT). A total of 36 Web-based students and 58 instructor-based students participated in this study. This study utilized a posttest-only intact group. The Kolb Learning Style Inventory (LSI) measured the learning styles of students. This study used learning methods (Web-based learning (WBL), instructor-based learning (IBL)), and learning styles (Diverger, Converger, Assimilator, and Accommodator) as independent variables. Student knowledge and student satisfaction was measured at the end of the course as independent variables. Based upon the results of the LSI, post-learning exam, and satisfaction a series of two-way analysis of variance (ANOVA 4x2) techniques and independent variable tests was used for each of the dependent variables, knowledge and satisfaction, based on a student's learning styles. The results revealed that students' learning styles were statistically significant for knowledge when learning on the Web versus instructor-led. In addition, the learning style was important factor for Web-based learning. The results indicated students with Assimilator and Converger as learning styles received better result with the Web-based learning method. Furthermore, this study found there is significant difference in student satisfaction based on learning on the Web versus instructor-led. The outcome of the study could be of particular interest in educational institutions; especially those that want to transfer some of their traditional courses onto the Web. The finding also has implications for training organizations as they seek efficient and effective ways to satisfy their training needs.

Em 1948, a cidade de Ribeirão Preto foi contemplada com uma faculdade de medicina, a Faculdade de Medicina de Ribeirão Preto (FMRP), cujas primeiras aulas foram ministradas em maio de 1952. Desde sempre, essa faculdade se dedicou à pesquisa e à formação pós-graduada, no entanto, a formação oferecida durante o ensino médico de graduação nunca deixou de ser uma preocupação constante. Mesmo tendo sofrido uma extensa reforma curricular, aprovada em 1992, implantada em 1993 e completada em 1998, o curso de ciências médicas da FMRP sofreu, após a aprovação das novas diretrizes curriculares nacionais para cursos de medicina, em 2001, uma revisão curricular, aprovada, em 2007, e implementada, em 2008, que determinou o desenvolvimento de atividades de forma articulada ao longo dos anos pela introdução de eixos longitudinais de formação. A Atenção à Saúde da Comunidade I ou, simplesmente, ASCI, foi a primeira disciplina do eixo Atenção à Saúde da Família e da Comunidade. Este estudo teve por objetivo realizar uma avaliação discente da disciplina ASCI, em seu primeiro ano de inclusão na grade curricular, identificando o que deveria permanecer, o que requereria aperfeiçoamento e o que deveria ser abandonado, obtendo, ainda, sugestões que permitissem introduzir, nos próximos anos, mudanças que aumentassem a efetividade do processo ensino-aprendizagem dos estudantes. Considerando a complexidade do objeto a ser estudado, uma abordagem metodológica quantitativaqualitativa que permitisse tanto a identificação de indicadores e tendências quantificáveis quanto de percepções e sugestões, foi adotada. A população de estudo escolhida foi: todos os estudantes do curso de ciências médicas da FMRP matriculados na disciplina ASCI, no ano de 2008, totalizando 103 indivíduos. Optouse pela construção de um instrumento de coleta de dados específico para essa pesquisa composto por: um questionário estruturado auto-aplicável capaz de caracterizar a população e quantificar as percepções discentes sobre cada variável estudada, uma questão não estruturada, destinada a captar evidências sobre a construção de um novo conhecimento a respeito da promoção da saúde e prevenção de doenças em uma comunidade, e um espaço para comentários e sugestões sobre a disciplina. Para a etapa quantitativa do estudo, foram escolhidas 9 como variáveis as características da disciplina: objetivo, metodologia de ensinoaprendizagem, conteúdos, diversificação de cenários, aprendizagem por meio de vivências, interação com a comunidade, tutoria, divisão em pequenos grupos, discussões em grupo, comunicação mediada por computador, metodologias de avaliação e carga horária. A coleta de dados ocorreu entre os dias 24 de novembro e 02 de dezembro de 2008. Os resultados quantitativos obtidos apontaram altos índices de aprovação discente à disciplina e os qualitativos, a construção de uma percepção discente adequada aos objetivos educacionais da disciplina incluindo a modificação do conceito sobre saúde e a aproximação entre discentes e seu futuro objeto de trabalho. Além disso, a população estudada demonstrou grande preocupação em contribuir para que a disciplina se tornasse, durante os próximos anos, ainda mais efetiva no cumprimento de seu objetivo educacional. / In 1948, the town of Ribeirão Preto was benefit by a faculty of medicine, the Faculdade de Medicina de Ribeirão Preto (FMRP), whose first classes were taught on May, 1952. Historically, this faculty has been focused in research and postgraduation training, however, the training offered during the medical graduation has always been a frequent concern. Even after an extensive curricular reforming, which was approved in 1992, introduced in 1993 and completed in 1998, the FMRP Medical Sciences Course passed through a curricular revision; that happened in consequence of the approval of the new national curriculum guidelines for courses in medicine in 2001, agreed in 2007, and implemented in 2008, which determined the articulated activities development over the years by the introduction of longitudinal axes of training. The Atenção à Saúde da Comunidade I (Attention to the Communitys Health I) or, simply, ASCI, was the first subject from the axis Atenção à Saúde da Família e da Comunidade (Attention to Family and Communitys Health). This study aims to perform a students assessment of the subject ASCI in its first year of curricular inclusion, identifying what should remain, what should be improved and what should be forsaken, obtaining, yet, suggestions that would permit to introduce, in the years to come, changes that would increase the students teaching and learning process effectiveness. Considering the complexity of the object to be studied, a quantitative and qualitative approach, that would allow even the identification of indicators and quantifying trends or perceptions and suggestions, was adopted. The chosen population for this study was: all the FMRP Medical Sciences course students enrolled in the subject ASCI, in the year of 2008, adding up 103 people. It was chosen for this research the construction of a specific data collection instrument composed by: a self applicable structured questionnaire that was able to characterize the population and quantify the students perceptions about each variable studied; a non-structured question, designated to absorb evidence about the construction of a new knowledge area concerning the health promotion and prevention of illnesses in a community; and a space for comments and suggestions about the subject. For the quantitative step of this study, were chosen as variables these subjects features: objective, teaching and learning methods, contents, scenery 11 diversification, learning through experience, interacting with the community, mentoring, working in small groups, group discussions, computer mediated communication, assessment methods and working hours. The data collection occurred between the days November 24th and December 2nd, 2008. The obtained quantitative results reveal high approval rates of the students in the subject and the qualitative demonstrated the students construction of a perception that corresponds to the educational aims of the subject, including the change in their concept about health and the approximation between them and their future work object. Besides, the studied population demonstrated a big concern in contributing so the subject would became, over the years, even more effective as fulfilling its educational goals.

Em 1948, a cidade de Ribeirão Preto foi contemplada com uma faculdade de medicina, a Faculdade de Medicina de Ribeirão Preto (FMRP), cujas primeiras aulas foram ministradas em maio de 1952. Desde sempre, essa faculdade se dedicou à pesquisa e à formação pós-graduada, no entanto, a formação oferecida durante o ensino médico de graduação nunca deixou de ser uma preocupação constante. Mesmo tendo sofrido uma extensa reforma curricular, aprovada em 1992, implantada em 1993 e completada em 1998, o curso de ciências médicas da FMRP sofreu, após a aprovação das novas diretrizes curriculares nacionais para cursos de medicina, em 2001, uma revisão curricular, aprovada, em 2007, e implementada, em 2008, que determinou o desenvolvimento de atividades de forma articulada ao longo dos anos pela introdução de eixos longitudinais de formação. A Atenção à Saúde da Comunidade I ou, simplesmente, ASCI, foi a primeira disciplina do eixo Atenção à Saúde da Família e da Comunidade. Este estudo teve por objetivo realizar uma avaliação discente da disciplina ASCI, em seu primeiro ano de inclusão na grade curricular, identificando o que deveria permanecer, o que requereria aperfeiçoamento e o que deveria ser abandonado, obtendo, ainda, sugestões que permitissem introduzir, nos próximos anos, mudanças que aumentassem a efetividade do processo ensino-aprendizagem dos estudantes. Considerando a complexidade do objeto a ser estudado, uma abordagem metodológica quantitativaqualitativa que permitisse tanto a identificação de indicadores e tendências quantificáveis quanto de percepções e sugestões, foi adotada. A população de estudo escolhida foi: todos os estudantes do curso de ciências médicas da FMRP matriculados na disciplina ASCI, no ano de 2008, totalizando 103 indivíduos. Optouse pela construção de um instrumento de coleta de dados específico para essa pesquisa composto por: um questionário estruturado auto-aplicável capaz de caracterizar a população e quantificar as percepções discentes sobre cada variável estudada, uma questão não estruturada, destinada a captar evidências sobre a construção de um novo conhecimento a respeito da promoção da saúde e prevenção de doenças em uma comunidade, e um espaço para comentários e sugestões sobre a disciplina. Para a etapa quantitativa do estudo, foram escolhidas 9 como variáveis as características da disciplina: objetivo, metodologia de ensinoaprendizagem, conteúdos, diversificação de cenários, aprendizagem por meio de vivências, interação com a comunidade, tutoria, divisão em pequenos grupos, discussões em grupo, comunicação mediada por computador, metodologias de avaliação e carga horária. A coleta de dados ocorreu entre os dias 24 de novembro e 02 de dezembro de 2008. Os resultados quantitativos obtidos apontaram altos índices de aprovação discente à disciplina e os qualitativos, a construção de uma percepção discente adequada aos objetivos educacionais da disciplina incluindo a modificação do conceito sobre saúde e a aproximação entre discentes e seu futuro objeto de trabalho. Além disso, a população estudada demonstrou grande preocupação em contribuir para que a disciplina se tornasse, durante os próximos anos, ainda mais efetiva no cumprimento de seu objetivo educacional. / In 1948, the town of Ribeirão Preto was benefit by a faculty of medicine, the Faculdade de Medicina de Ribeirão Preto (FMRP), whose first classes were taught on May, 1952. Historically, this faculty has been focused in research and postgraduation training, however, the training offered during the medical graduation has always been a frequent concern. Even after an extensive curricular reforming, which was approved in 1992, introduced in 1993 and completed in 1998, the FMRP Medical Sciences Course passed through a curricular revision; that happened in consequence of the approval of the new national curriculum guidelines for courses in medicine in 2001, agreed in 2007, and implemented in 2008, which determined the articulated activities development over the years by the introduction of longitudinal axes of training. The Atenção à Saúde da Comunidade I (Attention to the Communitys Health I) or, simply, ASCI, was the first subject from the axis Atenção à Saúde da Família e da Comunidade (Attention to Family and Communitys Health). This study aims to perform a students assessment of the subject ASCI in its first year of curricular inclusion, identifying what should remain, what should be improved and what should be forsaken, obtaining, yet, suggestions that would permit to introduce, in the years to come, changes that would increase the students teaching and learning process effectiveness. Considering the complexity of the object to be studied, a quantitative and qualitative approach, that would allow even the identification of indicators and quantifying trends or perceptions and suggestions, was adopted. The chosen population for this study was: all the FMRP Medical Sciences course students enrolled in the subject ASCI, in the year of 2008, adding up 103 people. It was chosen for this research the construction of a specific data collection instrument composed by: a self applicable structured questionnaire that was able to characterize the population and quantify the students perceptions about each variable studied; a non-structured question, designated to absorb evidence about the construction of a new knowledge area concerning the health promotion and prevention of illnesses in a community; and a space for comments and suggestions about the subject. For the quantitative step of this study, were chosen as variables these subjects features: objective, teaching and learning methods, contents, scenery 11 diversification, learning through experience, interacting with the community, mentoring, working in small groups, group discussions, computer mediated communication, assessment methods and working hours. The data collection occurred between the days November 24th and December 2nd, 2008. The obtained quantitative results reveal high approval rates of the students in the subject and the qualitative demonstrated the students construction of a perception that corresponds to the educational aims of the subject, including the change in their concept about health and the approximation between them and their future work object. Besides, the studied population demonstrated a big concern in contributing so the subject would became, over the years, even more effective as fulfilling its educational goals.

Collaborative learning as it pertained to leadership development was an obscured method of learning. There was little research addressing the attributes contributing to collaborative learning for leadership development in leadership development programs. By completing this manuscript, scholarly learners may have additional information on knowledge-based practicing organizations. The purpose of this qualitative study was to understand how collaborative learning influenced leadership development within leadership development programs within high performing organizations. Data collection included semistructured interview questions and a review of training documentation with a combination of dramaturgical coding and purposive sampling from 20 participants that attended leadership development programs within a high performing organization. The 7-step data analysis process, methodology triangulation, and member checking consisted of structure and credibility of the findings. There were primary and secondary themes that aligned with Hanson's leadership development interface model. The 2 primary themes were categorized as collaborative learning and shared knowledge, while the secondary themes included role models, communication: listening and feedback, problem-solving, knowledgeable: subject matter expert, transparency, and training and teaching. The findings of this study suggest that collaborative learning influenced leadership development programs by practicing group work and by sharing different ideas. These findings have potential implications for positive social change, as the information may add to the body of knowledge for future scholars and valuable information for stakeholders to build a knowledge-based practicing organization.

Η εργασία, που ακολουθεί, εστίασε την προσοχή της στους ενηλίκους που φοιτούν στο ΚΕΕ Αχαΐας το οποίο προσφέρει προγράμματα σπουδών και επιμόρφωσης σε αρκετές ειδικότητες. Τόσο η εκπαίδευση ενηλίκων στην Ελλάδα όσο και η μη τυπική εκπαίδευση σε συνάρτηση με το ζήτημα των κινήτρων τα οποία ωθούν τους ενήλικους εκπαιδευόμενους στην παρακολούθηση εκπαιδευτικών προγραμμάτων δεν έχουν ερευνηθεί ικανοποιητικά. Οι στόχοι της έρευνας ήταν: 1. η διαπίστωση του ποια είναι τα κίνητρα που ωθούν τους ενήλικους εκπαιδευομένους στο να παρακολουθούν προγράμματα εκπαίδευσης στο ΚΕΕ της Πάτρας σύμφωνα με τους παράγοντες της Κλίμακας Συμμετοχής στην Εκπαίδευση. 2. η κατάδειξη της σχέσης συνάφειας των παραγόντων της Κλίμακας Συμμετοχής στην Εκπαίδευση, με τους αντίστοιχους μαθησιακούς τρόπους που μαθαίνουν οι ενήλικοι, οι οποίοι συμμετέχουν σε εκπαιδευτικά προγράμματα που προσφέρονται από το ΚΕΕ Αχαΐας. 3. ο εντοπισμός των κινήτρων που ωθούν τους ενηλίκους στο να παρακολουθήσουν το πρόγραμμα επιμόρφωσης, η σύνδεση δημογραφικών στοιχείων των ενηλίκων με τους παράγοντες της Κλίμακας Συμμετοχής στην Εκπαίδευση, καθώς και η εύρεση διαφορών και ομοιοτήτων μεταξύ τους σε σχέση με τους αντίστοιχους προτιμώμενους μαθησιακούς τρόπους του Kolb. Το ερευνητικό μέρος αφορά έρευνα με τη χρήση δύο εργαλείων: α) την Κλίμακα Συμμετοχής στην Εκπαίδευση του Boshier η οποία αποτελεί μια τυπολογία επτά παραγόντων που περιγράφουν τα κίνητρα τα οποία ωθούν τους ενήλικους εκπαιδευόμενους να συμμετέχουν σε εκπαιδευτικά προγράμματα και β) το ερωτηματολόγιο (LSQ) το οποίο στηρίζεται στη θεωρητική βάση του Kolb και είναι σχεδιασμένο να μετράει τον προτιμώμενο μαθησιακό τρόπο από τους ενηλίκους, καθώς και τη σχετική ένταση των τεσσάρων διαφορετικών μαθησιακών τρόπων, (ενεργητικός, στοχαζόμενος, θεωρητικός και πειραματιζόμενος ή πραγματιστής). Το δείγμα αποτέλεσαν 156 εκπαιδευόμενοι στο ΚΕΕ Πάτρας. Η εργασία ολοκληρώνεται με την παράθεση των αποτελεσμάτων σε σχέση με τα ερευνητικά μας ερωτήματα τα οποία συζητούνται σε συνάρτηση με την υπάρχουσα βιβλιογραφία. Ακολουθούν οι προτάσεις για μελλοντικές ερευνητικές προσπάθειες οι οποίες θα προσφέρουν περισσότερη γνώση στο θέμα των κινήτρων και των μαθησιακών τύπων των ενηλίκων που ενδιαφέρονται για παρακολούθηση εκπαιδευτικών προγραμμάτων. / The work that followed, focused on adults who attend the KEE Achaia, which offers courses and training in several specialties. Non-formal education and adult education in Greece, according to the issue of incentives that motivate adult learners in monitoring educational programs have not been investigated adequately. The research part of investigating the use of two tools: a) Scale of Participation in Education (Boshier) which is a typology of seven factors that describe the incentives that motivate adult learners to participate in educational programs and b) Questionnaire (LSQ of Honey & Mumford) which is designed to measure the preferred way of learning by adults, and the relative intensity of four different learning modes, energetic, stochastic, theorist and pragmatist or experimenting. The sample consisted of 156 students in the KEE Patras. The work concludes with the presentation of results in relation to our research questions are discussed in relation to the existing literature. Below are suggestions for future research efforts that will provide more knowledge on the issue of incentives and types of learning for adults interested in monitoring educational programs.

Le credit scoring est généralement considéré comme une méthode d’évaluation du niveau du risque associé à un dossier de crédit potentiel. Cette méthode implique l'utilisation de différentes techniques statistiques pour aboutir à un modèle de scoring basé sur les caractéristiques du client.Le modèle de scoring estime le risque de crédit en prévoyant la solvabilité du demandeur de crédit. Les institutions financières utilisent ce modèle pour estimer la probabilité de défaut qui va être utilisée pour affecter chaque client à la catégorie qui lui correspond le mieux: bon payeur ou mauvais payeur. Les seules données disponibles pour construire le modèle de scoring sont les dossiers acceptés dont la variable à prédire est connue. Ce modèle ne tient pas compte des demandeurs de crédit rejetés dès le départ ce qui implique qu'on ne pourra pas estimer leurs probabilités de défaut, ce qui engendre un biais de sélection causé par la non-représentativité de l'échantillon. Nous essayons dans ce travail en utilisant l'inférence des refusés de remédier à ce biais, par la réintégration des dossiers refusés dans le processus d'octroi de crédit. Nous utilisons et comparons différentes méthodes de traitement des refusés classiques et semi supervisées, nous adaptons certaines à notre problème et montrons sur un jeu de données réel, en utilisant les courbes ROC confirmé par simulation, que les méthodes semi-supervisé donnent de bons résultats qui sont meilleurs que ceux des méthodes classiques. / Credit scoring is generally considered as a method of evaluation of a risk associated with a potential loan applicant. This method involves the use of different statistical techniques to determine a scoring model. Like any statistical model, scoring model is based on historical data to help predict the creditworthiness of applicants. Financial institutions use this model to assign each applicant to the appropriate category : Good payer or Bad payer. The only data used to build the scoring model are related to the accepted applicants in which the predicted variable is known. The method has the drawback of not estimating the probability of default for refused applicants which means that the results are biased when the model is build on only the accepted data set. We try, in this work using the reject inference, to solve the problem of selection bias, by reintegrate reject applicants in the process of granting credit. We use and compare different methods of reject inference, classical methods and semi supervised methods, we adapt some of them to our problem and show, on a real dataset, using ROC curves, that the semi-supervised methods give good results and are better than classical methods. We confirmed our results by simulation.

The main objective of the thesis is to analyze the process of training employees in the company XY MEDICAL, Ltd., identify its shortcomings and recommend opportunities for improvement. The theoretical part is processed by a method of analysis of professional literature on personnel management, respectively. specific development and training. It describes the learning process and identify the methods and forms of education used in the organization. In a research of methods are used semi-structured interviews with the Director of Human Resources, excursion in the educational activities and a questionnaire for employees. The research part is aimed to obtain information on the whole process of education in society, ie contains information on how to identify training needs, its planning and implementation, different types of training taking place in the organization as well as the evaluation of educational activities. The aim of the research is to find out how well the company access to education employees. Based on the findings of the research are at the end of work formulated recommendations for company XY MEDICAL, Ltd. Key words: education, employee training, the learning process, learning methods, questionnaire, interview, excursion.