The research was undertaken to analyse and evaluate the nature and quality of interactions in multicultural primary school classrooms. Special attention was focused on the influence 25 independent variables had on the dependent variable, namely group membership. Literature indicates that warm and nurturant relationships within the family help the child to achieve independence and promote social adjustment outside the home. Literature also reveals that self-acceptance and acceptance of others are dependent on the self-concept, and that acceptability in peer groups is enhanced by characteristics such as friendliness, cooperation, emotional stability and intellectual ability. It is essential to mention that some researchers claim that within multicultural classrooms, pupils often interact in racially and culturally segregated patterns. Others maintain that no racial and cultural discrimination is evident in the choice of friends in multicultural classrooms. The empirical research was undertal<.en by administering four measuring instruments, namely own designed questionnaire, the sociogram, the self-concept scale for primary school pupils and the children's personality questionnaire to 121 standard five pupils in multicultural primary schools. The administering of these instruments was aimed at determining the influence of the independent variables on the dependent variable. The stepwise discriminant analysis method revealed that of the 25 independent variables, only six, namely family background, friendship skills, gender, scholastic achievement and personality factors E (submissive versus dominant) and Q3 (undisciplined versus controlled) contributed to the variance in group membership. The multiple discriminant function was used to determine how close the individual scores of children were, in a given friendship group. The general pattern obtained, indicated that children choose each other on the basis of similar characteristics. A point that clearly came to light, is that race and language/culture do not contribute to the variance in group membership. Children formed various friendship groups across racial and cultural lines. In view of the aforementioned findings, the researcher made recommendations on ways in which parents and teachers can create suitable teaching and learning environments for children from diverse cultural milieus. / Psychology of Education / D.Ed. (Psychology of Education)

O uso de dados biométricos da face para verificação automática de identidade é um dos maiores desafios em sistemas de controle de acesso seguro. O processo é extremamente complexo e influenciado por muitos fatores relacionados à forma, posição, iluminação, rotação, translação, disfarce e oclusão de características faciais. Hoje existem muitas técnicas para se reconhecer uma face. Esse trabalho apresenta uma investigação buscando identificar uma face no banco de dados ORL com diferentes grupos de treinamento. É proposto um algoritmo para o reconhecimento de faces baseado na técnica de subespaço LDA (PCA + LDA) utilizando uma rede neural SOM para representar cada classe (face) na etapa de classificação/identificação. Aplicando o método do subespaço LDA busca-se extrair as características mais importantes na identificação das faces previamente conhecidas e presentes no banco de dados, criando um espaço dimensional menor e discriminante com relação ao espaço original. As redes SOM são responsáveis pela memorização das características de cada classe. O algoritmo oferece maior desempenho (taxas de reconhecimento entre 97% e 98%) com relação às adversidades e fontes de erros que prejudicam os métodos de reconhecimento de faces tradicionais. / The use of biometric technique for automatic personal identification is one of the biggest challenges in the security field. The process is complex because it is influenced by many factors related to the form, position, illumination, rotation, translation, disguise and occlusion of face characteristics. Now a days, there are many face recognition techniques. This work presents a methodology for searching a face in the ORL database with some different training sets. The algorithm for face recognition was based on sub-space LDA (PCA + LDA) technique using a SOM neural net to represent each class (face) in the stage of classification/identification. By applying the sub-space LDA method, we extract the most important characteristics in the identification of previously known faces that belong to the database, creating a reduced and more discriminated dimensional space than the original space. The SOM nets are responsible for the memorization of each class characteristic. The algorithm offers great performance (recognition rates between 97% and 98%) considering the adversities and sources of errors inherent to the traditional methods of face recognition.

Por apresentarem mecanismos de transmissão superponíveis, a infecção concomitante pelo vírus da hepatite C (VHC) e pelos vírus linfotrópicos de células T humanas dos tipos 1 (HTLV-1) e 2 (HTLV-2) é esperada. Considerando a relevância dessas infecções em nosso meio e a existência de lacunas no conhecimento da coinfeção VHC/HTLV, conduziu-se este estudo transversal, com o objetivo de comparar uma série de pacientes coinfectados, com indivíduos infectados pelo VHC isoladamente, no tocante a características sócio-demográficas e de exposição aos agentes virais, alterações clínicas e laboratoriais, bem como alterações histológicas do parênquima hepático. Selecionaram-se, com base em algoritmos de diagnóstico sorológico e de biologia molecular, pacientes adultos assistidos em ambulatórios do Hospital das Clínicas da FMUSP entre janeiro de 1993 e agosto de 2005, que apresentaram viremia pelo VHC, associada, ou não, a infecção por HTLV-1 ou HTLV-2, excluindo-se da amostra os coinfectados pelo VHB ou HIV. Coletaram-se dos pacientes selecionados características sócio-demográficas, informações acerca de exposição a vírus de transmissão sexual ou sangüínea, sinais e sintomas clínicos relacionados às infecções causadas pelo VHC ou HTLV, bem como dados laboratoriais hematológicos e de função hepática. Procedeu-se ainda à revisão sistemática dos achados histopatológicos do parênquima hepático, seguindo-se a classificação de Ishak. Compararam-se, então, os grupos VHC, VHC/HTLV-1 e VHC/HTLV-2, empregando-se o teste de X2 para as variáveis categóricas e o teste de Kruskal-Wallis para as variáveis contínuas. Em seguida, pela análise discriminante linear de Fischer, definiram-se funções classificatórias com variáveis que conjuntamente diferenciassem os grupos estudados. Finalmente, a acurácia discriminatória das funções classificatórias foi avaliada por validação cruzada, empregando-se a técnica leave-one-out. Compuseram a população estudada 85 pacientes, sendo 55 no grupo VHC, 24 no grupo VHC/HTLV-1 e 6 no grupo VHC/HTLV-2. À análise bivariada, não se observou diferença significativa entre os grupos no tocante a características sócio-demográficas, hábito de fumar, fatores de exposição às infecções virais, tais como transfusão sangüínea, tatuagem, acupuntura, ou número de parceiros sexuais. Ao contrário, o relato de uso de álcool, drogas endovenosas, ou cocaína inalatória, bem como a parceria sexual com UDEV foi mais freqüente entre os pacientes do grupo VHC/HTLV-2, enquanto o relato de parceiro sexual com hepatite predominou no grupo VHC. Do ponto de vista clínico, apenas a queixa de dor abdominal apresentou-se em freqüência significativamente diferente entre os grupos, sendo mais prevalente no grupo VHC. Em relação aos achados laboratoriais, apesar de contida nos intervalos de normalidade, houve diferença significativa na contagem de plaquetas em sangue periférico, com valores medianos mais elevados nos grupos de coinfectados. As concentrações séricas de aminotransferases e de GGT foram mais altas no grupo VHC. Apesar de freqüentemente encontradas alterações sugestivas de hepatopatia pelo VHC, como fibrose hepática e atividade necroinflamatória, a análise histopatológica não mostrou diferença significativa entre os grupos. À análise discriminante de Fischer, definiram-se funções classificatórias que melhor diferenciam os pacientes estudados, incluindo as variáveis sexo, faixa etária, relato de uso de drogas endovenosas e parceria sexual com indivíduo com hepatite. Por meio de validação cruzada, verificou-se que a acurácia discriminante das funções classificatórias foi alta (87,3%) para a identificação dos infectados pelo VHC isoladamente e intermediária (66,7%) para os coinfectados VHC/HTLV-2. O método não se mostrou, contudo, clinicamente útil na distinção de pacientes com coinfecção VHC/HTLV-1. / Co-infection with hepatitis C virus (HCV) and human T-lymphotropic virus types 1 (HTLV-1) and 2 (HTLV-2) is expected, as these viruses share common infection routes. Due to the relevance of these viral infections in Brazil and the existing gaps in knowledge about HCV/HTLV co-infection, we carried out this cross-sectional survey. A cohort of co-infected patients was compared to HCV-infected subjects, in regard to socio-demographic features, risk factors for viral acquisition, clinical and laboratory data, as well as liver histopathologic findings. Based on established serologic and molecular diagnostic algorithms, we selected HCV-viremic adult patients who attended the Hospital das Clínicas-FMUSP outpatient clinic from January 1993 to August 2005, whether or not they presented co-infection with HTLV-1 or HTLV-2. HBV and HIV-infected individuals were excluded from the sample. We collected patients\' sociodemographic characteristics, risk of exposure to blood-borne or sexually-transmitted viral agents, signs and symptoms related to HCV or HTLV disease, as well as laboratory data that included hematologic counts and liver function tests. Histopathologic findings were systematically reviewed, in accordance to the Ishak\'s scoring system. Patients from the HCV, HCV/HTLV-1 and HCV/HTLV-2 groups, were then compared by means of the X2 or Kruskal-Wallis tests for categorical or continuous variables, respectively. In addition, Fischer\'s linear discriminant analysis was applied to define classification functions that better identified the combined effect of variables important for discrimination of the study groups. Finally, the discriminating accuracy of the model was evaluated by cross-validation, using the leave-one-out technique. The study sample comprised 85 patients, 55 in the HCV group, 24 in the HCV/HTLV-1 group and 6 in the HCV/HTLV-2 group. In bivariable analysis, no significant difference was found among groups in regard to socio-demographic features, smoking, risk factors for viral acquisition, such as blood transfusion, tattooing, acupuncture, or number of sexual partners. In contrast, alcohol consumption, use of intravenous drugs or inhaled cocaine and sexual partnership with an intravenous drug user were more frequent in the HCV/HTLV-2 group, whereas patients in the HCV group more often reported a sexual partner with hepatitis. As far as clinical data are concerned, abdominal pain was the only variable to be reported differently, being more prevalent in the HCV group. Even though within normal ranges, co-infected patients presented higher median platelet counts, whereas aminotransferase and GGT levels were higher among HCV-infected subjects. No significant difference was seen in liver histopathologic findings, though HCV liver disease-associated abnormalities, such as fibrosis and necroinflammatory activity were often found in patients from the three groups. Classification functions, defined by discriminating analysis included as relevant variables sex, age, intravenous drug use and sexual partner with hepatitis. Cross-validation yielded high (87.3%) and intermediate (66,7%) discriminating accuracies for the HCV and HCV/HTLV-2 functions. However, this method was not shown clinically useful to distinguish HCV/HTLV-1 co-infected patients.

Cette thèse s’inscrit dans le cadre du projet "Prendre votre cœur en mains" visant à développer un dispositif médical d’aide à la prescription médicamenteuse pour les insuffisants cardiaques. Dans une première partie, une étude a été menée afin de mettre en évidence la valeur pronostique d’une estimation du volume plasmatique ou de ses variations pour la prédiction des événements cardiovasculaires majeurs à court terme. Deux règles de classification ont été utilisées, la régression logistique et l’analyse discriminante linéaire, chacune précédée d’une phase de sélection pas à pas des variables. Trois indices permettant de mesurer l’amélioration de la capacité de discrimination par ajout du biomarqueur d’intérêt ont été utilisés. Dans une seconde partie, afin d’identifier les patients à risque de décéder ou d’être hospitalisé pour progression de l’insuffisance cardiaque à court terme, un score d’événement a été construit par une méthode d’ensemble, en utilisant deux règles de classification, la régression logistique et l’analyse discriminante linéaire de données mixtes, des échantillons bootstrap et en sélectionnant aléatoirement les prédicteurs. Nous définissons une mesure du risque d’événement par un odds-ratio et une mesure de l’importance des variables et des groupes de variables. Nous montrons une propriété de l’analyse discriminante linéaire de données mixtes. Cette méthode peut être mise en œuvre dans le cadre de l’apprentissage en ligne, en utilisant des algorithmes de gradient stochastique pour mettre à jour en ligne les prédicteurs. Nous traitons le problème de la régression linéaire multidimensionnelle séquentielle, en particulier dans le cas d’un flux de données, en utilisant un processus d’approximation stochastique. Pour éviter le phénomène d’explosion numérique et réduire le temps de calcul pour prendre en compte un maximum de données entrantes, nous proposons d’utiliser un processus avec des données standardisées en ligne au lieu des données brutes et d’utiliser plusieurs observations à chaque étape ou toutes les observations jusqu’à l’étape courante sans avoir à les stocker. Nous définissons trois processus et en étudions la convergence presque sûre, un avec un pas variable, un processus moyennisé avec un pas constant, un processus avec un pas constant ou variable et l’utilisation de toutes les observations jusqu’à l’étape courante. Ces processus sont comparés à des processus classiques sur 11 jeux de données. Le troisième processus à pas constant est celui qui donne généralement les meilleurs résultats / This thesis is part of the "Handle your heart" project aimed at developing a drug prescription assistance device for heart failure patients. In a first part, a study was conducted to highlight the prognostic value of an estimation of plasma volume or its variations for predicting major short-term cardiovascular events. Two classification rules were used, logistic regression and linear discriminant analysis, each preceded by a stepwise variable selection. Three indices to measure the improvement in discrimination ability by adding the biomarker of interest were used. In a second part, in order to identify patients at short-term risk of dying or being hospitalized for progression of heart failure, a short-term event risk score was constructed by an ensemble method, two classification rules, logistic regression and linear discriminant analysis of mixed data, bootstrap samples, and by randomly selecting predictors. We define an event risk measure by an odds-ratio and a measure of the importance of variables and groups of variables using standardized coefficients. We show a property of linear discriminant analysis of mixed data. This methodology for constructing a risk score can be implemented as part of online learning, using stochastic gradient algorithms to update online the predictors. We address the problem of sequential multidimensional linear regression, particularly in the case of a data stream, using a stochastic approximation process. To avoid the phenomenon of numerical explosion which can be encountered and to reduce the computing time in order to take into account a maximum of arriving data, we propose to use a process with online standardized data instead of raw data and to use of several observations per step or all observations until the current step. We define three processes and study their almost sure convergence, one with a variable step-size, an averaged process with a constant step-size, a process with a constant or variable step-size and the use of all observations until the current step without storing them. These processes are compared to classical processes on 11 datasets. The third defined process with constant step-size typically yields the best results

Por apresentarem mecanismos de transmissão superponíveis, a infecção concomitante pelo vírus da hepatite C (VHC) e pelos vírus linfotrópicos de células T humanas dos tipos 1 (HTLV-1) e 2 (HTLV-2) é esperada. Considerando a relevância dessas infecções em nosso meio e a existência de lacunas no conhecimento da coinfeção VHC/HTLV, conduziu-se este estudo transversal, com o objetivo de comparar uma série de pacientes coinfectados, com indivíduos infectados pelo VHC isoladamente, no tocante a características sócio-demográficas e de exposição aos agentes virais, alterações clínicas e laboratoriais, bem como alterações histológicas do parênquima hepático. Selecionaram-se, com base em algoritmos de diagnóstico sorológico e de biologia molecular, pacientes adultos assistidos em ambulatórios do Hospital das Clínicas da FMUSP entre janeiro de 1993 e agosto de 2005, que apresentaram viremia pelo VHC, associada, ou não, a infecção por HTLV-1 ou HTLV-2, excluindo-se da amostra os coinfectados pelo VHB ou HIV. Coletaram-se dos pacientes selecionados características sócio-demográficas, informações acerca de exposição a vírus de transmissão sexual ou sangüínea, sinais e sintomas clínicos relacionados às infecções causadas pelo VHC ou HTLV, bem como dados laboratoriais hematológicos e de função hepática. Procedeu-se ainda à revisão sistemática dos achados histopatológicos do parênquima hepático, seguindo-se a classificação de Ishak. Compararam-se, então, os grupos VHC, VHC/HTLV-1 e VHC/HTLV-2, empregando-se o teste de X2 para as variáveis categóricas e o teste de Kruskal-Wallis para as variáveis contínuas. Em seguida, pela análise discriminante linear de Fischer, definiram-se funções classificatórias com variáveis que conjuntamente diferenciassem os grupos estudados. Finalmente, a acurácia discriminatória das funções classificatórias foi avaliada por validação cruzada, empregando-se a técnica leave-one-out. Compuseram a população estudada 85 pacientes, sendo 55 no grupo VHC, 24 no grupo VHC/HTLV-1 e 6 no grupo VHC/HTLV-2. À análise bivariada, não se observou diferença significativa entre os grupos no tocante a características sócio-demográficas, hábito de fumar, fatores de exposição às infecções virais, tais como transfusão sangüínea, tatuagem, acupuntura, ou número de parceiros sexuais. Ao contrário, o relato de uso de álcool, drogas endovenosas, ou cocaína inalatória, bem como a parceria sexual com UDEV foi mais freqüente entre os pacientes do grupo VHC/HTLV-2, enquanto o relato de parceiro sexual com hepatite predominou no grupo VHC. Do ponto de vista clínico, apenas a queixa de dor abdominal apresentou-se em freqüência significativamente diferente entre os grupos, sendo mais prevalente no grupo VHC. Em relação aos achados laboratoriais, apesar de contida nos intervalos de normalidade, houve diferença significativa na contagem de plaquetas em sangue periférico, com valores medianos mais elevados nos grupos de coinfectados. As concentrações séricas de aminotransferases e de GGT foram mais altas no grupo VHC. Apesar de freqüentemente encontradas alterações sugestivas de hepatopatia pelo VHC, como fibrose hepática e atividade necroinflamatória, a análise histopatológica não mostrou diferença significativa entre os grupos. À análise discriminante de Fischer, definiram-se funções classificatórias que melhor diferenciam os pacientes estudados, incluindo as variáveis sexo, faixa etária, relato de uso de drogas endovenosas e parceria sexual com indivíduo com hepatite. Por meio de validação cruzada, verificou-se que a acurácia discriminante das funções classificatórias foi alta (87,3%) para a identificação dos infectados pelo VHC isoladamente e intermediária (66,7%) para os coinfectados VHC/HTLV-2. O método não se mostrou, contudo, clinicamente útil na distinção de pacientes com coinfecção VHC/HTLV-1. / Co-infection with hepatitis C virus (HCV) and human T-lymphotropic virus types 1 (HTLV-1) and 2 (HTLV-2) is expected, as these viruses share common infection routes. Due to the relevance of these viral infections in Brazil and the existing gaps in knowledge about HCV/HTLV co-infection, we carried out this cross-sectional survey. A cohort of co-infected patients was compared to HCV-infected subjects, in regard to socio-demographic features, risk factors for viral acquisition, clinical and laboratory data, as well as liver histopathologic findings. Based on established serologic and molecular diagnostic algorithms, we selected HCV-viremic adult patients who attended the Hospital das Clínicas-FMUSP outpatient clinic from January 1993 to August 2005, whether or not they presented co-infection with HTLV-1 or HTLV-2. HBV and HIV-infected individuals were excluded from the sample. We collected patients\' sociodemographic characteristics, risk of exposure to blood-borne or sexually-transmitted viral agents, signs and symptoms related to HCV or HTLV disease, as well as laboratory data that included hematologic counts and liver function tests. Histopathologic findings were systematically reviewed, in accordance to the Ishak\'s scoring system. Patients from the HCV, HCV/HTLV-1 and HCV/HTLV-2 groups, were then compared by means of the X2 or Kruskal-Wallis tests for categorical or continuous variables, respectively. In addition, Fischer\'s linear discriminant analysis was applied to define classification functions that better identified the combined effect of variables important for discrimination of the study groups. Finally, the discriminating accuracy of the model was evaluated by cross-validation, using the leave-one-out technique. The study sample comprised 85 patients, 55 in the HCV group, 24 in the HCV/HTLV-1 group and 6 in the HCV/HTLV-2 group. In bivariable analysis, no significant difference was found among groups in regard to socio-demographic features, smoking, risk factors for viral acquisition, such as blood transfusion, tattooing, acupuncture, or number of sexual partners. In contrast, alcohol consumption, use of intravenous drugs or inhaled cocaine and sexual partnership with an intravenous drug user were more frequent in the HCV/HTLV-2 group, whereas patients in the HCV group more often reported a sexual partner with hepatitis. As far as clinical data are concerned, abdominal pain was the only variable to be reported differently, being more prevalent in the HCV group. Even though within normal ranges, co-infected patients presented higher median platelet counts, whereas aminotransferase and GGT levels were higher among HCV-infected subjects. No significant difference was seen in liver histopathologic findings, though HCV liver disease-associated abnormalities, such as fibrosis and necroinflammatory activity were often found in patients from the three groups. Classification functions, defined by discriminating analysis included as relevant variables sex, age, intravenous drug use and sexual partner with hepatitis. Cross-validation yielded high (87.3%) and intermediate (66,7%) discriminating accuracies for the HCV and HCV/HTLV-2 functions. However, this method was not shown clinically useful to distinguish HCV/HTLV-1 co-infected patients.

信用評等制度在美國已有百年以上歷史，而我國自民國80幾年開始發展評等制度，截至目前，僅有中華信用評等公司與台灣經濟新報社兩家公司提供評等服務，而台灣經濟新報社更將金融保險業排除於評等對象之外。站在穩定市場競爭、保障消費者權益、配合監理需求，以及輔助專案投標等方面來看，市場上的確需要一套能反映產險業行業特性之評等模式。 本文以美國接受A.M.Best評等之產險公司為研究對象，運用三種統計方法：多元區別分析(Multiple Discriminant Analysis，MDA)、羅吉斯迴歸(Unordered Logistic Regression，ULR)、順序性羅吉斯迴歸(Ordered Logistic Regression，OLR)，來建構產險公司之信用評等模式。樣本選擇方面：估計樣本，選取美國1993年到1996年接受A.M.Best評等之產險公司327家；保留樣本，為1997年78筆資料。 而本文預定達成目標如下： 一、建立等級預測模型：參考Ederington(1985)所作債券等級預測模型，以獲利能力、槓桿、流動性、投資風險、準備金適足性五類指標共38個財務比率，透過三種統計模型，建構等級預測模型。 二、藉由等級預測之建立，尋找能有效區別產險公司評等等級之財務指標，並分析其影響程度。 三、力求模型公信力：無論變數選擇或權數決定，皆由統計軟體按照樣本特性選取產生，減少人為主觀判斷。 在決定研究對象之初，因考慮到國內產險公司接受評等之家數不多，且年數又太短，資料數量無法據以建立評等模式，因而決定以美國的產險公司為對象，再以台灣樣本作為保留樣本，預測之等級結果僅供參考之用。 / Three possible models of the P-L Insurers rating process are estimated and compared：1. Muitiple Discriminant Model, 2. Unordered Logistic Model, 3. Ordered Logistic Model. Each model is estimated for a sample of 327 American P-L insurance companies using the same 38 independent variables. The three estimated models are then employed to predict ratings for a holdout sample of 78 companies. The study analyzes 1993 through 1997 data for a sample of P-L insurers that acquired A.M.Best Financial strength ratings between December 31,1993, and December 31, 1997. Empirical evidence suggests that even when models with the same basic structure were compared, differences in estimation procedures resulted in quite different coefficient estimates and classifications. The muitiple discriminant model clearly outperformed the regression model, while the unordered logistic model was clearly superior to the ordered logistic model.

In this thesis, the expression variation problem in two-dimensional (2D) and three-dimensional (3D) face recognition is tackled. While discriminant analysis (DA) methods are effective solutions for recognizing expression-variant 2D face images, they are not directly applicable when only a single sample image per subject is available. This problem is addressed in this thesis by introducing expression subspaces which can be used for synthesizing new expression images from subjects with only one sample image. It is proposed that by augmenting a generic training set with the gallery and their synthesized new expression images, and then training DA methods using this new set, the face recognition performance can be significantly improved. An important advantage of the proposed method is its simplicity; the expression of an image is transformed simply by projecting it into another subspace. The above proposed solution can also be used in general pattern recognition applications. The above method can also be used in 3D face recognition where expression variation is a more serious issue. However, DA methods cannot be readily applied to 3D faces because of the lack of a proper alignment method for 3D faces. To solve this issue, a method is proposed for sampling the points of the face that correspond to the same facial features across all faces, denoted as the closest-normal points (CNPs). It is shown that the performance of the linear discriminant analysis (LDA) method, applied to such an aligned representation of 3D faces, is significantly better than the performance of the state-of-the-art methods which, rely on one-by-one registration of the probe faces to every gallery face. Furthermore, as an important finding, it is shown that the surface normal vectors of the face provide a higher level of discriminatory information rather than the coordinates of the points. In addition, the expression subspace approach is used for the recognition of 3D faces from single sample. By constructing expression subspaces from the surface normal vectors at the CNPs, the surface normal vectors of a 3D face with single sample can be synthesized under other expressions. As a result, by improving the estimation of the within-class scatter matrix using the synthesized samples, a significant improvement in the recognition performance is achieved.

In this thesis, the expression variation problem in two-dimensional (2D) and three-dimensional (3D) face recognition is tackled. While discriminant analysis (DA) methods are effective solutions for recognizing expression-variant 2D face images, they are not directly applicable when only a single sample image per subject is available. This problem is addressed in this thesis by introducing expression subspaces which can be used for synthesizing new expression images from subjects with only one sample image. It is proposed that by augmenting a generic training set with the gallery and their synthesized new expression images, and then training DA methods using this new set, the face recognition performance can be significantly improved. An important advantage of the proposed method is its simplicity; the expression of an image is transformed simply by projecting it into another subspace. The above proposed solution can also be used in general pattern recognition applications. The above method can also be used in 3D face recognition where expression variation is a more serious issue. However, DA methods cannot be readily applied to 3D faces because of the lack of a proper alignment method for 3D faces. To solve this issue, a method is proposed for sampling the points of the face that correspond to the same facial features across all faces, denoted as the closest-normal points (CNPs). It is shown that the performance of the linear discriminant analysis (LDA) method, applied to such an aligned representation of 3D faces, is significantly better than the performance of the state-of-the-art methods which, rely on one-by-one registration of the probe faces to every gallery face. Furthermore, as an important finding, it is shown that the surface normal vectors of the face provide a higher level of discriminatory information rather than the coordinates of the points. In addition, the expression subspace approach is used for the recognition of 3D faces from single sample. By constructing expression subspaces from the surface normal vectors at the CNPs, the surface normal vectors of a 3D face with single sample can be synthesized under other expressions. As a result, by improving the estimation of the within-class scatter matrix using the synthesized samples, a significant improvement in the recognition performance is achieved.

Från 1900-talets början har banker och låneinstitut använt nyckeltal som hjälpmedel vid bedömning och kvantifiering av kreditrisk. För dagens investerare är den ekonomiska miljön mer komplicerad än för bara 40 år sedan då teknologin och datoriseringen öppnade upp världens marknader mot varandra. Bedömning av kreditrisk idag kräver effektiv analys av kvantitativa data och modeller som med god träffsäkerhet kan förutse risker. Under 1900-talets andra hälft skedde en snabb utveckling av de verktyg som används för konkursprediktion, från enkla univariata modeller till komplexa data mining-modeller med tusentals observationer. Denna studie undersöker om det är möjligt att prediktera att svenska företag kommer att gå i konkurs och vilka variabler som innehåller relevant information för detta. Metoderna som används är diskriminantanalys, logistisk regression och överlevnadsanalys på 50 aktiva och 50 företag försatta i konkurs. Resultaten visar på en träffsäkerhet mellan 67,5 % och 75 % beroende på vald statistisk metod. Oavsett vald statistisk metod är det möjligt att klassificera företag som konkursmässiga två år innan konkursens inträffande med hjälp av finansiella nyckeltal av typerna lönsamhetsmått och solvensmått. Samhällskostnader reduceras av bättre konkursprediktion med hjälp av finansiella nyckeltal vilka bidrar till ökad förmåga för företag att tillämpa ekonomistyrning med relevanta nyckeltal i form av lager, balanserad vinst, nettoresultat och rörelseresultat. / From the early 1900s, banks and lending institutions have used financial ratios as an aid in the assessment and quantification of credit risk. For today's investors the economic environment is far more complicated than 40 years ago when the technology and computerization opened up the world's markets. Credit risk assessment today requires effective analysis of quantitative data and models that can predict risks with good accuracy. During the second half of the 20th century there was a rapid development of the tools used for bankruptcy prediction. We moved from simple univariate models to complex data mining models with thousands of observations. This study investigates if it’s possible to predict bankruptcy in Swedish limited companies and which variables contain information relevant for this cause. The methods used in the study are discriminant analysis, logistic regression and survival analysis on 50 active and 50 failed companies. The results indicate accuracy between 67.5 % and 75 % depending on the choice of statistical method. Regardless of the selected statistical method used, it’s possible to classify companies as bankrupt two years before the bankruptcy occurs using financial ratios which measures profitability and solvency. Societal costs are reduced by better bankruptcy prediction using financial ratios which contribute to increasing the ability of companies to apply financial management with relevant key ratios in the form of stock , retained earnings , net income and operating income.

Financial processes may possess long memory and their probability densities may display heavy tails. Many models have been developed to deal with this tail behaviour, which reflects the jumps in the sample paths. On the other hand, the presence of long memory, which contradicts the efficient market hypothesis, is still an issue for further debates. These difficulties present challenges with the problems of memory detection and modelling the co-presence of long memory and heavy tails. This PhD project aims to respond to these challenges. The first part aims to detect memory in a large number of financial time series on stock prices and exchange rates using their scaling properties. Since financial time series often exhibit stochastic trends, a common form of nonstationarity, strong trends in the data can lead to false detection of memory. We will take advantage of a technique known as multifractal detrended fluctuation analysis (MF-DFA) that can systematically eliminate trends of different orders. This method is based on the identification of scaling of the q-th-order moments and is a generalisation of the standard detrended fluctuation analysis (DFA) which uses only the second moment; that is, q = 2. We also consider the rescaled range R/S analysis and the periodogram method to detect memory in financial time series and compare their results with the MF-DFA. An interesting finding is that short memory is detected for stock prices of the American Stock Exchange (AMEX) and long memory is found present in the time series of two exchange rates, namely the French franc and the Deutsche mark. Electricity price series of the five states of Australia are also found to possess long memory. For these electricity price series, heavy tails are also pronounced in their probability densities. The second part of the thesis develops models to represent short-memory and longmemory financial processes as detected in Part I. These models take the form of continuous-time AR(∞) -type equations whose kernel is the Laplace transform of a finite Borel measure. By imposing appropriate conditions on this measure, short memory or long memory in the dynamics of the solution will result. A specific form of the models, which has a good MA(∞) -type representation, is presented for the short memory case. Parameter estimation of this type of models is performed via least squares, and the models are applied to the stock prices in the AMEX, which have been established in Part I to possess short memory. By selecting the kernel in the continuous-time AR(∞) -type equations to have the form of Riemann-Liouville fractional derivative, we obtain a fractional stochastic differential equation driven by Brownian motion. This type of equations is used to represent financial processes with long memory, whose dynamics is described by the fractional derivative in the equation. These models are estimated via quasi-likelihood, namely via a continuoustime version of the Gauss-Whittle method. The models are applied to the exchange rates and the electricity prices of Part I with the aim of confirming their possible long-range dependence established by MF-DFA. The third part of the thesis provides an application of the results established in Parts I and II to characterise and classify financial markets. We will pay attention to the New York Stock Exchange (NYSE), the American Stock Exchange (AMEX), the NASDAQ Stock Exchange (NASDAQ) and the Toronto Stock Exchange (TSX). The parameters from MF-DFA and those of the short-memory AR(∞) -type models will be employed in this classification. We propose the Fisher discriminant algorithm to find a classifier in the two and three-dimensional spaces of data sets and then provide cross-validation to verify discriminant accuracies. This classification is useful for understanding and predicting the behaviour of different processes within the same market. The fourth part of the thesis investigates the heavy-tailed behaviour of financial processes which may also possess long memory. We consider fractional stochastic differential equations driven by stable noise to model financial processes such as electricity prices. The long memory of electricity prices is represented by a fractional derivative, while the stable noise input models their non-Gaussianity via the tails of their probability density. A method using the empirical densities and MF-DFA will be provided to estimate all the parameters of the model and simulate sample paths of the equation. The method is then applied to analyse daily spot prices for five states of Australia. Comparison with the results obtained from the R/S analysis, periodogram method and MF-DFA are provided. The results from fractional SDEs agree with those from MF-DFA, which are based on multifractal scaling, while those from the periodograms, which are based on the second order, seem to underestimate the long memory dynamics of the process. This highlights the need and usefulness of fractal methods in modelling non-Gaussian financial processes with long memory.