While postcraniometric sex estimation has shown promising results in North American (NA) samples, methods and standards for sex estimation in South Africa (SA) are restricted by incomplete samples and a lack of robust statistical techniques. The purpose of this study was to evaluate accuracies of sex estimation in the postcrania of modern South Africans using multivariate statistics and to compare pattern expression of sexual dimorphism in black, white and coloured groups. The study included analysing the skeletons of a total of 360 SA black, white and coloured individuals and the data of 240 NA black and white individuals (equal sex and ancestry). Sympercents expressed sexual dimorphism and where compared in the three SA groups and with the NA individuals. The creation of different bone models and a variety of multivariate models revealed the potential of multivariate techniques. Comparisons of linear discriminant analysis (LDA), flexible discriminant analysis (FDA) and logistic regression indicated which model provided the greatest discriminatory power between sex and sex-ancestry groups in SA. Among the SA groups coloureds were the most sexually dimorphic; however, overall NA individual showed the greatest differences between the sexes. Multivariate classification accuracies using bone models (various measurements from individual bones) ranged between 75% and 91%, whereas classification accuracies using multivariate subsets (combinations of measurements from different bones) ranged from 85% to 98%. When classifying into sex and ancestry, a multivariate subset using eight measurements achieved classification accuracies of up to 80%. Overall FDA achieved the best results, whereas logistic regression achieved the lowest results for both bone models and multivariate subsets. Postcranial bones achieve comparable classification accuracies to the pelvis and higher accuracies than metric or morphological techniques using the cranium in SA. Large differences in sexual dimorphism between NA and SA warrant the creation of population-specific standards and custom databases for SA. / Dissertation (MSc)--University of Pretoria, 2015. / Anatomy / MSc / Unrestricted

M.Comm. (Financial Management) / The costs of the 2007- 09 financial crises on global economies have resulted in new central bank rules to strengthen financial institutions. The question of whether there were any significant differences in capital structures between banks who were liquid and those who were liquidity constrained in the 2007– 2009 global financial crisis, still needs to be answered. Theoretical models on corporate failure partly explain how bank capital management impacts on whether a bank fails or not. This study investigates the differences in capital ratios between banks who were liquidity- stressed and those who were liquid. A comparative analysis of selected banking capital ratios were done followed by a discriminant analysis to determine if there is a relationship between the capital structures of liquid and liquidity- stressed banks. It was found that there were differences in capital structures of liquid and liquidity- stressed banks but capital ratios on their own, could not be used as early warning sign for bank failure.

Recently, automatic demographic classification has found its way into embedded applications such as targeted advertising in mobile devices, and in-car warning systems for elderly drivers. In this thesis, we present a complete framework for video-based gender classification and age estimation which can perform accurately on embedded systems in real-time and under unconstrained conditions. We propose a segmental dimensionality reduction technique utilizing Enhanced Discriminant Analysis (EDA) to minimize the memory and computational requirements, and enable the implementation of these classifiers for resource-limited embedded systems which otherwise is not achievable using existing resource-intensive approaches. On a multi-resolution feature vector we have achieved up to 99.5% compression ratio for training data storage, and a maximum performance of 20 frames per second on an embedded Android platform. Also, we introduce several novel improvements such as face alignment using the nose, and an illumination normalization method for unconstrained environments using bilateral filtering. These improvements could help to suppress the textural noise, normalize the skin color, and rectify the face localization errors. A non-linear Support Vector Machine (SVM) classifier along with a discriminative demography-based classification strategy is exploited to improve both accuracy and performance of classification. We have performed several cross-database evaluations on different controlled and uncontrolled databases to assess the generalization capability of the classifiers. Our experiments demonstrated competitive accuracies compared to the resource-demanding state-of-the-art approaches.

Dans cette thèse, on introduit la métrique "Coefficient de forme" pour la classement des données de dissimilitudes. Cette approche est inspirée par l'analyse discriminante géométrique et on a défini des règles de décision pour imiter le comportement du classifieur linéaire et quadratique. Le nombre de paramètres est limité (deux par classe). On a également étendu et amélioré cette démarche avantageuse et rapide pour apprendre uniquement à partir des représentations de dissimilitudes en utilisant l'efficacité du classificateur des Machines à Vecteurs de Support. Comme contexte applicatif pour la classification par dissimilitudes, on utilise la recherche d'images à l'aide d'une représentation des images en multi échelle en utilisant la "Pyramide Réduite Différentielle". Une application pour la description de visages est développée. Des résultats de classification à partir du coefficient de forme et utilisant une version adaptée des Machines à Vecteurs de Support, sur des bases de données issues des applications du monde réel sont présentés et comparés avec d'autres méthodes de classement basées sur des dissimilitudes. Il en ressort une forte robustesse de la méthode proposée avec des perfommances supérieures ou égales aux algorithmes de l'état de l'art. / The dissimilarity representation is an alternative for the use of features in the recognition of real world objects like images, spectra and time-signal. Instead of an absolute characterization of objects by a set of features, the expert or the system is asked to define a measure that estimates the dissimilarity between pairs of objects. Such a measure may also be defined for structural representations such as strings and graphs. The dissimilarity representation is potentially able to bridge structural and statistical pattern recognition. In this thesis we introduce a new fast Mahalanobis-like metric the “Shape Coefficient” for classification of dissimilarity data. Our approach is inspired by the Geometrical Discriminant Analysis and we have defined decision rules to mimic the behavior of the linear and quadratic classifier. The number of parameters is limited (two per class). We also expand and ameliorate this advantageous and rapid adaptive approach to learn only from dissimilarity representations by using the effectiveness of the Support Vector Machines classifier for real-world classification tasks. Several methods for incorporating dissimilarity representations are presented, investigated and compared to the “Shape Coefficient” in this thesis: • Pekalska and Duin prototype dissimilarity based classifiers; • Haasdonk's kernel based SVM classifier; • KNN classifier. Numerical experiments on artificial and real data show interesting behavior compared to Support Vector Machines and to KNN classifier: (a) lower or equivalent error rate, (b) equivalent CPU time, (c) more robustness with sparse dissimilarity data. The experimental results on real world dissimilarity databases show that the “Shape Coefficient” can be an alternative approach to these known methods and can be as effective as them in terms of accuracy for classification.

The purpose of this study is to investigate the usefulness of statistical decomposition measures in the prediction of industrial bond rating changes. Further, the predictive ability of decomposition measures is compared with multiple discriminant analysis on the same sample. The problem of this study is twofold. It stems in general from the statistical problems associated with current techniques employed in the study of bond ratings and in particular from the lack of attention to the study of bond rating changes. Two main hypotheses are tested in this study. The first is that bond rating changes can be predicted through the use of financial statement data. The second is that decomposition analysis can achieve the same performance as multiple discriminant analysis in duplicating and predicting industrial bond rating changes. To explain and predict industrial bond rating changes, statistical decomposition measures were computed for each company in the sample. Based on these decomposition measures, the two types of analyses performed were (a) a univariate analysis where each decomposition measure was compared with an industry average decomposition measure, and (b) a multivariate analysis where decomposition measures were used as independent variables in a probability linear model. In addition to statistical decomposition analysis, multiple discriminant analysis was used in duplicating and predicting bond rating changes. Finally, a comparison was made between the predictive abilities of decomposition analysis and discriminant analysis.

This dissertation studied the problem of face recognition when facial images have partial occlusions like sunglasses and scarfs. These partial occlusions lead to the loss of discriminatory information when trying to recognise a person's face using traditional face recognition techniques that do not take into account these shortcomings. This dissertation aimed to fill the gap of knowledge. Several papers in literature put forward the theory that not all regions of the face contribute equally when discriminating between different subjects. They state that some regions of the face are more equal than others, like the eyes and nose. While this may be true in theory there was a need to comprehensively study this problem. A weighting technique was introduced that that took into account the different features of the face and assigned weights for the different features of the face based on their distance from the five points that were identified as the centre of the weighing technique. Five centres were chosen which were the left eye, the right eye, the centre of the brows, the nose and the mouth. These centres perfectly captured were the five dominant regions of the face where roughly located. This weighing technique was fused with an image segmentation process that ultimately led to a hybrid approach to face recognition. Five features of the face were identified and studied quantitatively on how much they influence face recognition. These five features were the chin (C), eyes (E), forehead (F), mouth (M) and finally the nose (N). For the system to be robust and thorough, combinations of these five features were constructed to make 31 models that were used for both training and testing purposes. This meant that each of the five features had 16 models associated with it. For example, the chin (C) had the following models associated with it; C, CE, CF, CM, CN, CE, CEM, CEN, CFM, CFN, CMN, CEFM CEFN, CEMN, CFMN and CEFMN. These models were put in five different groupings called Category 1 up to Category 5. A Category 3 model implied that only three out of the five features were utilised for training the algorithm and testing. An example of a Category 3 model was the CFN model. This meant that this model simulated partial occlusion on the mouth and the chin region. The face recognition algorithm was trained on all these different models in order to ascertain the efficiency and effectiveness of this proposed technique. The results were then compared with various methods from the literature. / Dissertation (MEng (Computer Engineering))--University of Pretoria, 2020. / Electrical, Electronic and Computer Engineering / MEng (Computer Engineering) / Unrestricted

The thesis deals with selected classification methods. The thesis describes the basis of cluster analysis, discriminant analysis and theory of classification trees. The usage is demonstrated by classification of simulated data, the calculation is made in the program STATISTICA. In practical part of the thesis there is the comparison of the methods for classification of real data files of various extent. Classification methods are used for solving of the real task – prediction of air pollution based of the weather forecast.

Please read the abstract (Summary) in the 00front part of this document / Dissertation (MA (HMS))--University of Pretoria, 2002. / Biokinetics, Sport and Leisure Sciences / unrestricted

In this thesis, the performance of the classification methods Linear Discriminant Analysis (LDA), Random Forests (RF), and Support Vector Machines (SVM) are compared using procurement data to predict what size company will win a procurement. This is useful information for companies, since bidding on a procurement takes time and resources, which they can save if they know their chances of winning are low. The data used in the models are collected from OpenTender and allabolag.se and represent procurements that were awarded to companies in 2020. A total of 8 models are created, two versions of the LDA model, two versions of the RF model, and four versions of the SVM model, where some models are more complex than others. All models are evaluated on overall performance using hit rate, Huberty’s I Index, mean average error, and Area Under the Curve. The most complex SVM model performed the best across all evaluation measurements, whereas the less complex LDA model performed overall worst. Hit rates and mean average errors are also calculated within each class, and the complex SVM models performed best on all company sizes, except the small companies which were best predicted by the less complex Random Forest model.

This thesis covers misclassification probabilities via an Edgeworth-type expansion of the maximum likelihood based discriminant function. When deriving misclassification errors, first the expectation and variance in the population are assumed to be known where the variance is the same across populations and thereafter we consider the case where those parameters are unknown. Cumulants of the discriminant function for discriminating between two multivariate normal populations are derived. Approximate probabilities of the misclassification errors are established via an Edgeworth-type expansion using a standard normal distribution.