Cette dissertation présente un ensemble d'algorithmes visant à en permettre un usage rapide, robuste et automatique des « Support Vector Machines » (SVM) non supervisés dans un contexte d'analyse de données. Les SVM non supervisés se déclinent sous deux types algorithmes prometteurs, le « Support Vector Clustering » (SVC) et le « Support Vector Domain Description » (SVDD), offrant respectivement une solution à deux problèmes importants en analyse de données, soit la recherche de groupements homogènes (« clustering »), ainsi que la reconnaissance d'éléments atypiques (« novelty/abnomaly detection ») à partir d'un ensemble de données. Cette recherche propose des solutions concrètes à trois limitations fondamentales inhérentes à ces deux algorithmes, notamment I) l'absence d'algorithme d'optimisation efficace permettant d'exécuter la phase d'entrainement des SVDD et SVC sur des ensembles de données volumineux dans un délai acceptable, 2) le manque d'efficacité et de robustesse des algorithmes existants de partitionnement des données pour SVC, ainsi que 3) l'absence de stratégies de sélection automatique des hyperparamètres pour SVDD et SVC contrôlant la complexité et la tolérance au bruit des modèles générés. La résolution individuelle des trois limitations mentionnées précédemment constitue les trois axes principaux de cette thèse doctorale, chacun faisant l'objet d'un article scientifique proposant des stratégies et algorithmes permettant un usage rapide, robuste et exempt de paramètres d'entrée des SVDD et SVC sur des ensembles de données arbitraires.

No description available.

Being among the most popular and efficient classification and regression methods currently available, implementations of support vector machines exist in almost every popular programming language. Currently four R packages contain SVM related software. The purpose of this paper is to present and compare these implementations. (authors' abstract)

Being among the most popular and efficient classification and regression methods currently available, implementations of support vector machines exist in almost every popular programming language. Currently four R packages contain SVM related software. The purpose of this paper is to present and compare these implementations. (author's abstract) / Series: Research Report Series / Department of Statistics and Mathematics

Thesis (Ph. D.)--Oregon State University, 2009. / Printout. Includes bibliographical references (leaves 132-137). Also available on the World Wide Web.

Thesis (M. Sc.)--University of Alberta, 2009. / Title from pdf file main screen (viewed on Sept. 10, 2009). "A thesis submitted to the Faculty of Graduate Studies and Research in partial fulfillment of the requirements for the degree of Master of Science in Mining Engineering, Department of Civil and Environmental Engineering, University of Alberta." Includes bibliographical references.

No description available.

The Support Vector Machine (SVM) classification method has recently gained popularity due to the ease of implementing non-linear separating surfaces. SVM is an optimization problem with the two competing goals, minimizing misclassification on training data and maximizing a margin defined by the normal vector of a learned separating surface. We develop and implement new SVM models based on previously conceived SVM with L_1-Norm regularization with ramp loss error terms. The goal being a new SVM model that is both robust to outliers due to ramp loss, while also easy to implement in open source and off the shelf mathematical programming solvers and relatively efficient in finding solutions due to the mixed linear-integer form of the model. To show the effectiveness of the models we compare results of ramp loss SVM with L_1-Norm and L_2-Norm regularization on human organ microbial data and simulated data sets with outliers.

This study considers the dynamic pedestrian detection system and the static pedestrian detection system with a single camera. In the static detection system, this study reconstructs the static database. As to feature extraction, HOG combining with SVM classifier is used in this study. Experimental results show the database can detect people by this algorithm in several scenes. In the dynamic detection system, because the population of older persons and disabled persons increases gradually nowadays, cross the intersection is a challenge for older persons and disabled persons, so this study researches in dynamic pedestrian detection system by a single camera for assisting autonomous transport robots, and this system detects people at the intersection for assisting older persons and disabled persons when they cross the intersection. As to the algorithm this study uses the foot detection algorithm to detect dynamic pedestrians. According to the experimental results, the light and clothes effect on the experimental results both in the dynamic pedestrian system and the static pedestrian system. The dynamic pedestrian system still shows real-time performance not only in the longitudinal direction but also in the lateral direction.

Many computer vision problems involve building automatic systems by extracting complex high-level information from visual data. Such problems can often be modeled using structural models, which relate raw input variables to structural high-level output variables. Structural support vector machine is a discriminative method for learning structural models. It allows a flexible feature construction with good robustness against overfitting, and thus provides state-of-the-art prediction accuracies for structural prediction tasks in computer vision. This thesis first studies the application of structural SVMs in interactive image segmentation. A novel interactive image segmentation technique that automatically learns segmentation parameters tailored for each and every image is proposed. Unlike existing work, the proposed method does not require any offline parameter tuning or training stage, and is capable of determining image-specific parameters according to some simple user interactions with the target image. The segmentation problem is modeled as an inference of a conditional random field (CRF) over a segmentation mask and the target image. This CRF is parametrized by the weights for different terms (e.g., color, texture and smoothing). These weight parameters are learned via a one-slack structural SVM, which is solved using a constraint approximation scheme and the cutting plane algorithm. Experimental results show that the proposed method, by learning image-specific parameters automatically, outperforms other state-of-the-art interactive image segmentation techniques. This thesis then uses structural SVMs to speed up large scale relatively-paired space analysis. A new multi-modality analysis technique based on relatively-paired observations from multiple modalities is proposed. Relative-pairing information is encoded using relative proximities of observations in a latent common space. By building a discriminative model and maximizing a distance margin, a projection function that maps observations into the latent common space is learned for each modality. However, training based on large scale relatively-paired observations could be extremely time consuming. To this end, the training is reformulated as learning a structural model, which can be optimized by the cutting plane algorithm where only a few training samples are involved in each iteration. Experimental results validate the effectiveness and efficiency of the proposed technique. / published_or_final_version / Computer Science / Doctoral / Doctor of Philosophy