Obstructive sleep apnea is a potentially life-threatening condition characterized by repetitive episodes of upper airway obstruction that occur during sleep, usually associated with a reduction in blood oxygen saturation. In US population, 9% of women, 24% of men, and 2% of children have been diagnosed with obstructive sleep apnea, suggesting that 18 million people may suffer from the consequences of nightly episodes of apnea. One of the most significant symptoms of obstructive sleep apnea is profound and repeated hypoxia. The analysis of the interaction between cardiovascular and respiratory signals has been a widely-explored area of research due to the significance of the results in describing a functional relationship between the underlying physiologic systems; however, statistical and analytical approaches to analyze the changes in these signals before and after hypoxia are still in their early stages of evolution. A major motivation for this research has been the lack of methodologies to detect mean and/or variance shifts and identify root sources of variation in time-frequency characteristics of multichannel data. The contributions of this thesis are twofold. First, multiscale energy distributions based on wavelet transformations of the analyzed physiological signs are analyzed. This is followed by the development of an online multichannel monitoring approach based on principal curves that detects changes in the wavelet coefficients extracted from the analyzed signals.

Mean shift (MS) and subspace constrained mean shift (SCMS) algorithms are non-parametric, iterative methods to find a representation of a high dimensional data set on a principal curve or surface embedded in a high dimensional space. The representation of high dimensional data on a principal curve or surface, the class of mean shift type algorithms and their properties, and applications of these algorithms are the main focus of this dissertation. Although MS and SCMS algorithms have been used in many applications, a rigorous study of their convergence is still missing. This dissertation aims to fill some of the gaps between theory and practice by investigating some convergence properties of these algorithms. In particular, we propose a sufficient condition for a kernel density estimate with a Gaussian kernel to have isolated stationary points to guarantee the convergence of the MS algorithm. We also show that the SCMS algorithm inherits some of the important convergence properties of the MS algorithm. In particular, the monotonicity and convergence of the density estimate values along the sequence of output values of the algorithm are shown. We also show that the distance between consecutive points of the output sequence converges to zero, as does the projection of the gradient vector onto the subspace spanned by the D-d eigenvectors corresponding to the D-d largest eigenvalues of the local inverse covariance matrix. Furthermore, three new variations of the SCMS algorithm are proposed and the running times and performance of the resulting algorithms are compared with original SCMS algorithm. We also propose an adaptive version of the SCMS algorithm to consider the effect of new incoming samples without running the algorithm on the whole data set. As well, we develop some new potential applications of the MS and SCMS algorithm. These applications involve finding straight lines in digital images; pre-processing data before applying locally linear embedding (LLE) and ISOMAP for dimensionality reduction; noisy source vector quantization where the clean data need to be estimated before the quanization step; improving the performance of kernel regression in certain situations; and skeletonization of digitally stored handwritten characters. / Thesis (Ph.D, Mathematics & Statistics) -- Queen's University, 2013-09-30 18:01:12.959

Cette thèse travaille principalement sur trois sujets. Le premier concentre sur le clustering en ligne dans lequel nous présentons un nouvel algorithme stochastique adaptatif pour regrouper des ensembles de données en ligne. Cet algorithme repose sur l'approche quasi-bayésienne, avec une estimation dynamique (i.e., dépendant du temps) du nombre de clusters. Nous prouvons que cet algorithme atteint une borne de regret de l'ordre et que cette borne est asymptotiquement minimax sous la contrainte sur le nombre de clusters. Nous proposons aussi une implémentation par RJMCMC. Le deuxième sujet est lié à l'apprentissage séquentiel des courbes principales qui cherche à résumer une séquence des données par une courbe continue. Pour ce faire, nous présentons une procédure basée sur une approche maximum a posteriori pour le quasi-posteriori de Gibbs. Nous montrons que la borne de regret de cet algorithme et celui de sa version adaptative est sous-linéaire en l'horizon temporel T. En outre, nous proposons une implémentation par un algorithme glouton local qui intègre des éléments de sleeping experts et de bandit à plusieurs bras. Le troisième concerne les travaux qui visent à accomplir des tâches pratiques au sein d'iAdvize, l'entreprise qui soutient cette thèse. Il inclut l'analyse des sentiments pour les messages textuels et l'implémentation de chatbot dans lesquels la première est réalisé par les méthodes classiques dans la fouille de textes et les statistiques et la seconde repose sur le traitement du langage naturel et les réseaux de neurones artificiels. / This thesis works mainly on three subjects. The first one is online clustering in which we introduce a new and adaptive stochastic algorithm to cluster online dataset. It relies on a quasi-Bayesian approach, with a dynamic (i.e., time-dependent) estimation of the (unknown and changing) number of clusters. We prove that this algorithm has a regret bound of the order of and is asymptotically minimax under the constraint on the number of clusters. A RJMCMC-flavored implementation is also proposed. The second subject is related to the sequential learning of principal curves which seeks to represent a sequence of data by a continuous polygonal curve. To this aim, we introduce a procedure based on the MAP of Gibbs-posterior that can give polygonal lines whose number of segments can be chosen automatically. We also show that our procedure is supported by regret bounds with sublinear remainder terms. In addition, a greedy local search implementation that incorporates both sleeping experts and multi-armed bandit ingredients is presented. The third one concerns about the work which aims to fulfilling practical tasks within iAdvize, the company which supports this thesis. It includes sentiment analysis for textual messages by using methods in both text mining and statistics, and implementation of chatbot based on nature language processing and neural networks.