Master Thesis Defense - August 22, 2018: Bayesian Learning of Asymmetric Gaussian-Based Statistical Models Using Markov Chain Monte Carlo Techniques

Shuai Fu

Wednesday, August 22, 2018 at 2:00 p.m.
Room EV011.119

You are invited to attend the following M.A.Sc. (Information Systems Security) thesis examination.

Examining Committee

Dr. A. Youssef, Chair
Dr. N. Bouguila, Supervisor
Dr. J. Bentahar, CIISE Examiner
Dr. J. Lee, External Examiner (BCEE)

Abstract

A novel unsupervised Bayesian learning framework based on asymmetric Gaussian mixture (AGM) statistical model is proposed since AGM is shown to be more effective compared to the classic Gaussian mixture. The Bayesian learning framework is developed by adopting sampling- based Markov chain Monte Carlo (MCMC) methodology. More precisely, the fundamental learning algorithm is a hybrid Metropolis-Hastings within Gibbs sampling solution which is integrated within a reversible jump MCMC (RJMCMC) learning framework, a self-adapted sampling-based MCMC implementation, that enables model transfer throughout the mixture parameters learning process, therefore, automatically converges to the optimal number of data groups. Furthermore, a feature selection technique is included to tackle the irrelevant and unneeded information from datasets. The performance comparison between AGM and other popular solutions is given and both synthetic and real data sets extracted from challenging applications such as intrusion detection, spam filtering and image categorization are evaluated to show the merits of the proposed approach.