Master Thesis Defense - February 18, 2019: Distributions Based Regression Techniques for Compositional Data

Divya Ankam

Monday, February 18, 2019 at 1:00 p.m.
Room EV001.162

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

Examining Committee

Dr. C. Wang, Chair
Dr. N. Bouguila, Supervisor
Dr. F. Mafakheri, CIISE Examiner
Dr. G. Gopakumar, External Examiner (CES)

Abstract

In this thesis, initially different transformations for compositional data are explored in combination with partial least squares discriminant analysis (PLS-DA), a regression technique applied to classification problems. This method has been deployed for intrusion detection and spam filtering applications. Two novel regression approaches based on distributions are also proposed for compositional data, namely generalized Dirichlet regression and Beta-Liouville regression. They are extensions of Beta regression in a multi-dimensional scenario, similar to Dirichlet regression. The models are learned by maximum likelihood estimation algorithm using Newton-Raphson approach. The performance comparison between the proposed models and other popular solutions is given and both synthetic and real data sets extracted from challenging applications such as market share analysis using Google-Trends and occupancy estimation in smart buildings are evaluated to show the merits of the proposed approaches.