student profile: Mr Stephen Mccloskey


Map

Thesis work

Thesis title: Sleep Disorder Analysis Using Machine Learning Techniques

Supervisors: Irena KOPRINSKA , Bryn JEFFRIES

Thesis abstract:

The aim of this study is to determine whether distinct sets of characteristics can be found from sleepers with sleep disorders using machine-learning techniques on polysomnography data (i.e. EEG). The objectives include incorporating signal analysis techniques, including wavelet analysis and independent component analysis (ICA), on an existing EEG analysis pipeline to study EEG over a full night. Another objective of this study includes incorporating a Convolutional Neural Network (CNN) to classify EEG into sleep stages as well as comparing and determining the differences between traditional discrete sleep stages and a brain dynamics model that predicts continuous trajectories between sleep states. The goal would be to then perform unsupervised cluster analysis to determine sets of characteristics distinct to particular subtypes of people with sleep disorders such as insomnia disorder and Obstructive Sleep Apnea (OSA).

Note: This profile is for a student at the University of Sydney. Views presented here are not necessarily those of the University.