Evaluating Deep Learning Techniques for Automated Sleep Stage Scoring of EEG Data

Sean Tomlinson


Supervised by Matthias Treder; Moderated by Paul L Rosin

We will be evaluating the use of different neural network architectures with the purpose of developing a classifying deep learning system. This system should be capable of automatically sleep stage scoring human sleep data from a multivariate EEG source. We will be working with Cardiff University’s NaPS Laboratory (Neuroscience and Psychology of sleep) and CUBRIC (Cardiff University Brain Research Imaging Centre) with the hopes of providing a system that can aid in the scoring of their data to a high degree of accuracy; at least compared to current more primitive methods.

Initial Plan (04/02/2019) [Zip Archive]

Final Report (10/05/2019) [Zip Archive]

Publication Form