Self-supervised learning for EEG signals

An increasing number of wearable devices collect and use physiological information to track physical and mental health on a daily basis. While large-scale research initiatives allow an unprecedented amount of data to be collected, biosignal analysis techniques have yet to catch up. Indeed, analysis tools designed by hand based on small datasets available in traditional research settings are still widely used. In this project, we propose to use deep learning, a subfield of machine learning dedicated to jointly learning features and decision rules from large amounts of data, to automatically uncover key patterns that emerge when studying the brain activity of very large populations. These patterns can then be used to more effectively extract useful information from biosignals. This work will allow companies like InteraXon Inc. to create value from the physiological data they collect and develop useful applications for the everyday user of wearable devices.

Faculty Supervisor:

Sue Becker

Student:

Hubert Jacob Banville

Partner:

InteraXon Inc

Discipline:

Computer science

Sector:

Other services (except public administration)

University:

McMaster University