Electronic Thesis and Dissertation Repository

Thesis Format

Integrated Article


Master of Science


Computer Science


Boyu Wang

2nd Supervisor

Yalda Mohsenzadeh



Electroencephalography (EEG) has been widely used to record electromagnetic fields for motor imagery (MI)-based brain-computer interfaces (BCIs). However, collecting MI signals is often time-consuming and challenging to classify due to the inter-subject variability of EEG signals. To address these issues, we propose a novel framework MACNet, which stands for Multi-view Adversarial Contrastive Network. MACNet employs a contrastive learning approach to learn spatial and temporal features in two views, using Riemannian and Euclidean encoders. By jointly extracting underlying features and learning domain-invariant representations in both source and target features, MACNet improves the alignment and accuracy. In addition, we propose a domain mixup for the BCI field at the signal and embedding levels, to improve domain alignment. We evaluate MACNet on two public datasets and demonstrate that it outperforms all previous methods in inter-subject transfer learning. Specifically, MACNet achieves 83.79\% accuracy for the BCI Competition IV dataset and 80.00\% accuracy for the OpenBMI dataset.

Summary for Lay Audience

A Brain-Computer Interface (BCI) allows users to control external devices using their brain activity. Motor Imagery (MI) is one of the primary forms of brain-computer interfaces (BCIs) in which the participant is asked to imagine moving different parts of the body. The inter-subject variability of brain signals, which leads to a domain shift between sessions, is a significant issue in the practical use of MI systems. As a result, machine learning models trained on one session perform poorly on the other session since the data distribution varies from what they have learned. This thesis introduced a novel machine-learning model specifically for MI tasks to build a robust data-driven method that extracts and learns domain-invariant features in different views of EEG signals.

Available for download on Sunday, September 01, 2024