Electronic Thesis and Dissertation Repository

Thesis Format



Master of Science


Computer Science

Collaborative Specialization

Artificial Intelligence


Boyu Wang


Electroencephalography (EEG) based emotion recognition in affective brain-computer interfaces has advanced significantly in recent years. Unsupervised domain adaptation (UDA) methods have been successfully used to mitigate the need for large amounts of training data, which is required due to the inter-subject variability of EEG signals. Typical UDA solutions require access to raw source data to leverage the knowledge learned from the labelled source domains (previous subjects) across the target domain (a new subject), raising privacy concerns. To tackle this issue, we propose Attention-based Multi-Source-Free Domain Adaptation (AMFDA) for EEG emotion recognition. AMFDA attempts to transfer knowledge of source models to the target domain by aggregating adapted source models based on a set of learnable weights without accessing the source data. While the classifiers of source models are frozen, the set of learnable weights and the feature extractors are learned based on information maximization and a novel self-supervised pseudo-labelling method. A channel-wise attention layer is also used in the proposed framework to enhance the performance of source models, which in turn improves the performance of target models. We conducted extensive experiments on SEED and SEED-IV. The experimental results demonstrate that the proposed AMFDA method performs comparably to UDA state-of-the-art methods.

Summary for Lay Audience

It is important to understand emotions as they are a fundamental part of human communication and behaviour. Thus, it is crucial to understand how emotions can be interpreted through physiological signals in human-computer interaction. In general, physiological signals, such as EEG, can be highly affected by the psychological and physical characteristics of individuals, thereby necessitating the collection of large amounts of data. Additionally, EEG signals contain extensive private information that can be used to identify individuals.

To protect the privacy concerns of subjects and mitigate the need for large datasets, we introduce a novel approach to recognizing emotions based on EEG. The proposed method involves transferring knowledge from previous subjects (source domains) to a new one (target domain). The results of our research have demonstrated that our proposed method performs as well as those methods that require data from source domains, while also maintaining the privacy of participants by not utilizing the information of previous participants.