Key result
A novel class alignment network based on self-attention and adversarial learning strategies demonstrated efficacy and superiority for cross-subject EEG classification on two public datasets.
Why the study?
Existing domain adaptation and adversarial learning strategies for cross-subject EEG classification focus on domain alignment but overlook task-specific class boundaries, causing weak correlation between extracted features and categories.
A novel self-attention based class alignment network improves cross-subject EEG classification by aligning same-class features across different domains.
Novel EEG domain-adaptation method targets class boundaries; leaves open whether it outperforms alignment-only approaches in practice.
Due to the inherent variability in EEG signals across different individuals, domain adaptation and adversarial learning strategies are being progressively utilized to develop subject-specific classification models by leveraging data from other subjects. These approaches primarily focus on domain alignment and tend to overlook the critical task-specific class boundaries. This oversight can result in weak correlation between the extracted features and categories. To address these challenges, we propose a novel model that uses the known information from multiple subjects to bolster EEG classification for an individual subject through adversarial learning strategies. Our method begins by extracting both shallow and attention-driven deep features from EEG signals. Subsequently, we employ a class discriminator to encourage the same-class features from different domains to converge while ensuring that the different-class features diverge. This is achieved using our proposed discrimination loss function, which is designed to minimize the feature distance for samples of the same class across different domains while maximizing it for those from different classes. Additionally, our model incorporates two parallel classifiers that are harmonious yet distinct and jointly contribute to decision-making. Extensive testing on two publicly available EEG datasets has validated our model's efficacy and superiority.
No takes yet. Share an insight, caveat, or question.
Ma et al. (2024) studied EEG classification. Class alignment network based on self-attention was evaluated on Classification performance. A novel class alignment network based on self-attention and adversarial learning strategies demonstrated efficacy and superiority for cross-subject EEG classification on two public datasets.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: