Abstract
EEG signals play a crucial role in assessing cognitive load, which is a key element in ensuring the secure operation of human-computer interaction systems. However, the variability of EEG signals across different subjects poses a challenge in applying the pre-trained cognitive load assessment model to new subjects. Moreover, previous domain adaptation research has primarily focused on developing complex network architectures to learn more domain-invariant features, overlooking the noise introduced by pseudo-labels and the challenges posed by domain migration problems. Therefore, this study proposes a novel cross-attention swin-transformer network for cross-subject cognitive load assessment, which achieves inter-domain feature alignment through parameter sharing in cross attention mechanism without using pseudo-labels, and utilizes maximum mean discrepancy (MMD) to measure the difference between the feature distributions of the source and target domains, further promoting feature alignment between domains. This method aims to leverage the advantages of cross-attention mechanism and MMD to better mitigate individual differences among subjects in cross-subject cognitive workload assessment. To validate the classification performance of the proposed network, two datasets of image recognition task and N-back task were employed for testing. Results show that, the proposed model outperformed advanced methods with cross-subject classification results of 88.13% and 81.27% on the on local and public datasets. The ablation experiment results reveal that using either the cross-attention mechanism or the MMD strategy alone improves cross-subject classification performance by 2.11% and 2.95% on the local dataset, respectively. Furthermore, the results of the EEG features distribution differences between all subjects before and after network training showed a significant reduction in feature distribution differences between subjects, further confirming the network's effectiveness in minimizing inter-subject differences. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s11571-024-10160-7.