MST-net: A multi-scale swin transformer network for EEG-based cognitive load assessment

• Published in: Brain research bulletin 2024-01, Vol.206, p.110834-110834, Article 110834
• Main Authors: Li, Zhongrui, Zhang, Rongkai, Zeng, Ying, Tong, Li, Lu, Runnan, Yan, Bin
• Format: Article
• Language: English
• Subjects: Brain; Cognition; Cognitive load assessment; EEG; Electroencephalography; Humans; Multi-scale; Parallel convolution; Swin Transformer
• ISSN: 0361-9230; 1873-2747
• DOI: 10.1016/j.brainresbull.2023.110834

Cognitive load assessment plays a crucial role in monitoring safe production, resource allocation, and subjective initiative in human-computer interaction. Due to its high time resolution and convenient acquisition, Electroencephalography (EEG) is widely applied in brain monitoring and cognitive state assessment. In this study, a multi-scale Swin Transformer network (MST-Net) was proposed for cognitive load assessment, which extracts local features with different sensory fields using a multi-scale parallel convolution model and introduces the attention mechanism of the Swin Transformer to obtain the feature correlations among multi-scale local features. The performance of the proposed network was validated using the EEG signals collected during cognitive tasks and N-back tasks with three different load levels. Results show that the MST-Net network achieved the best classification accuracy on both local and public datasets, and was higher than the mainstream Swin Transformer and CNN. Furthermore, results of ablation experiments and feature visualization revealed that the proposed MST-Net could well characterize different cognitive loads, which not only provided novel and powerful tools for cognitive load assessment but also showed potential for broad application in brain-computer interface (BCI) systems. •The hybrid network model has significant advantages in cognitive load assessment based on EEG signals.•Increasing the richness of feature candidate sets is helpful for improving the performance of cognitive load assessment.•Parallel convolution operations can extract EEG differences under distinct cognitive load levels.