EEG-Deformer: A Dense Convolutional Transformer for Brain-Computer Interfaces

Effectively learning the temporal dynamics in electroencephalogram (EEG) signals is challenging yet essential for decoding brain activities using brain-computer interfaces (BCIs). Although Transformers are popular for their long-term sequential learning ability in the BCI field, most methods combining Transformers with convolutional neural networks (CNNs) fail to capture the coarse-to-fine temporal dynamics of EEG signals. To overcome this limitation, we introduce EEG-Deformer, which incorporates two main novel components into a CNN-Transformer: (1) a Hierarchical Coarse-to-Fine Transformer (HCT) block that integrates a Fine-grained Temporal Learning (FTL) branch into Transformers, effectively discerning coarse-to-fine temporal patterns; and (2) a Dense Information Purification (DIP) module, which utilizes multi-level, purified temporal information to enhance decoding accuracy. Comprehensive experiments on three representative cognitive tasksâcognitive attention, driving fatigue, and mental workload detectionâconsistently confirm the generalizability of our proposed EEG-Deformer, demonstrating that it either outperforms or performs comparably to existing state-of-the-art methods. Visualization results show that EEG-Deformer learns from neurophysiologically meaningful brain regions for the corresponding cognitive tasks.

Authors

• Yi Ding
• Yong Li
• Hao Sun
• Rui Liu
• Chengxuan Tong
• Chenyu Liu
• Xinliang Zhou Nanyang Technological University
• Cuntai Guan

Keywords

• Electroencephalography
• Transformers
• Decoding
• Feature extraction
• Purification
• Convolutional neural networks
• Electronics packaging
• IP networks
• Convolutional Transformation
• Neural Network
• Convolutional Neural Network
• Brain Activity
• Cognitive Tasks
• Cognitive Load
• Temporal Dynamics
• Temporal Information
• EEG Signals
• Signaling Dynamics
• Cognitive Attention
• Temporal Dimension
• Spatial Dimensions
• Feature Learning
• Temporal Features
• Independent Component Analysis
• EEG Data
• Removal Method
• Convolutional Neural Network Layers
• Linear Layer
• Macro F1 Score
• Reduction In Accuracy
• Saliency Map
• Coarse-grained Representation
• Log Power
• CNN-based Methods
• Shallow Features
• Smaller Model Size
• EEG Features
• Feature Encoder
• Deep learning
• transformer
• Brain-Computer Interfaces
• Humans
• Signal Processing, Computer-Assisted
• Neural Networks, Computer
• Adult
• Brain
• Male
• Young Adult