• We propose a compact convolutional Transformer, named EEG Conformer, to encapsulate local and global features in a unified EEG classification framework.
• The convolution module learns the low-level local features throughout the one-dimensional temporal and spatial convolution layers. The self-attention module is straightforwardly connected to extract the global correlation within the local temporal features. Subsequently, the simple classifier module based on fully-connected layers is followed to predict the categories for EEG signals.
• We also devise a visualization strategy to project the class activation mapping onto the brain topography.

• Python 3.10
• Pytorch 1.12

• BCI_competition_IV2a - acc 78.66% (hold out)
• BCI_competition_IV2b - acc 84.63% (hold out)
• SEED - acc 95.30% (5-fold)

Hope this code can be useful. I would be very appreciate if you cite us in your paper. 😊

@article{song2023eeg,
  title = {{{EEG Conformer}}: {{Convolutional Transformer}} for {{EEG Decoding}} and {{Visualization}}},
  shorttitle = {{{EEG Conformer}}},
  author = {Song, Yonghao and Zheng, Qingqing and Liu, Bingchuan and Gao, Xiaorong},
  year = {2023},
  journal = {IEEE Transactions on Neural Systems and Rehabilitation Engineering},
  volume = {31},
  pages = {710--719},
  issn = {1558-0210},
  doi = {10.1109/TNSRE.2022.3230250}
}