EEG-Conformer
EEG Conformer: Convolutional Transformer for EEG Decoding and Visualization [Paper]
Core idea: spatial-temporal conv + pooling + self-attention
News
πππ We've joined in braindecode toolbox. Use here for detailed info.
Thanks to Bru and colleagues for helping with the modifications.
Abstract
![Network Architecture](https://github.com/eeyhsong/EEG-Conformer/raw/main/visualization/Fig1.png)
- We propose a compact convolutional Transformer, 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.
Requirements:
Datasets
Please use consistent train-val-test split when comparing with other methods.
Citation
Hope this code can be useful. I would appreciate you citing us in your paper. π
@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}
}