TSFCNet

A Multi-Domain Convolutional Neural Network for EEG Motor Imagery Decoding

This is the PyTorch implementation of the TSFCNet architecture for EEG-MI classification.

TSFCNet: Architecture

TSFCNet: Results (Hold-out Scenario)

Dataset I: BCI Competition IV 2a Dataset
Dataset II: BCI Competition IV 2b Dataset
Dataset III: OpenBMI Dataset

Reproduced

A pytorch implementation for EEGNeX.

A pytorch implementation for ATCNet.

Citation

If you find this code useful to your research, please give credit to the following paper

@ARTICLE{zhi2023,
  author={Zhi, Hongyi and Yu, Zhuliang and Yu, Tianyou and Gu, Zhenghui and Yang, Jian},
  journal={IEEE Transactions on Neural Systems and Rehabilitation Engineering}, 
  title={A Multi-Domain Convolutional Neural Network for EEG-Based Motor Imagery Decoding}, 
  year={2023},
  volume={31},
  pages={3988-3998}
}

References:

Ravikiran Mane, Effie Chew, Karen Chua, Kai Keng Ang, Neethu Robinson, A.P. Vinod, Seong-Whan Lee, and Cuntai Guan, "FBCNet: An Efficient Multi-view Convolutional Neural Network for Brain-Computer Interface," arXiv preprint arXiv:2104.01233 (2021) https://arxiv.org/abs/2104.01233

Acknowledgment

We thank Ravikiran Mane et al. for their useful toolbox.