We have open-sourced a new high-performance hybrid multi-scale convolutional neural network and Transformer MI-EEG decoding model, namely MSCFormer. Extensive experiments on the BCI IV-2a and IV-2b datasets show that MSCFormer achieves average accuracies of 82.95% (BCI IV-2a) and 88.00% (BCI IV-2b), with kappa values of 0.7726 and 0.7599 in five-fold cross-validation, surpassing several state-of-the-art methods.
We would be honored if it could be integrated into the braindecode project. The project address is as follows:
https://github.com/snailpt/MSCFormer
Thanks for your time.
We have open-sourced a new high-performance hybrid multi-scale convolutional neural network and Transformer MI-EEG decoding model, namely MSCFormer. Extensive experiments on the BCI IV-2a and IV-2b datasets show that MSCFormer achieves average accuracies of 82.95% (BCI IV-2a) and 88.00% (BCI IV-2b), with kappa values of 0.7726 and 0.7599 in five-fold cross-validation, surpassing several state-of-the-art methods.
We would be honored if it could be integrated into the braindecode project. The project address is as follows:
https://github.com/snailpt/MSCFormer
Thanks for your time.