https://github.com/okbalefthanded/ssvepformer
Pytorch implementation for a transformer-based model for SSVEP classifcation in EEG based Brain-Computer Interface (BCI)
https://github.com/okbalefthanded/ssvepformer
bci eeg pytorch ssvep transformer
Last synced: about 2 months ago
JSON representation
Pytorch implementation for a transformer-based model for SSVEP classifcation in EEG based Brain-Computer Interface (BCI)
- Host: GitHub
- URL: https://github.com/okbalefthanded/ssvepformer
- Owner: okbalefthanded
- License: apache-2.0
- Created: 2024-12-28T15:54:18.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-02-08T15:29:46.000Z (about 1 year ago)
- Last Synced: 2025-02-08T16:29:59.963Z (about 1 year ago)
- Topics: bci, eeg, pytorch, ssvep, transformer
- Language: Jupyter Notebook
- Homepage:
- Size: 19.5 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# SSVEPformer
A transformer-based model for SSVEP classifcation in EEG based Brain-Computer Interface (BCI)
Reproducing the paper [A transformer-based deep neural network model for SSVEP classification](https://www.sciencedirect.com/science/article/abs/pii/S0893608023002319) (https://arxiv.org/abs/2210.04172) [1] on Dataset 1 from Nakanishi et al.2015 [2]
We followed the same procedure in the paper in the 1st experiment on the same dataset and got same results. to reproduce the experiment check the colab notebook in this repo, it is a straighforward self contained tutorial.
# Requirements
- PyTorch
- Numpy
- Scipy
# Keras 3
A Keras 3 version with JAX backend is available (only the SSVEPFormer model) on the [Keras site](keras.io) examples section : [EEG BCI SSVEP Tutorial](https://keras.io/examples/timeseries/eeg_bci_ssvepformer/)
# References
[1] Chen, J. et al. (2023) ‘A transformer-based deep neural network model for SSVEP classification’, Neural Networks, 164, pp. 521–534. Available at: https://doi.org/10.1016/j.neunet.2023.04.045.
[2] Nakanishi, M. et al. (2015) ‘A Comparison Study of Canonical Correlation Analysis Based Methods for Detecting Steady-State Visual Evoked Potentials’, Plos One, 10(10), p. e0140703. Available at: https://doi.org/10.1371/journal.pone.0140703.
# Usage
feel free to use the code and build upon it, just mention this repo.