EEGDiffuser

Label-guided EEG signals synthesis via diffusion model for BCI applications

🔍 About | 🔨 Setup | 🚢 Train | 🔗 Citation

🔥 NEWS: The paper "EEGDiffuser: Label-guided EEG signals synthesis via diffusion model for BCI applications" has been accepted by Neurocomputing!

🔍 About

We propose EEGDiffuser, a label-conditioned diffusion model for generating EEG signals to alleviate data scarcity in BCI.

🔨 Setup

Install Python.

Install PyTorch.

Install other requirements:

pip install -r requirements.txt

🚢 Train

You can train EEGDiffuser on our dataset or your custom dataset using the following code:

python diff_main.py

🔗 Citation

If you're using this repository in your research or applications, please cite using the following BibTeX:

@article{wang2026eegdiffuser,
  title={EEGDiffuser: Label-guided EEG signals synthesis via diffusion model for BCI applications},
  author={Wang, Jiquan and Zhao, Sha and Luo, Zhiling and Zhou, Yangxuan and Li, Shijian and Pan, Gang},
  journal={Neurocomputing},
  pages={132636},
  year={2026},
  publisher={Elsevier}
}