For more details about the GEDAI algorithm, please refer to the MATLAB implementation.
For standard CPU usage without heavy dependencies (~50 MB download):
pip install gedaiFor accelerated performance (up to 2.2x faster execution via vectorized PyTorch linear algebra):
pip install "gedai[torch]"Note:
gedaidefaults toengine="auto". If PyTorch is installed, acceleration is used automatically; otherwise, it falls back cleanly to NumPy.Tip for CPU-only systems: If you only need CPU acceleration on Windows/Linux and want to avoid downloading large GPU/CUDA binaries (~2 GB), install the lightweight PyTorch CPU wheel:
pip install torch --index-url https://download.pytorch.org/whl/cpu pip install gedai
Detailed documentation can be found on GEDAI website.
If you use GEDAI in your research, please cite the original publication:
Return of the GEDAI: Unsupervised EEG Denoising based on Leadfield Filtering (2025) [bioRxiv]. [DOI/Link to paper]
Ros, T, Férat, V., Huang, Y., Colangelo, C., Kia S.M., Wolfers T., Vulliemoz, S., & Michela, A.
As well as the specific version numbers of the software using the DOI provided by Zenodo.
You may use this software under the terms of the PolyForm Noncommercial License 1.0.0 LICENSE. This is suitable for personal use, research, or evaluation.
Commercial License
If you wish to use this software in a commercial or proprietary application without being bound by terms of the PolyForm Noncommercial License 1.0.0, you must purchase a commercial license. The core algorithms in this repository are the subject of a pending patent application, and a commercial license includes a grant for patent rights.
For any questions or enquiries, please contact: Tomas Ros - tomas.ros@unige.ch Victor Férat: victor.ferat@fcbg.ch
We are gratefully supported by the Center for Biomedical Imaging (CIBM), the Swiss National Science Foundation (SNSF), Unitec and the M/EEG & NMOD Platform, Fondation Campus Biotech Geneva, Geneva,.
