This complete and detailed example compares the classification performance of linear support vector machine (LinearSVC) on the Riemannian Transfer Learning method (RPA, Rodrigues et al., 2018) and the golden-standard subject-wise train-test cross-validation method using real P300 BCI data. It is very easy to understand and replicable. All the plots and table you will need are already given in both files.
- Make sure that the code is at least running on Python 3.11
- All the required packages (with compatible versions) and details are provided in Full-TL-Example.ipynb and FindSource.ipynb files
Fahim Doumi is a Master's student at Université Jean Monnet, Saint-Etienne and was an intern at GIPSA Lab, Grenoble. Contact : fahim.doumi@outlook.fr
Fatih Altindis is a Research Assistant at Abdullah Gul Univeristy, Kayseri. Contact : fthaltindis@gmail.com
Marco Congedo, is a Research Director of CNRS (Centre National de la Recherche Scientifique), working at UGA (University of Grenoble Alpes). Contact : marco.congedo@gipsa-lab.grenoble-inp.fr
This project is licensed under the BSD 3-Clause
P.L.C. Rodrigues, C. Jutten, M. Congedo (2018) Riemannian procrustes analysis: transfer learning for brain–computer interfaces IEEE Transactions on Biomedical Engineering, 66, 8, 2390-2401. pdf: https://hal.science/hal-01971856/document