Reconstructed EEG windows from BCI Competition IV Dataset 1 using EEGReXferNet

This dataset provides reconstructed EEG windows from BCI Competition IV Dataset 1, created using EEGReXferNet, a lightweight AI framework for EEG subspace reconstruction via cross-subject transfer learning and channel-aware embedding.The repository for the framework is available on GitHub: https://github.com/ShanSarkar75/EEGReXferNet/<b>Dataset Structure:</b><pre><pre>data/<br>└── BCICIV/<br> ├── ds1a/<br> │ └── Recon/c0/ # Reconstructed EEG windows (.npz)<br> ├── ds1b/<br> │ └── Recon/c0/<br> ├── ds1f/<br> │ └── Recon/c0/<br> └── ds1g/<br> └── Recon/c0/<br></pre></pre>Each subject-specific folder contains reconstructed EEG windows in <code>.npz</code> format.Files are organized by <b>subject</b>, <b>model type (A, B, C, D)</b>, and <b>window type</b>:Clean windowsNoisy windows (<code>&gt; ±3.5 σ</code>)<b>Note: </b>Due to GitHub file size limitations, reconstructed EEG windows are shared via FigShare. Users are encouraged to download the relevant files before performing model/data analysis or validation.<b>Citation:</b><br>If you use this data in your research, please cite:<br>@article {Sarkar2025EEGReXferNet, author = {Shantanu Sarkar and Piotr Nabrzyski and Saurabh Prasad and Jose Luis Contreras-Vidal}, title = {‘EEGReXferNet’ – A Lightweight Gen-AI Framework for EEG Subspace Reconstruction via Cross-Subject Transfer Learning and Channel-Aware Embedding}, year = {2025}, note = {Preprint},}<pre><b>Acknowledgment:</b> This work uses data from <b>BCI Competition IV Dataset 1</b> [1].<br></pre><pre><br><b>References:</b><br>[1] Blankertz, B., Dornhege, G., Krauledat, M., Müller, K.-R., &amp; Curio, G. (2007). <i>The non-invasive Berlin Brain-Computer Interface: Fast acquisition of effective performance in untrained subjects.</i> NeuroImage, 37(2), 539–550. DOI: https://doi.org/10.1016/j.neuroimage.2007.01.051</pre><br>