Metraipolis › archive › dc_d00bdedf483e
Coordinate-conditioned detector-atom network for montage-agnostic EEG channel completion: zero-shot transfer and a regime map — arXiv:2609.30582
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30582
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:19:11.714Z
- SHA-256 of the archived text
b714242bd785b354efa4f1c8d936e819d4e0bddf12440f19c20882271e023bb8- Stable URL of this page
https://metraipolis.com/documento/dc_d00bdedf483e
How to cite
Coordinate-conditioned detector-atom network for montage-agnostic EEG channel completion: zero-shot transfer and a regime map — arXiv:2609.30582 — arXiv (en), https://arxiv.org/abs/2609.30582 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d00bdedf483e (Metraipolis archive dc_d00bdedf483e, sha256 b714242bd785b354efa4f1c8d936e819d4e0bddf12440f19c20882271e023bb8)
BibTeX
@misc{dcd00bdedf483e,
title = {Coordinate-conditioned detector-atom network for montage-agnostic EEG channel completion: zero-shot transfer and a regime map — arXiv:2609.30582},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30582},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d00bdedf483e; sha256 b714242bd785b354efa4f1c8d936e819d4e0bddf12440f19c20882271e023bb8},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30582. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
EEG electrode layouts differ across devices, from consumer headsets to 128-channel nets, and learned methods for completing missing electrodes assume a fixed layout and within-dataset training, so they cannot be applied to unseen devices. We propose the coordinate-conditioned detector-atom network (CC-DAN), a self-supervised convolutional dictionary model whose atoms are spherical-harmonic functions of electrode coordinates and whose detector pools observed electrodes with coordinate-dependent weights, making it independent of electrode number, order, and names. In a plug-and-play protocol, a single model pretrained on five public datasets (132 subjects) is applied zero-shot to nine held-out sets with 8 to 128 channels and compared with nearest-neighbor and spherical spline interpolation (SSI), a within-subject oracle, and learned baselines on signal error, band-wise error, and downstream tasks. With five or fewer observed electrodes, sparse real layouts, and hemispheric dropout, CC-DAN beats both interpolations in nearly all subjects and approaches the oracle; on the EGI net and 8- to 16-channel devices it keeps this advantage up to 15 electrodes, whereas SSI is superior with 15 or more electrodes on dense 10-05 montages. CC-DAN is also the most robust to electrode-position errors. Mean-squared-error gains do not carry over to downstream accuracy, and the amplitude shrinkage of MSE-optimal prediction degrades power-based measures, which a variance-matching loss and gain calibration mitigate. The resulting regime map tells practitioners where learned completion pays off and where classical interpolation remains the method of choice, and the plug-and-play protocol lets one pretrained model connect an unseen device to a fixed-montage pipeline without retraining. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in eess.SP). Categorie arXiv: Signal Processing (eess.SP). Pagina del lavoro: https://arxiv.org/abs/2609.30582 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T03:49:53.452Z dalla pagina https://arxiv.org/catchup/eess.SP/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).