Modality-Aware Spectral Alignment for Personalized Federated EEG–Gaze Learning
IEEE Signal Processing Letters · 2026 · 33 · 4246-4250
DOI: 10.1109/lsp.2026.3743024 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Seo-Yeon Choi und 1 weiteren Autor:innen. Die Arbeit nennt 21 Literaturangaben. Gefördert von: Jeonbuk National University, National IT Industry Promotion Agency.
Abstract (Originalsprache)
Objective evaluation of robot-assisted surgery performance can benefit from multimodal physiological and visual measurements, but strong subject heterogeneity limits centralized and standard federated models. In this letter, we propose FedAlign-RAS, a personalized federated framework for multimodal surgical performance prediction using electroencephalography (EEG) and eye-gaze signals. The proposed method combines globally shared EEG and gaze encoders with lightweight client-local spectral and temporal alignment modules to compensate for subject-specific EEG shifts and cross-modal mismatch. We use the PhysioNet EEG-eye-gaze dataset for robot-assisted surgery performance evaluation as the main benchmark and leverage a public consumer-grade EEG–eye-tracking dataset for auxiliary pretraining. Experimental results show that the proposed approach improves performance prediction over centralized, local-only, and standard federated baselines. These findings suggest that subject-specific spectral-temporal personalization is an effective strategy for multimodal surgical skill assessment with raw EEG and gaze data kept local.
Förderung
- Jeonbuk National University
- National IT Industry Promotion Agency
Zitieren
APA
Choi, S., & Lee, K. (2026). Modality-Aware Spectral Alignment for Personalized Federated EEG–Gaze Learning. IEEE Signal Processing Letters, 33, 4246-4250. https://doi.org/10.1109/lsp.2026.3743024
Vancouver
Choi S, Lee K. Modality-Aware Spectral Alignment for Personalized Federated EEG–Gaze Learning. IEEE Signal Processing Letters. 2026;33:4246-4250. doi:10.1109/lsp.2026.3743024
BibTeX
@article{Choi2026,
author = {Choi, Seo-Yeon and Lee, Kyungsu},
title = {Modality-Aware Spectral Alignment for Personalized Federated EEG–Gaze Learning},
journal = {IEEE Signal Processing Letters},
year = {2026},
volume = {33},
pages = {4246--4250},
doi = {10.1109/lsp.2026.3743024}
}
EUVIMED