SIESTA: A Spectral-Temporal Unified Framework for Robust Cross-Subject EEG Analysis
eScholarship (California Digital Library) · 18.06.2025
DOI: 10.48448/djcv-dg68 ↗Kurz gefasst
Fachartikel in der Zeitschrift eScholarship (California Digital Library), erschienen am 18.06.2025. Verfasst von Cognitive Science Society 2025 und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Electroencephalography (EEG) provides critical insights into brain activity, yet its inherent variability and nonstationary nature pose significant challenges for computational analysis, particularly in cross-subject generalization tasks. We present SIESTA (Spectral Invariant EEG-based Semi-causal Transform Architecture), a novel EEG foundation model that addresses these challenges through three key innovations: (1) VQGAN-based spectral tokenization capturing wavelet representation of EEG; (2) a dual-stream Transformer architecture pre-trained using a semi-causal generative modeling approach; and (3) Contrastive Invariant Fine-Tuning (CIFT), a label-free domain adaptation strategy that aligns feature distributions across subjects by integrating spectral-temporal dynamics. Pre-trained on over 32,900 hours of diverse EEG data, SIESTA achieves state-of-the-art performance in epilepsy monitoring, improves F1-score by $12.4 \%$ on scalp EEG and $8.7 \%$ on intracranial EEG, respectively. Beyond epilepsy, SIESTA demonstrates strong generalizability to non-epilepsy tasks, including motor imagery and sleep stage classification. These results validate that spectrotemporal integration and domain-invariant learning are fundamental for modeling cross-subject EEG variability, establishing new benchmarks for robust brain-computing systems.
Schlagwörter
Zitieren
APA
2025, C. S. S., Yu, Y., & Zheng, R. (2025). SIESTA: A Spectral-Temporal Unified Framework for Robust Cross-Subject EEG Analysis. eScholarship (California Digital Library). https://doi.org/10.48448/djcv-dg68
Vancouver
2025 CSS, Yu Y, Zheng R. SIESTA: A Spectral-Temporal Unified Framework for Robust Cross-Subject EEG Analysis. eScholarship (California Digital Library). 2025. doi:10.48448/djcv-dg68
BibTeX
@article{2025,
author = {2025, Cognitive Science Society and Yu, Yuguo and Zheng, Ruizhe},
title = {SIESTA: A Spectral-Temporal Unified Framework for Robust Cross-Subject EEG Analysis},
journal = {eScholarship (California Digital Library)},
year = {2025},
doi = {10.48448/djcv-dg68}
}
EUVIMED