Universal semantic feature extraction from EEG signals: a task-independent framework
Journal of Neural Engineering · 01.06.2025 · 22 (3) · 036003
DOI: 10.1088/1741-2552/add08f ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Neural Engineering, online erschienen am 06.05.2025. Verfasst von Hossein Ahmadi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Mathematical Biology and Physiology, Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Turin, Italy. Hauptthemen laut MEDLINE: Electroencephalography, Semantics, Brain-Computer Interfaces. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objective. Extracting universal, task-independent semantic features from electroencephalography (EEG) signals remains an open challenge. Traditional approaches are often task-specific, limiting their generalization across different EEG paradigms. This study aims to develop a robust, unsupervised framework for learning high-level, task-independent neural representations. Approach. We propose a novel framework integrating convolutional neural networks, AutoEncoders, and Transformers to extract both low-level spatiotemporal patterns and high-level semantic features from EEG signals. The model is trained in an unsupervised manner to ensure adaptability across diverse EEG paradigms, including motor imagery (MI), steady-state visually evoked potentials (SSVEPs), and event-related potentials (ERPs, specifically P300). Extensive analyses, including clustering, correlation, and ablation studies, are conducted to validate the quality and interpretability of the extracted features. Main results. Our method achieves state-of-the-art performance, with average classification accuracies of 83.50% and 84.84% on MI datasets (BCICIV_2a and BCICIV_2b), 98.41% and 99.66% on SSVEP datasets (Lee2019-SSVEP and Nakanishi2015), and an average AUC of 91.80% across eight ERP datasets. t-distributed stochastic neighbor embedding and clustering analyses reveal that the extracted features exhibit enhanced separability and structure compared to raw EEG data. Correlation studies confirm the framework’s ability to balance universal and subject-specific features, while ablation results highlight the near-optimality of the selected model configuration. Significance. This work establishes a universal framework for task-independent semantic feature extraction from EEG signals, bridging the gap between conventional feature engineering and modern deep learning methods. By providing robust, generalizable representations across diverse EEG paradigms, this approach lays the foundation for advanced brain–computer interface applications, cross-task EEG analysis, and future developments in semantic EEG processing.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Mathematical Biology and Physiology, Department of Electronics and Telecommunications, Politecnico di Torino, 10129 Turin, Italy.
ORCID-Profile: Hossein Ahmadi, Luca Mesin
Zitieren
APA
Ahmadi, H., & Mesin, L. (2025). Universal semantic feature extraction from EEG signals: a task-independent framework. Journal of Neural Engineering, 22(3), 036003. https://doi.org/10.1088/1741-2552/add08f
Vancouver
Ahmadi H, Mesin L. Universal semantic feature extraction from EEG signals: a task-independent framework. Journal of Neural Engineering. 2025;22(3):036003. doi:10.1088/1741-2552/add08f
BibTeX
@article{Ahmadi2025,
author = {Ahmadi, Hossein and Mesin, Luca},
title = {Universal semantic feature extraction from EEG signals: a task-independent framework},
journal = {Journal of Neural Engineering},
year = {2025},
volume = {22},
number = {3},
pages = {036003},
doi = {10.1088/1741-2552/add08f}
}
EUVIMED