Lightweight EEG Phase Prediction Based on Channel Attention and Spatio-Temporal Parallel Processing
Brain Sciences · 22.12.2025 · 16 (1) · 11
DOI: 10.3390/brainsci16010011 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain Sciences, online erschienen am 22.12.2025. Verfasst von Shufei Duan und 4 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Shanxi University of Electronic Science and Technology, Linfen 041000, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Youth Fund of the National Natural Science Foundation of China, the Shanxi Scholarship Council of China, the Natural Science Foundation of Shanxi Province.
Abstract (Originalsprache)
Background/Objectives: Closed-loop phase-locked TMS aims to deliver stimulation at targeted EEG phases, but real-time phase prediction remains a practical bottleneck. Timing errors are especially harmful near peaks and troughs, where small offsets can substantially degrade phase targeting. We benchmark representative predictors and develop models that improve phase consistency while reducing peak/trough lag.
Methods
Using the publicly available Monash University TEPs–MEPs dataset, we benchmark classical predictors (AR- and FFT-based) and recurrent baselines (LSTM, GRU). To quantify extremum-specific behavior critical for closed-loop triggering, we propose Mean Lag Time (MLT), defined as the average temporal offset between predicted and ground-truth extrema, alongside PLV, APE, MAE, and RMSE. We further propose a parallel DSC-Attention-GRU architecture combining depthwise separable convolutions for efficient multi-channel spatio-temporal feature extraction with self-attention for spatial reweighting and dependency modeling, followed by a GRU phase predictor. A lightweight SqueezeNet-Attention-GRU variant is also designed for real-time constraints.
Results
LSTM/GRU outperform AR/FFT in capturing temporal dynamics but retain residual peak/trough lag. Across stimulation intensities and frequency bands, DSC-Attention-GRU consistently improves phase consistency and prediction accuracy and reduces extremum lag, lowering MLT from ~7.77–7.79 ms to ~7.50–7.56 ms. The lightweight variant maintains stable performance with an average 3.7% inference speedup.
Conclusions
Explicitly optimizing extremum timing via MLT and enhancing multi-channel modeling with DSC and attention reduces peak/trough lag and improves phase-consistent prediction, supporting low-latency closed-loop phase-locked TMS.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science and Technology, Shanxi University of Electronic Science and Technology, Linfen 041000, China.
- College of Electronic Information Engineering, Taiyuan University of Technology, Jinzhong 030600, China.
- School of Computing, Newcastle University, Newcastle NE1 7RU, UK.
ORCID-Profile: Shufei Duan
Förderung
- the Youth Fund of the National Natural Science Foundation of China
- the Shanxi Scholarship Council of China
- the Natural Science Foundation of Shanxi Province
- the Startup Fund of Shanxi University of Electronic Science and Technology
- Youth Fund of the National Natural Science Foundation of China
- Shanxi Scholarship Council of China
- Natural Science Foundation of Shanxi Province, China
- Startup Fund of Shanxi University of Electronic Science and Technology
Zitieren
APA
Duan, S., Yan, Y., Guo, Q., Li, F., & Liang, H. (2025). Lightweight EEG Phase Prediction Based on Channel Attention and Spatio-Temporal Parallel Processing. Brain Sciences, 16(1), 11. https://doi.org/10.3390/brainsci16010011
Vancouver
Duan S, Yan Y, Guo Q, Li F, Liang H. Lightweight EEG Phase Prediction Based on Channel Attention and Spatio-Temporal Parallel Processing. Brain Sciences. 2025;16(1):11. doi:10.3390/brainsci16010011
BibTeX
@article{Duan2025,
author = {Duan, Shufei and Yan, Yuting and Guo, Qianrong and Li, Fujiang and Liang, Huizhi},
title = {Lightweight EEG Phase Prediction Based on Channel Attention and Spatio-Temporal Parallel Processing},
journal = {Brain Sciences},
year = {2025},
volume = {16},
number = {1},
pages = {11},
doi = {10.3390/brainsci16010011}
}
EUVIMED