LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring
IEEE Transactions on Consumer Electronics · 2025-08 · 71 (3) · 7970-7982
DOI: 10.1109/tce.2025.3563341 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-08. Verfasst von Jingwei Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: First Batch of Industry–University Cooperation Collaborative Education Project, Ministry of Education of the People’s Republic of China, 2021, Minjiang University School-Level Scientific Research Project Funding.
Abstract (Originalsprache)
Driver drowsiness electroencephalogram (EEG) signal monitoring can promptly alert drivers of their drowsiness in edge-end Consumer Electronics (CE), thereby reducing the probability of traffic accidents. Graph convolutional networks (GCNs) have shown significant advancements in processing the non-stationary, time-varying, and non-Euclidean nature of EEG signals. However, the existing single-channel EEG adjacency graph construction process lacks interpretability, which hinders the ability of GCNs to effectively extract adjacency graph features, thus affecting the performance of drowsiness monitoring. To address this issue, we propose an edge-end Lightweight Dual Graph Convolutional Network (LDGCN). Specifically, we are the first to incorporate neurophysiological knowledge to design a Baseline Drowsiness Status Adjacency Graph (BDSAG), which characterizes driver drowsiness status. Additionally, to express more features within limited EEG data, we introduce the Augmented Graph-level Module (AGM). This module captures global and local information at the graph level, ensuring that BDSAG features remain intact while enhancing effective feature expression capability. To further enhance the application of CE, we apply Adaptive Pruning Optimization (APO) to the channels and neurons of LDGCN, which nearly halves the inference latency. Experiments on benchmark datasets demonstrate that LDGCN offers the best trade-off between monitoring performance and hardware resource utilization, outperforming existing state-of-the-art algorithms.
Förderung
- First Batch of Industry–University Cooperation Collaborative Education Project
- Ministry of Education of the People’s Republic of China, 2021
- Minjiang University School-Level Scientific Research Project Funding
- Minjiang University Introduced Talents Scientific Research Start-up Fund
- Digital Media Art, Key Laboratory of Sichuan Province, Sichuan Conservatory of Music
- Ministry of Education’s First Batch of Industry–University Cooperation Collaborative Education Projects in 2024
- Fujian Province Software Industry Technology Innovation Key Research and Industrialization Project (Second Batch), “AI Intelligent Modeling Platform Based on D…
- Putian Science and Technology Plan
Zitieren
APA
Huang, J., Wang, C., Huang, J., Fan, H., Grau, A., & Zhang, F. (2025). LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring. IEEE Transactions on Consumer Electronics, 71(3), 7970-7982. https://doi.org/10.1109/tce.2025.3563341
Vancouver
Huang J, Wang C, Huang J, Fan H, Grau A, Zhang F. LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring. IEEE Transactions on Consumer Electronics. 2025;71(3):7970-7982. doi:10.1109/tce.2025.3563341
BibTeX
@article{Huang2025,
author = {Huang, Jingwei and Wang, Chuansheng and Huang, Jiayan and Fan, Haoyi and Grau, Antoni and Zhang, Fuquan},
title = {LDGCN: An Edge-End Lightweight Dual GCN Based on Single-Channel EEG for Driver Drowsiness Monitoring},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {3},
pages = {7970--7982},
doi = {10.1109/tce.2025.3563341}
}
EUVIMED