Bidirectional Temporal Dynamics Modeling for EEG-based Driving Fatigue Recognition

2026-02-15

AI Summary

This work proposes DeltaGateNet, a novel framework addressing the performance limitations in driving fatigue detection caused by the non-stationarity of EEG signals and the asymmetric dynamics of neural activity. The method introduces a bidirectional Delta module that explicitly models positive and negative temporal differences to decouple neural activation and inhibition patterns. Integrated with channel-specific gated temporal convolution and depthwise separable convolution, the architecture effectively captures long-range dependencies and temporal dynamics across multiple EEG channels. Evaluated on the SEED-VIG and SADT datasets, DeltaGateNet achieves an intra-subject accuracy of 96.84% and an inter-subject accuracy of 84.49%, significantly outperforming existing approaches. The model demonstrates superior robustness and generalization, particularly in cross-subject settings and under class imbalance conditions.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Driving fatigue is a major contributor to traffic accidents and poses a serious threat to road safety. Electroencephalography (EEG) provides a direct measurement of neural activity, yet EEG-based fatigue recognition is hindered by strong non-stationarity and asymmetric neural dynamics. To address these challenges, we propose DeltaGateNet, a novel framework that explicitly captures Bidirectional temporal dynamics for EEG-based driving fatigue recognition. Our key idea is to introduce a Bidirectional Delta module that decomposes first-order temporal differences into positive and negative components, enabling explicit modeling of asymmetric neural activation and suppression patterns. Furthermore, we design a Gated Temporal Convolution module to capture long-term temporal dependencies for each EEG channel using depthwise temporal convolutions and residual learning, preserving channel-wise specificity while enhancing temporal representation robustness. Extensive experiments conducted under both intra-subject and inter-subject evaluation settings on the public SEED-VIG and SADT driving fatigue datasets demonstrate that DeltaGateNet consistently outperforms existing methods. On SEED-VIG, DeltaGateNet achieves an intra-subject accuracy of 81.89% and an inter-subject accuracy of 55.55%. On the balanced SADT 2022 dataset, it attains intra-subject and inter-subject accuracies of 96.81% and 83.21%, respectively, while on the unbalanced SADT 2952 dataset, it achieves 96.84% intra-subject and 84.49% inter-subject accuracy. These results indicate that explicitly modeling Bidirectional temporal dynamics yields robust and generalizable performance under varying subject and class-distribution conditions.

Problem

• EEG
• driving fatigue recognition
• non-stationarity
• asymmetric neural dynamics
• temporal dynamics

Innovation

• Bidirectional Temporal Dynamics
• DeltaGateNet
• Asymmetric Neural Dynamics
• Gated Temporal Convolution
• EEG-based Fatigue Recognition