Efficient vigilance estimation in driving scenarios requires a balance between model performance and practicality. Electroencephalography (EEG), which can directly reflect brain activity, is widely used for vigilance estimation, but its acquisition process is complicated and difficult to apply to real-world driving. In contrast, physiological signals such as electrooculogram, electrodermal activity, and photoplethysmography have more advantages for practical deployment, but the information they provide is relatively limited. To address the above issues, we propose a delay-aware cross-modal knowledge distillation method. EEG signals are only used to train the teacher model. Then, an information-theoretic criterion based on mutual information and response delay is employed to determine which physiological signals are suitable as student modality for knowledge distillation from the EEG-based teacher model. On this basis, considering the inherent temporal differences caused by different physiological signals with varying sensitivities to cognitive responses, a delay-aware soft alignment mechanism (DASA) is proposed, which handles the temporal misalignment of different physiological signals and captures the asynchronous dynamics of the EEG and other physiological signals through the introduction of learnable delay and spread parameters at the patch level, to achieve soft, temporally-aligned supervision from the teacher to the student model. Finally, an objective function incorporating cross-modal consistency, patch level alignment, and smooth regularization is designed to support the effective training of the proposed cross-modal knowledge distillation method. Extensive experiments on MMV and SEED-VIG datasets validates that the proposed method outperforms existing methods in terms of estimation accuracy and temporal alignment while maintaining the real-time performance required for edge deployment.

Ensuring timely task execution in multiprocessor systems under Global Fixed-Priority Scheduling (GFPS) remains a significant challenge. While traditional heuristic methods often struggle to derive feasible priority assignments for complex task sets, existing Deep Reinforcement Learning (DRL) approaches—though more powerful—suffer from two key limitations: (1) they fail to adequately capture relative priorities among high-priority tasks during encoding, and (2) their convergence to suboptimal policies due to sensitivity to local reward signals, an inherent drawback of reinforcement learning frameworks. To overcome these issues, we propose PAGFN, a novel learning-based framework that combines Priority-Aware Attention with Generative Flow Networks. We formulate the priority assignment problem as a Markov Decision Process (MDP) and employ an encoder-decoder architecture with auto-regressive decoding. Our framework introduces a priority-aware module to explicitly model task dependencies, enhancing assignment quality. Additionally, to mitigate sparse rewards, we integrate expert pretraining and prioritized experience replay, enabling diverse policy exploration without relying on intricate reward shaping. Experimental results on synthetic tasks show that PAGFN outperforms heuristic and learning-based baselines, particularly in scheduling previously unschedulable tasks, validating its effectiveness and scalability.

The coordinated operation of multiple connected autonomous vehicles (CAVs) is conducive to resolving the bottleneck problem in on-ramp merging areas. However, achieving cooperation under the interference of connected manual vehicles (CMVs) remains challenging. This study integrates lane volume balancing and game theory, developing a regional cooperative decision-making model based on coalition game (RCD-CG) in mixed traffic. First, a progressive cooperation method is proposed, and multiple cooperative regions are designed in the merging area and its upstream section with dynamically adjustable boundaries in response to the time-varying traffic flow. Second, within these regions, CAVs form a coalition to maximize overall efficiency while ensuring safety. Additionally, considering the influence of CMVs outside the coalition on the cooperation of multiple CAVs, the payoffs of CMVs with different driving styles are quantified to solve non-cooperative games between CAVs and CMVs. To validate the model, simulations are conducted on an on-ramp merging scenario with a three-lane mainline, comparing the performance of RCD-CG with other methods across varying CAV penetration, traffic demand, and lane flow unevenness. The results demonstrate that under medium and high CAV penetrations and on-ramp demands, the use of the RCD-CG offers clear benefits in terms of efficiency, with the average speed increase rates reaching 23.2%.

Coal and gas outbursts classification has become more important than before due to the serious threat to the safety of coal production, in this paper, we proposed a novel combination model consists of feature decomposition and reconstruction, feature selection and feature extraction for classification of coal and gas outbursts. First, EMD is used to decompose the coal and gas outbursts index features into a number of different IMFS; Second, in order to find out the relevance of IMFS with regard to the features, a wrapper algorithm Boruta with the RF classifier is employed, and the IMFS which has high relevance with the feature are selected to form a new index feature, then the new obtained features construct new influencing factors that affect coal and gas outbursts; Furtherly, in order to eliminate the redundancy between the new generated features and the uncorrelation between the index features and outbursts, the LDA is used to extract the features with class differentiation. Finally, the SVM classifiers based on the optimal parameters by Bayesian optimisation algorithm is employed to evaluate the proposed feature extraction scheme. Experimental results show that the proposed comprehensive model can achieve significant performance in terms of classification accuracy and feature size compared to existing methods for coal and gas outbursts classification.