Driving fatigue is a major contributor to traffic accidents and is characterized by its prevalence, concealment, and associated risks. It impairs drivers' physiological functions and depletes their psychological cognitive resources. Therefore, a comprehensive understanding of its underlying mechanisms, coupled with the development of accurate monitoring, early warning, and intervention technologies, is crucial to enhancing road safety. However, existing reviews often lack a systematic integration of research on fatigue mechanisms and advancements in associated monitoring and intervention technologies. To address this gap, this paper systematically reviews the causal factors and mechanistic hypotheses underlying fatigue and evaluates the current status of monitoring, warning, and intervention technologies. Current research indicates that multisource information fusion, which integrates physiological signals, visual imagery, and driving behavior data, significantly enhances the robustness and accuracy of fatigue detection compared to single-modality approaches. Meanwhile, early-warning and intervention strategies are evolving from passive monitoring toward active prediction, incorporating temporal analysis and contextual awareness. These strategies include the use of in-vehicle visual, auditory, and tactile stimuli; the development of autonomous vehicle takeover systems; and the optimization of road infrastructure design. This review synthesizes recent progress and emerging trends in the research on driving fatigue mechanisms and associated monitoring-warning technologies, and proposes integrated strategies to support effective fatigue management.

In physiological monitoring, electroencephalography remains the gold standard, with deep learning models such as convolutional neural network (CNN)-attention methods achieving accuracy rates of up to 97.8%. Electrocardiography and heart rate variability measurements are also widely used, but their applicability is limited by the intrusiveness of the sensors. Therefore, current research focuses on noninvasive alternatives such as photoplethysmography and miniaturized devices, although challenges such as motion artifacts and environmental interference persist. Visual monitoring leverages computer vision and deep learning, including CNNs and long short-term memory models, to analyze features such as eye closure percentage, yawn frequency, and head pose, achieving accuracy rates of up to 92.7%. However, its performance is susceptible to lighting conditions, occlusions, and individual differences, necessitating improvements in real-world robustness. Driving behavior monitoring uses data on vehicle dynamics such as steering wheel variability and lane deviation, and machine learning models trained on these data achieve accuracies of up to 91.2%. While this method is privacy-preserving and readily deployable, it suffers from detection latency and is influenced by road conditions and driving habits, which limit its effectiveness for early warning. Multisource data fusion overcomes these limitations by integrating physiological, visual, and behavioral data using architectures such as multicolumn CNNs, achieving superior accuracy. However, high computational demands, data heterogeneity, and model interpretability issues pose challenges for real-time deployment. In terms of warnings and interventions, conventional systems rely on real-time detection to trigger alerts. Current research is shifting focus toward proactive prediction using bio-mathematical models and recurrent neural networks, achieving accuracies of up to 88.2% in forecasting fatigue several minutes in advance. Large language models enable intelligent, adaptive dialogue for graded intervention, supporting integrated "monitoring-assessment-response" frameworks. Autonomous driving technologies, particularly conditional automation, can reduce fatigue by allowing drivers to perform non-driving tasks and by providing emergency vehicle takeover capabilities. Road design and managerial measures complement these technological solutions within a holistic "human-vehicle-road-environment- management" framework.

This review outlines the mechanisms underlying fatigue, the associated monitoring technologies, and intervention strategies to address fatigue, emphasizing the key role of multisource data fusion in improving fatigue detection accuracy. The shift from passive warning to proactive intervention, supported by artificial intelligence and autonomous systems, represents a critical technological pathway. However, challenges remain in areas such as the precision of real-time predictions, the comfort of wearable devices, and the computational efficiency of multisource data fusion models. Future research should prioritize dynamic mechanism modeling, cross-scenario adaptive algorithms, and human-machine collaborative intervention to develop more reliable and scalable fatigue mitigation solutions.

Decommissioning of nuclear facilities is a critical phase in the lifecycle of nuclear energy utilization, and the safety of the procedure directly impacts environmental and public health. As an increasing number of nuclear facilities worldwide near the end of their designed service life, the question of how to carry out safe and effective decommissioning has become an urgent issue to address. During this process, precisely evaluating the radioactive contamination of structural components is fundamental to formulating decommissioning plans and management measures. Although diverse source term survey methods exist, in practice, because of the inadequacy or inaccuracy of process data, it is frequently necessary to rely on radiation measurement techniques to obtain specific information on radioactive contamination. Therefore, this study aims to develop a measurement technology to enhance the accuracy of measuring the radioactivity distribution of structural components during the decommissioning of nuclear facilities, providing a scientific basis for the secure decommissioning of nuclear facilities.

This research employs a collimated gamma detector, which primarily consists of a gamma detector and a collimator. The collimator is used to limit the direction of incident rays to enhance the spatial resolution and sensitivity of the measurement. The structural components involved in the decommissioning of nuclear facilities can be categorized as flat plates and pipelines based on their geometric features, each requiring different scanning and measurement strategies. The scanning measurement techniques appropriate for flat panel structural components can be selected based on the contamination type. A circular scanning measurement method is adopted for pipe structural components. During the measurement process, the collimated gamma detector traverses the structural component surface, recording gamma-ray signals from all potentially contaminated areas and conducting preliminary analysis of the collected data to assess data quality and integrity. To determine the radioactivity distribution of the structural components from the measurement data, both equal-resolution reconstruction and super-resolution reconstruction methods are proposed. Equal-resolution reconstruction employs grid sizes that are identical to the collimator's aperture size for gridding the area under test, while super-resolution reconstruction uses grid sizes smaller than the collimator's aperture size to achieve higher resolution. Equal-resolution reconstruction is suitable for tasks requiring faster reconstruction speeds, and super-resolution reconstruction is suitable for tasks demanding higher resolution. Both methods are implemented through iterative algorithms.

The results demonstrate that the methods proposed are effective in measuring the radioactivity distribution of structural components during the decommissioning of nuclear facilities, with good position and angular resolution. By conducting Monte Carlo simulation validation, the relative deviation of the radioactivity derived by both the reconstruction methods is within 10%, and the position resolution at a detection distance of 60 cm derived by equal-resolution reconstruction and super-resolution reconstruction methods reached 3.2 mm and 1.6 mm, with corresponding angular resolutions of 0.3° and 0.2°.The average reconstruction speed of the super-resolution method is slower than that of the equal-resolution method. However, in practical applications, the appropriate reconstruction method that is most suitable for specific needs may be selected.

This study develops a measurement technology for radioactivity distribution based on a collimated gamma detector, providing a novel technical strategy for accurately measuring radioactivity in structural components during the decommissioning of nuclear facilities. The technology enhances the accuracy and resolution of measurements through systematic modeling and algorithm design, providing technical support for the secure decommissioning of nuclear facilities. Future research can further optimize the hardware parameters of the detector, which, when combined with this study's results, provide more comprehensive technical support for the secure decommissioning of nuclear facilities.