Search Results (54)

Level 2 driving automation requires continuous driver supervision, yet common attention metrics often capture gaze allocation rather than the structure of supervisory scanning. This study proposes a quantitative approach for describing supervisory gaze organisation using first-order Markov chain analysis of gaze transitions. Forty-three licensed drivers ($N=43$) completed a simulator drive with Level 2 automation for either 5 or 15 min (between-subjects), representing typical Japanese expressway intervals between service areas. Supervisory behaviour was analysed at the scenario level, without introducing secondary tasks, allowing attentional drift to emerge naturally under automation. Eye-tracking data were manually annotated frame-by-frame at 60 Hz and modelled as transition probability matrices across key Areas of Interest (AOIs): road centre, mirrors, periphery, and the human–machine interface. Compared with the 5 min condition, the 15 min condition showed fewer mirror-to-road-centre recovery transitions and slower System-Recognised Reaction Time (SRRT) at the takeover request. These patterns suggest a gradual weakening of supervisory gaze organisation rather than a simple loss of attention. The proposed framework offers a reproducible way to calibrate driver monitoring and evaluate human–machine interfaces by linking gaze transition probabilities to takeover readiness. By quantifying how supervisory behaviour reorganises under extended automation in realistic driving scenarios, this study provides a practical basis for the development of safety-relevant driver monitoring indicators in Level 2 driver assistance systems. Full article

With the rapid advancement of smart grids driven by renewable energy integration and the extensive deployment of supervisory control and data acquisition (SCADA) and phasor measurement units (PMUs), addressing the escalating alarm flooding via intelligent analysis of large-scale alarm data is pivotal to safeguarding the safe and stable operation of power grids. To tackle these challenges, this study introduces a pioneering alarm optimization framework based on symmetry-driven crowdsourced active learning and interpretable deep reinforcement learning (DRL). Firstly, an anomaly alarm annotation method integrating differentiated crowdsourcing and active learning is proposed to mitigate the inherent asymmetry in data distribution. Secondly, a symmetrically structured DRL-based hierarchical attention deep Q-network is designed with a dual-path encoder to balance the processing of multi-scale alarm features. Finally, a SHAP-driven interpretability framework is established, providing global and local attribution to enhance decision transparency. Experimental results on a real-world power alarm dataset demonstrate that the proposed method achieves a Fleiss’ Kappa of 0.82 in annotation consistency and an F1-Score of 0.95 in detection performance, significantly outperforming state-of-the-art baselines. Additionally, the false positive rate is reduced to 0.04, verifying the framework’s effectiveness in suppressing alarm flooding while maintaining high recall. Full article

This article focuses on the choice of the religious life for women during the early modern period, following a Rule that ensured harmony within the cloister. We trace the emergence of codes of life for female communities across time, with particular attention to the Rule of St. Benedict and its adoption by Cistercian communities, where silence assumed a particular significance. Silence, sounds, and monastic daily life as governed by the Rule, by the Tridentine decrees and, in the case of Portuguese Cistercian communities, obedience to the Autonomous Congregation of Alcobaça and to its supervisory mechanism of Visitations, were elements that shaped both the discourse presented here and its interpretive framework. While the Council of Trent emphasized the importance of vocation and simultaneously imposed upon women the so-called “fourth vow” (enclosure), documentary evidence allows us to observe to what extent the conventual milieu, composed of women from diverse social origins, remained engaged with the wider world outside cloister; nunneries became both a mode of existence and a space of affirmation for women, one that fostered creativity (in music, writing, painting) and upheld authority and power, embodied in the figure of the abbess and in the acts, rituals, and ceremonies associated with her. Full article

With the acceleration of digital transformation, open-source software has become a fundamental component of modern smart grids and other critical infrastructures. However, the complex dependency structures of open-source ecosystems and the continuous emergence of vulnerabilities pose substantial challenges to software supply chain security. In power information networks and cyber–physical control systems, vulnerabilities in open-source components integrated into Supervisory Control and Data Acquisition (SCADA), Energy Management System (EMS), and Distribution Management System (DMS) platforms and distributed energy controllers may propagate along the supply chain, threatening system security and operational stability. In such application scenarios, large language models (LLMs) often suffer from limited semantic accuracy when handling domain-specific security terminology, as well as deployment inefficiencies that hinder their practical adoption in critical infrastructure environments. To address these issues, this paper proposes KD-SecBERT, a domain-specific semantic bidirectional encoder optimized through multi-level knowledge distillation for open-source software supply chain security in smart grid applications. The proposed framework constructs a hierarchical multi-teacher ensemble that integrates general language understanding, cybersecurity-domain knowledge, and code semantic analysis, together with a lightweight student architecture based on depthwise separable convolutions and multi-head self-attention. In addition, a dynamic, multi-dimensional distillation strategy is introduced to jointly perform layer-wise representation alignment, ensemble knowledge fusion, and task-oriented optimization under a progressive curriculum learning scheme. Extensive experiments conducted on a multi-source dataset comprising National Vulnerability Database (NVD) and Common Vulnerabilities and Exposures (CVE) entries, security-related GitHub code, and Open Web Application Security Project (OWASP) test cases show that KD-SecBERT achieves an accuracy of 91.3%, a recall of 90.6%, and an F1-score of 89.2% on vulnerability classification tasks, indicating strong robustness in recognizing both common and low-frequency security semantics. These results demonstrate that KD-SecBERT provides an effective and practical solution for semantic analysis and software supply chain risk assessment in smart grids and other critical-infrastructure environments. Full article

Despite increasing attention to gender disparities in Science, Technology, Engineering, and Mathematics (STEM) fields, little is known about how these dynamics manifest within interdisciplinary public health domains such as Occupational Safety and Health (OSH). This study presents a bibliometric analysis of 144 empirical publications on work-related stress management interventions published between 1977 and 2023. Drawing from five major academic databases, we examine gender differences in authorship patterns, scientific productivity, citation impact, and collaboration patterns, with a focus on first, corresponding, and last authorship as indicators of contribution and leadership. Our findings reveal a significant increase in women’s participation over time, particularly in first authorship roles, while a persistent gender gap in senior and supervisory positions favors male researchers, in line with the leaky pipeline framework. Productivity, citation rates, and cooperation patterns suggest positive trends toward gender equity, though subtle structural disparities remain. We discuss implications for inclusive research environments, equitable authorship recognition, and the design of gender-sensitive science policy in occupational health. This study contributes to understanding the gendered contours of scientific influence within OSH and highlights the need for more inclusive academic ecosystems. Full article

The recent expansion of sustainability studies has reshaped corporate governance and public oversight with direct implications for financial exposure and risk management. In particular, environmental auditing generates decision-useful signals on environmental liabilities, remediation and compliance costs, and budgetary/fiscal risks that affect both corporate financing conditions (e.g., cost of capital) and public finance resilience. This study conducts a comparative examination of environmental auditing practices in Moldova and Bulgaria over 2020–2025, asking how audit mandates, coverage, and disclosure practices inform banks, insurers, investors, and budget holders. Using documents from national legal databases and supervisory portals, we apply descriptive content analysis across structural, substantive, and procedural dimensions, with special attention to financial-risk channels (contingent liabilities, sanction risk, value-for-money and procurement risks). We find that Bulgaria exhibits stronger institutional implementation capacity, while Moldova shows legislative innovation; in both cases, stronger transparency, public participation, and digital audit analytics are needed to quantify fiscal and enterprise-level ESG risks. Overall, this paper positions environmental auditing as a governance lever linking sustainability oversight to finance- and risk-related outcomes, aligning with focus on sustainable finance, ESG disclosure, and governance. Full article

Facing the challenges of scarce annotations in forward-looking sonar image segmentation, this paper proposes a teacher–student network for unsupervised domain adaptation. The proposed model undergoes supervised learning with optical image data to endow the student model with basic segmentation capabilities, using the segment anything model (SAM) as the teacher to generate pseudo-labels in the sonar image domain, thus achieving knowledge transfer without relying on annotated sonar images. An adaptive weighting approach is proposed, which generates a consistency map using predictive consistency in the source domain and the target domain to assess the quality of pseudo-labels. This method dynamically adjusts supervisory strength, preventing incorrect fitting caused by noisy pseudo-labels. In addition, a multi-scale attention module is designed to refine bottleneck features of the U-Net. The effectiveness of the proposed method is validated on a self-built public forward-looking sonar image dataset, achieving a mean intersection over union (IoU) of 40.8% and a mean average precision (mAP) of 70.3%, demonstrating significant improvements over existing typical UDA methods. Full article

Accurate reactive power optimization in wind farms (WFs) is critical for optimizing operations and ensuring grid stability, yet it faces challenges from noisy, nonlinear, and dynamic Supervisory Control and Data Acquisition (SCADA) data. This study proposes an innovative framework, WBS-BiGRU, integrating three novel components to address these issues. Firstly, the Wavelet-DBSCAN (WDBSCAN) method combines wavelet transform’s time–frequency analysis with density-based spatial clustering of applications with noise (DBSCAN)’s density-based clustering to effectively remove noise and outliers from complex WF datasets, leveraging multi-scale features for enhanced adaptability to non-stationary signals. Subsequently, a Boomerang Evolutionary Optimization (BAEO) with the Seasonal Decomposition Improved Process (SDIP) synergistically decomposes time series into trend, seasonal, and residual components, generating diverse candidate solutions to optimize data inputs. Finally, a Bidirectional Gated Recurrent Unit (BiGRU) network enhanced with an attention mechanism captures long-term dependencies in temporal data and dynamically focuses on key features, improving reactive power forecasting precision. The WBS-BiGRU framework significantly enhances forecasting accuracy and robustness, offering a reliable solution for WF operation optimization and equipment health management. Full article

Deep learning (DL) has revolutionized medical image analysis (MIA), enabling early anomaly detection, precise lesion segmentation, and automated disease classification. However, its clinical integration faces two major challenges: reliance on limited, narrowly annotated datasets that inadequately capture real-world patient diversity, and the inherent “black-box” nature of DL decision-making, which complicates physician scrutiny and accountability. Eye tracking (ET) technology offers a transformative solution by capturing radiologists’ gaze patterns to generate supervisory signals. These signals enhance DL models through two key mechanisms: providing weak supervision to improve feature recognition and diagnostic accuracy, particularly when labeled data are scarce, and enabling direct comparison between machine and human attention to bridge interpretability gaps and build clinician trust. This approach also extends effectively to multimodal learning models (MLMs) and vision–language models (VLMs), supporting the alignment of machine reasoning with clinical expertise by grounding visual observations in diagnostic context, refining attention mechanisms, and validating complex decision pathways. Conducted in accordance with the PRISMA statement and registered in PROSPERO (ID: CRD42024569630), this review synthesizes state-of-the-art strategies for ET-DL integration. We further propose a unified framework in which ET innovatively serves as a data efficiency optimizer, a model interpretability validator, and a multimodal alignment supervisor. This framework paves the way for clinician-centered AI systems that prioritize verifiable reasoning, seamless workflow integration, and intelligible performance, thereby addressing key implementation barriers and outlining a path for future clinical deployment. Full article

Gearbox failure represents one of the most time-consuming maintenance challenges in wind turbine operations. Abnormal temperature variations in the gearbox high-speed shaft (GHSS) serve as reliable indicators of potential faults. This study proposes a Spatio-Temporal Attentive (STA) synergistic architecture for GHSS fault detection and early warning by utilizing the in situ monitoring data from a wind farm. This comprehensive architecture involves five modules: data preprocessing, multi-dimensional spatial feature extraction, temporal dependency modeling, global relationship learning, and hyperparameter optimization. It was achieved by using real-time monitoring data to predict the GHSS temperature in 10 min, with an accuracy of 1 °C. Compared to the long short-term memory (LSTM) and convolutional neural network and LSTM hybrid models, the STA architecture reduces the root mean square error of the prediction by approximately 37% and 13%, respectively. Furthermore, the architecture establishes a normal operating condition model and provides benchmark eigenvalues for subsequent fault warnings. The model was validated to issue early warnings up to seven hours before the fault alert is triggered by the supervisory control and data acquisition system of the wind turbine. By offering reliable, cost-effective prognostics without additional hardware, this approach significantly improves wind turbine health management and fault prevention. Full article

In Supervisory Control and Data Acquisition (SCADA) systems, central to industrial automation and control systems, the Front-end Processor (FEP) facilitates seamless communication between field control devices and central management systems. As the Industrial Internet of Things (IIoT) and Industry 4.0 centered on the smart factory paradigm gain traction, conventional FEPs are increasingly showing limitations in various aspects. To address these issues, Data Distribution Service, a real-time communication middleware, and Kubernetes, a container orchestration platform, have garnered attention. However, the effective integration of conventional SCADA protocols, such as DNP3.0, IEC 61850, and Modbus with DDS, remains a key challenge. Therefore, this article proposes a Kubernetes-based real-time FEP for the modernization of SCADA systems. The proposed FEP ensures interoperability through an efficient translation mechanism between traditional SCADA protocols—DNP3.0, IEC 61850, and Modbus—and the Data Distribution Service protocol. In addition, the performance evaluation shows that the FEP achieves high throughput and sub-millisecond latency, confirming its suitability for real-time industrial control applications. This approach overcomes the limitations of conventional FEPs and enables the realization of more flexible and scalable industrial control systems. However, further research is needed to validate the system under large-scale deployment scenarios and enhance security capabilities. Future work will focus on performance evaluation in realistic conditions and the integration of quantum-resistant security mechanisms to strengthen resilience in critical infrastructure environments. Full article

Industrial control systems (ICSs) are a critical component of key infrastructure. However, as ICSs transition from isolated systems to modern networked environments, they face increasing security risks. Traditional anomaly detection methods struggle with complex ICS traffic due to their failure to fully utilize both low-frequency and high-frequency traffic information, and their poor performance in heterogeneous and non-stationary data environments. Moreover, fixed threshold methods lack adaptability and fail to respond in real time to dynamic changes in traffic, resulting in false positives and false negatives. To address these issues, this paper proposes a deep learning-based traffic anomaly detection algorithm. The algorithm employs the Hilbert–Huang Transform (HHT) to decompose traffic features and extract multi-frequency information. By integrating feature and temporal attention mechanisms, it enhances modeling capabilities and improves prediction accuracy. Additionally, the deep probabilistic estimation approach dynamically adjusts confidence intervals, enabling synchronized prediction and detection, which significantly enhances both real-time performance and accuracy. Experimental results demonstrate that our method outperforms existing baseline models in both prediction and anomaly detection performance on a real-world industrial control traffic dataset collected from an oilfield in China. The dataset consists of approximately 260,000 records covering Transmission Control Protocol/User Datagram Protocol (TCP/UDP) traffic between Remote Terminal Unit (RTU), Programmable Logic Controller (PLC), and Supervisory Control and Data Acquisition (SCADA) devices. This study has practical implications for improving the cybersecurity of ICSs and provides a theoretical foundation for the efficient management of industrial control networks. Full article

Addressing the challenges and significant risks associated with diagnosing faults in wind turbine yaw systems, along with the typically low diagnostic accuracy, this study introduces a Long Short-Term Memory (LSTM) neural network augmented by a self-attention mechanism (SAM) as a novel fault diagnosis technique for wind turbine yaw systems. The method integrates the automatic weighting capability of the self-attention mechanism on input features with the advantage of LSTM in processing time series data, thereby effectively capturing key information and long-term dependencies in the operating data of the yawing system. This combination enhances the accuracy of fault feature extraction to more accurately identify various types of fault modes within the yawing system. Six types of feature parameters are extracted from the raw data collected by the SCADA (Supervisory Control And Data Acquisition) system of the wind turbine and are utilized as inputs for the diagnostic model. These parameters are then fed into the self-attention–LSTM neural network model to diagnose the health status of the yaw system, including yaw bearing damage, yaw gearbox failure, yaw motor failure, and sensor failure. The experimental results demonstrate that the accuracy of LSTM fault diagnosis, when enhanced with the self-attention mechanism, can reach 98.67% with an appropriate amount of training samples, verifying its significant advantages in terms of accuracy and stability of fault diagnosis. The proposed fault diagnosis method exhibits a better model fitting effect, strong generalization ability, and high accuracy compared to other methods, providing robust support for the reliable operation and maintenance of wind turbines. Full article

Face images hold exceptional significance in contemporary society, serving as direct identifiers due to their rich personal attributes, enhancing daily life and work efficiency. However, advancements in deep learning and image processing have led to the proliferation of sophisticated face forgery software, rendering detection increasingly challenging. We propose a novel face tampering detection method utilizing a spatial attention-enhanced bidirectional convolutional neural network to address this. This approach synergizes the strengths of dense convolutional and depthwise separable networks for superior image feature extraction, thereby improving the accuracy of authentic and manipulated face detection. Furthermore, the network is trained to initially localize tampered regions within face images by integrating a spatial channel-based attention module as supervisory input. On three widely used public face forgery datasets, our method achieves an AUC of no less than 96.45%. The experimental results validate the effectiveness of our method in accurately detecting and initially localizing face tampering. Full article

The optimization of the efficiency of wind turbine systems is a fundamental task, from the perspective of a growing share of electricity produced from wind. Despite this, and given the complex multivariate dependence of the power of wind turbines on environmental conditions and working parameters, the literature is lacking studies specifically devoted to a careful characterization of wind farm performance. In particular, in the literature, it is overlooked that there are several types of faults which have similar manifestations and that can be defined as static errors. This kind of error manifests as a static bias occurring from a certain time onward, which can affect the anemometer, the absolute or relative pitch of the blades, or the yaw system. Static or systematic errors typically do not cause the functional failure of the wind turbine system, but they deserve attention due to the fact that they cause power production loss throughout the operation time. Based on this, the first objective of the present study is a critical review of the recent papers devoted to three types of wind turbine static errors: anemometer bias, static yaw error, and pitch misalignment. As a result, a comprehensive viewpoint, enhancing the state of the art in the literature, is developed in this study. Given that the use of data collected by Supervisory Control And Data Acquisition (SCADA) systems has, up to now, been prevailing for the diagnosis of systematic errors compared to the use of further specific sensors, particular attention in the present study is thus devoted to the discussion of the phenomena which can be observable through SCADA data analysis. Based on this, finally, a rigorous work flow is formulated for detecting static errors and discriminating among them through SCADA data analysis. Nevertheless, methods based on additional information sources (like further sensors or meteorological data) are also discussed. An important aspect of this study is that, for each considered type of systematic error, some previously unpublished results based on real-world SCADA data are reported in order to corroborate the proposed framework. Summarizing, then, the present is the first paper which considers and discusses several types of wind turbine static errors in a unified viewpoint, correctly interprets apparently controversial results collected in the literature, and finally provides guidelines for the diagnosis of this kind of error and for the quantification of the performance drop associated with their presence. Full article