Search Results (17,496)

Reliable vision-based sensing of protective equipment wearing compliance is essential for safety monitoring in underground mining environments, where complex lighting conditions, similar background textures, and large variations in the scale of wearable items significantly degrade detection performance. To address these challenges, this study proposes a vision-based protective equipment wearing compliance detection method for underground personnel based on CGALS-YOLO. Traditional object detection models often introduce substantial redundant background information during multi-scale feature fusion, which weakens the perception of key wearing regions, particularly for small-scale targets. To alleviate this issue, a content-guided feature fusion (CGAFusion) module is incorporated into the neck of the YOLOv8 network, enabling adaptive fusion of same-scale multi-path features through the collaborative effects of channel, spatial, and pixel attention mechanisms. This design enhances target-related feature representation while suppressing background interference in complex underground scenes. Furthermore, to reduce parameter redundancy and improve cross-scale discrimination consistency in the detection head, a lightweight shared convolution detection (LSCD) structure is introduced. By employing cross-scale shared convolution parameters, group normalization, and scale-adaptive regression, the proposed model achieves a parameter reduction of approximately 23.9% while lowering computational complexity and maintaining stable multi-scale detection performance. Experimental results on an underground protective equipment wearing compliance dataset demonstrate that CGALS-YOLO improves detection accuracy by approximately 4.6% and recall by 3.1% compared with the baseline YOLOv8n, achieving an mAP@0.5 of 89.4%. These results validate the effectiveness and practical applicability of the proposed method for real-time vision-based safety monitoring in underground environments. Full article

Attribute-based encryption (ABE) provides a robust mechanism for fine-grained access control, making it an ideal candidate for secure cloud data sharing. However, existing schemes often incur significant computational overhead, hindering their large-scale deployment, especially on resource-constrained nodes. In this work, we propose a practical ABE scheme that simultaneously simplifies access policy structures and enhances overall efficiency. By introducing a weighted access policy, our scheme achieves rich expressiveness while maintaining a compact logic structure, offering enhanced flexibility through the redefinability of attribute weights. Notably, the proposed construction is pairing-free and yields small-size ciphertexts and private keys compared to traditional tree-based models. Security analysis demonstrates that our scheme is selectively secure against chosen-ciphertext attacks. Extensive simulation results show that encryption and decryption latency is reduced to nearly 10 ms when 20 attributes are involved, which is a typical requirement in cloud data sharing scenarios. This validates the efficiency of our scheme in resource-constrained environments. Full article

Regional flood frequency analysis (RFFA) is a cornerstone for estimating design floods at ungauged or data-scarce sites by pooling information within hydrologically homogeneous regions. This study proposes and evaluates a hybrid RFFA framework that integrates the Index-Flood (IF) technique with a bivariate logistic extreme-value model whose marginal distributions are formulated under both stationary and non-stationary assumptions. Non-stationarity is incorporated through a covariate-dependent location parameter, using time and large-scale climate indices—the Pacific Decadal Oscillation (PDO) and the Southern Oscillation Index (SOI)—as explanatory variables. The proposed approach is applied to two contrasting hydrological regions in Mexico—RH10 (Sinaloa) and RH23 (Chiapas Coast)—to assess its performance under differing climatic and hydrological regimes. Model adequacy and stability are evaluated using likelihood-based goodness-of-fit criteria (log-likelihood and Akaike Information Criterion) and a leave-one-out (jackknife) cross-validation scheme embedded within the IF regionalization workflow. Results indicate that non-stationary bivariate formulations dominate model selection at most stations and yield stable regional growth curves, providing robust and engineering-relevant performance under cross-validation. Overall, the proposed framework offers a conservative and operational pathway for regional flood quantile estimation that bridges local data scarcity and regional hydrological characterization in environments influenced by climate variability and long-term change. Full article

The Ieodo plume is a distinctive suspended sediment plume near the Ieodo Ocean Research Station (I-ORS), located in the middle of the northern East China Sea. Because the Ieodo plume exhibits multiple different spatial scales, this study conducted an integrated remote sensing observation using satellites and unmanned aerial vehicles (UAVs) to observe its development and dispersion. Sentinel-2 and Geostationary Ocean Color Imager-II (GOCI-II) data were used to determine the plume’s spatial characteristics, broad-scale behavior, hourly variability, and turbidity characteristics. Also, TPXO model outputs were employed to evaluate the relationship between plume occurrence and tides, together with satellite imagery. Plume was repeatedly observed near the top of the Ieodo Seamount, with an affected extent of 11.4 ± 3.2 km in the east–west direction and 14.3 ± 4.1 km in the north–south direction. Moreover, hourly variations observed using GOCI-II showed that the Ieodo plume rotated clockwise with shifting tidal currents, forming a counterclockwise curved band or a ring-shaped structure. Total suspended solids (TSSs) in the plume reached their maximum when the southward component of the TPXO tidal current was dominant. Based on UAV optical surveys at the I-ORS, fine-scale morphology at the early stage of plume development was revealed, and it was confirmed that the Ieodo plume can occur even when it is not detected by satellite imagery. Furthermore, the u- and v-velocity vectors of the propagating Ieodo plume were derived by applying large-scale particle image velocimetry (LSPIV) to geometrically corrected sequential UAV imagery obtained in I-ORS. Plume speed was greatest near the source during the initial stage (0.81 ± 0.30 m s⁻¹) and gradually decreased to 0.34 ± 0.29 m s⁻¹ over distance. Based on the results above, we propose that the Ieodo plume is primarily generated by a pressure reduction associated with tidally accelerated currents over topography, driven by the Bernoulli effect. This study shows that an integrated satellite and UAV observation framework can effectively monitor rapidly evolving suspended sediment plumes. It can further help improve our understanding of dynamically driven submesoscale marine events. Full article

Background/Objectives: Evidence-Based Nursing is imperative for high-quality care, but its implementation continues to face the know-do gap. While organizational barriers are often cited, the role of individual competencies, specifically Emotional Competence, in facilitating adoption remains underexplored on a large scale. This study aimed to analyze the association between perceived Emotional Competence, Evidence-Based Nursing adoption, and perceived attitudes and barriers in a nationwide sample of nurses registered with the Portuguese Order of Nurses. Methods: A quantitative, cross-sectional, correlational study was conducted using a non-probabilistic sample of 3014 nurses registered with the Portuguese Order of Nurses. The Clinical Effectiveness and Evidence-Based Practice Questionnaire, the Attitudes and Barriers Questionnaire, and the Emotional Competence Questionnaire were administered. Data were analyzed using bivariate correlations and a multivariable linear regression model. Results: Nurses reported high levels of perceived Emotional Competence (M = 204.7; SD = 20.3). In the multivariable regression model, Emotional Competence remained robustly and independently associated with Evidence-Based Nursing adoption (B = 0.315; p < 0.001), even after adjusting for sociodemographic and professional covariates. The perception of organizational barriers (e.g., time, incentives) did not correlate with adoption (r_s = 0.011; p = 0.54). Conclusions: Perceived Emotional Competence is a significant and independent correlate of Evidence-Based Nursing adoption. The results suggest that developing socio-emotional skills, including emotional regulation, may be a relevant training target to support evidence implementation. Full article

This study addresses the critical need for accurate, continuous monitoring of surface water quality parameters (SWQPs) using remote sensing, overcoming limitations in existing models that often rely on pre-trained networks ill-suited for complex aquatic environments. We present a customized convolutional neural network (CNN) architecture, implemented in the MATLAB environment, designed to simultaneously predict optically active (Total Organic Carbon, TOC) and non-optically active (Dissolved Oxygen, DO) parameters from eighteen Sentinel-2 Level-2A satellite images, acquired between 2023 and 2024. Our approach integrates spatial and spectral data through a customized CNN with three convolutional layers and two dense layers, optimized via adaptive learning strategies, data augmentation, and rigorous regularization to enhance predictive performance and prevent overfitting. The models were trained and validated on fused datasets of satellite imagery and in situ measurements, organized into comprehensive four-dimensional arrays capturing spectral, spatial, and sample dimensions. The results demonstrated high accuracy, with coefficient of determination (R²) values exceeding 0.97 and low root mean square error (RMSE) across training, validation, and testing subsets. Spatial prediction maps generated at high resolution revealed realistic ecological and hydrological patterns consistent with known regional water quality dynamics in New Brunswick. Our contribution, accessible to users with MATLAB, lies in the development of a transparent, adaptable, and reproducible CNN framework tailored for multiparameter water quality estimation, which extends beyond traditional empirical, site-specific regression models by enabling non-invasive, cost-effective, and continuous monitoring from satellite platforms over a large, heterogeneous province-scale domain. Additionally, model interpretability was enhanced through SHapley Additive exPlanations (SHAP) analysis, which identified key spectral bands influencing predictions and provided ecological insights, offering guidance for future sensor design and data reduction strategies. This study addresses a significant research gap by providing a dual-parameter focused, end-to-end deep learning solution optimized for province-scale remote sensing data, facilitating more informed environmental management. This study can support water managers and agencies by providing province-wide DO and TOC maps derived from freely available Sentinel-2 imagery, reducing reliance on sparse field sampling alone and helping to identify areas of low oxygen or high organic carbon. Future work will extend this framework temporally and spatially and explore hybrid CNN architectures incorporating temporal dependencies for improved generalization and accuracy. Full article

Optical microscopy is a fundamental tool in the physical, chemical, and life sciences, enabling direct investigation of structure, dynamics, and function across multiple spatial and temporal scales. Advances in optical design, detectors, and computational techniques have greatly enhanced performance, but have also increased the complexity of modern microscopes, which are now software-driven and embedded in data-intensive workflows. Artificial intelligence has become an important component of this landscape, particularly through task-specific machine learning approaches for image analysis, optimization, and limited instrument control. While effective, these solutions are often fragmented and lack the ability to integrate experimental intent, contextual knowledge, and multi-step reasoning. Recent progress in large language models (LLMs) offers a new paradigm for intelligent microscopy. As foundation models trained on large-scale text and code, LLMs exhibit emergent capabilities in reasoning, abstraction, and tool coordination, allowing them to act as natural interfaces between users and complex experimental systems. This perspective highlights how LLMs can function as cognitive and orchestration layers that connect experiment design, instrument control, data analysis, and knowledge integration. Emerging applications include conversational microscope control, workflow supervision, and scientific assistance for data exploration and hypothesis generation, alongside important technical, ethical, and governance challenges. Full article

Cone-beam computed tomography (CBCT) plays an important role in dental diagnosis; however, radiation exposure remains a concern. This study evaluated the feasibility of artificial intelligence (AI)-based image processing for improving image quality in low-dose CBCT. CBCT scans were acquired from a single healthy adult male at three radiation dose levels (10%, 20%, and 100% of the standard dose), and each dataset was subsequently processed using an AI-based image enhancement model. Five dental specialists independently assessed image quality using a 6-point scoring system across 12 anatomical and diagnostic criteria, including anatomical visibility, structural delineation, and overall diagnostic acceptability. The AI-processed 20% dose images showed no statistically significant difference in image quality compared with the 100% raw dose images (median 4.45, range 3.50–5.30 vs. median 5.05, range 4.50–5.50; p > 0.05). In contrast, the AI-processed 10% dose images demonstrated significantly lower scores (p = 0.0074), and the AI-processed 100% dose images were rated lower than the corresponding raw images. These preliminary findings suggest that AI-assisted enhancement may partially mitigate image quality degradation associated with moderate CBCT dose reduction. Further large-scale studies involving diverse patient populations and clinical settings are required to validate these results. Full article

Efficient workflow scheduling in cloud–edge environments is severely bottlenecked by long-horizon dependencies and myopic resource fragmentation. This paper proposes the Decoupled Offline Sequence-based (DOS) scheduling framework to address these challenges. By decoupling expert policy learning from runtime deployment, DOS utilizes a multi-dimensional priority-aware linearization strategy to deterministically transform DAG-structured workflows into dependency-consistent sequences. Leveraging offline expert trajectories, we train UDC, a Gated CNN achieving unified sequence modeling via innovative triplet-to-unary encoding, equipped with explicit action masking to distill long-horizon spatio-temporal packing patterns. This mechanism enables rapid feed-forward inference without costly online environment interactions or policy updates. Extensive evaluations on real-world Alibaba cluster workloads demonstrate that DOS not only consistently minimizes average makespan compared to classical heuristics, but also drastically reduces resource-blocked steps under extreme concurrency versus online Actor–Critic experts. Crucially, compared to the Decision Transformer (DT) baseline, the UDC model achieves strictly scale-invariant and significantly lower inference latency, highlighting its robust scalability and practicality for large-scale continuum systems. Full article

With the large-scale integration of distributed energy resources, modern energy systems are becoming increasingly dependent on communication networks for monitoring and control. This growing reliance exposes integrated energy systems (IESs) to potential cyber threats, as attackers may exploit vulnerabilities in communication protocols to disrupt system operation. However, most existing studies primarily investigate the stable operation of electro–thermal coupled systems from a defensive standpoint, while paying limited attention to the potential economic damage that could be induced from an attacker’s perspective. Motivated by this gap, this paper develops an optimal coordinated attack strategy targeting both energy storage units and load-side resources from the attacker’s viewpoint. First, an economic dispatch model for an electricity–heat–gas integrated energy system is established, and a fully distributed solution algorithm is proposed to obtain the optimal economic operating cost. Subsequently, by compromising energy storage and load units with relatively low security levels, a three-stage coordinated cyber-attack framework is designed for the IES. In the first two stages, covert data integrity attacks (DIAs) are launched to inject falsified power information into the system. In the third stage, a denial-of-service (DoS) attack is introduced to operate in synergy with the DIAs, forcing the system to converge to a feasible yet economically suboptimal operating point. The optimal initiation timing of the DoS attack is derived through theoretical analysis. Simulation results demonstrate that the proposed strategy can induce an economic loss of approximately 21.7% while maintaining system feasibility. By revealing these latent vulnerabilities from an attacker-oriented perspective, this study provides a theoretical basis for the development of proactive defense mechanisms, thereby enhancing the long-term economic and operational security of future integrated energy systems. Full article

Personalized e-learning seeks to adapt sequences of learning activities to individual learners, yet most existing adaptive platforms continue to rely on heuristic rules or single-objective optimization strategies. This paper introduces AlphaLearn, a conceptual evolutionary agent that frames learning pathway design as a constrained multi-objective optimization problem. The framework integrates knowledge graphs, learner modelling, and evolutionary algorithms to generate, evaluate, and iteratively refine candidate learning pathways under multiple pedagogical criteria. The contribution of this work is threefold. First, it presents a structured architectural framework for evolutionary learning pathway optimization, including a formal description of the optimization cycle and pathway representation. Second, it provides a descriptive analysis of large-scale learning analytics data from the Open University Learning Analytics Dataset (OULAD), illustrating substantial variability in learner outcomes, failure rates, and dropout across modules. Third, it offers an explicit discussion of fairness and bias mitigation, positioning equity as an integral dimension of adaptive pathway optimization rather than a post-hoc concern. The descriptive findings highlight pronounced heterogeneity in learner performance and engagement, motivating the need for adaptive systems capable of balancing learning effectiveness, efficiency, engagement, and fairness. While AlphaLearn is presented as a conceptual and methodological framework rather than a validated system, it establishes a foundation for future empirical evaluation and the development of fairness-aware evolutionary approaches to personalized e-learning. Full article

In the intelligent operation and maintenance of industrial equipment, labeling failure data remains a challenging task due to its high cost and low efficiency. Although incorporating a large amount of unlabeled data alongside limited labeled samples can partially alleviate this “labeling bottleneck,” the performance and robustness of models still heavily depend on the scale and quality of annotated data, which often leads to generalization issues in real industrial scenarios. To address these challenges, this paper proposes an unsupervised fault diagnosis method based on an efficient domain adaptation model named E-DANNMK. This approach reduces reliance on manually labeled fault data, thereby mitigating annotation-related issues such as high cost and potential bias. The E-DANNMK model integrates residual networks, an efficient channel attention mechanism, and domain adversarial neural networks to improve both feature discriminability and cross-domain adaptability. To validate its effectiveness, experiments were conducted on two major bearing fault datasets. The results demonstrate that the proposed E-DANNMK model achieves an average diagnostic accuracy of 94.21%, outperforming mainstream domain adaptation methods—including CDAN, CORAL, DANN, CNN-Transformer, DMT and DANN-MK—by a margin ranging from 3.12% to 7.15%. Full article

Photoelectrochemical (PEC) water splitting offers a sustainable route for solar-to-hydrogen conversion, yet its large-scale deployment is often hindered by energy-intensive and costly fabrication processes for semiconductor photoelectrodes. Electrodeposition provides an attractive alternative owing to its solution-based, low-temperature, and scalable nature; however, the relationship between electrochemical deposition parameters and photoelectrode functionality remains insufficiently understood. Herein, we systematically investigate system-level control in electrodeposition for photoelectrode synthesis using BiVO₄ photoanodes and CuO/Cu₂O photocathodes as model systems. By modulating deposition potential, current density, and electrical control modes, we elucidate how interfacial ion dynamics and growth kinetics govern film morphology, phase evolution, and PEC performance. DC electrodeposition establishes a baseline structure–performance relationship governed by precursor concentration and current density, while pulsed operation enables decoupling of nucleation and growth, leading to refined nanostructures and enhanced photocurrent responses. Further incorporation of reverse-pulsed potentials provides dynamic interfacial reset, enabling precise control over porosity and grain connectivity. The optimized BiVO₄ photoanodes fabricated under tailored reverse-pulsed conditions exhibit improved photocurrent density compared to continuously deposited counterparts. The insights presented here provide practical guidelines for rationally engineering high-performance, scalable, and environmentally benign photoelectrodes for PEC water splitting. Full article

The proliferation of intelligent sensor networks in urban surveillance and remote sensing has triggered the explosive growth of unstructured visual sensor data. Accurately retrieving targets from these massive streams based on complex cross-modal user intents remains a critical bottleneck for efficient intelligent perception. Composed Image Retrieval (CIR) addresses this by enabling retrieval via a multi-modal query that combines a reference image with semantic control signals. However, existing methods often struggle with abstract instructions in real-world scenarios. Consequently, models often suffer from feature distribution shifts due to focus ambiguity, as well as semantic erosion caused by highly entangled visual and textual features. To address these challenges, we propose a geometry-based Selective Orthogonal Projection Network (SOP). First, the Selective Focus Recovery module quantifies instruction uncertainty via information entropy and calibrates shifted query features to the true target distribution using structural consistency regularization. Second, to ensure data fidelity, we introduce Orthogonal Subspace Projectionand Geometric Composition Fidelity. These mechanisms employ Gram–Schmidt orthogonalization to decouple features into a constant visual base and an orthogonal modification increment, restricting semantic modifications to the null space. Extensive experiments on FashionIQ, Shoes, and CIRR datasets demonstrate that SOP significantly outperforms SOTA methods, offering a novel solution for efficient large-scale sensor data retrieval and analysis. Full article

Sand production in tight gas wells can cause severe erosion of downhole and surface facilities and pose a significant risk to safe and stable production. Proppant flowback is recognized as a key mechanism governing this process, and laboratory determination of the critical sand-production velocity provides an effective means for quantitative evaluation. Most existing studies are based on modified American Petroleum Institute (API) conductivity tests, which require large sample volumes and involve long experimental cycles and high costs. Building on previous work, critical sand-production behavior was investigated under consistent experimental conditions by comparing plunger core samples with conventional API cells, focusing on the influence of closure pressure and sample scale. The results show that, under identical closure pressure, the critical sand-production velocity measured using plunger cores is lower than that obtained from API cells. At a closure pressure of 10 MPa, the critical velocity is approximately 30.8% lower, while the difference decreases to 0.67% at 30 MPa. Based on the experimental data, critical sand-production velocity models corresponding to the two sample scales were established and show good agreement with experimental observations. The model was further applied to the production history of Well W-1 in the Wenxing gas field to evaluate sand production risk and support production optimization. The field results demonstrate that the model can identify high-risk sand-production stages and provide quantitative guidance for stabilizing production and reducing sand production in tight gas wells. Full article