Search Results (73,273)

Accurate cropland parcel mapping is essential for food security and sustainable land management in arid Africa, yet it remains challenging in Egypt due to edge blurring, spectral confusion, and fragmented fields in medium-resolution imagery. A novel dual-encoder deep learning method that integrates multi-scale axial attention and boundary constraints (MAA-BCNet) is proposed for the precise extraction of croplands in Egypt from Sentinel-2 multispectral images. A dual-path encoder is designed to fuse CNN-based local textures with an RMT global branch using spatial decay attention for complementary feature extraction. A multi-scale axial attention module is introduced to capture anisotropic parcel structures for improved spectral–spatial discrimination, and a multi-directional gradient edge enhancement module is developed for explicitly preserving boundary integrity. A U-Net++ decoder is employed for dense multi-scale aggregation. Experimental results in Egypt demonstrate that MAA-BCNet achieves superior performance in delineating cropland parcels, particularly for irregular or fragmented croplands with complex landscapes and fuzzy boundaries. Compared with the widely used segmentation models such as DeepLabV3_plus, PSPnet, Link_net, FCN_resnet101, and U-Net++ under the same training and evaluation settings, our model has the best performance, with Recall, Precision, IoU, and F1-Score reaching 94.92%, 90.77%, 86.57%, and 92.80%, respectively. These advancements make MAA-BCNet suitable for cropland mapping of large areas of Egypt, with applications in precision agriculture and sustainable land management. Full article

Recent studies have shown that AI models can memorize specific data records, resulting in sensitive data exposure through model access. Current privacy-enhancing technologies often overlook the crucial, context-dependent nature of privacy risk as they largely fail to account for the inherent relationships and complex interactions between data records, leading to high risks associated with memorization and potential data aggregation. Our research first investigates two key factors influencing AI privacy risks: implicit connections and data redundancy. These experiments have shown that AI models learn subtle links between private data, even when they are discretely distributed. To address the privacy issue, we introduce PrivGraph, a hierarchically structured knowledge graph for modeling and aggregating private information. Based on PrivGraph, we introduce the Sensitivity Level Factor (SLF) to quantify the degree to which an individual’s private information is embedded in the data. In addition, we propose a PrivGraph-based knowledge probing method to facilitate post-training privacy assessments. Our experiments demonstrated that PrivGraph achieves comparable performance to existing models in the Personally Identifiable Information (PII) detection task, while effectively modeling the aggregation of private information even with lengthy texts and data obtained from multiple origins. Finally, we discuss PrivGraph’s integration into the AI engineering lifecycle for full-spectrum, full-lifecycle, and traceable privacy protection. Full article

Plant-parasitic nematodes (PPNs) cause big crop losses globally. Safe/reliable methods for their durable management strategies can harness various beneficial relationships among the plant immune system and related microbiomes. Molecular mechanisms basic to these relations reveal wide arrays of significant roles for plant-healthy growth. This review focuses on such relations of microbiomes to prime and immunize plants against PPNs. It also highlights molecular issues facing PPN-resistant varieties with possible solutions such as genetic breeding/engineering, grafting, PPN-antagonistic root exudates, and novel resistant cultivars. These issues call for optimal uses of various widespread groups of microbiomes. Related plant signaling hormones and transcription factors that regulate gene expression and modulate nematode-responsive genes to ease positive/negative adaptation are presented. Exploring PPN-resistance genes, their activation mechanisms, and signaling networks offers a holistic grasp of plant defense related to biotic/abiotic factors. Such factors relevant to systemic acquired resistance (SAR) via plant–microbe interactions to manage PPNs are stressed. The microbiomes can be added as inoculants and/or steering the indigenous rhizosphere ones. Consequently, SAR is mediated by the accumulation of salicylic acid and the subsequent expression of pathogenesis-related genes. To activate SAR, adequate priming and induction of plant defense against PPNs would rely on closely linked factors. They mainly include the engaged microbiome species/strains, plant genotypes, existing fauna/flora, compatibility with other involved biologicals, and methods/rates of the inoculants. To operationalize improved plant resistance and the microbiome’s usage, novel actionable insights for research and field applications are necessary. Synthesis of adequate screening techniques in plant breeding would better use multiple parameters (molecular and classical ones)-based ratings for PPN-host suitability designation. Sound statistical analyses and interpretation approaches can better identify genotypes with high-level, stable resistance to PPNs than the commonly used ones. Linking molecular mechanisms to consistent field relevance can be progressed via dissemination of many advanced techniques. The CRISPR/Cas9 system has been effective in knocking out both the OsHPP04 gene in rice to confer resistance against Meloidogyne graminicola and the GhiMLO3 gene in cotton to minimize the Rotylenchulus reniformis reproduction. Its genetic modifications in crops synthesized “transgene-free” PPN-resistant plants without decreased growth/yield. Characterizing microbiome species/strains needed to prime and immunize plants requires better molecular tools for fine-scale taxonomic resolution than the common ones used. The former can distinguish closely related ones that exhibit divergent phenotypes for key attributes like stability and production of enzymes and secondary metabolites. As PPN-control strategies via tritrophic interactions are more sensitive to the relevant settings than chemical nematicides, it is suggested herein to test these settings on a case-by-case basis to avoid erratic/contradictory results. Moreover, expanding the use of automated systems to expedite detection/count processes of PPN and related microbes with objectivity/accuracy is discussed. When PPNs and their related microbial distribution patterns were modeled, more aspects of their field distributions were discovered in order to optimize their integrated management. Hence, the feasibility of site-specific microbiome application in PPN–hotspot infections can be evaluated. The main technical challenges and controversies in the field are also addressed herein. Their conceptual revision based on harnessing novel techniques/tools is direly needed for future clear trends. This review also engages raising growers’ awareness to leverage such strategies for enhancing plant resistance and advancing the microbiome role. Microbiomes enjoy wide spectrum efficacy, low fitness cost, and inheritance to next generations in durable agriculture. Full article

Accurate forecasting of container resource usage is crucial for efficient resource scheduling and ensuring Quality of Service (QoS) in cloud data centers. The inherent complexity of container workloads, characterized by strong temporal dependencies, multivariate correlations, and non-stationarity, challenges existing forecasting models, which often fail to efficiently capture both fine-grained local patterns and global trends. To address this gap, this paper proposes a novel Patch-based State-space Hybrid Network (PSH). PSH features a dual-branch architecture: a Local Transformer Path to model complex short-range dependencies and a Global Mamba Path, leveraging a State-Space Model (SSM) with linear-complexity, to efficiently capture long-range dependencies. This method uses an initial patching mechanism to reduce sequence length, which lowers computational overhead and supports efficient feature processing, and a cross-attention fusion module to integrate representations from its dual-branch architecture (Local Transformer Path for short-range dependencies, Global Mamba Path for long-range trends). The fusion module enables bidirectional interaction between the two paths: global context from the Global Mamba Path refines local features from the Local Transformer Path, balancing the model’s ability to capture both local patterns and global trends while maintaining high computational efficiency. Extensive experiments on the large-scale, real-world Alibaba Cluster Traces 2018 dataset demonstrate that PSH significantly outperforms existing state-of-the-art forecasting models in terms of accuracy and robustness. Full article

Shadow removal aims to restore photometric, chromatic, and structural consistency between shadowed and non-shadowed image regions. Although weakly supervised shadow removal methods reduce the reliance on densely paired training data, they still struggle to fully exploit appearance priors from non-shadow regions. As a result, their shadow removal outputs often appear unnatural, exhibiting color shifts and loss of fine texture details. To address this issue, we propose an ab-dynamic feature refinement network (AB-DFRNet) for weakly supervised shadow removal that more effectively exploits structural and chromatic symmetry during training. A high-frequency information enhancement (HFIE) module is introduced into the shadow generation subnet to extract and enhance high-frequency components via frequency separation and dense convolutions, thereby facilitating the learning of fine structural symmetry and enriching pseudo-shadow details. In the removal subnet, a dual-attention adaptive fusion (DAAF) module combines global and local attention mechanisms to adaptively recalibrate channel-wise and spatial features, improving multi-scale feature integration. Furthermore, a chrominance-only consistency (COC) loss is designed to minimize differences between the a and b channels of restored regions and their non-shadow references in the Lab color space. This additional color refinement constraint encourages a symmetric distribution of chromatic information and helps the refinement network produce more natural shadow-removed results. Extensive experiments are conducted on three benchmark datasets: ISTD, SRD, and Video Shadow Removal. The results confirm the effectiveness of AB-DFRNet, demonstrating competitive quantitative performance and noticeably better visual quality compared with existing weakly supervised shadow removal methods. Full article

Traffic accident prediction is of great importance for intelligent transportation systems and public safety management. Unlike conventional traffic flow forecasting tasks, accident data are characterized by low occurrence frequency and highly imbalanced distributions, with near-zero values during most time periods and occasional concentrated bursts. Accident occurrences are also strongly influenced by daily and weekly periodic patterns, resulting in mixed characteristics of low baseline levels, abrupt peaks, and long-term trends. These properties make traditional time series forecasting methods based on stationarity assumptions or single-period modeling less effective. To address this issue, this study proposes a time series forecasting framework that integrates patch-aware local perception with global basis representation. Specifically, this study aims to improve traffic accident time-series forecasting accuracy under sparse and bursty conditions by integrating patch-aware local perception with global basis representation. The patch-level structure captures fine-grained fluctuations in accident sequences by modeling short-term local variations, while basis decomposition provides robust modeling of overall trends through a set of global latent components, leading to complementary effects at both local and global levels. Experimental results on the I-405 highway accident dataset demonstrate that the proposed model significantly outperforms baseline methods, reducing mean squared error (MSE) and mean absolute error (MAE) by approximately 9.7% and 12.6% compared with PatchTST, and by 22.3% and 28.2% compared with Basisformer. Furthermore, experiments on public benchmark datasets ETTh1 and Electricity show that the proposed method achieves comparable or superior performance to mainstream models, indicating its effectiveness and generalization ability across different types of time series scenarios. Full article

Detecting minute defects, such as spurs on the surface of a Printed Circuit Board (PCB), is extremely challenging due to their small size (average size < 20 pixels), sparse features, and high dependence on circuit topology context. The original Mosaic data augmentation method faces significant challenges with semantic adaptability when dealing with such tasks. Its unrestricted random cropping mechanism easily disrupts the topological structure of minute defects attached to the circuits, leading to the loss of key features. Moreover, a splicing strategy without domain constraints struggles to simulate real texture interference in industrial settings, making it difficult for the model to adapt to the complex and variable industrial inspection environment. To address these issues, this paper proposes a Context-aware and Domain-consistent Mosaic (CD-Mosaic) augmentation algorithm. This algorithm abandons pure randomness and constructs an adaptive augmentation framework that synergizes feature fidelity, geometric generalization, and texture perturbation. Geometrically, an intelligent sampling and dynamic integrity verification mechanism, driven by “utilization-centrality”, is designed to establish a controlled sample quality distribution. This prioritizes the preservation of the topological semantics of dominant samples to guide feature convergence. Meanwhile, an appropriate number of edge-truncated samples are strategically retained as geometric hard examples to enhance the model’s robustness against local occlusion. For texture, a dual-granularity visual perturbation strategy is proposed. Using a homologous texture library, a hard mask is generated in the background area to simulate foreign object interference, and a local transparency soft mask is applied in the defect area to simulate low signal-to-noise ratio imaging. This strategy synthesizes visual hard examples while maintaining photometric consistency. Experiments on an industrial-grade PCB dataset containing 2331 images demonstrate that the YOLOv11m model equipped with CD-Mosaic achieves a significant performance improvement. Compared with the native Mosaic baseline, the core metrics mAP@0.5 and Recall reach 0.923 and 86.1%, respectively, with a net increase of 8.3% and 8.8%; mAP@0.5:0.95 and AP_small, which characterize high-precision localization and small target detection capabilities, are improved to 0.529 (+3.0%) and 0.534 (+3.3%), respectively; the comprehensive metric F1-score jumps to 0.903 (+6.2%). The experiments prove that this method effectively solves the problem of missed detections of industrial minute defects by balancing sample quality and detection difficulty. Moreover, the inference speed of 84.9 FPS fully meets the requirements of industrial real-time detection. Full article

Background: Rapid Eye Movement (REM) sleep behavior disorder (RBD) is a parasomnia resulting from degeneration of pontine and medullary circuits responsible for muscle atonia during REM sleep, leading to dream-enactment behaviors and vocalizations. It is strongly linked to α-synucleinopathies, particularly Parkinson’s disease. Current biomarkers such as neurophysiological measures and imaging support diagnosis and monitoring, but remain invasive or costly. Aim: This study aims to evaluate vocal and speech alterations as exploratory, non-validated candidate biomarkers of REM sleep behavior disorder. Methods: A systematic review was conducted according to PRISMA 2020 guidelines. PubMed, IEEE Digital Library Web of Science, Embase and the Cochrane Library were systematically searched for studies published from database inception to November 2025, as preregistered on the Open Science Framework. Studies were selected through a multi-step screening process and underwent qualitative quality assessment. Results: Twelve studies met inclusion criteria. Individuals with RBD exhibited abnormal nocturnal vocalizations and early lexical, syntactic, and narrative disruptions despite preserved perceptual speech. Quantitative analyses identified consistent deficits in prosody, phonation stability, timing, and articulation, with significant group differences and diagnostic accuracy up to 96% sensitivity. Multilingual cohorts demonstrated progression over time, while digital phenotyping detected emerging Parkinsonian signs with AUC > 0.70. Conclusions: Speech and vocal abnormalities in iRBD reflect early neurodegenerative changes and show promising but still exploratory diagnostic and prognostic potential. Integrating vocal markers with established biomarkers may enhance early detection; however, further research is required to validate a reliable and reproducible vocal signature of prodromal synucleinopathies. Full article

Amid debates over internet penetration’s impact on leisure diversity—“macro-level entropy increase” vs. “micro-level entropy reduction”—this study explores their intrinsic link by introducing Shannon’s information entropy theory and constructing a three-tier framework (“micro-individual decision-making—macro-regional growth—macro–micro linkage”). Using microdata from the China General Social Survey and macro data from the China Economic and Financial Research Database, we adopt a multi-method approach (benchmark regression, mediation/nonlinear analysis) to test hypotheses. Key findings: micro-level internet penetration boosts individual leisure entropy; macro-level impact may follow an inverted U-shape, mediated by micro-level internet use; the entropy-increasing effect is strongest for learning-oriented leisure, weakest for social-oriented leisure; education, income, and internet penetration are core configurational conditions. This study contributes a quantitative leisure diversity framework, an integrated macro–micro model, and insights into the nonlinearities of internet penetration. Full article

Background: Dialysis adequacy (Kt/V) remains an essential marker of hemodialysis quality; however, it does not fully capture patients’ overall well-being. Growing evidence underscores the need for a more holistic, patient-centered approach that integrates clinical efficiency with factors affecting daily functioning and quality of life (QoL). Objectives: This study aimed to identify the key determinants of health-related quality of life (HRQoL) among Polish patients undergoing hemodialysis. Methods: Seventy hemodialysis patients from a single center completed the KDQOL-36 questionnaire and provided demographic and clinical data. Statistical analyses included Pearson’s and Spearman’s correlations, as well as multiple linear regression, to determine predictors of HRQoL. Results: The mean (SD) KDQOL summary score was 60.9 (17.3). Pain (B = −15.9, p < 0.001) and the need for additional dialysis sessions (B = −10.2, p = 0.008) were the strongest independent predictors of poorer HRQoL, collectively accounting for 28.6% of variance. Longer dialysis-related transportation time (r = −0.238, p = 0.03) and longer hemodialysis vintage (r = −0.254, p = 0.03) were also significantly associated with lower HRQoL, while dialysis adequacy showed no significant effect. Conclusions: Pain, additional dialysis sessions, and longer dialysis-related transportation time are key, modifiable contributors to reduced HRQoL in Polish hemodialysis patients. These findings underscore the importance of a patient-centered approach that supplements clinical measures with interventions targeting comfort, education, and accessibility. Incorporating structured pain management and improved transport into routine nephrology practice can meaningfully improve patient QoL. Full article

During the construction period, numerous site photographs are routinely captured; however, their use is largely limited to simple visual inspection of construction status. To enhance the practical utilization of such photographic information, this study proposes a 4D-based construction progress management system that visually evaluates schedule progress by integrating site photographs within a BIM-based information management framework. The proposed system synchronizes site photographs with corresponding 4D model images using coordinate linkage and applies deep learning–based object detection to identify matching construction elements. Construction progress is approximately estimated by analyzing bounding box overlap between detected elements in site photographs and planned elements in 4D model images. A case study conducted on a bridge construction project demonstrated that the trained model achieved an overall mAP@0.5 of 0.532, and that the proposed method enables intuitive and approximate progress evaluation. The results indicate that the proposed system can improve the usability of site photographs as supporting information for 4D-based construction progress management. Full article

The accurate detection of electricity theft is crucial for reducing non-technical losses in smart grids. However, many existing data-driven methods rely on a single data modality, such as either the raw 1D consumption sequence or its transformed 2D image. This single-modality approach may not fully capture the complex spatio-temporal patterns associated with fraudulent behavior. To address this limitation, this paper proposes a novel detection method that integrates Markov Transition Fields (MTFs) with a hybrid neural network. First, this approach uses MTF to convert 1D time-series consumption data into 2D feature images, which enhances state-transition patterns. A parallel Residual Network and Long Short-Term Memory (ResNet-LSTM) architecture is then designed to simultaneously extract global temporal features from the original 1D data and local spatial features from the MTF images, with their fused representation used for classification. Experimental validation on a real-world dataset from the State Grid Corporation of China (SGCC)—comprising 6000 users over 304 days—demonstrates the effectiveness of our approach. The proposed model achieves a detection accuracy of 94.0% on an independent test set of 1200 users, significantly outperforming several state-of-the-art single-modality benchmarks. This work provides a new technical method for intelligent electricity theft prevention system. Full article

Understanding information on the regional water–energy–food system pressure (WEFSP) is crucial for ensuring resource security and promoting sustainable regional development. Existing studies often lack a focus on water quality issues, which cannot fully reveal the current situation of WEFSP. This study incorporated the grey water footprint as a measurement indicator to integrate water quality into the WEF nexus, re-examining the WEFSP across 30 Chinese provinces from 2006 to 2020. The spatiotemporal evolutionary characteristics of the WEFSP were characterized using Standard Deviation Ellipse (SDE) and Kernel Density Estimation (KDE). Furthermore, the GeoDetector method was employed to identify the key driving factors and their interactive effects. The results revealed that (1) China’s WEFSP initially increased and then decreased, and the WEFSP changes the most during the five-year plan transition period. The energy subsystem was under the greatest pressure, while water quality scarcity caused by pollution was the dominant driver of pressure within the water subsystem. (2) Spatially, the WEFSP exhibited an east-high and west-low pattern, with the center of gravity of the WEFSP mainly located in Anhui and Henan provinces, and during the study period, it experienced two stages of transfer: from northwest to southeast and vice versa. (3) The explanatory power of driving factors for the spatial heterogeneity of the WEFSP exhibited dynamic variability. The most influential factor shifted from annual average precipitation to per capita consumption expenditure. Significant interactive effects were identified among factors, all demonstrating either bilateral or nonlinear enhancement. These findings provide a comprehensive insight into the current state of WEFSP and the influence of external factors, offering a scientific basis for formulating targeted resource management strategies to ensure the security of the WEF nexus. Full article

As the core load-transfer medium in bonded structures, the adhesive layer critically governs overall reliability, with Mode I fracture representing its dominant failure mechanism under tensile loading. This study systematically compares the eXtended Finite Element Method (XFEM) and its two coupled variants—the XFEM-Cohesive Zone Model (CZM) and XFEM-Virtual Crack Closure Technique (VCCT)—in simulating Mode I fractures of adhesive joints. Key comparisons include predictions of stress distribution, load-transfer evolution, and crack propagation paths, all validated through Double Cantilever Beam (DCB) simulations and experiments. Results show that standard XFEM accurately predicts initial stiffness (error < 8%) but overestimates peak load by 10.7%. XFEM-CZM maintains errors below 8% for both stiffness and peak load, while XFEM-VCCT achieves exceptional peak-load accuracy (error < 1%) but overestimates stiffness. In crack evolution, standard XFEM yields an idealized propagation path, whereas the coupled methods reveal a distinct three-stage process. Stress/strain fields in standard XFEM remain stable during propagation, while the coupled approaches exhibit interfacial irregularities before crack arrival, followed by tip concentration and band-like transfer during stable growth. Each method offers distinct advantages, underscoring that selection should align with specific research objectives and modeling requirements. Full article

As the Industry 5.0 transition unfolds, engineering education must evolve to integrate Lean manufacturing with advanced digital tools and sustainable, human-centred practices. This study presents the design and implementation of a Lean Learning Factory (LLF) that addresses this challenge by combining traditional Lean methods with technologies such as simulation, robotics, and virtual reality in a modular educational environment. At the University Centre Pitești, six hands-on projects were implemented to guide students through key concepts, including production system layout, digital assistance, sustainability, and human–robot collaboration. Through experiential learning, students engage in iterative design, data analysis, and practical validation using real equipment and software platforms. The results indicate that the LLF effectively supports the development of technical, digital, transversal, and human-centred competencies aligned with EUR-ACE^® standards. Students acquire skills in process optimisation, ergonomics, and sustainable production, while also reflecting on the ethical and social implications of automation. The study concludes that the LLF model provides a scalable and adaptable framework for engineering education. It fosters competence-based learning and prepares students for the demands of Industry 5.0. This paper contributes a replicable educational approach that blends Lean efficiency, digital transformation, and human-centred values into a cohesive learning ecosystem. Full article