Search Results (9,608)

Porcine reproductive and respiratory syndrome (PRRS) has been prevalent in Germany for over 30 years, posing a significant threat to the local swine industry. There are limited analyses to offer German PRRSV ORF5 genetic and evolutionary characteristics and GP5 structural and functional features. In this study, a total of 518 sequences of the PRRSV GP5 gene were obtained from the GenBank database, encompassing 102 sequences from Germany to investigate the genetic relationships and GP5 structural and functional features. Similarly, phylogenetic and recombination analyses were used to identify genetic relationships. Two German PRRSV-1 lineage 1 strains exhibited more than 98.0% nucleotide similarity with vaccine strains. Eighteen German PRRSV-2 lineage 5 strains exhibited more than 98.0% nucleotide similarity with a prototype vaccine strain. German PRRSV-1 lineage 1 was predominant. GP5 structural and functional features were determined by N-glycosylation sites, B-cell epitopes, and transmembrane domain predictions. The main N-glycosylation patterns and transmembrane domains of German PRRSV-1 lineage 1 were time-dependent. Mutations of German PRRSV-1 lineage 3 in the primary neutralizing epitope were detected. In conclusion, these findings reveal lineage-specific molecular variation and improve the understanding of the molecular evolution of German PRRSV. Full article

Accurate wind power forecasting is critical for grid stability and long-term sustainability, but mountainous wind farms face challenges from complex micro-meteorology, restricted communication, and non-IID data, exacerbated by data silos that prevent centralized learning. Most federated learning relies on data-driven averaging that ignores multi-farm coupling, or adopt complex local models that increase communication overhead. To address these, a physics-guided personalized federated approach is proposed to enhance wind power forecasting. Its core is a physics-guided aggregation mechanism that constructs a dynamic weight matrix from distance, elevation, and real-time wind direction to enable personalized aggregation capturing multi-farm coupling. The federated framework combines a shared CNN-LSTM with multi-head attention for regional patterns and a personalized layer for local microclimate. A risk-aware asymmetric loss is incorporated to penalize high-power errors, enhancing operational reliability under high-power conditions. Validation on mountainous wind farms for 3-day forecasting under typical and extreme scenarios across wet, dry, and normal seasons shows that the average R² exceeds 0.95, and the average RMSE is reduced by more than 24% compared to baselines, achieving high accuracy under strict privacy preservation. By enabling multi-farm coupling under data isolation, this approach achieves high forecasting accuracy on the studied wind farms, showing promise for similar ones. Full article

In the multivariate time-series fault diagnosis task for aviation electro-hydrostatic actuators (EHA), the overall signal morphologies of different fault categories are relatively similar, while the key discriminative differences are hidden in local segments and variations in variable coupling. Therefore, existing Transformer-based methods usually have difficulty characterizing local specificity. To address this issue, this paper proposes a Local Prototype-Global Generic Dual-branch Transformer (LPG-Former). First, to obtain local information capable of characterizing class differences, a class-specific discriminative prototype (CDP) is constructed. The CDP selects discriminative time points from the time-series samples of each class to capture key local morphological variations, and constructs local prototypes carrying class-related local differential features. To further improve the ability of the CDP to capture multivariate fault coupling relationships, a multivariate coupling-aware prototype matching strategy (MCPM) is designed. The MCPM extends univariate prototypes into multivariate local prototype blocks and jointly measures local dissimilarity, variable correlation, and trend consistency, thereby enabling prototype learning with awareness of multivariate coupling relationships. Finally, to fuse local discriminative information and global temporal information, a dual-branch Transformer is constructed. LPG-Former encodes the differential features between the CDP and the best-fit subsequence (BFS) of the input sample through a Local Prototype Transformer, and complements global generic information through a Global Generic Transformer, thereby achieving collaborative dual-branch representation. Experimental results on an eight-class EHA operating-state dataset show that LPG-Former achieves an accuracy of 98.74% and an F1-score of 98.78%, significantly outperforming classical methods such as InceptionTime and TapNet. Full article

Urban vitality is a key indicator for characterizing the quality of urban space and the operational status of urban functions. However, existing studies still have limitations in multidimensional vitality measurement at the block scale, the representation of hierarchical differences in cultural facilities, and the coupling coordination diagnosis of multidimensional vitality. This study takes 2504 blocks in the central urban area of Nanjing as the basic analytical units and integrates multi-source geospatial data, including VIIRS nighttime light data, Baidu Huiyan population heat data, POIs, road networks, and water systems, to construct a three-dimensional urban vitality evaluation system encompassing economic, social, and cultural vitality. A Composite Nighttime Light Index (CNLI) is constructed by geometrically fusing VIIRS nighttime light data with the kernel density of industry- and consumption-related POIs to reduce the impact of the spatial generalization of nighttime lights on block-scale economic vitality measurement. Meanwhile, population heat data and cultural POIs are used to characterize social vitality and cultural resource supply, respectively, and PCA, a coupling coordination model, and spatial autocorrelation analysis are combined to identify the spatial structure of multidimensional vitality and the dominant factors of disorder. External reference variables are also introduced to conduct convergent validity verification. The results indicate that the comprehensive vitality of Nanjing’s central urban area exhibits a distinct “core agglomeration–multi-node diffusion” structure. High-vitality zones are primarily concentrated in Xinjiekou, Confucius Temple, Hunan Road–Zhongyang Road, Longjiang, and the Nanjing Olympic Sports Center, with localized vitality patches forming at peripheral commercial and transportation nodes. Both comprehensive vitality and coupling coordination degree exhibit significant positive spatial autocorrelation, with Moran’s I values of 0.8089 and 0.8372, respectively. The disorder types show distinct quantitative differences and spatial differentiation. Among these, blocks with lagging cultural vitality are the most numerous; peripheral new towns and newly developed residential areas are more prone to cultural vitality lag; areas surrounding scenic spots, universities, and large ecological spaces tend to exhibit economic vitality lag; and less developed peripheral blocks primarily exhibit comprehensive disorder. Based on accessible multi-source geospatial data, this study constructs a block-scale framework for measuring multidimensional urban vitality and diagnosing coordination status. This framework can provide a reference for vitality identification, functional shortcoming diagnosis, and refined spatial governance in Nanjing’s central urban area, and offer a case reference for historic and cultural cities with similar spatial structures. Full article

This study introduces a modular approach to the validation of non-invasive coating inspection. It involves RGB imaging, visible and near-infrared spectroscopy, measurements of the physical parameters of the coating, and 3D Gaussian Splatting. As publicly available datasets containing these different types of information for the same coating samples are rare, each module was considered separately. The study also defines the type of paired data required for future data-fusion experiments. During the analysis of the painted-metal image dataset, exact-file hashing identified 68 duplicate images shared between the training and test sets. After removing these images and the duplicates within the test set, the best fixed $48\times 48$ image classifier achieved an accuracy of 78.49% and a balanced accuracy of 78.99% on 93 distinct test images. In addition, an additional sensitivity analysis was conducted using an ImageNet-pretrained EfficientNetB0 model with $224\times 224$ images. This model achieved an accuracy of 66.67%. This result shows that higher-resolution images and a pretrained model do not directly improve performance on a small and domain-specific dataset. Coated-wood defect localization, controlled steel-defect detector comparison, duplicate-grouped ship-coating spectroscopy, public gloss, roughness, scanning-electron-microscopy workbooks, and reflective-scene reconstruction were recomputed as separate validation blocks. The reflective-scene reconstruction achieved a peak signal-to-noise ratio of $25.018\mathrm{dB}$, a structural similarity index of $0.8947$, and a learned perceptual image patch similarity value of $0.1522$. However, camera distortion and unidirectional geometry limitations restrict this module to feasibility analysis. Our framework provides reproducible baselines and defines the paired-data requirements for future calibrated coating-monitoring systems. Full article

In remote sensing image–text retrieval (RSITR), precise cross-modal retrieval is often hindered by centroid drift and ambiguous decision boundaries caused by high inter-class visual similarity. To address these bottlenecks, this study proposes a Category-aware Global–Local Semantic Alignment (CGLSA) framework fine-tuned on the CLIP (ViT-B/16) backbone. The architecture orchestrates two complementary mechanisms: Global Semantic Collaborative Alignment that regularizes macro-level category centroids using momentum updates and Bayesian prior calibration, and Local Fine-grained Feature Alignment that refines instance-level matching via dynamic scale adjustment and category-aware topological masks. Extensive evaluations on three major benchmark datasets (RSICD, RSITMD, and UCM-Captions) validate the model’s efficacy. Compared to strictly controlled CLIP-family baselines under equivalent supervised conditions, CGLSA achieves new state-of-the-art performance across all R@K metrics and mean recall. Extensions adapting this robust centroid formation to semi-supervised and open-vocabulary scenarios are identified for future work. Full article

This study addresses the dual challenges of seasonal water scarcity and urban flooding in the Garzan River basin, a region with a semi-arid climate. We propose and analyze an integrated water management system designed to mitigate these risks and promote both ecological and economic sustainability. Our methodology began with a comprehensive analysis of meteorological data from 2000 to 2024, which quantified the significant seasonal irregularity in the annual rainfall regime. The findings revealed that the bulk of the average 800 mm of rainfall occurs between January and May, while the summer months experience near-drought conditions. Based on this, we calculated the potential of various water conservation strategies. The system combines rainwater harvesting from a 1000 m² roof and a 500 m² parking lot, projected to collect 1020 m³ annually, with greywater reclamation and low-flow fixtures, which add a combined 400 m³ of annual savings. The total annual water savings of 1420 m³ were found to provide a gross annual economic benefit of $3550. Considering the installation and maintenance costs, the project’s payback period is estimated to be around 32 years. We also developed an annual precipitation prediction model providing a locally applicable early warning mechanism that forecasts total rainfall based on spring data. The use of proactive hydrometeorological data can improve the feasibility of long-term infrastructure projects to a certain extent. Finally, the proposed system’s design was confirmed to be eligible for multiple LEED certification credits, demonstrating its alignment with international sustainability standards. In conclusion, this research provides a comprehensive and viable solution that addresses local water issues and offers a valuable model for other regions facing similar challenges. Full article

Autonomous inspection of ballast water tanks requires three-dimensional (3D) LiDAR-based simultaneous localization and mapping (SLAM) in Global Positioning System (GPS)-denied, geometrically repetitive interiors, where sensing, mapping, and control modules share a limited onboard memory budget. Graph SLAM backends that rely on sparse factorization can incur fill-in, increasing peak memory and limiting deployment on edge computers. The proposed architecture couples a robust hierarchical bundle adjustment frontend with a factorization-free Kaczmarz backend. The frontend combines residual-adaptive weighting, damped and bounded pose updates, soft fallback, local-map compression, and memory-aware keyframe control. The backend stores the whitened Jacobian in compressed sparse row (CSR) format and performs row-wise projections without explicitly forming the normal equations, a Cholesky factor, or a transpose cache. Evaluation was conducted on Norwegian University of Science and Technology (NTNU) Ballast Water Tank missions 1–3, containing 851, 1202, and 1084 LiDAR frames. Following robust local bundle adjustment and verified similarity alignment, translational root-mean-square errors were 0.080, 0.110, and 0.127 m, corresponding to 0.137%, 0.143%, and 0.122% of the reference path lengths; archived baseline ratios ranged from 0.281% to 0.372%. These results support a numerical architecture that combines frontend stabilization, row-wise optimization, and memory-aware policies for resource-constrained marine inspection robots. Full article

Canine mammary tumors have been investigated to determine the causes of malignancy and to promote the development of more effective therapies. The current standard of care, surgical resection where possible, often still results in recurrence of disease. Thus, there is an unmet need for better, more effective therapies that can suppress recurrence in canine patients. Because canine and human mammary cancers, particularly carcinomas and adenocarcinomas, share many similarities in genetic defects, etiology, natural history, and environment, canine mammary cancer cell lines have also been used as effective models of human disease. The genetics and immune response to canine mammary/breast cancers have been investigated to better understand this disease complex and to promote the development of more effective therapies designed to treat individual canine patients. As cancer is a heterogeneous disease, the potential to determine and possibly predict the mechanisms promoting neoplasia would allow the advancement of targeted therapeutic targets/strategies to combat cancer directly. These investigations have led to the development and evaluation of immunotherapies designed to elicit immune recognition of cancer and its suppression, thus improving survival. Hybrid dendritic-cell fusion vaccines and other autologous cancer vaccine formulations have proven effective in suppressing recurrence and extending survival in canine mammary cancer patients following surgical resection. Although current vaccines are somewhat impractical for direct application in veterinary clinics, reported success points the way toward the development of more practical vaccines designed to promote the treatment of canine mammary cancer. They also suggest a possible mechanism whereby removing a tumor from its microenvironment can promote antigenicity by removing local extracellular vesicle-mediated immunosuppression. This review provides a novel perspective on the potential of canine genetics to inform and promote more successful immunotherapies and their value as models of human disease. Full article

Ultraviolet (UV) insect traps enable continuous field pest monitoring, but their images contain severe scale variation, dense and overlapping targets, incomplete specimens, background stains, insect fragments, non-target insects, inter-class similarity, and long-tailed distributions, leading to missed detections, false positives, and class confusion. To address these challenges, we constructed a real-world UV insect-trap pest dataset comprising 12,426 high-resolution images and 38,003 annotated instances from 36 pest categories, and propose FCD-DETR, a foreground-aware and context-enhanced Detection Transformer based on RT-DETR-R18. The main distinction of FCD-DETR lies in a progressive enhancement design tailored to UV insect-trap images, where FADM first reduces foreground–background confusion by decoupling pest foreground cues from multi-scale semantic information, C2f_CFBlock strengthens local-detail and contextual representations in the lightweight backbone, and DHSA further alleviates high-level semantic ambiguity through dynamic-range histogram self-attention in the Transformer encoder. On the proposed dataset, FCD-DETR achieved 64.42% mAP@0.5 and 41.33% mAP@50:95, improving the baseline by 5.25 and 5.11 percentage points, respectively, and outperforming representative CNN- and Transformer-based detectors. Comprehensive experimental analyses confirm that FCD-DETR improves foreground discrimination and detection robustness in complex UV insect-trap scenarios. Full article

Soybean variety recognition supports germplasm management and intelligent agricultural inspection, but remains challenging because varieties often show subtle inter-class differences, large intra-class imaging variation, and imbalanced samples. This study adopts a cascaded pipeline that combines YOLO-based object localization, manual verification and cropping, and fine-grained classification, allowing the classifier to learn from standardized cropped soybean seed images rather than original whole images. To improve Swin Transformer for this task, we propose Swin-Diff-DCA, which introduces Dynamic Channel Aggregation (DCA) in Stage 3 for middle-level local feature reuse and a differential attention branch in Stage-4 window attention for deep discriminative enhancement. On a dataset containing 25 soybean varieties and 1511 test images, Swin-Diff-DCA achieves average results of 87.18% Accuracy, 82.33% Macro-F1, and 87.44% Weighted-F1 across three random seeds under the current split and evaluation protocol. It outperforms RegNet, ResNet-50, ViT, the Swin Transformer baseline, and single-module variants. The results show that combining middle-level feature reuse with deep differential enhancement improves cropped soybean variety classification, while low-sample and visually similar classes remain the main sources of misclassification. Full article

Fusing infrared and visible images can effectively compensate for the inherent limitations of each modality in different scenes, resulting in fused images that contain richer information. However, existing methods often struggle to balance global dependency modeling with local detail preservation and to effectively coordinate heterogeneous local and global features during fusion. To address these issues, this paper proposes a Significance-Preserving Progressive Fusion Network (SiPFusion). First, a progressive feature extraction framework was designed, which hierarchically extracts multi-scale local features using CNNs and then models long-range dependencies across scales via a Transformer-based global module. To adaptively integrate local-global complementary features, a significance-preserving fusion module was designed to obtain significance attention maps with a spatial selection mechanism, enabling dynamic fusion of multi-source features. Furthermore, we propose a significance similarity loss function that leverages intermediate feature guidance to enhance structural consistency and preserve salient-region information in the fused image. Extensive experiments on the MSRS, RoadScene, and TNO datasets demonstrate that SiPFusion achieves competitive visual quality and strong overall quantitative performance against 15 state-of-the-art fusion methods, obtaining leading results on most evaluated metrics. Full article

Detecting defective pixels in CMOS Image Sensors is a critical task for ensuring high-quality image acquisition, as even minor defects can significantly degrade performance in vision systems and downstream processing. This study evaluates the performance of several supervised machine learning algorithms for defective pixel detection using 300 grayscale images of $512\times 512$ pixels from the publicly available TAMPERE17 dataset, in which dead and hot pixels were randomly introduced. The evaluated algorithms include k-Nearest Neighbors (kNN), Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine (SVM), and Multilayer Perceptron. Performance was assessed using specificity, recall, precision, and the phi coefficient. A sensitivity analysis was additionally performed using neighborhood windows of $3\times 3$, $5\times 5$, and $7\times 7$ pixels during feature extraction. The results showed that the neighborhood size has a noticeable impact on classification performance, with the best overall results obtained using an SVM classifier with an RBF kernel and a $3\times 3$ feature extraction window. This configuration achieved a phi coefficient of 98.08%, together with a specificity of 99.00%, a recall of 99.00%, and a precision of 99.02%. Statistical analysis further indicated that SVM (RBF) and Multilayer Perceptron exhibited statistically comparable performance under the evaluated experimental conditions. The analysis further revealed that defective pixels are primarily characterized by highly local intensity variations, while larger neighborhoods do not necessarily improve classification performance. Compared with previously reported defective pixel detection methods, the proposed approach achieved highly competitive results and the highest phi coefficient among the evaluated methods. Additionally, the impact of defective pixel detection on image quality was assessed using a simple median filter correction stage and evaluated through Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). The best-performing configuration achieved a PSNR of 40.96 dB and an SSIM of 98.68% after median filter correction, demonstrating substantial improvement over median filtering alone, although the resulting image quality remains below that of the best-performing state-of-the-art correction methods. The proposed framework provides reproducible reference results for evaluating supervised machine learning approaches to defective pixel detection while analyzing the influence of feature extraction window size on classification performance and reconstructed image quality. Full article

High-quality synthetic datasets are critical for environmental monitoring due to the high cost of primary geochemical data collection. However, selection criteria for generative frameworks under small-sample constraints remain poorly defined. This study evaluates two architectures—the deep-learning-based Tabular Variational Autoencoder (TVAE) and the parametric Gaussian copula—using an empirical geochemical dataset (N = 297) of 25 log-transformed elements. Synthesis quality was benchmarked via marginal distribution fidelity (KSComplement), correlation preservation (CorrelationSimilarity), privacy (LogisticDetection), and a composite QualityScore, supplemented by divergence metrics and a rare-earth element (REE+Th+U) subgroup analysis. In this dataset, the Gaussian copula demonstrated superior global correlation preservation (CorrelationSimilarity: 0.9633 vs. 0.9482), particularly for weak-to-moderate dependencies. Conversely, TVAE better replicated marginal distributions (KSComplement: 0.8742 vs. 0.8596), maintained localized correlations (MAD: 0.0728 vs. 0.1196), and showed enhanced privacy (LogisticDetection: 0.5757 vs. 0.3063). These complementary profiles suggest that, for this case study, the Gaussian copula may be preferable for dependency modeling, while TVAE appears better suited for secure open-data dissemination. Further validation on additional datasets is needed to assess the generalizability of these findings. Full article

By systematically conducting seismic damage investigations of tunnels crossing active faults, this study summarizes the failure characteristics of typical damage cases and performs model tests at a similarity ratio of 1:50 to examine the dislocation-induced failure mechanisms of tunnel structures subjected to reverse strike-slip faulting, reverse faulting, and strike-slip faulting, respectively. In view of the lack of systematic theoretical calculations in existing articulated anti-dislocation fortification methods, a displacement-pattern-based calculation method for the articulated fortification width is proposed. The main conclusions are as follows: The failure of tunnels crossing active faults results from the coupling of fault dislocation, strong-motion inertial forces, and surrounding rock restraint, and is jointly controlled by multiple factors including fault type, movement mode, geometric relationship, structural stiffness, and surrounding rock properties. Under reverse strike-slip faulting, the tunnel failure is dominated by a combination of oblique shear and compression, exhibiting an overall spatial “S”-shaped deformation; under strike-slip faulting, the tunnel experiences combined shear and bending failure with an overall planar “S”-shaped deformation; under reverse faulting, shear failure prevails, locally accompanied by tensile failure. The proposed calculation method for the articulated fortification width not only fills the gaps in previous studies but also broadens its scope of application. It is applicable not only to the displacement patterns addressed in this paper but also to other displacement patterns that conform to tunnel dislocation. Full article