Search Results (385)

Image blur is a major factor that degrades object detection in agricultural applications, particularly in orchards where crop occlusion, leaf movement, and camera shake frequently reduce image quality. This study proposed a lightweight generative adversarial network, AGG-DeblurGAN, to address non-uniform motion blur in citrus tree images. The model integrates the GhostNet backbone, attention-enhanced Ghost modules, and a Gated Half Instance Normalization Module. A blur detection mechanism enabled dynamic routing, reducing computation on sharp images. Experiments on a citrus dataset showed that AGG-DeblurGAN maintained restoration quality while improving efficiency. For object detection, restored citrus images achieved an 86.4% improvement in mAP@0.5:0.95, a 76.9% gain in recall, and a 40.1% increase in F1 score compared to blurred images, while the false negative rate dropped by 63.9%. These results indicate that AGG-DeblurGAN can serve as a reference for improving image preprocessing and detection performance in agricultural vision systems. Full article

The constrained bi-objective Minimum Spanning Tree (MST) problem is a fundamental challenge in network design, as it simultaneously requires minimizing both total edge weight and maximum hop distance under strict feasibility limits; however, most existing algorithms tend to emphasize one objective over the other, resulting in imbalanced solutions, limited Pareto fronts, or poor scalability on larger instances. To overcome these shortcomings, this study introduces a Hybrid MOCPO–AGE-MOEA algorithm that strategically combines the exploratory strength of Multi-Objective Crested Porcupines Optimization (MOCPO) with the exploitative refinement of the Adaptive Geometry-based Evolutionary Algorithm (AGE-MOEA), while a Kruskal-based repair operator is integrated to strictly enforce feasibility and preserve solution diversity. Moreover, through extensive experiments conducted on Euclidean graphs with 11–100 nodes, the hybrid consistently demonstrates superior performance compared with five state-of-the-art baselines, as it generates Pareto fronts up to four times larger, achieves nearly 20% reductions in hop counts, and delivers order-of-magnitude runtime improvements with near-linear scalability. Importantly, results reveal that allocating 85% of offspring to MOCPO exploration and 15% to AGE-MOEA exploitation yields the best balance between diversity, efficiency, and feasibility. Therefore, the Hybrid MOCPO–AGE-MOEA not only addresses critical gaps in constrained MST optimization but also establishes itself as a practical and scalable solution with strong applicability to domains such as software-defined networking, wireless mesh systems, and adaptive routing, where both computational efficiency and solution diversity are paramount Full article

As global climate change intensifies the frequency of extreme weather events, urban flood control and disaster reduction efforts face unprecedented challenges. With the limitations of traditional, top-down emergency management becoming increasingly apparent, many countries are actively incorporating community-based participation into flood risk governance. While research in this area is expanding, the specific impact of urban flood inundation severity on residents’ participation in relief efforts remains significantly underexplored. To address this research gap, this study employs the Community Capitals Framework (CCF) and a Gradient Boosting Decision Tree (GBDT) model to empirically analyze 1322 survey responses from Zhengzhou, China, exploring the non-linear relationship between flood severity and public participation. Our findings are threefold: (1) As the most direct source of residents’ risk perception, flood inundation severity has a significant association with their participation level. (2) This relationship is distinctly non-linear. For instance, inundation severity within a 200 m radius of a resident’s home shows a predominantly negative relation with participation level, with the negative effect lessening at extreme levels of inundation. The distance from inundated areas, conversely, exhibits an “S-shaped” curve. (3) Flood severity exhibits a significant reinforcement interaction with both communication technology levels and government organizational mobilization. This indicates that, during public crises like flash floods, robust information channels and effective organizational support are positively related to residents’ transition from passive to active participation. This study reveals the complex, non-linear associations between flood severity and civic engagement, providing theoretical support and practical insights for optimizing disaster policies and enhancing community resilience within the broader context of urban land management and sustainable development. Full article

The study investigates the use of powerful machine learning approaches to the real-time detection of phishing URLs, addressing a critical cybersecurity concern. The dataset we utilized in this research work was collected from the University of California Irvine (UCI) Machine Learning Repository. It has 235,795 instances with fifty-four distinct parameters. The label class is of binomial type and has only two target classes. We used a range of complex algorithms, including k-nearest neighbor, naive Bayes, decision trees, random forests, and random tree, to assess the discriminative characteristics retrieved from URLs. The random forest classifier beat the other classifiers, reaching the greatest accuracy of 99.99%. The study demonstrates that these models achieve superior accuracy in identifying phishing attempts, significantly outperforming traditional detection methodologies. The findings underscore the potential of machine learning to provide a scalable, efficient, and robust solution for real-time phishing detection. Implementing these innovative platforms to existing security solutions is going to play a critical role in sustaining the protective line against continuously evolving and persistent phishing schemes. Full article

Instance segmentation in high-resolution images is essential for applications such as remote sensing, medical imaging, and precision agriculture, yet remains challenging due to factors such as small object sizes, irregular shapes, and occlusions. Tiling-based approaches, such as Slicing-Aided Hyper Inference (SAHI), alleviate some of these challenges by processing smaller patches but introduce border artifacts and increased computational cost. Overlapping tiles can mitigate certain boundary effects but often result in duplicate detections and boundary inconsistencies, particularly along patch edges. Conventional deduplication techniques, including Non-Maximum Suppression (NMS) and Non-Mask Merging (NMM), rely on Intersection over Union (IoU) thresholds and frequently fail to merge fragmented or adjacent masks with low mutual IoU that nonetheless correspond to the same object. To address deduplication and mask fragmentation, Spatial Mask Merging (SMM) is proposed as a graph clustering approach that integrates pixel-level overlap and boundary distance metrics while using R-tree indexing for efficient candidate retrieval. SMM was evaluated on the iSAID benchmark using standard segmentation metrics, with tile overlap configurations systematically examined to determine the optimal setting for segmentation accuracy. The method achieved a nearly 7% increase in precision, with consistent gains in F1 score and Panoptic Quality over existing approaches. The integration of R-tree indexing facilitated faster candidate retrieval, enabling computational performance improvements over standard merging algorithms alongside the observed accuracy gains. Full article

Background/Objectives: Hospital compounding is essential for the delivery of patient-tailored therapies—particularly for pediatric and oncology patients and other groups requiring precise dosing. Its role is expected to grow as, for instance, the UK MHRA’s new Guidance on Decentralised Manufacturing promotes alternative manufacturing pathways that integrate hospital preparation units. However, drug substances that remain stable in commercial oral formulations may undergo rapid degradation under alternative conditions (e.g., aqueous suspension, light exposure, or in the presence of specific excipients). Despite these risks, formulation strategies in hospital compounding often rely on empirical practices and lack structured guidance regarding stability, impurity control, and reproducibility. Methods: This study proposes a risk-based scientific framework for formulation design, integrating degradation profiling with predictive toxicology. Potential degradation pathways (hydrolytic, oxidative, and photolytic) are systematically identified through forced-degradation studies combined with ab initio modeling. These risks are translated into formulation strategies using a structured decision tree encompassing solvent selection, pH adjustment, excipient compatibility, and packaging considerations, even in the absence of a pharmacopeial monograph. The toxicological relevance of degradation products is evaluated using in silico approaches aligned with ICH M7 guidelines, thereby defining critical quality attributes (cQAs) and critical process parameters (CPPs). Results: The applicability of the framework is demonstrated through hospital compounding case studies, with further extension toward advanced applications such as semi-solid extrusion (SSE) 3D printing. Conclusions: By integrating mechanistic understanding of drug degradation into formulation planning, the proposed framework enhances the safety, reproducibility, and quality of compounded preparations. This approach reinforces Good Preparation Practices (GPPs) and is consistent with international quality-by-design (QbD) principles in the context of personalized medicine. Full article

The rapid growth of the automobile industry has intensified the demand for accurate price prediction models in the used car market. Buyers often struggle to determine fair market value due to the complexity of factors such as mileage, brand, model, transmission type, accident history, and overall condition. This study presents a comparative analysis of machine learning models for used car price prediction, with a strong emphasis on the impact of feature engineering. We begin by evaluating multiple models, including Linear Regression, Decision Trees, Random Forest, Support Vector Regression (SVR), XGBoost, Stacking Regressor, and Keras-based neural networks, on raw, unprocessed data. We then apply a comprehensive feature engineering pipeline that includes categorical encoding, outlier removal, data standardization, and extraction of hidden features (e.g., vehicle age, horsepower). The results demonstrate that advanced preprocessing significantly improves predictive performance across all models. For instance, the Stacking Regressor’s R² score increased from 0.14 to 0.8899 after feature engineering. Ensemble methods, such as CatBoost and XGBoost, also showed strong gains. This research not only benchmarks models for this task but also serves as a practical tutorial illustrating how engineered features enhance performance in structured ML pipelines for the fellow researchers. The proposed workflow offers a reproducible template for building high-accuracy pricing tools in the automotive domain, fostering transparency and informed decision making. Full article

UAV airborne network intrusion detection faces challenges due to highly imbalanced datasets, where normal samples significantly outnumber intrusion instances. This paper proposes an improved stratified sampling and ensemble learning (ISSEL) method to address this issue. The method improves upon traditional stratified sampling by clustering normal samples and performing distance-based sampling from cluster centers to ensure better feature space representation. Subsequently, five tree models, namely, decision tree, extra tree, random forest, gradient boosting tree, and XGBoost, are utilized to train each subset. The model prediction results are then integrated using an adaptive weighting strategy based on the F1 score. The experimental results on the MIL-STD-1553B data bus demonstrated that the ISSEL method maintained a high accuracy rate of 99.42% while significantly enhancing the recognition ability for minority-class attacks. The precision, recall, and F1 score reached 98.94%, 97.62%, and 98.28%, respectively. These results validate the effectiveness of the ISSEL method in handling imbalanced datasets, highlighting its potential application in the field of airborne network intrusion detection. Full article

Spatial co-location patterns are used to describe the spatial associations between features, finding wide applications in geographic information systems, urban planning, and other fields. Traditional frameworks for mining spatial features typically consist of two stages: constructing spatial proximity relationships and discovering frequent patterns. However, existing methods have limitations: the construction of proximity relationships relies on fixed distance thresholds or clustering centers, making it difficult to adapt to spatial density heterogeneity; meanwhile, frequency metrics overly depend on participation indices, lacking quantitative analysis of the strength of geometric associations between features. To address these issues, a spatial co-location pattern mining method based on Hausdorff distance is proposed. Drawing on the concept of Hausdorff distance, this method employs Voronoi tessellation to achieve data-adaptive partitioning of the spatial domain. Combined with a K-dimensional tree, it adopts an iterative strategy of direct allocation, proportional allocation, and residual allocation to align instances, generating a spatial proximity relationship graph. Additionally, a new frequency metric based on instance distribution—alignment rate—is introduced, leveraging the decreasing trend of alignment rate in conjunction with a pruning optimization algorithm. Experimental results demonstrate that this method excels in handling noise points, effectively addressing the challenges of uneven data density distribution while enhancing the identification of weakly associated yet potentially valuable patterns. Full article

Pine wilt disease endangers the ecological stability of China’s coniferous woodlands. In a specific region, the number of dead pine trees has exhibited a consistent year-on-year increase, highlighting the urgent need for efficient and sustainable monitoring strategies. However, UAV-based remote sensing methods currently face challenges in complex environments, including insufficient feature-capture capabilities, interference from visually similar objects, and limited localization accuracy. This study developed a remote sensing workflow leveraging high-resolution UAV imagery to oversee pine trees affected with pine wilt disease. An enhanced YOLOv5 detection model was employed to identify symptomatic trees. To strengthen feature extraction capabilities—particularly for color and texture traits indicative of infection—different types of attention mechanisms, for instance SE, CBAM, ECA, and CA, were integrated as part of the model. Furthermore, a BiFPN structure was incorporated to enhance the fusion of features across multiple scales, and the EIoU loss function was adopted to boost the accuracy of bounding box prediction, ultimately enhancing detection precision. Experimental results show that the enhanced SEBiE-YOLOv5 framework achieved a precision of 89.4%, with an AP of 86.1% and an F1-score of 83.1%. UAV-based monitoring conducted during the spring and autumn of 2023 identified 616 dead trees, with field verification accuracy ranging from 88.91% to 92.42% and localization errors within 1–10 m. These findings validate the method’s high accuracy and spatial precision in complex mountainous forest environments. By integrating attention mechanisms, BiFPN, and the EIoU loss function, the proposed SEBiE-YOLOv5 model substantially enhances the recognition accuracy of key features in infected trees as well as their localization performance, and offers a practical and computationally efficient approach for the long-term surveillance of pine wilt disease in challenging terrain. Full article

Code smells are code structures that indicate a potential issue in code design or implementation. These issues could affect the processes of code testing and maintenance, and overall software quality. Therefore, it is important to detect code smells in the early stages of software development to enhance system quality. Most studies have focused on detecting code smells of a single programming language. This article explores TL for cross-language code smell detection, where Java is the source, and both C# and Python are the target datasets, focusing on Large Class, Long Method, and Long Parameter List code smells. We conducted a comparison study across two transfer learning approaches—instance-based (Importance Weighting Classifier, Nearest Neighbors Weighting, and Transfer AdaBoost) and parameter-based (Transfer Tree, Transfer Forest)—with various base models. The results showed that the instance-based approach outperformed the parameter-based approach, particularly with Transfer AdaBoost using ensemble learning base models. The Transfer AdaBoost approach with Gradient Boosting and Extra Trees achieved consistent and robust results across both C# and Python, with an 83% winning rate, as indicated by the Wilcoxon signed-rank test. These findings underscore the effectiveness of transfer learning for cross-language code smell detection, supporting its generalizability across different programming languages. Full article

To address the negative sample selection bias and limited interpretability of traditional debris-flow event susceptibility models, this study proposes a framework that enhances generalization by integrating negative sample screening via a stacking ensemble model with an interpretable random forest. Using Wenchuan County, Sichuan Province, as the study area, 19 influencing factors were selected, encompassing topographic, geological, environmental, and anthropogenic variables. First, a stacking ensemble—comprising logistic regression (LR), decision tree (DT), gradient boosting decision tree (GBDT), and random forest (RF)—was employed as a preliminary classifier to identify very low-susceptibility areas as reliable negative samples, achieving a balanced 1:1 ratio of positive to negative instances. Subsequently, a stacking–random forest model (Stacking-RF) was trained for susceptibility zonation, and SHAP (Shapley additive explanations) was applied to quantify each factor’s contribution. The results show that: (1) the stacking ensemble achieved a test-set AUC (area under the receiver operating characteristic curve) of 0.9044, confirming its effectiveness in screening dependable negative samples; (2) the random forest model attained a test-set AUC of 0.9931, with very high-susceptibility zones—covering 15.86% of the study area—encompassing 92.3% of historical debris-flow events; (3) SHAP analysis identified the distance to a road and point-of-interest (POI) kernel density as the primary drivers of debris-flow susceptibility. The method quantified nonlinear impact thresholds, revealing significant susceptibility increases when road distance was less than 500 m or POI kernel density ranged between 50 and 200 units/km²; and (4) cross-regional validation in Qingchuan County demonstrated that the proposed model improved the capture rate for high/very high susceptibility areas by 48.86%, improving it from 4.55% to 53.41%, with a site density of 0.0469 events/km² in very high-susceptibility zones. Overall, this framework offers a high-precision and interpretable debris-flow risk management tool, highlights the substantial influence of anthropogenic factors such as roads and land development, and introduces a “negative-sample screening with cross-regional generalization” strategy to support land-use planning and disaster prevention in mountainous regions. Full article

The Minimum Spanning Tree with Conflicting Edge Pairs is a generalization that adds conflict constraints to a classical optimization problem on graphs used to model several real-world applications. In recent years, several heuristic and exact approaches have been proposed to tackle this problem. In this paper, we present a mixed-integer linear program not previously applied to this problem, and we solve it with an open-source solver. Computational results for the benchmark instances commonly adopted in the literature of the problem are reported. The results indicate that the approach we propose obtains results aligned with those of the much more sophisticated approaches available, notwithstanding it being much simpler to implement. During the experimental campaign, six instances were closed for the first time, with nine improved best-known lower bounds and sixteen improved best-known upper bounds over a total of two hundred thirty instances considered. Full article

Accurate measurement of seedling traits is essential for plant phenotyping, particularly in understanding growth dynamics and stress responses. Elm trees (Ulmus spp.), ecologically and economically significant, pose unique challenges due to their curved seedling morphology. Traditional manual measurement methods are time-consuming, prone to human error, and often lack consistency. Moreover, automated approaches remain limited and often fail to accurately process seedlings with nonlinear or curved morphologies. In this study, we introduce GLEN, a deep learning-based model for detecting germinating elm seeds and accurately estimating their lengths of germinating structures. It leverages a dual-path architecture that combines pixel-level spatial features with instance-level semantic information, enabling robust measurement of curved radicles. To support training, we construct GermElmData, a curated dataset of annotated elm seedling images, and introduce a novel synthetic data generation pipeline that produces high-fidelity, morphologically diverse germination images. This reduces the dependence on extensive manual annotations and improves model generalization. Experimental results demonstrate that GLEN achieves an estimation error on the order of millimeters, outperforming existing models. Beyond quantifying germinating elm seeds, the architectural design and data augmentation strategies in GLEN offer a scalable framework for morphological quantification in both plant phenotyping and broader biomedical imaging domains. Full article

Cross-modal semantic segmentation of individual tree LiDAR point clouds is critical for accurately characterizing tree attributes, quantifying ecological interactions, and estimating carbon storage. However, in forest environments, this task faces key challenges such as high annotation costs and poor cross-domain generalization. To address these issues, this study proposes a cross-modal semantic transfer framework tailored for individual tree point cloud segmentation in forested scenes. Leveraging co-registered UAV-acquired RGB imagery and LiDAR data, we construct a technical pipeline of “2D semantic inference—3D spatial mapping—cross-modal fusion” to enable annotation-free semantic parsing of 3D individual trees. Specifically, we first introduce a novel Multi-Source Feature Fusion Network (MSFFNet) to achieve accurate instance-level segmentation of individual trees in the 2D image domain. Subsequently, we develop a hierarchical two-stage registration strategy to effectively align dense matched point clouds (MPC) generated from UAV imagery with LiDAR point clouds. On this basis, we propose a probabilistic cross-modal semantic transfer model that builds a semantic probability field through multi-view projection and the expectation–maximization algorithm. By integrating geometric features and semantic confidence, the model establishes semantic correspondences between 2D pixels and 3D points, thereby achieving spatially consistent semantic label mapping. This facilitates the transfer of semantic annotations from the 2D image domain to the 3D point cloud domain. The proposed method is evaluated on two forest datasets. The results demonstrate that the proposed individual tree instance segmentation approach achieves the highest performance, with an IoU of 87.60%, compared to state-of-the-art methods such as Mask R-CNN, SOLOV2, and Mask2Former. Furthermore, the cross-modal semantic label transfer framework significantly outperforms existing mainstream methods in individual tree point cloud semantic segmentation across complex forest scenarios. Full article