Search Results (1,233)

With the rapid development of vehicular network technology, data sharing and collaborative training among vehicles have become key to enhancing the efficiency of intelligent transportation systems. However, the heterogeneity of data and potential Byzantine attacks cause the model to update in different directions during the iterative process, causing the boundary between benign and malicious gradients to shift continuously. To address these issues, this paper proposes a privacy-preserving Byzantine-tolerant federated learning scheme. Specifically, we design a gradient detection method based on median absolute deviation (MAD), which calculates MAD in each round to set a gradient anomaly detection threshold, thereby achieving precise identification and dynamic filtering of malicious gradients. Additionally, to protect vehicle privacy, we obfuscate uploaded parameters to prevent leakage during transmission. Finally, during the aggregation phase, malicious gradients are eliminated, and only benign gradients are selected to participate in the global model update, which improves the model accuracy. Experimental results on three datasets demonstrate that the proposed scheme effectively mitigates the impact of non-independent and identically distributed (non-IID) heterogeneity and Byzantine behaviors while maintaining low computational cost. Full article

Foreign Object Debris (FOD) detection is paramount for airport operations. The precise identification and removal of FOD are critical for ensuring airplane flight safety. This study collected FOD images using optical imaging sensors installed at Urumqi Airport and created a custom FOD dataset based on these images. To address the challenges of small targets and complex backgrounds in the dataset, this paper proposes optimizations and improvements based on the advanced detection network Dab-Deformable. First, this paper introduces a Lightweight Deep-Shallow Feature Fusion algorithm (LDSFF), which integrates a hotspot sensing network and a spatial mapping enhancer aimed at focusing the model on significant regions. Second, we devise a Multi-Directional Deformable Channel Attention (MDDCA) module for rational feature weight allocation. Furthermore, a feedback mechanism is incorporated into the encoder structure, enhancing the model’s capacity to capture complex dependencies within sequential data. Additionally, when combined with a Threshold Selection (TS) algorithm, the model effectively mitigates the distraction caused by the serialization of multi-layer feature maps in the Transformer architecture. Experimental results on the optical small FOD dataset show that the proposed network achieves a robust performance and improved accuracy in FOD detection. Full article

Background: Mild Cognitive Impairment (MCI) represents an intermediate stage between normal cognitive aging and Alzheimer’s Disease (AD). Early and accurate identification of MCI is crucial for implementing interventions that may delay or prevent further cognitive decline. This study aims to develop a machine learning-based model for differentiating between Cognitively Normal (CN) individuals and MCI patients using data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Methods: An ensemble classification approach was designed by integrating Extra Trees, Random Forest, and Light Gradient Boosting Machine (LightGBM) algorithms. Feature selection emphasized clinically relevant biomarkers, including Amyloid-β 42, phosphorylated tau, diastolic blood pressure, age, and gender. The dataset was split into training and held-out test sets. A probability thresholding strategy was employed to flag uncertain predictions for potential deferral, enhancing model reliability in borderline cases. Results: The final ensemble model achieved an accuracy of 83.2%, a recall of 80.2%, and a precision of 86.3% on the independent test set. The probability thresholding mechanism flagged 23.3% of cases as uncertain, allowing the system to abstain from low-confidence predictions. This strategy improved clinical interpretability and minimized the risk of misclassification in ambiguous cases. Conclusions: The proposed AI-driven ensemble model demonstrates strong performance in classifying MCI versus CN individuals using multimodal ADNI data. Incorporating a deferral mechanism through uncertainty estimation further enhances the model’s clinical utility. These findings support the integration of machine learning tools into early screening workflows for cognitive impairment. Full article

This study investigates the impact and mechanisms of digital inclusive finance (DIF) on high-quality economic development in China. Drawing on panel data from 281 prefecture-level cities between 2011 and 2021, we employ a Spatial Durbin Model (SDM) to analyze both the direct effects and spatial spillovers of DIF. The results indicate that (1) DIF has a significantly positive effect on high-quality development, which remains robust after conducting various stability and endogeneity tests; (2) DIF strongly contributes to economic upgrading in eastern regions, while its impact is weaker or even negative in central and western regions, revealing notable regional disparities exist; (3) a key finding is the identification of a double-threshold effect, suggesting that the positive influence of DIF only emerges when financial and industrial development surpass certain thresholds; (4) results from the two-regime SDM further show that spillover effects are more prominent in non-central cities than in central ones; and (5) mechanism analysis reveals that DIF facilitates high-quality growth primarily by promoting industrial structure upgrading. These findings underscore the importance of region-specific policy strategies to enhance the role of DIF and reduce spatial disparities in development across China. Full article

The automated detection and classification of immature macauba (Acrocomia aculeata) fruits is critical for improving post-harvest processing and quality control. In this study, we present a comparative evaluation of two state-of-the-art YOLO architectures, YOLOv11x and YOLOv12x, trained on the newly constructed VIC01 dataset comprising 1600 annotated images captured under both background-free and natural background conditions. Both models were implemented in PyTorch and trained until the convergence of box regression, classification, and distribution-focal losses. Under an IoU (intersection over union) threshold of 0.50, YOLOv11x and YOLOv12x achieved an identical mean average precision (mAP₅₀) of 0.995 with perfect precision and recall or TPR (true positive rate). Averaged over IoU thresholds from 0.50 to 0.95, YOLOv11x demonstrated superior spatial localization performance (mAP_50–95 = 0.973), while YOLOv12x exhibited robust performance in complex background scenarios, achieving a competitive mAP_50–95. Inference throughput averaged 3.9 ms per image for YOLOv11x and 6.7 ms for YOLOv12x, highlighting a trade-off between speed and architectural complexity. Fused model representations revealed optimized layer fusion and reduced computational overhead (GFLOPs), facilitating efficient deployment. Confusion-matrix analyses confirmed YOLOv11x’s ability to reject background clutter more effectively than YOLOv12x, whereas precision–recall and F1-score curves indicated both models maintain near-perfect detection balance across thresholds. The public release of the VIC01 dataset and trained weights ensures reproducibility and supports future research. Our results underscore the importance of selecting architectures based on application-specific requirements, balancing detection accuracy, background discrimination, and computational constraints. Future work will extend this framework to additional maturation stages, sensor fusion modalities, and lightweight edge-deployment variants. By facilitating precise immature fruit identification, this work contributes to sustainable production and value addition in macauba processing. Full article

Climate change disrupts lives globally and poses significant challenges to mental health. Although several scales assess climate anxiety, many either conflate symptoms with coping responses or fail to adequately capture the core symptomatology of anxiety. Hence, this study aimed to develop and validate the Brief Anxiety Scale for Climate Change (BACC), a self-report measure designed to assess symptoms of climate anxiety. A preliminary pool of 21 items was generated based on the diagnostic criteria for generalized anxiety disorder and climate-related stress. Study 1 (n = 300) explored the factor structure via an exploratory factor analysis while Study 2 (n = 400) independently validated the structure via a confirmatory factor analysis (CFA). Analyses of the internal consistency, content validity, and discriminant validity helped refine the scale to a final 13-item version with two factors: cognitive and functional impairment. The CFA results indicated that all the fit indices met the recommended thresholds, and the final version demonstrated excellent internal consistency (Cronbach’s α = 0.92). Additionally, latent correlations revealed that climate anxiety was moderately associated with generalized anxiety and depression. The BACC was developed to identify individuals in the community who experience climate anxiety beyond an adaptive level, thereby promoting sustainable mental health in the context of climate change. These findings suggest that the BACC is a promising tool for assessing climate anxiety. With better identification, mental health professionals, community practitioners, and policymakers can utilize the scale to develop climate-sensitive public health programs and tailored intervention strategies. Full article

Madagascar harbors a rich marine biodiversity, yet detailed knowledge of its fish species remains limited. Of the 1689 species listed in 2018, only 22% had accessible cytochrome oxidase I (COI) sequences in public databases. In response to growing pressure on fishery resources, this study aims to strengthen biodiversity monitoring tools. Its objectives were to enrich the COI database for Malagasy marine fishes, create the first 12S reference library, and evaluate the taxonomic resolution of different 12S metabarcodes for eDNA analysis, namely MiFish, Teleo1, AcMDB, Ac12S, and 12SF1/R1. An integrated approach combining morphological, molecular, and phylogenetic analyses was applied for specimen identification of fish captured using various types of fishing gear in Toliara and Ranobe Bays from 2018 to 2023. The Malagasy COI database now includes 2146 sequences grouped into 502 Barcode Index Numbers (BINs) from 82 families, with 14 BINs newly added to BOLD (The Barcode of Life Data Systems), and 133 cryptic species. The 12S library comprises 524 sequences representing 446 species from 78 families. Together, the genetic datasets cover 514 species from 84 families, with the most diverse being Labridae, Apogonidae, Gobiidae, Pomacentridae, and Carangidae. However, the two markers show variable taxonomic resolution: 67 species belonging to 35 families were represented solely in the COI dataset, while 10 species from nine families were identified exclusively in the 12S dataset. For 319 species with complete 12S gene sequences associated with COI BINs (Barcode Index Numbers), 12S primer sets were used to evaluate the taxonomic resolution of five 12S metabarcodes. The MiFish marker proved to be the most effective, with an optimal similarity threshold of 98.5%. This study represents a major step forward in documenting and monitoring Madagascar’s marine biodiversity and provides a valuable genetic reference for future environmental DNA (eDNA) applications. Full article

Multibeam echosounder systems (MBESs) are widely used in unmanned surface vehicle swarms (USVs) to perform various marine bathymetry surveys because of their excellent performance. To address the challenges of systematic error superposition and edge beam error propagation in multibeam bathymetry surveying, this study proposes a novel error adjustment method integrating crossover error density clustering and beam incident angle (BIA) compensation. Firstly, a bathymetry error detection model was developed based on adaptive Density-Based Spatial Clustering of Applications with Noise (DBSCAN). By optimizing the neighborhood radius and minimum sample threshold through analyzing sliding-window curvature, the method achieved the automatic identification of outliers, reducing crossover discrepancies from ±150 m to ±50 m in the deep sea at a depth of approximately 5000 m. Secondly, an asymmetric quadratic surface correction model was established by incorporating the BIA as a key parameter. A dynamic weight matrix ω = 1/(1 + 0.5θ²) was introduced to suppress edge beam errors, combined with Tikhonov regularization to resolve ill-posed matrix issues. Experimental validation in the Western Pacific demonstrated that the RMSE of crossover points decreased by about 30.4% and the MAE was reduced by 57.3%. The proposed method effectively corrects residual systematic errors while maintaining topographic authenticity, providing a reference for improving the quality of multibeam bathymetric data obtained via USVs and enhancing measurement efficiency. Full article

Large turbine generators rely on shaft earthing brushes to safely divert harmful shaft currents to ground, protecting bearings from electrical damage. This paper presents a novel deep learning-based diagnostic framework to detect and classify faults in shaft earthing brushes of large turbine generators. A key innovation lies in the use of FFT-derived spectrograms from both voltage and current waveforms as dual-channel inputs to the CNN, enabling automatic feature extraction of time–frequency patterns associated with different SEB fault types. The proposed framework combines advanced signal processing and convolutional neural networks (CNNs) to automatically recognize fault-related patterns in shaft grounding current and voltage signals. In the approach, raw time-domain signals are converted into informative time–frequency representations, which serve as input to a CNN model trained to distinguish normal and faulty conditions. The framework was evaluated using data from a fleet of large-scale generators under various brush fault scenarios (e.g., increased brush contact resistance, loss of brush contact, worn out brushes, and brush contamination). Experimental results demonstrate high fault detection accuracy (exceeding 98%) and the reliable identification of different fault types, outperforming conventional threshold-based monitoring techniques. The proposed deep learning framework offers a novel intelligent monitoring solution for predictive maintenance of turbine generators. The contributions include the following: (1) the development of a specialized deep learning model for shaft earthing brush fault diagnosis, (2) a systematic methodology for feature extraction from shaft current signals, and (3) the validation of the framework on real-world fault data. This work enables the early detection of brush degradation, thereby reducing unplanned downtime and maintenance costs in power generation facilities. Full article

Background/Objectives: The overuse of short-acting β₂-agonists (SABAs) has been associated with increased asthma morbidity and mortality, prompting changes in treatment guidelines. However, the role of frequent short-acting muscarinic antagonists (SAMAs) use remains poorly defined and unaddressed in current recommendations. This study offers the first real-world analysis of SAMA overuse in asthma, quantifying its association with exacerbation risk and healthcare utilization and comparing its predictive value to that of SABAs. Methods: A retrospective multicenter cohort study analyzed electronic health records (EHRs) from 132 adults with asthma in the Spanish National Health System (SNS). Associations between annual SAMA use and clinical outcomes were assessed using negative binomial regression and 5000-sample bootstrap simulations. Interaction and threshold models were applied to explore how SAMA use affected outcomes and identify clinically actionable cutoffs. Results: SAMA use was independently associated with a 19.2% increase in exacerbation frequency per canister and a nearly sixfold increase in the odds of experiencing ≥1 exacerbation (OR = 5.97; 95% CI: 2.43–14.66). An inflection point at 2.5 canisters/year marked the threshold beyond which annual exacerbations exceeded one. Increased SAMA use was also associated with a higher number of respiratory consultations and with more frequent prescriptions of systemic corticosteroids and antibiotics. The risk increased more sharply with SAMAs than with SABAs, and the lack of correlation between them suggests distinct clinical patterns underlying their use. Conclusions: SAMA use emerges as a digitally traceable and clinically meaningful indicator of asthma instability. While the associations observed are robust and consistent across multiple outcomes, they should be considered provisional due to the study’s retrospective design and limited sample size. Replication in larger and more diverse cohorts is needed to confirm external validity. These findings support the integration of SAMA tracking into asthma management tools—alongside SABAs—to enable the earlier identification of uncontrolled disease and guide therapeutic adjustment. Full article

Target detection is the key technology of the apple-picking robot. To overcome the limitations of existing apple target detection methods, including low recognition accuracy of multi-species apples in complex orchard environments and a complex network architecture that occupies large memory, a lightweight apple recognition model based on the improved YOLO11 model was proposed, named YOLO-WAS model. The model aims to achieve efficient and accurate automatic multi-species apple identification while reducing computational resource consumption and facilitating real-time applications on low-power devices. First, the study constructed a high-quality multi-species apple dataset and improved the complexity and diversity of the dataset through various data enhancement techniques. The YOLO-WAS model replaced the ordinary convolution module of YOLO11 with the Adown module proposed in YOLOv9, the backbone C3K2 module combined with Wavelet Transform Convolution (WTConv), and the spatial and channel synergistic attention module Self-Calibrated Spatial Attention (SCSA) combined with the C2PSA attention mechanism to form the C2PSA_SCSA module was also introduced. Through these improvements, the model not only ensured lightweight but also significantly improved performance. Experimental results show that the proposed YOLO-WAS model achieves a precision (P) of 0.958, a recall (R) of 0.921, and mean average precision at IoU threshold of 0.5 (mAP@50) of 0.970 and mean average precision from IoU threshold of 0.5 to 0.95 with step 0.05 (mAP@50:95) of 0.835. Compared to the baseline model, the YOLO-WAS exhibits reduced computational complexity, with the number of parameters and floating-point operations decreased by 22.8% and 20.6%, respectively. These results demonstrate that the model performs competitively in apple detection tasks and holds potential to meet real-time detection requirements in resource-constrained environments, thereby contributing to the advancement of automated orchard management. Full article

With increasing global climate change, extreme weather threats to indoor environments are growing. Heatwave events provide essential data for building thermal resilience analysis. However, existing heatwave definition indicators vary widely and lack standardized criteria. To more accurately evaluate indoor overheating risks, this study compared indoor overheating responses under different heatwave definition indicators, considering the temporal disconnect between indoor and outdoor heat conditions. Focusing on Beijing, this study established an indoor–outdoor coupled heatwave evaluation framework using 1951–2021 meteorological data and the heat index as an overheating metric. By analyzing indoor overheating degree and overlap degree to characterize indoor–outdoor correlations, we concluded that different definitions of heatwaves lead to variations in identifications, while multidimensional indicators better capture extreme events. Heatwaves with prolonged duration and high intensity pose greater health risks. Although Beijing’s indoor thermal conditions are generally safe, peak heat indices during summer heatwaves exceed danger thresholds in some buildings, highlighting thermal safety concerns. The metrics for heatwave 6 and heatwave 7 optimally integrate indoor–outdoor characteristics with higher thresholds identifying more extreme events. These findings support the design of building thermal resilience, overheating early warnings, and climate-adaptive electrification strategies. Full article

Unplanned postoperative coronary angiography (uCAG) following isolated coronary artery bypass grafting (CABG) represents a significant clinical challenge, reflecting postoperative myocardial ischemia (PMI) with substantial impact on outcomes. The incidence of uCAG varies from 0.39 to 5.3%, depending on institutional protocols and diagnostic thresholds. Elevated cardiac biomarkers (high-sensitivity troponin and CK-MB), ECG changes, and hemodynamic instability are key indicators guiding uCAG. While associated with increased short-term mortality and morbidity, timely identification and treatment of graft-related complications via uCAG can improve midterm survival. Percutaneous coronary intervention (PCI) often emerges as the preferred therapeutic strategy over redo CABG. Future efforts should focus on refining risk stratification models, expanding the role of non-invasive imaging modalities, and validating early intervention strategies through prospective studies. Establishing standardized criteria for diagnosing and managing PMI remains critical to enhance outcomes and healthcare efficiency. Full article

The accurate identification of pulmonary nodules is critical for the early diagnosis of lung diseases; however, this task remains challenging due to inadequate feature representation and limited localization sensitivity. Current methodologies often utilize channel attention mechanisms and intersection over union (IoU)-based loss functions. Yet, they frequently overlook spatial context and struggle to capture subtle variations in aspect ratios, which hinders their ability to detect small objects. In this study, we introduce an improved YOLOV11 framework that addresses these limitations through two primary components: a spatial squeeze-and-excitation (SSE) module that concurrently models channel-wise and spatial attention to enhance the discriminative features pertinent to nodules and explicit aspect ratio penalty IoU (EAPIoU) loss that imposes a direct penalty on the squared differences in aspect ratios to refine the bounding box regression process. Comprehensive experiments conducted on the LUNA16, LungCT, and Node21 datasets reveal that our approach achieves superior precision, recall, and mean average precision (mAP) across various IoU thresholds, surpassing previous state-of-the-art methods while maintaining computational efficiency. Specifically, the proposed SSE module achieves a precision of 0.781 on LUNA16, while the EAPIoU loss boosts mAP@50 to 92.4% on LungCT, outperforming mainstream attention mechanisms and IoU-based loss functions. These findings underscore the effectiveness of integrating spatially aware attention mechanisms with aspect ratio-sensitive loss functions for robust nodule detection. Full article

Accurate online identification of abnormal sudden change observations is crucial for ensuring data reliability and has been a key challenge in dam safety monitoring. Traditional methods, such as those based on the Pauta criterion, often fail to effectively identify anomalies in complex data sequences like step-type and oscillatory-type data, primarily due to unreasonable early warning threshold settings. To address this issue, this paper introduces a novel method for setting early warning thresholds by combining the scale estimator ST based on the location M-estimator with the confidence interval radius D derived from predicted values, thereby constructing the MZ criterion with a threshold of 3ST+D. The proposed model demonstrates strong resistance to outliers and good robustness, effectively improving the accuracy of online anomaly identification for various data sequences. The MZ standard achieves a false alarm and missed detection rate of less than 10% in the monitoring data of the XB hydropower plant, which is a significant improvement in detection accuracy compared to the traditional Pauta standard. Engineering applications have shown that the MZ criterion-based identification method achieves a low misjudgment and omission rate, high recognition accuracy, and is highly reliable for online dam safety monitoring. This method holds significant value for both theoretical research and practical engineering applications. Full article