Search Results (146,530)

Slow-moving landslides can trigger severe disasters when activated by earthquakes, torrential rains, or typhoons. Early detection is crucial for mitigating loss of life and property damage. Interferometric Synthetic Aperture Radar (InSAR) technology is among the most effective techniques for detecting slow-moving landslides, though its accuracy can be further improved through integration with optical imagery and Digital Elevation Models (DEM). Current machine learning approaches that combine InSAR and optical data suffer from limited efficiency, poor transferability, and challenges in regional-scale application. To address these limitations, this study proposes a multimodal dual-path network that integrates InSAR products with textural information from optical imagery to detect slow-moving landslides. One path processes InSAR deformation rates and topographic factors, while the other incorporates texture information and auxiliary data. Together, these paths extract semantic information from high-dimensional spatial features and condense it into low-dimensional representations. A pyramid pooling module is employed to capture multi-scale features during low-level semantic extraction. For feature fusion, a rate-constrained adaptive module is introduced to enhance the contribution of deformation rates to slow-moving landslides. According to the results, the proposed method improves the F1-score for landslide detection by 6% compared to using InSAR products alone. These results provide reliable technical support for regional landslide inventory compilation and disaster management, as well as new insights for regional-scale surveys in slow-moving landslide-prone areas. Full article

Background/Objectives: The rise of artificial intelligence is injecting intelligence into the healthcare sector, including surgery. Vision-based intelligent systems that assist surgical procedures can significantly increase productivity, safety, and effectiveness during surgery. Surgical instruments are central components of any surgical intervention, yet detecting and locating them during live surgeries remains challenging due to adverse imaging conditions such as blood occlusion, smoke, blur, glare, low-contrast, instrument scale variation, and other artifacts. Methods: To address these challenges, we developed an advanced segmentation architecture termed the frozen-filters-based morphology-aware segmentation network (FFMS-Net). Accurate surgical instrument segmentation strongly depends on edge and morphology information; however, in conventional neural networks, this spatial information is progressively degraded during spatial processing. FFMS-Net introduces a frozen and learnable feature pipeline (FLFP) that simultaneously exploits frozen edge representations and learnable features. Within FLFP, Sobel and Laplacian filters are frozen to preserve edge and orientation information, which is subsequently fused with learnable initial spatial features. Moreover, a tri-atrous blending (TAB) block is employed at the end of the encoder to fuse multi-receptive-field-based contextual information, preserving instrument morphology and improving robustness under challenging conditions such as blur, blood occlusion, and smoke. Datasets focused on surgical instruments often suffer from severe class imbalance and poor instrument visibility. To mitigate these issues, FFMS-Net incorporates a progressively structure-preserving decoder (PSPD) that aggregates dilated and standard spatial information after each upsampling stage to maintain class structure. Multi-scale spatial features from different encoder levels are further fused using light skip paths (LSPs) to project channels with task-relevant patterns. Results/Conclusions: FFMS-Net is extensively evaluated on three challenging datasets: UW-Sinus-surgery-live, UW-Sinus-cadaveric, and CholecSeg8k. The proposed method demonstrates promising performance compared with state-of-the-art approaches while requiring only 1.5 million trainable parameters. In addition, an open-source large language model is integrated for non-clinical summarization of the surgical scene based on the predicted mask and deterministic descriptors derived from it. Full article

With the rapid development of the aviation industry, engines operate under extreme conditions of high temperature, high pressure, and high vibration, making them prone to surface damage such as ablation. Ablation not only affects the structural integrity of engine components but also threatens flight safety, making efficient and accurate detection of paramount importance. Traditional detection methods rely on manual visual inspection and non-destructive testing, which suffer from high subjectivity and low efficiency. In recent years, deep learning has achieved significant progress in industrial defect detection. However, conventional CNN-and Transformer-based architectures still suffer from substantial computational overhead and inadequate boundary segmentation accuracy in aero-engine ablation detection. This paper proposes a novel dual-pathway network Visual State-Space Residual Neural Network (VSS-ResNet) based on Mamba that combines Visual State Space (VSS) modules with ResNet50. This architecture leverages the global modeling capability of VSS modules and the local feature extraction capability of CNNs, effectively enhancing the accuracy and robustness of ablation boundary detection with the support of multi-scale feature fusion modules. Experimental results demonstrate that the proposed method achieves superior performance in mIoU, mPA, and Acc compared to mainstream segmentation models such as U-Net, Pyramid Scene Parsing Network (PSPNet), and DeepLab V3+ on a self-constructed engine endoscopic ablation dataset, validating its potential in intelligent aero-engine inspection. Full article

Most existing deep learning models for remote sensing scene classification (RSSC) adopt an offline learning paradigm, where all classes are jointly optimized on fixed-class datasets. In dynamic real-world scenarios with streaming data and emerging classes, such paradigms are inherently prone to catastrophic forgetting when models are incrementally trained on new data. Recently, a growing number of class-incremental learning (CIL) methods have been proposed to tackle these issues, some of which achieve promising performance by rehearsing training data from previous tasks. However, implementing such strategy in real-world scenarios is often challenging, as the requirement to store historical data frequently conflicts with strict memory constraints and data privacy protocols. To address these challenges, we propose a novel memory-efficient feature-replay CIL framework (FR-CIL) for RSSC that retains compact feature embeddings, rather than raw images, as exemplars for previously learned classes. Specifically, a progressive multi-scale feature enhancement (PMFE) module is proposed to alleviate representation ambiguity. It adopts a progressive construction scheme to enable fine-grained and interactive feature enhancement, thereby improving the model’s representation capability for remote sensing scenes. Then, a specialized feature calibration network (FCN) is trained in a transductive learning paradigm with manifold consistency regularization to adapt stored feature descriptors to the updated feature space, thereby effectively compensating for feature space drift and enabling a unified classifier. Following feature calibration, a bias rectification (BR) strategy is employed to mitigate prediction bias by exclusively optimizing the classifier on a balanced exemplar set. As a result, this memory-efficient CIL framework not only addresses data privacy concerns but also mitigates representation drift and classifier bias. Extensive experiments on public datasets demonstrate the effectiveness and robustness of the proposed method. Notably, FR-CIL outperforms the leading state-of-the-art CIL methods in mean accuracy by margins of 3.75%, 3.09%, and 2.82% on the six-task AID, seven-task RSI-CB256, and nine-task NWPU-45 datasets, respectively. At the same time, it reduces memory storage requirements by over 94.7%, highlighting its strong potential for real-world RSSC applications under strict memory constraints. Full article

This study presents a performance and techno-economic evaluation of a 24 kWp grid-connected rooftop photovoltaic system in Yeşilova, Burdur, Türkiye, based on measured operational data from 2024. Beyond conventional software comparisons, this research establishes a validated benchmarking protocol for medium-scale rooftop PV systems by quantifying the divergence between measured data and predictive modeling under fluctuating seasonal conditions. Measured results were compared with energy yield predictions from PVsyst and HelioScope. Key performance indicators, including final yield, performance ratio (PR), and capacity factor, were evaluated alongside main loss components. The system produced an annual energy output of 33,977.5 kWh, corresponding to an average PR of 75.7% and a capacity factor of 16.99%. Simulation results show deviations from measured values, with PVsyst moderately overestimating and HelioScope underestimating the annual yield. Thermal effects were identified as the dominant contributor to performance losses, particularly during elevated summer temperatures. A techno-economic assessment indicates a payback period of 8.4 years, a levelized cost of electricity (LCOE) of 0.0485 US$/kWh, and an internal rate of return (IRR) of 15.58%. These findings underline the importance of validating simulation-based assessments with site-specific measurements to improve the reliability of photovoltaic system performance and investment evaluations. Full article

Gully erosion is a significant threat to the sustainability of soil in Mediterranean basins. Despite its impact, there is a lack of research providing accurate regional-scale cartography of complete gully networks. This study aims to automatically map the gully network in the olive-growing landscapes of the Guadalquivir basin (Spain) using Machine Learning (ML) algorithms: Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and Logistic Regression (LR). We integrated these models with 17 predictive variables (including hydrotopographic, climatic, and edaphic factors) and the Gully Head Initiation (GHI) index. RF was the most suitable model, achieving an Area Under the Curve (AUC) of 0.91 and an F1-score of 0.83, and enabled the delineation of a gully network totalling 8439.05 km. Variable importance analysis revealed that flow accumulation (17.33%) and the GHI index (nearly 30%) were the primary predictors, with the Rainy Day Normal (RDN)-based formulation outperforming the maximum daily precipitation (Pmax)-based one. Spatially, countryside hill landscapes exhibited the highest gully densities (42.50 m/ha). The results demonstrate the effectiveness of combining ML with physically based indices to generate high-resolution gully cartography for soil conservation planning in Mediterranean olive groves. Full article

Accurate and early identification of breast cancer from mammography is key to reducing breast cancer mortality, and automated analysis is challenging due to subtle lesion appearances, heterogeneous breast density, and the variance caused by modality. Standard Convolutional Neural Networks (CNNs) are excellent at capturing localized textures, whereas Vision Transformers (ViTs) capture long-range dependencies; however, both often struggle to produce a unified representation that consistently supports diagnostic decision-making. To address these limitations, this study presents a dual-stream framework integrating ConvNeXt for high-fidelity local feature extraction with Swin Transformer V2 for hierarchical global context modeling. A Bi-Directional Cross-Guidance (BDCG) mechanism is added to harmonize interactions between the two feature domains and ensure mutual information learning in the representations. Furthermore, a Prototype-Anchored Similarity Head (PASH) is used to stabilize classification using distance-based reasoning instead of using linear separation. Comprehensive experiments show the effectiveness of the proposed method using two benchmark datasets. On Dataset 1, the model achieves accuracy: 98.8%, precision: 98.7%, recall: 98.6%, and F1 score: 97.2%, outperforming existing models based on CNN, ViTs, and hybrid architectures, and provides a lower inference time (8.3 ms/image). On the more heterogeneous Dataset 2, the model maintains strong performance, with an accuracy of 97.0%, precision of 95.4%, recall of 94.8%, and F1-score of 95.1%, demonstrating its resilience to domain shift and imaging variability. These results underscore the value of structural multi-scale feature interaction and prototype-driven classification for robust mammographic analysis. The consistent performance across internal and external evaluations indicates the potential for the proposed framework to be reliably applied in computer-aided screening systems. Full article

Under non-independent and identically distributed (Non-IID) conditions, significant variations exist in local model updates across clients and training phases during the collaborative modeling process of differential privacy federated learning (DP-FL). Fixed clipping thresholds and noise scales struggle to accommodate these diverse update differences, leading to mismatches between local update intensity and noise perturbations. This imbalance results in data privacy leaks and suboptimal model accuracy. To address this, we propose a differential privacy federated learning method based on adaptive clipping thresholds. During each communication round, the server adaptively estimates the global clipping threshold for that round using a quantile strategy based on the statistical distribution of client update norms. Simultaneously, clients adaptively adjust their noise scales according to the clipping threshold magnitude, enabling dynamic matching of clipping intensity and noise perturbation across training phases and clients. The novelty of this work lies in a quantile-driven, round-wise global clipping adaptation that synchronizes sensitivity bounding and noise calibration across heterogeneous clients, enabling improved privacy–utility behavior under a fixed privacy accountant. Using experimental results on the rail damage datasets, our proposed method slightly reduces the attacker’s MIA ROC-AUC by 0.0033 and 0.0080 compared with Fed-DPA and DP-FedAvg, respectively, indicating stronger privacy protection, while improving average accuracy by 1.55% and 3.35% and achieving faster, more stable convergence. We further validate its effectiveness on CIFAR-10 under non-IID partitions. Full article

Psychological comorbidity is increasingly recognized as a critical factor influencing outcomes in chronic illness management, particularly in patients with end-stage renal disease (ESRD). The present study examines the psychological burden associated with long-term hemodialysis in patients with ESRD, focusing on emotional distress and maladaptive personality traits. Specifically, it explores group differences between hemodialysis patients and matched healthy controls in levels of stress, anxiety, depression, and psychopathological tendencies, including neuroticism, paranoia, and psychopathy-related traits, as well as exploratory associations with treatment duration. A purposive sample of 60 participants (30 patients undergoing chronic hemodialysis and 30 age- and sex-matched healthy controls) was assessed using validated psychometric instruments: The Hospital Anxiety and Depression Scale, the Pichot Neuroticism and Psychopathy Questionnaire, and a 23-item stress measurement questionnaire adapted to the dialysis context. Both descriptive and inferential statistical analyses were conducted, including independent-samples t-tests and effect size calculations (Cohen’s d). Compared to healthy controls, hemodialysis patients exhibited significantly higher levels of psychological distress across multiple domains. Large between-group effect sizes were observed for depression (Cohen’s d = 1.26) and perceived stress (d = 1.51), while moderate effects were identified for anxiety (d = 0.70), neuroticism (d = 0.58), and psychopathy-related traits (d = 0.82). Exploratory analyses indicated that patients with less than 10 years of dialysis experience reported significantly higher stress levels than those with longer treatment duration, whereas differences in anxiety, depression, and personality traits by dialysis duration were not statistically significant. These findings highlight the substantial emotional burden associated with long-term hemodialysis and underscore the importance of routine psychological screening and early psychosocial interventions to support adaptation, treatment adherence, and quality of life in nephrology care. Full article

Self-supervised contrastive learning has become an effective approach for visual representation learning when large-scale annotation is impractical. In this study, we evaluate three widely used methods—SimCLR, MoCo v2, and BYOL—for large-scale stock keeping unit (SKU) recognition in retail environments. Experiments are conducted on the RP2K benchmark and a domain-specific in-house dataset (InSKU) using both linear probing and full fine-tuning. Under the original RP2K configuration with extended self-supervised pre-training, SimCLR achieves the highest Top-1 accuracy under linear evaluation (94.98%). In contrast, BYOL attains the highest performance under full fine-tuning (99.22% Top-1 accuracy). After filtering and deduplicating the dataset to reduce class imbalance and near-duplicate samples, MoCo v2 achieves competitive, and in some cases superior, linear performance under a reduced training budget. Cross-domain evaluation on InSKU indicates that SimCLR generalises more effectively under frozen-encoder constraints, whereas BYOL and MoCo v2 require full adaptation. These results highlight the sensitivity of contrastive representations to dataset composition, optimisation regime, and domain shift, providing practical guidance for deployment in dynamic retail settings. Full article

Background: The use of digital media in childhood offers both opportunities and risks. Digital stressors—such as excessive screen time, constant availability, information overload, and social media pressures—affect primary school children but have been rarely studied systematically. Despite growing research, no validated instruments adequately capture how younger children perceive and express digital stress. This study presents the development and validation of a three-dimensional instrument for children under 14: the “Digital Stress in Children” scale (DSS-CH). The DSS-CH is theory-driven and child-appropriate, with three interrelated but distinct dimensions: (1) excessive screen time, (2) compulsive media behavior, and (3) approval anxiety. Methods: In a cross-sectional survey of n = 907 Swiss primary school children (grades 5–6; ages 10–14), participants completed an online questionnaire in class. Latent variable modeling with cluster-robust inference accounted for classroom nesting. Competing models (1-, 2-, 3-factor CFA; ESEM; bifactor-ESEM) were evaluated. Results: The 1-factor CFA fit poorly (CFI ≈ 0.81; RMSEA ≈ 0.15), while the 3-factor CFA showed acceptable fit (CFI ≈ 0.96; RMSEA ≈ 0.07). Allowing cross-loadings improved fit substantially in the 3-factor ESEM and bifactor-ESEM (CFI ≈ 0.999; RMSEA ≈ 0.01), supporting a general digital stress factor alongside facet-specific variance. Subscales showed good reliability (ordinal α ≈ 0.81 − 0.89) and moderate intercorrelations (r ≈ 0.28 − 0.47). Scalar invariance across gender and age was supported (ΔCFI ≤ 0.003; ΔRMSEA ≤ 0.012). Conclusions: The DSS-CH demonstrates good reliability, model fit, and measurement invariance. It provides valid evidence for interpreting children’s digital stress as three related facets and can help identify elevated stress profiles to inform preventive efforts. Full article

Dust generated during coal mining and transportation poses serious threats to miners’ health, operational safety, and the surrounding environment. However, comprehensive review studies on dust suppression in coal mines remain limited, particularly those integrating dust movement laws with numerical simulation approaches. This review presents a systematic and reproducible analysis of dust control methods in coal mines with a particular focus on numerical simulation. Current research progress and development trends are summarized from three aspects: structural optimization of dust suppression devices, optimization of operating conditions, and ventilation system design. Existing studies indicate that structural improvements mainly concentrate on nozzle geometry, diameter, installation position, and spraying distance, while operating condition optimization primarily involves pressure regulation. Due to the complexity and high cost of full-scale experimental platforms, ventilation system optimization is largely achieved through numerical simulation, supplemented by field measurements. Studies based purely on numerical simulations remain limited in addressing the chemical modification of dust removers; however, with the advancement of molecular dynamics techniques, this area may represent a promising direction for future research. Full article

Background: Valproic acid (VPA) poisoning has a dynamic clinical course and may require extracorporeal toxin removal (ECTR) in severe cases. Intermittent hemodialysis is the preferred ECTR technique; however, clinical experience with expanded hemodialysis (HDx) using medium cut-off (MCO) membranes in acute VPA intoxication is scarce. We describe a case of severe VPA poisoning managed with intermittent HDx and outline the clinical rationale and kinetic response. Case Report: A 54-year-old woman presented to the emergency department after accidental presumably ingesting approximately 4 g of VPA, with depressed consciousness (Glasgow Coma Scale 7) and metabolic acidosis (pH 7.10, HCO₃⁻ 13 mmol/L, PCO₂ 50 mmHg, lactate 2.8 mmol/L, ionized calcium 0.8 mmol/L, elevated anion gap). Initial plasma VPA was 262.99 µg/mL, ammonia was 14 µmol/L, and cranial computed tomography showed no acute abnormalities. ECTR was initiated in the intensive care unit as intermittent HDx using an MCO dialyzer for 4 h. Serial VPA concentrations were obtained before treatment, at 2 h, and at the end of the session to guide real-time prescription adjustment, with an increase in blood flow from 200 to 230 mL/min. Results: VPA decreased from 262.99 µg/mL pre-HD to 141.48 µg/mL at 2 h (46.2% reduction) and 97.81 µg/mL at 4 h (62.8% reduction), with clear improvement in the level of consciousness. A mild post-dialysis rebound was observed (100.07 µg/mL at 14 h). The patient recovered without additional ECTR and was discharged with normalized VPA levels on follow-up. Conclusions: In this patient, intermittent HDx with an MCO membrane was feasible, well tolerated, and associated with rapid VPA clearance and neurological recovery. Serial drug monitoring enabled bedside optimization of the dialysis prescription and post-treatment evaluation. A single HDx session was sufficient, and VPA therapy was safely reintroduced under close monitoring. Full article

Background: Short-segment posterior fixation with intermediate pedicle screws is widely used for thoracolumbar junction (TLJ) burst fractures. However, the optimal penetration depth of intermediate screws remains controversial. The aim of this study was to evaluate whether intermediate screw penetration depth influences radiographic alignment and functional outcomes at 12 months following short-segment posterior fixation of AO Spine A3–A4 thoracolumbar burst fractures. Methods: This retrospective cohort study included 105 patients with AO Spine A3–A4 TLJ burst fractures treated between 1 January 2019 and 31 December 2022. All patients underwent short-segment posterior stabilization with intermediate screws at the fracture level. Penetration depth was categorized as either <50% (Group A) or ≥50% (Group B) of vertebral body depth. Radiographic parameters (kyphotic deformity, segmental kyphosis, sagittal index, anterior vertebral body height) and clinical outcomes (Visual Analog Scale and Oswestry Disability Index) were evaluated preoperatively and at 12 months. Results: Both groups demonstrated significant postoperative improvement in radiographic alignment and clinical outcomes. No statistically significant differences were detected between groups in kyphotic correction, loss of correction, pain reduction, disability scores, operative time, length of stay, or complication rates at 12 months. Conclusions: Within the limitations of this retrospective study, intermediate screw penetration depth did not significantly influence radiographic or clinical outcomes at 12 months. Screw length selection may therefore depend on anatomical considerations and surgeon preference rather than expected differences in clinical performance. Full article

To investigate the drag reduction mechanism of shark skin placoid scales and develop high-efficiency drag-reducing surfaces, this study designed and fabricated a biomimetic shark skin surface featuring staggered microscale groove structures. The fabrication process involved laser etching on silicon wafers to create a placoid microstructure template, followed by polydimethylsiloxane (PDMS) replication to obtain biomimetic shark skin samples. Sedimentation experiments demonstrated that the biomimetic surface significantly reduced settling time compared to a smooth surface, achieving a drag reduction rate of 5.65%. Further computational fluid dynamics (CFD) simulations were conducted to analyze the near-wall flow characteristics around the biomimetic surface. The results revealed that the drag reduction mechanism primarily stems from the effective regulation of near-wall laminar flow by the micro-groove structures: a low-velocity fluid layer formed within the grooves reduces the near-wall velocity gradient, thereby decreasing frictional drag, while stable recirculation zones develop within the grooves, contributing to momentum redistribution and reduced energy dissipation. Additionally, the staggered arrangement of the grooves promotes a smoother pressure distribution along the flow direction, mitigating pressure drag by reducing the pressure differential between windward and leeward surfaces. The experimental and simulation results showed excellent agreement (simulated drag reduction rate: 5.08%), collectively verifying the feasibility and effectiveness of the proposed biomimetic placoid structure in achieving fluid drag reduction. Full article