Search Results (824)

To address the challenges of image inpainting in scenarios with extensive or irregular missing regions—particularly detail oversmoothing, structural ambiguity, and textural incoherence—this paper proposes an Image Structure-Guided (ISG) framework that hierarchically integrates structural priors with semantic-aware texture synthesis. The proposed methodology advances a two-stage restoration paradigm: (1) Structural Prior Extraction, where adaptive edge detection algorithms identify residual contours in corrupted regions, and a transformer-enhanced network reconstructs globally consistent structural maps through contextual feature propagation; (2) Structure-Constrained Texture Synthesis, wherein a multi-scale generator with hybrid dilated convolutions and channel attention mechanisms iteratively refines high-fidelity textures under explicit structural guidance. The framework introduces three innovations: (1) a hierarchical feature fusion architecture that synergizes multi-scale receptive fields with spatial-channel attention to preserve long-range dependencies and local details simultaneously; (2) spectral-normalized Markovian discriminator with gradient-penalty regularization, enabling adversarial training stability while enforcing patch-level structural consistency; and (3) dual-branch loss formulation combining perceptual similarity metrics with edge-aware constraints to align synthesized content with both semantic coherence and geometric fidelity. Our experiments on the two benchmark datasets (Places2 and CelebA) have demonstrated that our framework achieves more unified textures and structures, bringing the restored images closer to their original semantic content. Full article

This present study proposes different machine learning-based predictors for the assessment of the residual compressive strength of Self-Compacting Concrete (SCC) subjected to high temperatures. The investigation is based on several literature algorithmic approaches based on Artificial Neural Networks with distinct training algorithms (Bayesian Regularization, Levenberg–Marquardt, Scaled Conjugate Gradient, and Resilient Backpropagation), Support Vector Regression, and Random Forest methods. A training database of 150 experimental data points is derived from a careful literature review, incorporating temperature (20–800 °C), geometric ratio (height/diameter), and corresponding compressive strength values. A statistical analysis revealed complex non-linear relationships between variables, with strong negative correlation between temperature and strength and heteroscedastic data distribution, justifying the selection of advanced machine learning techniques. Feature engineering improved model performance through the incorporation of quadratic terms, interaction variables, and cyclic transformations. The Resilient Backpropagation algorithm demonstrated superior performance with the lowest prediction errors, followed by Bayesian Regularization. Support Vector Regression achieved competitive accuracy despite its simpler architecture. Experimental validation using specimens tested up to 800 °C showed a good reliability of the developed systems, with prediction errors ranging from 0.33% to 23.35% across different temperature ranges. Full article

Pesticide exposure gradients between occupational, para-occupational, and general populations remain poorly characterized in North African agricultural contexts. This study evaluates urinary pesticide levels among farmers, indirectly exposed individuals, and a control group in Morocco’s Fez-Meknes region. A cross-sectional survey measured pesticide concentrations using LC-MS/MS in urine samples collected from 154 adults residing in both rural and urban areas. A questionnaire was used to gather information from participants regarding factors that may elevate the risk of pesticide exposure. The results revealed that farmers exhibited the highest concentrations of pesticides in their urine, including compounds classified as Ia/Ib by the World Health Organization. Indirectly exposed individuals showed moderate levels of contamination, with notable detections such as dichlofluanid (22.13 µg/L), while the control group had residual traces of neonicotinoids, notably imidacloprid (2.05 µg/L). Multivariate analyses revealed several sociodemographic factors significantly associated with increased pesticide exposure. The main risk factors identified included low education, residence in an agricultural area, and the consumption of untreated water (wells/rivers). Conversely, wearing personal protective equipment was associated with reduced urinary concentrations. This study highlights intense occupational exposure among farmers, secondary environmental contamination among residents living near treated areas, and the widespread dispersion of pesticide residues into urban areas. Full article

Accurate estimation of forest carbon stock is critical for understanding ecosystem carbon dynamics and informing climate mitigation strategies. This study presents a deep learning framework that integrates Sentinel-2 multispectral imagery with an enhanced residual neural network for estimating aboveground forest carbon stock in the Liuchong River Basin, Bijie City, Guizhou Province, China. The proposed model incorporates multiscale residual blocks and channel attention mechanisms to improve spatial feature extraction and spectral dependency modeling. A dataset of 150 ground inventory plots was employed for supervised training and validation. Comparative experiments with Random Forest, Gradient Boosting Decision Trees (GBDT), and Vision Transformer (ViT) demonstrate that the enhanced ResNet achieves the best performance, with a root mean square error (RMSE) of 23.02 Mg/ha and a coefficient of determination ($R^2$) of 0.773 on the test set. Spatial mapping results further reveal that the model effectively captures fine-scale carbon stock variations across mountainous forested landscapes. These findings underscore the potential of combining multispectral remote sensing and advanced neural architectures for scalable, high-resolution forest carbon estimation in complex terrain. Full article

Background: Poststroke dysphagia is a common condition that can lead to complications such as aspiration pneumonia and malnutrition, significantly affecting the quality of life. Most patients recover their swallowing function spontaneously, but in others difficulties persist beyond six months. Can we predict this in advance? On the other hand, there have been recent attempts to use machine learning to predict disease prognosis. Therefore, this study aims to investigate whether machine learning can predict the long-term prognosis for poststroke dysphagia using early videofluoroscopic swallowing study (VFSS) data. Methods: Data from VFSSs performed within 1 month of onset and swallowing status at 6 months were collected retrospectively in patients with dysphagia who experienced their first acute stroke at a university hospital. We selected 14 factors (lip closure, bolus formation, mastication, apraxia, tongue-to-palate contact, premature bolus loss, oral transit time, triggering of pharyngeal swallow, vallecular residue, laryngeal elevation, pyriform sinus residue, coating of the pharyngeal wall, pharyngeal transit time, and aspiration) from the VFSS data, scored them, and analyzed whether they could predict the long-term prognosis using five machine learning algorithms: Random forest, CatBoost classifier, K-neighbor classifier, Light gradient boosting machine, Extreme gradient boosting. These algorithms were combined through an ensemble method to create the final model. Results: In total, we collected data from 448 patients, of which 70% were used for training and 30% for testing. The final model was evaluated using accuracy, precision, recall, F1-score, and Area Under the Receiver Operating Characteristic Curve (AUC), resulting in values of 0.98, 0.94, 0.84, 0.88, and 0.99, respectively. Conclusions: Machine learning models using early VFSS data have shown high accuracy and predictive power in predicting the long-term prognosis of patients with poststroke dysphagia, and they are likely to provide useful information for clinicians. Full article

Vegetation is a fundamental component of terrestrial ecosystems. Understanding how vegetation changes and what drives these evolutions is crucial for developing a high-quality ecological environment and addressing global climate change. Extensive evidence has shown that China has undergone substantial vegetation changes, characterized primarily by greening. To quantify vegetation dynamics in China and assess the contributions of various drivers, we explored the spatiotemporal variations in the kernel Normalized Difference Vegetation Index (kNDVI) from 2001 to 2020, and quantitatively separated the influences of climate and human factors. The kNDVI time series were generated from the MCD19A1 v061 dataset based on the Google Earth Engine (GEE) platform. We employed the Theil-Sen trend analysis, the Mann-Kendall test, and the Hurst index to analyze the historical patterns and future trajectories of kNDVI. Residual analysis was then applied to determine the relative contributions of climate change and human activities to vegetation dynamics across China. The results show that from 2001 to 2020, vegetation in China showed a fluctuating but predominantly increasing trend, with a significant annual kNDVI growth rate of 0.002. The significant greening pattern was observed in over 48% of vegetated areas, exhibiting a clear spatial gradient with lower increases in the northwest and higher amplitudes in the southeast. Moreover, more than 60% of vegetation areas are projected to experience a sustained increase in the future. Residual analysis reveals that climate change contributed 21.89% to vegetation changes, while human activities accounted for 78.11%, being the dominant drivers of vegetation variation. This finding is further supported by partial correlation analysis between kNDVI and temperature, precipitation, and the human footprint. Vegetation dynamics were found to respond more strongly to human influences than to climate drivers, underscoring the leading role of human activities. Further analysis of tree cover fraction and cropping intensity data indicates that the greening in forests and croplands is primarily attributable to large-scale afforestation efforts and improved agricultural management. Full article

Image dehazing technology is a crucial component in the fields of intelligent transportation and autonomous driving. However, most existing dehazing algorithms only process images in the spatial domain, failing to fully exploit the rich information in the frequency domain, which leads to residual haze in the images. To address this issue, we propose a novel Frequency-domain Information Guided Symmetric Dual-branch Dehazing Network (FIGD-Net), which utilizes the spatial branch to extract local haze features and the frequency branch to capture the global haze distribution, thereby guiding the feature learning process in the spatial branch. The FIGD-Net mainly consists of three key modules: the Frequency Detail Extraction Module (FDEM), the Dual-Domain Multi-scale Feature Extraction Module (DMFEM), and the Dual-Domain Guidance Module (DGM). First, the FDEM employs the Discrete Cosine Transform (DCT) to convert the spatial domain into the frequency domain. It then selectively extracts high-frequency and low-frequency features based on predefined proportions. The high-frequency features, which contain haze-related information, are correlated with the overall characteristics of the low-frequency features to enhance the representation of haze attributes. Next, the DMFEM utilizes stacked residual blocks and gradient feature flows to capture local detail features. Specifically, frequency-guided weights are applied to adjust the focus of feature channels, thereby improving the module’s ability to capture multi-scale features and distinguish haze features. Finally, the DGM adjusts channel weights guided by frequency information. This smooths out redundant signals and enables cross-branch information exchange, which helps to restore the original image colors. Extensive experiments demonstrate that the proposed FIGD-Net achieves superior dehazing performance on multiple synthetic and real-world datasets. Full article

This study examines fatigue crack growth behavior in induction-hardened S38C axle steel with a gradient microstructure. High-frequency three-point bending fatigue tests were conducted to evaluate crack growth rates (da/dN) across three depth-defined regions: a hardened layer, a heterogeneous transition zone, and a normalized core. Depth-resolved da/dN–ΔK relationships were established, and Paris Law parameters were extracted. The surface-hardened layer exhibited the lowest crack growth rates and flattest Paris slope, while the transition zone showed notable scatter due to microstructural heterogeneity and residual stress effects. These findings provide experimental insight into the fatigue performance of gradient-structured axle steels and offer guidance for fatigue life prediction and inspection planning. Full article

A sensitive method was developed for detecting diazepam residues in aquatic products using magnetic dispersive solid-phase extraction (MDSPE) coupled with ultra-performance liquid chromatography–tandem mass spectrometry (UPLC-MS/MS). Samples extracted with 1% ammonia–acetonitrile were purified using synthesized Fe₃O₄@SiO₂-PSA nanoparticles via MDSPE before UPLC-MS/MS analysis. Separation was performed on a C₁₈ column with gradient elution using 0.1% formic acid–2 mM ammonium acetate/methanol. Detection employed positive electrospray ionization (ESI⁺) in multiple reaction monitoring (MRM) mode. Characterization confirmed Fe₃O₄@SiO₂-PSA’s mesoporous structure with excellent adsorption capacity and magnetic properties. The method showed good linearity (0.1–10 μg/L, r > 0.99) with an LOD and LOQ of 0.20 μg/kg and 0.50 μg/kg, respectively. Recoveries at 0.5–15.0 µg/kg spiking levels were 74.9–109% (RSDs 1.24–11.6%). This approach provides rapid, accurate, and high-precision analysis of diazepam in aquatic products, meeting regulatory requirements. Full article

Dendrobium, a prominent genus in the Orchidaceae family, has generated significant research attention due to its demonstrated biological potential, particularly its notable anti-inflammatory and antioxidant activities. In this study, two fractions of fermented Dendrobium officinale polysaccharides (FDOPs) were successfully isolated through a multi-stage purification strategy including gradient ethanol precipitation, gel column chromatography, and ion exchange chromatography with Lactobacillus reuteri CCFM863. Structural characterization revealed that both Dendrobium officinale polysaccharide fractions consisted of (1→4)-β-D-Manp, (1→4)-β-D-Glcp, and (1→4)-α-D-Glcp residues. The anti-inflammatory efficacy and keratinocyte-protective potential of FDOPs (FDOP-1A and FDOP-2A) were investigated by using lipopolysaccharide (LPS)-induced RAW264.7 and HaCaT cells models, which showed significant inhibitions on the inflammatory factors of monocyte chemoattractant protein-1 (MCP-1), tumor necrosis factor-alpha (TNF-α), nitric oxide (NO), and interleukin-1 beta (IL-1β); recovered levels of filaggrin (FLG), aquaporin 3 (AQP3), transient receptor potential vanilloid 4 (TRPV4), cathelicidin antimicrobial peptide (CAMP)/LL-37, and adiponectin (ADIPOQ); and the reduced protein expression of the TLR4/IκB-α/NF-κB/NLRP3 pathway. Notably, the FDOPs exhibited a remarkable reactive oxygen species (ROS) scavenging capacity, demonstrating superior antioxidant activity. Therefore, FDOPs show dual anti-inflammatory and antioxidant properties, making them suitable as active ingredients for modulating epidermal inflammation and promoting skin barrier repair. Full article

This study investigates pre-seismic ionospheric anomalies preceding the 2023 Jishishan Ms6.2 earthquake using total electron content (TEC) data derived from BDS geostationary orbit (GEO) satellites. Multi-scale analysis integrating Butterworth filtering and wavelet transforms resolved TEC disturbances into three distinct frequency regimes: (1) high-frequency perturbations (0.56–3.33 mHz) showed localized disturbances (amplitude ≤ 4 TECU, range < 300 km), potentially associated with near-field acoustic waves from crustal stress adjustments; (2) mid-frequency signals (0.28–0.56 mHz) exhibited anisotropic propagation (>1200 km) with azimuth-dependent N-shaped waveforms, consistent with the characteristics of acoustic–gravity waves (AGWs); and (3) low-frequency components (0.18–0.28 mHz) demonstrated phase reversal and power-law amplitude attenuation, suggesting possible lithosphere–atmosphere–ionosphere (LAI) coupling oscillations. The stark contrast between near-field residuals and far-field weak fluctuations highlighted the dominance of large-scale atmospheric gravity waves over localized acoustic disturbances. Geometry-based velocity inversion revealed incoherent high-frequency dynamics (5–30 min) versus anisotropic mid/low-frequency traveling ionospheric disturbance (TID) propagation (30–90 min) at 175–270 m/s, aligning with theoretical AGW behavior. During concurrent G1-class geomagnetic storm activity, spatial attenuation gradients and velocity anisotropy appear primarily consistent with seismogenic sources, providing insights for precursor discrimination and contributing to understanding multi-scale coupling in seismo-ionospheric systems. Full article

Wind shear at the Hong Kong International Airport (HKIA) poses a significant safety risk due to terrain-induced airflow disruptions near the runways. Accurate assessment is essential for safeguarding aircraft during take-off and landing, as abrupt changes in wind speed or direction can compromise flight stability. This study introduces a hybrid framework for short-term wind shear prediction based on data collected from Doppler LiDAR systems positioned near the central and south runways of the HKIA. These systems provide high-resolution measurements of wind shear magnitude along critical flight paths. To predict wind shear more effectively, the proposed framework integrates a signal processing technique with a deep learning strategy. It begins with optimized variational mode decomposition (OVMD), which decomposes the wind shear time series into intrinsic mode functions (IMFs), each capturing distinct temporal characteristics. These IMFs are then modeled using bidirectional gated recurrent units (BiGRU), with hyperparameters optimized via the Tree-structured Parzen Estimator (TPE). To further enhance prediction accuracy, residual errors are corrected using Extreme Gradient Boosting (XGBoost), which captures discrepancies between the reconstructed signal and actual observations. The resulting OVMD–BiGRU–XGBoost framework exhibits strong predictive performance on testing data, achieving R² values of 0.729 and 0.926, RMSE values of 0.931 and 0.709, and MAE values of 0.624 and 0.521 for the central and south runways, respectively. Compared with GRUs, LSTM, BiLSTM, and ResNet-based baselines, the proposed framework achieves higher accuracy and a more effective representation of multi-scale temporal dynamics. It contributes to improving short-term wind shear prediction and supports operational planning and safety management in airport environments. Full article

Graph attention networks are pivotal for modeling non-Euclidean data, yet they face dual challenges: training oscillations induced by projection-based high-dimensional constraints and gradient anomalies due to poor adaptation to heterophilic structure. To address these issues, we propose LDC-GAT (Lyapunov-Stable Graph Attention Network with Dynamic Filtering and Constraint-Aware Optimization), which jointly optimizes both forward and backward propagation processes. In the forward path, we introduce Dynamic Residual Graph Filtering, which integrates a tunable self-loop coefficient to balance neighborhood aggregation and self-feature retention. This filtering mechanism, constrained by a lower bound on Dirichlet energy, improves multi-head attention via multi-scale fusion and mitigates overfitting. In the backward path, we design the Fro-FWNAdam, a gradient descent algorithm guided by a learning-rate-aware perceptron. An explicit Frobenius norm bound on weights is derived from Lyapunov theory to form the basis of the perceptron. This stability-aware optimizer is embedded within a Frank–Wolfe framework with Nesterov acceleration, yielding a projection-free constrained optimization strategy that stabilizes training dynamics. Experiments on six benchmark datasets show that LDC-GAT outperforms GAT by 10.54% in classification accuracy, which demonstrates strong robustness on heterophilic graphs. Full article

In the field of intelligent decision-making, time-series data collected by sensors serves as the core carrier for interaction between the physical and digital worlds. Accurate analysis is the cornerstone of decision-making in critical scenarios, such as industrial monitoring and intelligent transportation. However, the inherent spatio-temporal coupling characteristics and cross-period long-range dependency of sensor data cause traditional time-series prediction methods to face performance bottlenecks in feature decoupling and multi-scale modeling. This study innovatively proposes a Spatio-Temporal Attention-Enhanced Network (TSEBG). Breaking through traditional structural designs, the model employs a Squeeze-and-Excitation Network (SENet) to reconstruct the convolutional layers of the Temporal Convolutional Network (TCN), strengthening the feature expression of key time steps through dynamic channel weight allocation to address the redundancy issue of traditional causal convolutions in local pattern capture. A Bidirectional Gated Recurrent Unit (BiGRU) variant based on a global attention mechanism is designed, leveraging the collaboration between gating units and attention weights to mine cross-period long-distance dependencies and effectively alleviate the gradient disappearance problem of Recurrent Neural Network (RNN-like) models in multi-scale time-series analysis. A hierarchical feature fusion architecture is constructed to achieve multi-dimensional alignment of local spatial and global temporal features. Through residual connections and the dynamic adjustment of attention weights, hierarchical semantic representations are output. Experiments show that TSEBG outperforms current dominant models in time-series single-step prediction tasks in terms of accuracy and performance, with a cross-dataset R² standard deviation of only 3.7%, demonstrating excellent generalization stability. It provides a novel theoretical framework for feature decoupling and multi-scale modeling of complex time-series data. Full article

Carbon market price prediction is critical for stabilizing markets and advancing low-carbon transitions, where capturing multifractal dynamics is essential. Traditional models often neglect the inherent long-term memory and nonlinear dependencies of carbon price series. To tackle the issues of nonlinear dynamics, non-stationary characteristics, and inadequate suppression of modal aliasing in existing models, this study proposes an integrated prediction framework based on the coupling of gradient-sensitive time-series adversarial training and dynamic residual correction. A novel gradient significance-driven local adversarial training strategy enhances immunity to volatility through time step-specific perturbations while preserving structural integrity. The GSLAN-BiLSTM architecture dynamically recalibrates historical–current information fusion via memory-guided attention gating, mitigating prediction lag during abrupt price shifts. A “decomposition–prediction–correction” residual compensation system further decomposes base model errors via wavelet packet decomposition (WPD), with ARIMA-driven dynamic weighting enabling bias correction. Empirical validation using China’s carbon market high-frequency data demonstrates superior performance across key metrics. This framework extends beyond advancing carbon price forecasting by successfully generalizing its “multiscale decomposition, adversarial robustness enhancement, and residual dynamic compensation” paradigm to complex financial time-series prediction. Full article