Search Results (51,818)

Forest fires occur frequently in China; however, the complex terrain and incomplete road networks severely constrain ground rescue efficiency. Accurate forest road information is essential for the optimization of emergency response and rescue force deployment. Existing road extraction algorithms are primarily designed for urban environments and exhibit limited efficacy in forest scenarios due to dense canopy, complex background interference and specific forest road features. To address this gap, this study proposes a forest road extraction method based on an enhanced DeepLabv3+ model using multi-temporal, high-resolution satellite imagery. Specifically, a Multi-Scale Channel Attention (MCSA) mechanism is embedded in skip connections to suppress background interference, while strip pooling is integrated into the Atrous Spatial Pyramid Pooling (ASPP) module to better capture slender road features. A composite Focal-Dice loss function is also constructed to mitigate sample imbalance. Finally, by applying the model in multi-temporal remote sensing images, a fusion strategy is introduced to integrate multi-seasonal road masks to enhance overall accuracy and topological integrity. Experimental results show that the proposed method achieves a precision of 54.1%, an F1-Score of 59.3%, and an IoU of 41.8%, effectively enhancing road continuity and providing robust technical support for fire-rescue decision-making. Full article

Infrared small target detection is a critical task in remote sensing. However, it remains highly challenging due to low contrast, heavy background clutter, and large variations in target scale. Traditional convolutional networks are inadequate for joint modeling, as they cannot effectively capture both fine structural details and global contextual dependencies. To address these issues, we propose FSGPNet, a frequency–spatial domain jointly guided perceptual network that explicitly exploits complementary representations in both the frequency and spatial domains. Specifically, a Frequency–Spatial Enhancement Module (FSEM) is introduced to strengthen target details while suppressing background interference through high-frequency enhancement and Perona–Malik diffusion. To enhance global context modeling, we propose a Multi-Scale Global Perception (MSGP) module that integrates non-local attention with multi-scale dilated convolutions, enabling robust background modeling. Furthermore, a Gabor Transformer Attention Module (GTAM) is designed to achieve selective frequency–spatial feature aggregation via self-attention over multi-directional and multi-scale Gabor responses, effectively highlighting discriminative structures of various small targets. Extensive experiments are conducted on two benchmark datasets (IRSTD-1K and NUDT-SIRST) that cover typical remote sensing infrared scenarios. Quantitative and qualitative results demonstrate that FSGPNet consistently outperforms state-of-the-art methods across multiple evaluation metrics. These findings validate the effectiveness and robustness of the proposed FSGPNet for detecting small infrared targets in remote sensing applications. Full article

The extensive cultivation scale of sugar beet seedlings has resulted in the necessity for accurate identification and monitoring of the seedling count, a task which has become crucial and highly challenging in the sugar industry. However, sugar beet seedlings in UAV aerial photography scenarios are mostly small targets with complex backgrounds. Existing general detection models not only have insufficient detection accuracy, but also struggle to balance computational efficiency and resource consumption. To meet the practical needs of field monitoring, this paper proposes the LDH-RTDETR, a sugar beet seedling detection model that balances high accuracy and light weight. This model uses LSNet for feature extraction to reduce size, adds a deformable attention (DAttention) module to capture fine-grained seedling features, and adopts HS-FPN to improve multi-scale feature fusion in the neck network. Experimental results show that the improved model significantly outperforms the original RT-DETR model, with a 3.6% increase in accuracy, a 2.1% increase in mAP50, a recall rate of 86.0%, and a final model size of only 43.3 MB, thus achieving an effective balance between accuracy and model size. This study’s improved model offers an efficient solution for large-area identification and counting of sugar beet seedlings, and is highly significant for advancing the automation of sugar crop field management and agricultural digital transformation. Full article

In abnormal goat lung sound recognition, high inter-class similarity and large intra-class variability pose significant challenges. To address this issue and improve recognition performance, we propose a deep learning model, AAF-SwinT, based on an improved Swin Transformer. The model replaces the original Swin Transformer self-attention module with Axial Decomposed Attention (ADA), modeling the temporal and frequency axes separately and integrating attention weights to mitigate inter-class feature similarity. Adaptive Spatial Aggregation for Patch Merging (ASAP) is designed to emphasize key time-frequency regions, and a Frequency-Aware Multi-Layer Perceptron (FAM) is introduced to model features across different frequency bands, further enhancing the discriminative ability for abnormal lung sounds. Experiments on a self-constructed goat lung sound dataset demonstrate that AAF-SwinT achieves an accuracy of 88.21%, outperforming existing mainstream Transformer-based models by 2.68–5.98%. Ablation studies further confirm the effectiveness of each proposed module, improving the accuracy of baseline Swin Transformer model from 85.53% to 88.21%. These results indicate that the proposed approach exhibits strong robustness and practical potential for abnormal lung sound recognition in goats, providing technical support for early diagnosis and management of respiratory diseases in large-scale goat farming. Full article

Accurate liver and tumor segmentation from abdominal computed tomography (CT) scans is essential for diagnosis and treatment planning; however, centralized deep learning approaches are often constrained by privacy regulations and inter-institution data-sharing limitations. To address these challenges, we propose a skip-free feature-forward collaborative segmentation framework called Feature-Forward Residual U-Net (FF-ResUNet), in which each institution executes the encoder locally and transmits only compact bottleneck representations to a central server. High-resolution encoder features and skip connections remain strictly within institutional boundaries, reducing privacy exposure and communication overhead. The server reconstructs segmentation masks using a multi-scale dilated residual decoder with progressive upsampling and returns lightweight updates for encoder refinement. FF-ResUNet is evaluated on the Liver Tumor Segmentation (LiTS) Challenge dataset, with cross-domain testing on 3D-IRCADb and AMOS-CT to assess robustness under distribution shifts and simulated multi-institution collaboration. On LiTS, the proposed framework achieves a liver Dice score of 0.952 ± 0.015 and a tumor Dice score of 0.737 ± 0.060, with a tumor HD95 of 10.9 ± 4.1 mm. Cross-domain experiments demonstrate stable generalization to unseen datasets, while multi-client simulations show improved performance as the number of participating institutions increases before saturation. Compared with skip-based collaborative U-Net architectures, FF-ResUNet reduces communication payload by 92–98% per training iteration while maintaining competitive segmentation accuracy. These results indicate that FF-ResUNet provides an effective balance between segmentation performance, communication efficiency, and privacy preservation evaluated under simulated multi-institution collaborative settings, supporting practical multi-center clinical deployment in bandwidth- and policy-constrained healthcare environments. Full article

Ensuring the structural reliability of power transmission networks is a fundamental prerequisite for the stable operation of modern energy systems. To address the challenges posed by complex weather interference and the small scale of insulator defects during power line inspections, this paper proposes LID-YOLO, a lightweight insulator defect detection network. First, to mitigate image feature degradation caused by weather interference, we design the C3k2-CDGC module. By leveraging the input-adaptive characteristics of dynamic convolution and the spatial preservation properties of coordinate attention, this module enhances feature extraction capabilities and robustness in complex weather scenarios. Second, to address the detection challenges arising from the significant scale disparity between insulators and defects, we propose Detect-LSEAM, a detection head featuring an asymmetric decoupled architecture. This design facilitates multi-scale feature fusion while minimizing computational redundancy. Subsequently, we develop the NWD-MPDIoU hybrid loss function to balance the weights between distribution metrics and geometric constraints dynamically. This effectively mitigates gradient instability arising from boundary ambiguity and the minute size of insulator defects. Finally, we construct a synthetic multi-weather condition insulator defect dataset for training and validation. Compared to the baseline, LID-YOLO improves precision, recall, and mAP@0.5 by 1.7%, 3.6%, and 4.2%, respectively. With only 2.76 M parameters and 6.2 G FLOPs, it effectively maintains the lightweight advantage of the baseline, achieving an optimal balance between detection accuracy and computational efficiency for insulator inspections under complex weather conditions. This lightweight and robust framework provides a reliable algorithmic foundation for automated grid monitoring, supporting the continuous and resilient operation of modern energy systems. Full article

Unmanned Aerial Vehicle (UAV)-assisted hierarchical federated learning (HFL) has emerged as a promising architecture for Internet of Things (IoT)-based smart agriculture, which enables scalable model training over large and sparse farmlands. In this setting, UAVs act as mobile edge servers, aggregating local updates from distributed agricultural IoT devices and relaying them to the cloud server. While HFL improves scalability and reduces communication overhead, it still faces critical security threats due to its reliance on public wireless channels and the vulnerability of model aggregation to malicious updates. In this paper, we propose a secure authentication scheme that integrates anomaly detection with elliptic curve cryptography (ECC)-based mutual authentication to protect both the communication and training phases. In the proposed scheme, UAVs authenticate participating clients before receiving their local models, then perform anomaly detection to identify and exclude malicious participants. If a client is found to be malicious, its identity credentials are revoked and broadcast by the cloud server to prevent future participation. The security of the proposed scheme is formally verified using Burrows–Abadi–Needham (BAN) logic, the Real-or-Random (RoR) model, and the Automated Validation of Internet Security Protocols and Applications (AVISPA) tool, along with informal security analysis. The performance evaluation includes comparisons of security features, computation cost, and communication cost with other related schemes, and an experimental assessment of anomaly detection performance. The results demonstrate that our scheme provides strong security guarantees, low overhead, and effective malicious client detection, making it well suited for UAV-assisted HFL in smart agriculture. Full article

Laser Powder Bed Fusion for metals (PBF-LB/M) is a complex additive manufacturing process in which metal powder is selectively melted layer-by-layer to fabricate 3D parts. Process parameters critically influence the resulting microstructure in nickel alloys, with features such as melt pool marks, grain size and orientation, porosity, and cracks serving as key process signatures. These features are typically analyzed post-process to identify suboptimal conditions. This research aims to develop automated post-process measurement and analysis techniques using image processing, pattern recognition, and statistical learning to correlate process parameters with part quality. Optical microscopy images of build surfaces are analyzed using machine learning algorithms to evaluate porosity, grain size, and relative density in fabricated test coupons. Effect plots are generated to identify trends related to increasing energy density. A novel deep learning approach based on Mask R-CNN is used to detect and segment melt pool regions in optical microscopy images. From the segmented regions, melt pool dimensions—such as width, depth, and area—are extracted using bounding geometry coordinates. Manually labeled images (Type I and Type II) are used to train the model. A comparison between ResNet-50 and ResNet-101 backbones shows that the ResNet-50-based model (Model 2) achieves superior performance, with lower training loss (0.1781 vs. 0.1907) and validation loss (8.6140 vs. 9.4228). Quantitative evaluation using the Jaccard index, precision, and recall metrics shows that the ResNet-101 backbone outperforms ResNet-50, achieving about 4% higher mean Intersection-over-Union, with values of 0.85 for Type I and 0.82 for Type II melt pools, where Type I is detected more accurately due to its more regular morphology and clearer boundaries. By extending Faster R-CNNs with a mask prediction branch, the method allows for precise melt pool measurements, providing valuable insights into process quality and dimensional accuracy, and aiding in the detection of defects in PBF-LB-fabricated parts. Full article

This study introduces a modified computational scheme for handling linear and nonlinear fractal time-dependent partial differential equations. The method is constructed using three different stages that provide third-order accuracy in the fractal time variable. The stability of the approach is examined using scalar fractal models and Fourier analysis, while convergence is established for coupled convection–diffusion systems. The numerical algorithm is applied to analyze the mixed convective flow of a Carreau–Yasuda non-Newtonian fluid over stationary and oscillating plates under the influence of viscous dissipation and magnetic field effects. For spatial discretization, the incompressible continuity equation is handled by a first-order difference scheme, whereas higher-order compact schemes are implemented for the momentum, thermal, and concentration equations. The numerical findings show that increasing the Weissenberg number and magnetic field inclination reduces the velocity distribution. An accuracy assessment against existing numerical techniques demonstrates that the present method yields smaller computational errors, particularly when central difference schemes are used in space. In addition, a surrogate machine learning model is developed to predict the skin friction coefficient and local Nusselt number using Reynolds, Weissenberg, Prandtl, and Eckert numbers as input features. The predictive capability of the model is validated through Parity plots, bar charts for sensitivity analysis, scatter visualization, and Taylor Diagrams, confirming strong agreement with the numerical results. Full article

Under high renewable energy penetration, wind power forecasting faces pronounced challenges due to strong randomness and uncertainty, making conventional point-forecast-centric paradigms insufficient for risk-aware and reliable power system scheduling. An uncertainty-aware temporal transformer framework for wind power forecasting is presented, integrating probabilistic modeling with deep temporal representation learning to jointly optimize prediction accuracy and uncertainty characterization. Crucially, rather than treating uncertainty quantification merely as a post-processing step, the central conceptual contribution lies in modularizing uncertainty directly within the attention mechanism. A probability-driven temporal attention mechanism is incorporated at the encoding stage to emphasize high-variability and high-risk time slices during feature aggregation, while a multi-quantile output and interval modeling strategy is adopted at the prediction stage to directly learn the conditional distribution of wind power, enabling simultaneous point and interval forecasts with statistical confidence. Extensive experiments on multiple public wind power datasets demonstrate that the proposed method consistently outperforms traditional statistical models, deep temporal models, and deterministic transformers, as validated by formal statistical significance testing. Specifically, the method achieves an MAE of $0.089$, an RMSE of $0.132$, and a MAPE of $10.84\%$ on the test set, corresponding to reductions of approximately $8\%$–$10\%$ relative to the deterministic transformer. In uncertainty evaluation, a PICP of $0.91$ is attained while compressing the MPIW to $0.221$ and reducing the CWC to $0.241$, indicating a favorable balance between coverage reliability and interval compactness. Compared with mainstream probabilistic forecasting methods, the model further reduces RMSE while maintaining coverage levels close to the 90% target, effectively mitigating excessive interval conservatism. Moreover, by adaptively generating heteroscedastic intervals that widen during high-volatility events and narrow under stable conditions, the model achieves a highly focused and effective capture of critical uncertainty information. Full article

Cascade dams fragment river habitats, but how seasonal hydrology modulates the biogeography and assembly of fish gut microbiota remains unclear. We surveyed gut bacterial communities of the omnivorous fish Saurogobio punctatus across 10 reaches separated by cascade dams in the Qijiang River during the wet (summer) and dry (winter) seasons using 16S rRNA gene amplicon sequencing. Sampling was synchronized among reaches to minimize temporal variability. Winter exhibited stronger differentiation among reaches and a steeper distance–decay pattern, and reach-scale environmental heterogeneity (especially dissolved inorganic nitrogen) was more stable under weak hydrodynamics. Null model analyses showed that stochastic processes dominated in summer, with dispersal-related processes and drift being prominent under high connectivity, whereas deterministic assembly increased in winter and was mainly associated with homogeneous selection. Compositionality-aware differential abundance analysis (ANCOM-BC2) identified 409 genera with a significant seasonal differential abundance after adjusting for reach (FDR q < 0.05). Random forest classification, used as a complementary prediction-oriented feature-ranking analysis, indicated higher reach discriminability in winter, with Nitrospirota ranking among the top features. PLS-PM indicated that α-diversity had the strongest direct association with β-diversity in the specified model, whereas spatial and environmental effects were linked to β-diversity mainly through indirect, α-diversity-mediated pathways. Biologically, α-diversity may reflect an integrative summary of the within-gut taxon pool shaped by host filtering and environmentally derived inputs (e.g., diet- and habitat-associated sources), which can influence the magnitude of between-reach compositional turnover. Together, these results show that seasonal hydrological regimes tune spatial turnover and assembly of fish gut microbiota in cascade-regulated rivers. Full article

In complex traffic environments such as low light, strong glare, occlusion and at night, systems that rely solely on visible light single sensors for pedestrian detection have drawbacks such as low detection accuracy and poor robustness. Based on the YOLOv8 convolutional network, this paper adopts a dual-branch structure to process visible light and infrared images simultaneously, fully utilizing feature information at different scales to effectively detect pedestrian targets in complex and changeable environments. To address the issues of insufficient interaction of modal feature information and fixed fusion weights, a cross-modal feature interaction and enhancement mechanism was introduced. A modal-channel interaction block (MCI-Block) was designed, in which residual connection structures and weight interaction were added within the module to achieve feature enhancement and filter out noise information. Introduce a dynamic weighted feature fusion strategy, adaptively adjusting the contribution ratio of different modal features in the fusion process, aiming to enhance the discrimination ability of the key pedestrian area. The training and testing of the network designed in this paper were completed on the visible light and infrared pedestrian detection dataset LLVIP and Kaist. At the same time, the test results of the dual-branch model and the model designed in this paper were further verified in actual traffic scenarios. The results show that the dual-branch YOLOv8 network for visible light and infrared images, which was constructed in this paper, can reliably enhance the detection performance of pedestrian targets in complex traffic environments, including accuracy, recall rate, and mAP@0.5, etc., thereby improving the robustness of pedestrian detection. Full article

Background: Dengue virus (DENV) does not have any effective antiviral therapy. The Cinnamomum verum has cinnamic acid and oleic acid that could inhibit important viral proteins. Aim: To compare their inhibitory capacity with the key DENV proteins through molecular docking, molecular dynamics and in silico ADMET. Methods: Phytochemical profiling of the ethanolic extract of the bark was done by GCMS. AutoDock Vina (version 1.2.0) was used to dock cinnamic acid and oleic acid to key proteins of DENV (NS5, NS3, and envelope) in the presence of ribavirin as the reference. The best complexes were then subjected to 50 ns of molecular dynamics simulation and stability measured by RMSD, RMSF, Rg, SASA, hydrogen bonding and RDF. Validated in silico tools were used to predict the ADMET properties. Results: Analysis of GC–MS revealed cinnamic acid (85.92%) and oleic acid (5.33%). The outcome of docking was that the cinnamic acid had the greatest affinity with NS5 (−5.970 kcal/mol) and the capsid protein (−5.755 kcal/mol), and oleic acid showed the highest affinity with the capsid (−6.150 kcal/mol) and then with NS5 (−5.209 kcal/mol). Both ligands had a relatively weak interaction with NS3. Simulation of the molecular dynamics showed the stability of the top complexes, especially the cinnamic acid–NS5 complex, that retained low RMSD (1.6–1.9 A), stable Rg and SASA profiles, and continued hydrogen bonding during the 50 ns period. The use of cinnamic acid in ADMET projections was more preferable, as it was more soluble, orally bioavailable (0.91), and drug-like (QED 0.65), but oleic acid revealed higher lipophilicity and lower drug-like properties (QED 0.29). Conclusions: Cinnamic acid showed specificity towards the NS5 proteins with the help of stable dynamics and good predicted pharmacokinetics, which are features that make it a promising multi-target anti-DENV scaffold. Oleic acid exhibited poor affinity and poor pharmacokinetic properties. The findings are predictive and must be validated using biochemical, cellular, and toxicological means to prove the antiviral efficacy and safety. Full article

This study proposes a four-dimensional Historical Building Defect Information Modeling (HBDIM) framework designed to support the documentation, diagnosis, and conservation of deteriorated historic stucco elements. The framework integrates multi-source digital documentation techniques, including terrestrial laser scanning (TLS), high-resolution photogrammetry, and automated total station measurements with laboratory-based material diagnostics to create a unified digital environment for defect detection and conservation assessment. The approach was applied to the Baron Empain Palace in Egypt as a representative case study of complex architectural heritage affected by material deterioration. Within the HBDIM workflow, point cloud processing and defect-oriented information modeling were used to identify and spatially localize deterioration features such as cracking, erosion, and material loss. Laboratory investigations—including computed tomography (CT), scanning electron microscopy (SEM), transmission electron microscopy (TEM), and X-ray fluorescence (XRF)—were conducted to evaluate the effectiveness of calcium hydroxide nanoparticle consolidation treatments and to relate microstructural material behavior to spatially mapped defects within the digital model. Mechanical testing demonstrated a significant improvement in material performance, with treated stucco samples exhibiting an average compressive strength increase of approximately 69.06% compared to untreated specimens. The results demonstrate that integrating digital documentation, defect-oriented modeling, and material diagnostics within a four-dimensional framework provides a robust platform for linking geometric deterioration patterns with material-level conservation performance. By embedding diagnostic data and treatment outcomes within a temporally structured digital model, the HBDIM approach supports preventive conservation strategies, long-term monitoring, and data-driven decision-making in sustainable heritage management. Full article

Natural anthraquinones possess a wide range of biological activities, including antibacterial, antiviral, antitumor, and antioxidant effects. However, studies on their ability to inhibit amyloid protein aggregation remain relatively limited. In this study, we used insulin as a model protein to investigate the anti-amyloidogenic potential of several natural anthraquinones. Specifically, the inhibitory mechanisms of five anthraquinones (emodin, anthraflavin, aloe-emodin, alizarin, and purpurin) on insulin amyloid fibrillation were explored in both dilute and crowded environments (PEG 2000 and PEG 4000). Multidisciplinary analytical results demonstrated that all five anthraquinones could effectively inhibit insulin amyloid fibrillation in both dilute and crowded environments. Simultaneously, crowded agents themselves also exhibited inhibitory effects on insulin amyloid aggregation. However, the inhibitory efficacy of anthraquinones was weaker in crowded environments than in dilute solutions, indicating that although crowded agents themselves suppressed insulin aggregation, they may interfere with the regulatory roles of anthraquinones on insulin aggregation behavior. Interestingly, purpurin showed stronger inhibitory activity in crowded environments compared to dilute solutions. Furthermore, fluorescence spectral analysis suggested that the quenching mechanism of insulin by all these anthraquinones was identified as static quenching mode. Molecular simulation studies revealed that anthraquinones could bind to the aggregation-prone regions of insulin via hydrogen bonding and hydrophobic interactions, thereby inhibiting insulin amyloid aggregation. Notably, the inhibitory capacity of these compounds was correlated with their structural features and the binding affinities to insulin. Collectively, this study explored the anti-amyloid activity of anthraquinones, which held significant research value for the development of potential therapeutic agents for amyloid-associated proteinopathies. Full article