Search Results (2,450)

Hyperspectral image (HSI) denoising is challenged by complex spatial-spectral noise coupling. Existing deep learning methods, primarily designed for RGB images, fail to address HSI-specific noise distributions and spectral correlations. This paper proposes a Hybrid-Domain Synergistic Transformer (HDST) integrating frequency-domain enhancement and multiscale modeling. Key contributions include (1) a Fourier-based preprocessing module decoupling spectral noise; (2) a dynamic cross-domain attention mechanism adaptively fusing spatial-frequency features; and (3) a hierarchical architecture combining global noise modeling and detail recovery. Experiments on realistic and synthetic datasets show HDST outperforms state-of-the-art methods in PSNR, with fewer parameters. Visual results confirm effective noise suppression without spectral distortion. The framework provides a robust solution for HSI denoising, demonstrating potential for high-dimensional visual data processing. Full article

Kidney diseases represent an increasingly significant global public health challenge, with an estimated prevalence of around 10% among adults and a rising trend influenced by factors such as population aging and exposure to nephrotoxic agents. Given the limitations of conventional treatments, which often only slow disease progression and may cause adverse effects, there is growing interest in exploring alternative therapies based on natural compounds. Sansevieria trifasciata, commonly known for its ornamental use, has been widely used in traditional medicine in Mexico and other tropical regions due to its antioxidant, anti-inflammatory, and regenerative properties. Recently, its phytochemical profile has drawn scientific attention, particularly due to its high content of hydroxylated aromatic compounds such as flavonoids, terpenes, and phenolic acids, which may offer protective effects on kidney function. For this review, searches were conducted in specialized databases such as PubMed, Scopus, and Google Scholar, as well as platforms like ChEMBL and SWISS, selecting articles published between 2008 and 2025. This work aims to compile and critically analyze the available scientific literature on the nephroprotective potential of the phytochemicals found in S. trifasciata, and includes a preliminary exploration of their possible mechanisms of action using pharmacokinetic and pharmacodynamic prediction tools. Full article

Bolted connections are extensively utilized in aerospace, civil, and mechanical systems for structural assembly. However, inevitable structural vibrations can induce bolt loosening, leading to preload reduction and potential structural failure. Early-stage preload degradation, particularly during initial loosening, is often undetectable by conventional monitoring methods due to limited sensitivity and poor noise resilience. To address these limitations, this study proposes an intelligent bolt preload monitoring framework that combines electromechanical impedance (EMI) signal analysis with a parallel deep learning architecture. A multiphysics-coupled model of flange joint connections is developed to reveal the nonlinear relationships between preload degradation and changes in EMI conductance spectra, specifically resonance peak shifts and amplitude attenuation. Based on this insight, a parallel convolutional neural network (P-CNN) is designed, employing dual branches with 1 × 3 and 1 × 7 convolutional kernels to extract local and global spectral features, respectively. The architecture integrates dilated convolution to expand frequency–domain receptive fields and an enhanced SENet-based channel attention mechanism to adaptively highlight informative frequency bands. Experimental validation on a flange-bolt platform demonstrates that the proposed P-CNN achieves 99.86% classification accuracy, outperforming traditional CNNs by 20.65%. Moreover, the model maintains over 95% accuracy with only 25% of the original training samples, confirming its robustness and data efficiency. The results demonstrate the feasibility and scalability of the proposed approach for real-time, small-sample, and noise-resilient structural health monitoring of bolted connections. Full article

Depth completion aims to reconstruct dense depth maps from sparse LiDAR measurements guided by RGB images. Although BPNet enhanced depth structure perception through a bilateral propagation module and achieved state-of-the-art performance at the time, there is still room for improvement in leveraging 3D geometric priors and adaptively fusing heterogeneous modalities. To this end, we proposed GAC-Net, a Geometric–Attention Fusion Network that enhances geometric representation and cross-modal fusion. Specifically, we designed a dual-branch PointNet++-S encoder, where two PointNet++ modules with different receptive fields are applied to extract scale-aware geometric features from the back-projected sparse point cloud. These features are then fused using a channel attention mechanism to form a robust global 3D representation. A Channel Attention-Based Feature Fusion Module (CAFFM) was further introduced to adaptively integrate this geometric prior with RGB and depth features. Experiments on the KITTI depth completion benchmark demonstrated the effectiveness of GAC-Net, achieving an RMSE of 680.82 mm, ranking first among all peer-reviewed methods at the time of submission. Full article

With the vigorous development of deep learning technology, lane detection tasks have achieved phased results. However, existing lane detection models do not consider the unique geometric and visual features of lanes when dealing with some challenging scenarios, resulting in many difficulties and limitations. To this end, we propose a lane detection network based on full-dimensional convolutional Transformer (OTVLD-Net) to improve the adaptability of the model under extreme road conditions and better handle complex lane topology. In order to extract richer contextual features, we designed ODVT-Net, which uses full-dimensional dynamic convolution combined with improved feature flip fusion layer and non-local network layer, and aggregates lane symmetry features by utilizing the horizontal symmetry of lanes. A feature weight generation mechanism based on Transformer is designed, and a cross-attention mechanism between feature maps and lane requests is added in the decoding stage to enable the network to aggregate global feature information. At the same time, a vanishing point detection module is introduced, and a joint weighted loss function is designed to be trained in coordination with the lane detection task to improve the generalization ability of the lane detection model. Experimental results on the OpenLane and CurveLanes datasets show that the detection effect of the OTVLD-Net model has reached the current advanced level. In particular, the accuracy on the OpenLane dataset is 6.4% higher than the F1 score of the second-ranked model, and the average performance in different challenging scenarios is also improved by 8.9%. At the same time, when ResNet-18 is used as the template feature extraction network, the model achieves a speed of 103FPS and a computing power of 14.2 GFlops, achieving good performance while ensuring real-time performance. Full article

With the rising importance of nuclear energy in the global energy landscape, the sustainable development of uranium resources has garnered increasing attention. Salt lake brine, as an unconventional uranium source, holds significant potential due to its relatively high uranium concentration and the co-occurrence of valuable elements such as lithium, boron, and potassium. However, the high salinity and complex ionic composition of brine environments pose considerable challenges for the efficient and selective extraction of uranium. In recent years, the rapid advancement of novel adsorbent materials has provided promising technological pathways for uranium extraction from salt lake brine. This review systematically summarizes recent progress in the application of inorganic and carbon-based materials, organic polymers with functional group modifications, and biomass-derived and green adsorbents in this field. The construction strategies, performance characteristics, and adsorption mechanisms of these materials are discussed in detail, with particular emphasis on their selectivity and stability under complex saline conditions. Furthermore, the application status and future prospects of emerging materials and techniques—such as photocatalysis and electrochemistry—are also explored. This review aims to offer theoretical insights and technical references to support the sustainable exploitation of uranium resources from salt lake brines. Full article

High-resolution remote sensing images suffer from large intra-class variance, high inter-class similarity, and significant scale variations, leading to incomplete segmentation and imprecise boundaries. To address these challenges, Transformer-based methods, despite their strong global modeling capability, often suffer from feature confusion, weak detail representation, and high computational cost. Moreover, existing multi-scale fusion mechanisms are prone to semantic misalignment across levels, hindering effective information integration and reducing boundary clarity. To address these issues, a Category-Guided Transformer (CIGFormer) is proposed. Specifically, the Category-Information-Guided Transformer Module (CIGTM) integrates global and local branches: the global branch combines window-based self-attention (WSAM) and window adaptive pooling self-attention (WAPSAM), using class predictions to enhance global context modeling and reduce intra-class and inter-class confusion; the local branch extracts multi-scale structural features to refine semantic representation and boundaries. In addition, an Adaptive Wavelet Fusion Module (AWFM) is designed, which leverages wavelet decomposition and channel-spatial joint attention for dynamic multi-scale fusion while preserving structural details. Extensive experiments on the ISPRS Vaihingen and Potsdam datasets demonstrate that CIGFormer, with only 21.50 M parameters, achieves outstanding performance in small object recognition, boundary refinement, and complex scene parsing, showing strong potential for practical applications. Full article

Ten years after the Paris Agreement the escalating global geopolitical turmoil and waning interest in climate change’s effects, posit cities again as critical arenas for addressing the global energy transition. Drawing on the concept of the city as a living entity, the role of energy at the urban scale is considered not only as a technical infrastructure but as a complex system embedded in the spatial, political, and social fabric. The energy transition is situated within the broader context of urban governance and spatial planning, arguing that energy should be considered a foundational urban good essential to everyday life and ensuring equitable development. The study adopts a conceptual and literature-based approach, synthesizing insights from urban studies, energy geography, and climate governance literature. Special attention is given to the Italian context, where a lack of coordination across European, national, and regional political levels hinders energy transition efforts. Key references include theoretical frameworks on urban metabolism, socio-technical systems, and planning innovation, focusing on the intersection of infrastructure, policy, and local agency. The findings highlight the need to reframe energy planning as an integral part of urban and territorial governance. While grounded in Italy, the study’s insights reveal how governance fragmentation and multi-level coordination barriers resonate with European urban energy challenges, offering transferable lessons for territories with complex political and spatial systems. This would help integrate energy concerns into urban design, reduce consumption through spatial organization, and foster civic and institutional cooperation for rapid, often unplanned local energy actions to respond more swiftly to crises than traditional planning mechanisms. As a result, embedding energy within urban policy and spatial design fosters co-evolution between energy production, behavioral change, and infrastructural transformation. Recognizing this is vital for global urban policy and planning to drive resilient, equitable transitions in a rapidly changing energy landscape. Full article

Under the severe situation of increasing global climate change, it is urgent to improve the ability of cities to cope with climate change and achieve sustainable development. As a key institutional arrangement for China’s climate adaptation, the climate-resilient city initiative has been piloted in 67 cities across two batches since 2017, aiming to foster urban resilience through systematic governance. Based on complex adaptive system theory, this study constructs an urban ecological resilience evaluation framework under the “Pressure–State–Response” (PSR) model. Using panel data from 243 prefecture-level cities from 2010 to 2022 and a difference-in-differences model, it empirically examines the impact of climate-resilient city construction on ecological resilience, further exploring the moderating mechanism of government attention to environmental protection and spatial heterogeneity effects. Key findings include the following: (1) climate-resilient city construction significantly enhances urban ecological resilience, with pilot cities experiencing an average increase of approximately 0.74%; (2) government attention to environmental protection strengthens policy effectiveness, demonstrating a significant positive moderating effect; and (3) policy effects show notable regional variations, with more pronounced improvements in resource-based cities, western regions, and ecologically vulnerable areas. Full article

With the rapid growth of job-related crimes in developing economies, there is an urgent need for intelligent judicial systems to standardize sentencing practices. This study proposes a Multi-Level Feature Fusion Network (MLFFN) to enhance the accuracy and interpretability of sentencing predictions in job-related crime cases. The model integrates hierarchical legal feature representation, beginning with benchmark judgments (including starting-point penalties and additional penalties) as the foundational input. The frontend of MLFFN employs an attention mechanism to dynamically fuse word-level, segment-level, and position-level embeddings, generating a global feature encoding that captures critical legal relationships. The backend utilizes sliding-window convolutional kernels to extract localized features from the global feature map, preserving nuanced contextual factors that influence sentencing ranges. Trained on a dataset of job-related crime cases, MLFFN achieves a 6%+ performance improvement over the baseline models (BERT-base-Chinese, TextCNN, and ERNIE) in sentencing prediction accuracy. Our findings demonstrate that explicit modeling of legal hierarchies and contextual constraints significantly improves judicial AI systems. Full article

As the safety requirements of elevator systems continue to rise, the detection of loose bolts and the high-precision segmentation of anti-loosening lines have become critical challenges in elevator landing door inspection. Traditional manual inspection and conventional visual detection often fail to meet the requirements of high precision and robustness under real-world conditions such as oil contamination and low illumination. This paper proposes two improved algorithms for detecting loose bolts and segmenting anti-loosening lines in elevator landing doors. For small-bolt detection, we introduce the DS-EMA model, an enhanced YOLOv8 variant that integrates depthwise-separable convolutions and an Efficient Multi-scale Attention (EMA) module. The DS-EMA model achieves a 2.8 percentage point improvement in mAP over the YOLOv8n baseline on our self-collected dataset, while reducing parameters from 3.0 M to 2.8 M and maintaining real-time throughput at 126 FPS. For anti-loosening-line segmentation, we develop an improved DeepLabv3+ by adopting a MobileViT backbone, incorporating a Global Attention Mechanism (GAM) and optimizing the ASPP dilation rate. The revised model increases the mean IoU to 85.8% (a gain of 5.4 percentage points) while reducing parameters from 57.6 M to 38.5 M. Comparative experiments against mainstream lightweight models, including YOLOv5n, YOLOv6n, YOLOv7-tiny, and DeepLabv3, demonstrate that the proposed methods achieve superior accuracy while balancing efficiency and model complexity. Moreover, compared with recent lightweight variants such as YOLOv9-tiny and YOLOv11n, DS-EMA achieves comparable mAP while delivering notably higher recall, which is crucial for safety inspection. Overall, the enhanced YOLOv8 and DeepLabv3+ provide robust and efficient solutions for elevator landing door safety inspection, delivering clear practical application value. Full article

With the rapid expansion of global maritime transportation, infrared ship detection has become increasingly critical for ensuring navigational safety, enhancing maritime monitoring, and supporting environmental protection. To address the limitations of conventional methods in handling small-scale targets and complex background interference, in this paper, we propose an improved approach by embedding the convolutional block attention module (CBAM) into different components of the YOLOv5 architecture. Specifically, three enhanced models are constructed: the YOLOv5n-H (CBAM embedded in the head), the YOLOv5n-N (CBAM embedded in the neck), and the YOLOv5n-HN (CBAM embedded in both the neck and head). The comprehensive experiments are conducted on a publicly available infrared ship dataset to evaluate the impact of attention placement on detection performance. The results demonstrate that the YOLOv5n-HN achieves the best overall performance, attaining the mAP@0.5 of $86.83\%$, significantly improving the detection of medium- and large-scale maritime targets. The YOLOv5n-N exhibits superior performance for small-scale target detection. Furthermore, the incorporation of the attention mechanism substantially enhances the model’s robustness against background clutter and its discriminative capacity. This work offers practical guidance for the development of lightweight and robust infrared ship detection models. Full article

Early-onset colorectal cancer (EOCRC) is emerging as a significant global health concern, particularly among individuals under the age of 50. This alarming trend has coincided with an increase in the consumption of processed foods that often rely heavily on synthetic preservatives. At the same time, these additives play a critical role in ensuring food safety and shelf life. Growing evidence suggests that they may contribute to adverse gut health outcomes, which is a known risk factor in colorectal cancer development. At the same time, synthetic preservatives serve essential roles such as preventing microbial spoilage, maintaining color, and prolonging shelf life. Natural preservatives, on the other hand, not only provide antimicrobial protection but also exhibit antioxidant and anti-inflammatory properties. These contrasting functions form the basis of current discussions on their safety and health implications. Despite their widespread use, the long-term health implications of synthetic preservatives remain inadequately understood. This review synthesizes recent clinical, epidemiological, mechanistic, and toxicological data to examine the potential link between synthetic food preservatives and EOCRC. Particular focus is placed on compounds that have been associated with DNA damage, gut microbiota disruption, oxidative stress, and chronic inflammation, which are the mechanisms that collectively increase cancer risk. In contrast, natural preservatives derived from plants and microbes are gaining attention for their antioxidant, antimicrobial, and possible anti-inflammatory effects. While these alternatives show promise, scientific validation and regulatory approval remain limited. This review highlights the urgent need for more rigorous, long-term human studies and advocates for enhanced regulatory oversight. It advocates for a multidisciplinary approach to developing safer preservation strategies and highlights the importance of public education in making informed dietary choices. Natural preservatives, though still under investigation, may offer a safer path forward in mitigating EOCRC risk and shaping future food and health policies. Full article

The livestock sector, a crucial source of revenue and global food security, is facing serious challenges due to climate change driven by global warming. This leads to serious effects on animal health and productivity, making it difficult for the livestock industry to meet the global demand and sustain the livelihoods of farmers. The main factor affecting livestock’s productivity is heat stress. However, animals develop various adaptive mechanisms to cope with the effects of heat stress. Cellular and molecular responses act as key defense mechanisms, enabling animals adapt to environmental changes. The recent advancements in molecular biology have opened up opportunities for extensive research on epigenetics, which has a key role in regulating gene expression in animals in response to environmental stimuli. Such studies have gained considerable attention regarding heat acclimation in animals due to the fact that epigenetic mechanisms have been recognized as key players in long-term adaptation to high temperatures in farm animals. This review summarizes the different mechanisms and methodologies used to assess heat stress-associated epigenetic changes, including DNA methylation, which is an extensively studied epigenetic regulatory mechanism in relation to gene expression. The review also highlights the mechanisms and regulation of adaptation to heat stress in animals and collates information related to various epigenetic markers to assess the heat stress response, thereby aiding in improving thermal resilience in animals. Full article

Aiming at the problems of detail blurring and structural distortion caused by speckle noise, additive white noise and hybrid noise interference in synthetic aperture radar (SAR) images, this paper proposes a Dynamic Adaptive Transformer Network (DAT-Net) integrating a dynamic gated attention module and a frequency-domain multi-expert enhancement module for SAR image denoising. The proposed model leverages a multi-scale encoder–decoder framework, combining local convolutional feature extraction with global self-attention mechanisms to transcend the limitations of conventional approaches restricted to single noise types, thereby achieving adaptive suppression of multi-source noise contamination. Key innovations comprise the following: (1) A Dynamic Gated Attention Module (DGAM) employing dual-path feature embedding and dynamic thresholding mechanisms to precisely characterize noise spatial heterogeneity; (2) A Frequency-domain Multi-Expert Enhancement (FMEE) Module utilizing Fourier decomposition and expert network ensembles for collaborative optimization of high-frequency and low-frequency components; (3) Lightweight Multi-scale Convolution Blocks (MCB) enhancing cross-scale feature fusion capabilities. Experimental results demonstrate that DAT-Net achieves quantifiable performance enhancement in both simulated and real SAR environments. Compared with other denoising algorithms, the proposed methodology exhibits superior noise suppression across diverse noise scenarios while preserving intrinsic textural features. Full article