Search Results (16,895)

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

Soil moisture (SM) in the mountains is critical for agropastoral productivity, and it is subject to both large-scale climate gradients and fine-scale effects of terrain, vegetation and soil. However, how the climate, topography, soil and vegetation factors impact surface SM spatiotemporal dynamics remains elusive in mountainous terrains, due to their complex interactions. Based on multi-source datasets, this study employs the structural equation model to investigate the impact pathways of climate and vegetation factors on annual surface SM dynamics from the year 2000 to 2022 in the Tianshan Mountains of China (TS). We also utilize the factor and interaction detectors of Geographical Detector to explore the individual and interactive effects of climate, topography, soil and vegetation factors on the spatial pattern of the annual surface SM. Moreover, their integrated impacts on the spatiotemporal dynamics of annual surface SM were investigated based on the explanatory power from the factor detector and total effects from structural equation modeling. The results showed that the multi-year average surface SM was 0.21 m³·m⁻³ for the whole region, with greater values in areas with dense vegetation and high elevation. Annual surface SM exhibited significant increasing trends across different land cover classifications and elevation zones, which was directly influenced by vegetation greenness enhancement. Precipitation (PRE) and relative humidity (RH) also significantly influenced the temporal variations in surface SM through their indirect effect on vegetation greenness, while these indirect effects were much lower than the direct effect of vegetation greenness. RH, PRE and surface net solar radiation (SSR) showed strong individual and interactive effects on the spatial distribution of surface SM, particularly the interactive effects of RH and PRE with wind speed (WS). Surface SM was highly sensitive to RH and PRE in the central TS. Overall, vegetation greenness, PRE and RH were the main drivers of surface SM variations across both temporal and spatial scales, while SSR, total evaporation and WS primarily shaped its spatial distribution. These insights enhance our understanding of land–atmosphere interactions in mountainous areas and provide scientific references for sustainable agropastoral water resource management under global warming. Full article

The aim of the paper was to analyse the genesis of the idea of carbon footprint (CF) reporting, the current EU regulations in force in this regard, and to provide a concrete example of practical measures in poultry production. The CF is the total sum of greenhouse gas (GHG) emissions generated directly or indirectly by an organisation, product, service, event or human activity, expressed as a CO₂ equivalent. Livestock production accounts for 12% to 14.5% of global methane and nitrous oxide emissions. GHG emissions from livestock production are closely linked to the species of animals; the highest CF values apply to products derived from ruminants, but poultry is also considered an environmental threat, inter alia due to the production scale. The CF of poultry production is not uniform and depends on many factors, including the farm location and climatic conditions of the region, the profile of production, its stage, the birds feeding and CF method of analysis. Industrial development is a continuous process that must align with the principles of sustainability and EU climate policy; therefore, it is necessary to look for and implement solutions to reduce its emissions in line with evolving European legal standards. Full article

Existing autonomous navigation systems for Unmanned Aerial Vehicles (UAVs) face the dual challenges of local minima entrapment and computational complexity that scales with environmental density. This paper proposes a hierarchical navigation architecture integrating deep representation learning with an improved Vortex Artificial Potential Field (APF). At the decision layer, a Convolutional Neural Network (CNN) encodes the environment as a fixed-dimensional tensor and generates global waypoints with constant-time inference, independent of obstacle count. At the control layer, a Vortex APF resolves the Goal Non-Reachable with Obstacles Nearby (GNRON) problem and limit-cycle oscillations through tangential rotational potentials, achieving significant improvement in trajectory smoothness compared to traditional APF methods. A closed-loop replanning mechanism further ensures robust performance under execution drift. Experiments across varying obstacle densities demonstrate that the combined system achieves high navigation success rates in dense environments with substantially reduced computation time compared to sampling-based planners such as Rapidly exploring Random Tree star (RRT*), while maintaining superior trajectory quality. This architecture provides a computationally efficient solution for resource-constrained UAV platforms operating in GPS-denied or obstacle-rich environments such as warehouses, forests, and disaster sites. Full article

Hydropower is a cornerstone of global renewable energy; however, reservoir sedimentation directly undermines its benefits and operational lifespan. A critical, often overlooked, aspect of sedimentation is the compaction of fine-grained deposits, which introduces systematic discrepancies between standard siltation calculation methods. This study addresses this gap by developing a machine learning-based model to quantify sediment compaction and correct siltation estimates using the Xiluodu Hydropower Station on the Jinsha River, China, as a case study from 2014 to 2020. Based on hydrological, sediment, and fixed-section monitoring data, we applied five machine learning algorithms (Linear Regression, Neural Network, Random Forest, Gradient Boosting, and Support Vector Regression) to establish a relationship between the compaction thickness and the following key predictors: Year, Cumulative Sediment Thickness, Annual Sediment Thickness, and Distance to the Dam. The results demonstrate that the Neural Network (NN) model significantly outperforms traditional models, effectively capturing complex, nonlinear compaction dynamics with strong predictive accuracy (test R² = 0.766, RMSE = 0.047 m) and no significant overfitting. SHAP analysis revealed the dominant influences of consolidation time (years) and overburden stress (Cumulative Sediment Thickness), linking the model’s predictions to fundamental geotechnical principles. Applying the NN model to correct for the cross-sectional volume method markedly improved its consistency with the independent sediment transport method, reducing the average relative difference from −33.7% to −6.5% (2016–2020). This study provides the first quantitative, continuous (198 km, 221 sections) assessment of reservoir-scale sediment compaction, confirming its widespread existence and demonstrating its critical role in the long-standing methodological discrepancies. Our study transformed compaction from an acknowledged phenomenon into a quantifiable correction, offering a novel, data-driven framework to enhance the accuracy of reservoir sedimentation assessments globally. Full article

In an era of rapid urbanisation and climate challenges, understanding how urban land patterns contribute to resilience is crucial for sustainable development. This theoretical review introduces a novel framework positing that greater heterogeneity in plot sizes and land uses enhances urban resilience by promoting the long-term preservation of built environments, multifunctional spaces, and socio-cultural adaptability. Drawing on urban morphology, assemblage theory, and resilience science, we argue that fragmented ownership in small-plot fabrics acts as a barrier to large-scale redevelopment, fostering diversity that buffers against shocks. Through comparative case studies of Venice (Italy), Tokyo (Japan), Hong Kong, Mexico City (Mexico), and York (UK), we illustrate how historical small-plot subdivisions have endured centuries, supporting ecological, economic, and social sustainability. The analysis reveals common patterns: ownership fragmentation preserves fine-grained urban forms, enabling adaptive reuse (exaptation) and inclusivity. The five case studies serve an illustrative function, demonstrating how the theoretical linkages between plot heterogeneity, institutional friction, incremental transformation, and long-term resilience outcomes can plausibly operate in real-world historic urban fabrics. This paper addresses a gap in the literature by synthesising plot-level heterogeneity with broader resilience outcomes, offering policy implications for protecting such fabrics amid global urbanisation pressures. The findings align with land system science, emphasising multifunctionality for regenerative urbanism. Full article

Global climate change and increasingly complex geological conditions have led to more frequent landslides in the red-bed sedimentary layers of western Sichuan, China, posing severe threats to human safety and hindering progress toward regional Sustainable Development Goals (SDGs), particularly those related to disaster risk reduction and ecological protection. To address this challenge and advance sustainable disaster management, this study proposes a lightweight hybrid model, termed Transformer–Attention–LSTM, which integrates the global attention mechanism of Transformers with the local time-series modeling capabilities of Long Short-Term Memory networks. Focusing on the Kuyaogou landslide, the model achieves an optimal balance between parameter scale, sequence length, and prediction accuracy. The mean Coefficient of Determination (R²) values for the test samples in the X, Y, and Z directions reached 0.948, representing enhancements of 9.9%, 4.2%, and 2.3%, respectively, compared to the suboptimal Attention–LSTM model. Concurrently, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were reduced to 9.23 mm and 7.17 mm, respectively. Based on these displacement predictions, the landslide evolution stage was determined by calculating the tangent angle, indicating that the Kuyaogou landslide will remain in a stable creep phase over the ensuing ten-day period with low overall risk of rapid movement, though localized instability requires continued monitoring. This research provides a ‘small, fast, and accurate’ paradigm for red-bed landslide displacement prediction, offering scientific support for disaster prevention and emergency decision-making. The framework demonstrates potential for broader application in monitoring other geological hazards, thereby contributing to the implementation of sustainable development strategies in geohazard-prone regions. Full article

As mobile networks increasingly support sustainable and green Internet of Things (IoT) applications, energy-efficient solutions that address coverage constraints have become paramount. Although backscatter communication (BackCom) offers a low-power option for IoT devices, particularly battery-less IoT nodes, it can suffer from limited coverage. To overcome this, we exploit aerial platforms (UAVs) integrated with non-orthogonal multiple access (NOMA) to enhance both coverage and spectral efficiency. In this paper, we propose a UAV-supported NOMA-enabled BackCom system to serve massive backscatter node (BN) networks. We aim to maximize system throughput by jointly optimizing the power allocation and reflection coefficients of the BNs, along with the trajectory and data collection locations of the UAV. We derive closed-form solutions for the reflection coefficients and the optimal collection locations of the UAV and achieve global optimality in power allocation by utilizing the Karush–Kuhn–Tucker (KKT) optimality conditions in conjunction with the golden-section search (GSS). In addition, we formulate the UAV trajectory optimization problem as a Traveling Salesman Problem (TSP) and propose an efficient low-complexity genetic algorithm (GA)-based solution. The numerical results demonstrate that the proposed scheme outperforms the benchmark schemes in terms of sum-throughput rate and achieves an overall performance enhancement of $8.983$ dB, underscoring the potential of our approach for large-scale battery-less IoT deployments. Full article

Incipient fault signatures in rolling bearings are often compromised by intense background noise and stochastic impulses. Conventional resonance demodulation frequently relies on rigid frequency partitioning, which tends to disrupt the physical continuity of resonance bands and results in the incomplete capture of essential diagnostic information. Furthermore, the robustness of prevailing optimal demodulation frequency band (ODFB) selection indicators remains limited under heavy noise interference. This study develops the WLERgram framework, which utilizes regularized Fourier series to capture the global morphology of the vibration spectrum. By anchoring filter boundaries at natural energy troughs, the method mitigates spectral truncation based on inherent signal characteristics. The framework integrates an Adaptive Morphological Consensus (AMC) strategy, employing multi-scale operators to extract rotation-correlated components and enhance resistance to incoherent interference. By incorporating a Weighted Logarithmic Energy Ratio (WLER) metric, the method utilizes a nonlinear operator to implement differential mapping between coherent fault harmonics and stochastic noise, enabling autonomous optimization of the demodulation band. Validations using synthetic simulations and experimental benchmarks (CWRU and UORED) suggest that WLERgram offers reliable feature extraction performance and diagnostic robustness under harsh noise environments. Full article

The cryptocurrency market has attracted significant attention from global investors, with Cardano (ADA) ranking among the top cryptocurrencies by market capitalization. However, predicting ADA returns remains challenging due to the complex, multi-scale dynamics influenced by Federal Reserve policies, geopolitical events, and high-frequency trading. This study proposes a “Sliding EMD–Multi Variables” framework for cryptocurrency return prediction, leveraging Empirical Mode Decomposition’s multi-scale fractal properties to capture nonlinear dynamics at different time scales. The sliding window decomposition method addresses data leakage issues while incorporating key economic and policy variables at the component level. The empirical results demonstrate that the Sliding EMD system significantly outperforms univariate and multivariate benchmarks. Compared to the univariate system, it improves MSE, RMSE, SMAPE, and DSTAT by 0.83%, 0.42%, 5.23%, and 0.43%, respectively, while enhancing investment metrics (maximum drawdown, Sharpe ratio, Sortino ratio, Calmar ratio) by 0.19, 0.36, 0.95, and 0.15. Against the multivariate system, improvements reach 5.52%, 3.14%, 5.74%, and 17.62% in prediction accuracy, with investment performance gains of 0.47, 1.69, 4.27, and 0.31. Incorporating economic variables at the component level yields additional improvements of 0.94%, 0.47%, and 0.78% in MSE, RMSE, and MAE. These findings offer valuable insights for cryptocurrency portfolio optimization using fractal-based decomposition methods. Full article

Fault-induced delayed voltage recovery (FIDVR) poses a serious threat to modern power grid operation, where stalled induction motors following a fault can sustain dangerously low bus voltages and potentially trigger cascading failures. While deep reinforcement learning (DRL) has shown promise for emergency load shedding control, existing centralized DRL approaches require extensive communication infrastructure and large neural network models that are computationally prohibitive to train at scale. Fully decentralized approaches, on the other hand, lack inter-agent information sharing and coordination, often resulting in inadequate voltage recovery across area boundaries. To address these limitations, we propose a Cloud–Edge Collaborative DRL framework that combines lightweight, area-specific edge agents for local load shedding control with a supervisory cloud agent that coordinates their actions globally, achieving scalable training and system-wide voltage recovery simultaneously. Training is further accelerated through a modified Guided Surrogate-gradient-based Evolutionary Random Search (GSERS) algorithm. Validation on the IEEE 300-bus system demonstrates that the proposed framework reduces training time by approximately 90% compared to the fully centralized approach, while achieving comparable voltage recovery performance to the centralized method and approximately 80% better reward performance than the fully decentralized approach, confirming the critical benefit of the cloud-level coordination mechanism. Full article

Object detection in UAV-based fire rescue scenarios faces multiple challenges, including densely distributed small targets, severe occlusion, and interference from smoke and flames. Existing mainstream detection models, such as the YOLO series, often prioritize inference speed at the expense of modeling global context and spatial positional information, resulting in limited performance in such complex environments. To address these limitations, this paper proposes FirePM-YOLO, an object detection architecture optimized for fire rescue applications. Based on the YOLO framework, the proposed model introduces two key innovations: first, a Position-Aware Enhanced Mamba module (PEMamba) is designed, which incorporates a compact positional encoding mechanism, lightweight spatial enhancement, and an adaptive feature fusion strategy to significantly improve scene perception while maintaining computational efficiency. Second, a PEMBottleneck structure is constructed, which dynamically balances local convolutional features and global PEMamba features via learnable weights. This module is embedded into the shallow layers of the backbone network, forming an enhanced PEM-C3K2 module that captures long-range dependencies with linear complexity while preserving fine local details, thereby enabling holistic contextual understanding of fireground environments. Experimental results on the self-built “FireRescue” dataset demonstrate that compared with the original YOLOv12 and other mainstream detectors, the proposed model achieves improvements in both mean average precision (mAP) and recall while maintaining real-time inference capability. Notably, it exhibits superior detection performance on challenging samples, such as small-scale and partially occluded professional firefighting vehicles. Full article

Background: The aim of this study was to derive and internally validate a prescriptive clinical prediction rule (CPR) for identifying baseline factors associated with short-term clinical improvement in patients with neck pain (NP) undergoing a manual therapy (MT)-based physiotherapy program. Methods: A prospective cohort study was conducted, including 71 patients with NP (18–65 years). Participants received six MT-based sessions over three weeks. Baseline assessments included Pain Intensity Numeric Rating Scale (PI-NRS), Neck Disability Index (NDI), Body Mass (BM), Body Mass Index (BMI), International Physical Activity Questionnaire-Short Form (IPAQ-SF), Hospital Anxiety and Depression Scale (HADS), Minnesota Satisfaction Questionnaire-Short Form (MSQ), and Craniovertebral Angle (CVA). Clinical improvement was defined using the Global Perceived Effect Scale (GPES-7). Univariate analyses, receiver operating characteristic (ROC) curve analysis, and forward stepwise logistic regression were performed to derive the predictive model. Results: Fifty-six participants (78.9%) reported moderate to complete improvement. BM ≥ 76.5 kg and MSQ score ≤ 42.5 were retained in the final regression model. When both predictors were present, the probability of clinical improvement increased to 96.43% (positive likelihood ratio = 7.58). The model demonstrated adequate fit (Nagelkerke R² = 0.247; Hosmer–Lemeshow p = 0.804). Internal validation yielded an optimism-corrected AUC of 0.741, suggesting minimal overfitting. Conclusions: Higher BM and lower MSQ score were associated with greater short-term improvement following MT in patients with NP. These findings highlight the relevance of integrating physical and psychosocial factors in prescriptive rehabilitation approaches. External validation of this CPR is required before clinical implementation. Full article

The widespread utilization of synthetic dyes within the textile industry, driven by their chemical recalcitrance and diverse chromatic spectra, constitutes a significant global environmental challenge. Improper discharge of these highly stable effluents into natural water bodies leads to severe ecological imbalances, affecting aquatic life and soil integrity while posing indirect risks to human health due to their mutagenic potential. Conventional physicochemical treatment methods are often hindered by prohibitive operational costs and the frequent generation of hazardous secondary pollutants. Consequently, there is an urgent demand for sustainable biotechnological alternatives to mitigate these industrial impacts. Bioremediation, specifically using white-rot fungi, represents a robust and eco-friendly strategy for the degradation of complex aromatic structures. Species such as Trametes versicolor, Pleurotus ostreatus, and Phanerochaete chrysosporium utilize a specialized extracellular enzymatic complex to mineralize toxic compounds effectively. Here we review the ligninolytic capacity of white-rot fungi and their specialized enzymatic systems for environmental sustainability. The primary points are: (i) the biochemical mechanisms of the ligninolytic system of laccases and peroxidases during dye degradation; (ii) the influence of operational parameters such as pH, temperature, and nutrient availability on fungal metabolic efficiency; (iii) the diverse environmental applications of these microorganisms in treating real textile effluents; (iv) the current biotechnological challenges, including maintaining enzymatic stability in non-sterile industrial environments; and (v) the future perspectives for scaling up fungal treatment systems from laboratory research to large-scale industrial implementation. Full article

Hydrogen energy is pivotal to the global energy transition, and the development of high-efficiency, safe hydrogen storage technologies constitutes a prerequisite for its large-scale commercialization. Kinetic bottlenecks including slow reactions, delayed front propagation, and marked spatial heterogeneity driven by strong thermal–mass transfer coupling restrict the engineering application of solid-state metal hydrides. However, the current research mainly focusing on overall performance lacks a systematic understanding of the spatiotemporal evolution mechanisms and their intrinsic links to internal structural control. In this work, a 3D multiphysics model of a LaNi₅-based reactor is developed to systematically elucidate spatiotemporal evolution patterns, facilitating the proposal of a structural decoupling framework based on synergistic thermal–mass resistance reconfiguration. Both absorption and desorption show distinct three-stage evolution, shifting from kinetic dominance to transfer limitation: absorption causes core self-inhibition via heat-hydrogen supply mismatch, leading to much lower core than surface storage capacity; desorption results in significant inner-layer lag due to endothermic cooling-driven pressure drops. Thermal–mass coupling-induced inverted spatiotemporal evolution is identified as the root cause of spatial heterogeneity. Quantitative comparison of straight-pipe, spiral-tube, and honeycomb structures reveals that internal architectures achieve effective thermal–mass decoupling through expanded heat-exchange areas, reconstructed diffusion pathways, and optimized heat source distribution. Notably, the honeycomb structure with a parallel micro-unit network achieves 89.1% and 86.6% reductions in absorption and desorption times, respectively, showing superior dynamic performance and field uniformity. This study provides a theoretical basis for the mechanism-driven design and synergistic performance optimization of high-efficiency solid-state hydrogen storage reactors. Full article