Search Results (2,601)

To address the challenges in multi-scale defect detection on railway track surfaces—such as the high likelihood of missing tiny defects, weak anti-interference capability in complex environments, and poor scale adaptability—this paper proposes a WTConv-YOLOv11 detection model based on wavelet convolution and scale dynamic loss, specifically tailored for embedded scenarios in intelligent inspection robots. By embedding a wavelet convolution module, the model leverages multi-frequency decomposition characteristics to enhance multi-scale defect feature extraction, effectively compensating for the shortcomings of traditional convolution in detail extraction and limited receptive fields. Meanwhile, a Scale Dynamic Loss (SD Loss) function is introduced to adaptively adjust regression weights according to defect scales, significantly reducing multi-scale target localization deviations and Intersection over Union (IoU) fluctuations. Experiments conducted on a real-world railway dataset comprising 2396 track defect images demonstrate that the proposed model achieves mean Average Precision (mAP)@0.5 of 82.56%, which is 12.16 percentage points higher than the original YOLOv11. With an inference speed of 99 FPS, the model balances high accuracy with real-time performance. Real-world testing further verifies the model’s robustness under strong light, shadows, and water stains, providing effective technical support for intelligent unmanned railway inspection. Full article

Background: Highly educated migrants in Norway often experience prolonged delays before accessing employment that matches their qualifications. During this period, many participate in compulsory education or language training, or work in jobs unrelated to their professions. This study explores how the introductory program for migrants and work outside one’s professional field shape health, identity, and the broader integration process. Methods: This exploratory qualitative study used semi-structured interviews with eight highly educated migrants enrolled in the introductory program in Kristiansand municipality in Norway. Interviews were transcribed verbatim and analyzed using reflexive thematic analysis informed by Social Identity Theory. Findings: Participants described employment, and particularly their former professions, as central to their self-esteem, sense of meaning, and social belonging. Prolonged credential recognition processes and limited opportunities for meaningful social contact due to employment status loss contributed to feelings of stagnation, exclusion, and weakened professional identity. Many participants emphasized a strong desire to contribute to society and regain their professional status. While the introductory program offered valuable peer support and facilitated language learning, it was not experienced as a direct pathway to inclusion in Norwegian society and professional life. The findings indicate that early access to work-based integration opportunities, such as internships or relevant job placements, may enhance well-being, foster language acquisition, and strengthen social inclusion for highly educated migrants. Conclusions: The study findings suggest that policymakers and practitioners should prioritize measures that streamline credential recognition and expand early, relevant work-based integration opportunities. Such approaches can improve language development, support identity reconstruction, strengthen social belonging, and ultimately promote better health and integration outcomes for highly educated migrants. Full article

Electrode-particle fracture and thermal runaway remain major safety and durability challenges for lithium-ion batteries. Deterministic degradation models are limited in representing random crack nucleation, long-range crack interactions, and critical transitions from stable operation to failure. A computational framework is proposed that combines a Lévy-jump-driven nonlocal stochastic partial differential equation (SPDE) model with a Bifurcation-Aware Physics-Informed Neural Network (BA-PINN). The framework couples fractional diffusion, peridynamic damage evolution, thermal feedback, state-space eigenvalue tracking, and damage-variance monitoring. Evaluation is conducted on controlled synthetic fracture simulations, Oxford battery cycling records, and open-access abuse-test records from the Battery Failure Databank. The damage-field results are interpreted as numerical consistency and surrogate-learning evidence, with direct experimental crack-map validation remaining outside the present dataset scope. On the simulated fracture dataset, the proposed method obtains a damage-field mean squared error of 0.023 ± 0.002 and a structural similarity index of 0.962 ± 0.006. For the evaluated thermal-runaway warning task, it achieves an AUC-ROC of 0.987 ± 0.004 and an average model-inferred warning lead time of 5.2 ± 0.2 h. These results demonstrate the methodological feasibility of combining stochastic nonlocal fracture modeling with bifurcation-aware learning. However, broader validation remains necessary, particularly using particle-resolved experiments and larger event-level thermal-runaway datasets. Full article

Soil monitoring is a key component of precision agriculture and environmental sensing systems, where reliable measurements support irrigation management and crop monitoring. Although high-end sensing platforms provide accurate measurements, their cost limits widespread adoption, particularly in resource-constrained agricultural environments. Low-cost soil sensors, such as widely available 7-in-1 probes capable of measuring soil moisture, temperature, electrical conductivity, and pH, offer a scalable alternative for distributed monitoring; however, their limited accuracy raises concerns regarding their reliability for decision-support systems. This study investigates whether measurements from a single low-cost 7-in-1 soil sensor contain sufficient information to reconstruct the outputs of a commercial high-end sensing platform (CropX), specifically volumetric water content (VWC) and pore-water electrical conductivity (ECpw). Field data were collected in a tropical Hass avocado orchard in Colombia, and four machine learning models were evaluated to reconstruct CropX measurements from low-cost sensor signals at three soil depths (20, 41, and 66 cm). Random Forest achieved the highest reconstruction performance, with coefficient of determination R2 values between 0.9965 and 0.9986 and consistently low root mean square error (RMSE) and mean absolute error (MAE) across depths. Out-of-bag validation and multi-seed stability analyses confirmed the robustness of the models despite the limited dataset size. A chronological validation (80–20%) showed substantially reduced performance, indicating that the proposed approach is more suitable for reconstructing high-end sensor signals under concurrent measurement conditions than for strict temporal extrapolation. Therefore, the framework should be interpreted as a virtual sensing strategy for reconstructing simultaneous CropX measurements from low-cost sensor observations rather than as a standalone model for predicting future soil conditions without periodic recalibration. These results demonstrate that low-cost multi-parameter sensors can support high-fidelity virtual reconstruction of high-end soil measurements, contributing to the development of scalable and cost-effective soil monitoring systems for precision agriculture. Full article

Galloping of overhead transmission lines threatens grid safety and requires non-contact measurement methods that can quantify three-dimensional (3D) motion from field video. This paper proposes a deep-vision and binocular-collaboration framework for dynamic conductor displacement measurement. The framework combines three components that are matched to the physical structure of transmission lines: adaptive image enhancement using Retinex illumination decomposition and Wiener blind deconvolution; a structure-prior dual-branch extraction module that uses an improved YOLOv11 keypoint branch for spacer-equipped sections and an improved U-Net branch with Dynamic Snake Convolution (DSC) and Strip Pooling for bare conductors; and stereo reconstruction with Kalman-filter-based temporal association for continuous trajectory estimation. Compared with the original submission, the revised manuscript further clarifies the real-video data acquisition, annotation procedure, camera synchronization, calibration workflow, training/testing independence, and runtime measurement protocol. Additional validation on a public real power-line image dataset is also reported. The proposed method achieves a Z-axis Root Mean Square Error (RMSE) of 24.5 mm for spacer sections in the controlled binocular field test, a dominant-frequency relative error below 3.5%, and 32 FPS on edge hardware when preprocessing, visual extraction, stereo projection, and temporal filtering are included. On the supplementary public power-line dataset, the segmentation branch obtains a Dice coefficient of 0.9039 and an IoU of 0.8395. These results indicate that the proposed framework reduces the depth-scale limitation of monocular vision and provides a practical quantitative tool for field galloping monitoring. Full article

This paper tackles the problem of performance limitations on channel estimation accuracy in near-field massive MIMO systems resulting from the sparse reconstruction method with fixed spatial grid dictionaries. It presents a deep unfolded network with a learnable sparse dictionary (LSD-UnfoldNet) to address the grid mismatch, thereby obtaining high accuracy and low-complexity near-field channel estimation as the sparse dictionary and channel reconstruction parameters are jointly optimized using end-to-end learning. The iterative shrinking threshold algorithm is unfolded into an L-layer neural network with L learnable sparse dictionaries and linear transformation matrices in each layer of the network. Besides, to improve the correlation characteristics of the sensing matrix, an orthogonal regularization term is introduced. During training of the neural network, the Adam optimizer and cosine annealing learning rate scheduling are applied to jointly minimize the normalized mean square error and total loss of learned dictionary correlations. Experimental results demonstrate that the proposed method, at a representative signal-to-noise ratio of 20 dB, achieves normalized mean square errors of −24.5 dB. The root mean square errors for angle and distance estimation were 0.50° and 0.18 m, respectively, achieving superior performance relative to heuristic algorithms and deep learning-based algorithms. Beyond its strong robustness to different grid granularities and spatial distances, the proposed method also achieves competitive pilot overhead compared with other approaches. Full article

Accurate atmospheric temperature and humidity profiles are fundamental to weather monitoring and prediction. Geostationary imagers such as the Advanced Meteorological Imager (AMI) provide continuous observations and enable profile retrievals through radiative transfer–based algorithms; however, these products remain affected by systematic biases associated with the limited number of spectral channels and reliance on background fields from numerical weather prediction models. This study presents a data-driven post-processing framework to generate reanalysis-consistent profiles by refining AMI-retrieved temperature, mixing ratio, and relative humidity profiles using Light Gradient Boosting Machine (LGBM) models trained with ERA5 reanalysis data. Using four years (2020–2023) of hourly observations, the refined profiles were evaluated against both ERA5 and independent radiosonde measurements. Relative to ERA5, the refinement yields modest but consistent reductions in root mean square error (RMSE), including approximately 0.04 g kg⁻¹ (6–7%) for mixing ratio and 1.9 percentage points (≈14%) for relative humidity, while temperature shows a smaller error reduction of about 0.02 K (2–3%). When compared with radiosondes, temperature RMSE shows a marginal increase overall (<1%) with a larger increase in the lower troposphere, whereas improvements are observed for mixing ratio (2–3%) and relative humidity (6–7%). Seasonal and diurnal analyses reveal systematic error structures in the original AMI profiles, particularly wet-bias patterns in summer moisture fields, which are partially mitigated by the refinement. Feature-importance analysis using Shapley Additive Explanations (SHAP) identifies the dominant contribution of AMI water vapor channels, consistent with their known vertical sensitivity. Overall, this long-term evaluation demonstrates the feasibility of machine learning-based refinement for geostationary imager atmospheric profiles, while also highlighting inherent limitations related to the information content of current-generation imagers. Full article

The current trend towards decarbonization has increased the pressure towards land use change through the installation of solar parks on agricultural fields. The usefulness of RothC to model the evolution of soil carbon after the installation of the solar park has been validated in a field with historic data. The model has been applied to evaluate the impact of a large-scale modification of land use in Valencia (Spain), a mediterranean region with an ambitious plan for the installation of renewable energy. The removal of the orange trees for the installation of a solar park would generate a carbon release in CO₂ eq to 72 Mg ha⁻¹. If the soil is left vacant of vegetation, another 28 Mg ha⁻¹ would be emitted in 30 years. By contrast, if the soil is covered by scrubland, an overall CO₂ capture of −226 Mg ha⁻¹ could be achieved, including the impact of the initial plant removal. If we consider the Valencia region, the installation of 12.000 hectares of solar parks could generate up to 1.2 × 10⁶ Mg of CO₂ emissions or capture 2.7 × 10⁶ Mg of CO₂. Also, a sensitivity analysis to evaluate the effect of the main labels has been performed, revealing that the original carbon content is the most relevant label, followed by plant input and the % of soil covered by the solar panels. The limited availability in experimental data means that this study should be considered an exploratory evaluation of the impact of including plantations in solar parks. Full article

We propose a decentralized strategy for coordinating the bidirectional charging and discharging of battery electric vehicles (BEVs) in renewable-powered parking lots. The framework combines mean-field games (MFGs) and model predictive control (MPC) to address the coupled stochastic dynamics induced by uncertain renewable generation and random vehicle arrivals and departures. Solar and wind power fluctuations are modeled using autoregressive moving-average (ARMA) processes, while the time-varying vehicle population is represented through finite Poisson processes. The coordination problem is formulated as a large-scale game, where an aggregator designs individual cost functions to maximize available energy utilization while promoting fairness through near-equal states of charge (SOCs) at departure. Scalability is achieved through MFG theory, ensuring convergence and stability even under highly volatile generation and fluctuating agent populations. Numerical simulations validate the proposed strategy against two straightforward algorithms: capacity-ordered saturation allocation (COSA) and capacity-ordered fair allocation (COFA). These centralized approaches achieve high target fulfillment in static, low-intensity environments, where available energy accommodates a stable fleet without exceeding power limits. However, their efficacy degrades significantly in dynamic, high-intensity environments, where the interplay of volatile generation, continuous fleet turnover, and strict power constraints strains the system. In contrast, the proposed MFG-MPC framework provides a decentralized response that elegantly navigates the trade-offs between energy availability, demand stochasticity, and power limits. Ultimately, this approach ensures robust energy utilization while safeguarding vehicle equity, confirming its strong suitability for real-time deployment. Full article

The resilience pads of sleeper floating tracks (STEDEF) are key components that absorb shock loads and vibrations induced by train traffic. Currently, under the Korean domestic guidelines for track facility performance evaluation, one sample per 500 m is collected from the field, and the static spring stiffness is assessed through laboratory testing. However, this approach requires nighttime track possession, incurs significant manpower and cost, and provides limited reliability because the condition of an entire section is inferred from a small number of samples. Therefore, this study proposes an impact-hammer–FRF-based method for evaluating the spring stiffness of resilience pads without pad extraction. Field impact-hammer tests were conducted to identify the dominant first-mode natural frequency of the track-support system. Configuration-specific finite element models were then used to derive frequency–stiffness relationships for the investigated STEDEF configurations. The novelty of the proposed method lies in converting the local first-mode frequency measured in situ into a static-equivalent stiffness index that can be directly compared with the maintenance reference value used in the Korean inspection framework. The finite element model reproduced the mean natural frequencies of the reference configurations with differences of 0.08–3.61%. Based on the configuration-specific relationships, estimation equations were developed to support in situ screening of resilience-pad stiffness at the measured locations. Full article

Winter underuse of urban parks in severe-cold cities limits year-round outdoor activity, especially for cold-sensitive users. This study developed a comfort–risk–adaptation framework integrating thermal perception, model-estimated cold-stress risk, and behavioral responses. Field microclimate measurements and synchronous questionnaires were conducted in Nanhu Park, Changchun, China, under clear winter conditions, yielding 386 paired human–environment samples. The Universal Thermal Climate Index (UTCI), Required Clothing Insulation (IREQ), wind chill temperature (WCT), and contact cooling indicators were used to quantify thermal exposure and cold-stress risk. Results showed significant spatial differences in wind speed, solar radiation, mean radiant temperature, and UTCI, while air temperature and humidity varied little. The neutral UTCI was 3.14 °C (unweighted) and 3.70 °C (weighted), and the 80% thermal acceptability threshold was −15.24 °C (95% CI: −16.14 to −14.22 °C). Despite acceptable thermal perception, physiological cold-stress risks remained under certain conditions. The findings highlight the need to integrate solar access, wind mitigation, low-conductivity materials, and moderate activity routes to improve winter usability in severe-cold urban parks. Results are condition-specific and reflect observed users under clear to partly cloudy winter daytime conditions rather than universal thresholds. Full article

The segmentation model achieved Mean IoU values of 0.7723 for Water Stress 2025, 0.9164 for Common Rust 2025, and 0.9531 on the benchmark dataset. The classifier achieved 99.54% accuracy for the five-class task; however, the improvement over the strongest baselines and the RGB + multispectral configuration was limited. Therefore, the classification component is not presented as a substantially superior classification-only model. Instead, it is interpreted as an exploratory multimodal analysis that quantifies the contribution and limitation of RGB, multispectral, Wavelet, and GLCM branches under the adopted UAV dataset protocol. For classification-only deployment, simpler alternatives such as DenseNet201 or the RGB + multispectral configuration may be more practical because they provide comparable accuracy with lower architectural or preprocessing complexity. Ablation, modality-controlled, and 21-run stability experiments showed reproducible segmentation results and clarified the behavior of the classification branches. RGB and multispectral branches mainly provided the peak classification accuracy, whereas Wavelet and GLCM branches mainly affected offline convergence rather than final accuracy. RGB, NDVI, and NDRE visualizations were also added for qualitative support. Since direct physiological ground measurements were not available for all samples, the masks are interpreted as adaptive index-guided labels rather than direct physiological ground truth. Overall, the main evidence of practical benefit is associated with UAV-based dataset construction, adaptive index-guided segmentation, and field-scale stress/disease mapping, while the classification experiments should be interpreted as modality-contribution and convergence analyses rather than proof of a practically superior complex classifier. Full article

High reclaimed asphalt pavement (RAP) mixtures can improve pavement sustainability by reducing virgin binder and aggregate demand, but high RAP contents may increase mixture stiffness and reduce cracking tolerance. This study evaluates whether commercially available para-aramid fibers can improve the intermediate-temperature cracking resistance of high-RAP hot-mix asphalt using the IDEAL-CT test. Two para-aramid fiber products, a wax-coated fiber and an emulsion-treated fiber, were evaluated at dosages of 0.05%, 0.10%, and 0.15% by total mixture weight in asphalt mixtures containing 15%, 25%, and 40% RAP. The results showed that fiber effectiveness depended strongly on RAP content, fiber treatment, and dosage. The 25% RAP mixture had the lowest control CTIndex and showed the greatest improvement from fiber addition. In this group, 0.10% wax-coated fiber increased CTIndex by 170%, while 0.15% emulsion-treated fiber increased CTIndex by 263%. For the 15% RAP mixture, 0.05% emulsion-treated fiber and 0.10% wax-coated fiber produced statistically significant improvements. For the 40% RAP mixture, 0.10% emulsion-treated fiber produced the highest mean CTIndex among all mixtures tested, but the improvement was not statistically significant because of high specimen variability. Overall, the findings indicate that para-aramid fibers can improve laboratory cracking resistance in RAP mixtures, but the optimum dosage is mixture-specific and should not be applied uniformly across RAP contents. Because this study was limited to Ideal-CT, additional rutting, fatigue, aging, workability analysis and field validation are recommended before broad implementation. Full article

Maize (Zea mays L.) is the dominant cereal of continental Hungary, yet the Pannonian belt lost one-third of its planted area over the last decade (1150 kha to 770 kha in 2025). This study quantified how supplemental irrigation and biostimulants affect maize transpiration. Fourteen Dynamax Flow32-1K stem-heat-balance sensors recorded sap flow at 15 min resolution on the Sushi FAO 340 hybrid across seven irrigated–rainfed plot pairs at Karcag, Hungary. Measurements spanned a dry 2024 season (irrigation: 253 mm; precipitation: 7.9 mm; VPD_max: 1.71 kPa) and a wetter 2025 season (120 mm irrigation; 62.9 mm precipitation; mean VPD_max: 1.33 kPa). A Control-only mixed-effects model returned a year × irrigation interaction F(1, 84) = 106 (p < 10⁻¹⁵): irrigation raised transpiration by 77% in 2024 and lowered it by 12% in 2025. The VPD_max–transpiration coupling was inverted in 2024, the field signature of stomatal closure under soil-water limitation. The irrigated Big Compost plot reached a grain-based WUE of 97.5 kg mm⁻¹ versus 41.6 kg mm⁻¹ for the matched Control. This was a 2.3-fold within-2025 separation at similar per-plant transpiration. The irrigation response differed sharply between seasons. However, the amendment classes were tested in different years, and the irrigation dose differed between seasons (253 mm in 2024 versus 120 mm in 2025). The cross-class contrast is therefore exploratory, and every cross-year comparison is provisional. With one sensor per plot, the amendment ranking remains a hypothesis for a replicated, same-season, and same-dose follow-up. Full article

Radiation monitoring at contaminated industrial sites is often restricted by safety, access, and operational constraints. Under such conditions, a modelling approach that can use a limited number of field measurements is useful for preliminary screening, route planning, and prioritization of verification surveys. This study presents a sparse spatiotemporal polynomial interpolation model for estimating the gamma radiation equivalent dose rate (EDR) along the perimeter of the Base-S radiation-hazardous industrial site. The model represents EDR as a function of spatial coordinates and time, and uses a reduced measurement structure consisting of four seasonal temporal nodes and five representative spatial nodes. The reduced structure is intended to support conservative preliminary assessment under the ALARA principle, not to replace field measurements. A 2021 case study is presented for 61 numbered perimeter points. The article presents one of the universal mathematical models developed by the authors to determine the impact of gamma radiation on the personnel of tailings facilities and industrial sites through the calculation of the equivalent dose rate during personnel residence stays, depending on time. The proposed polynomial interpolation model for rapid radiation dose assessment at radiation-hazardous industrial sites estimates equivalent dose-rate values for a specific planning case. The model represents the EDR field as a spatiotemporal polynomial f(x, y, t), where x and y are planar coordinates, and t is the day of the year. A conservative reduced scheme uses four seasonal maximum values and five representative spatial points to decrease the number of required field measurements and personnel residence time. For the 2021 case study, the model-estimated EDR at 61 numbered perimeter points ranged from 0.118 to 0.415 µSv/hour, with a mean of 0.242 µSv/hour. This model provides initial data for building a 2D model and, if necessary, a 3D model of radiation contamination within the research-object territory. The resulting 2D and 3D maps are interpreted as model-estimated visualization products. The proposed method, the model form of which is described as a cubic polynomial in t and a quadratic in x,y, allows for effective interpolation of complex multidimensional dependencies of observed data. Full article