Search Results (1,954)

Improving construction site safety remains a critical challenge in Saudi Arabia’s rapidly growing construction sector, where high accident rates and diverse labor forces demand evidence-based managerial interventions. This study investigated the influence of Managers’ Safety Perceptions and Practices (MSP) on Workers’ Safety Behaviors (WSB) in the Saudi construction industry, emphasizing the mediating roles of Workers’ Safety Awareness (WSA), Safety Competency (WSC), and Safety Actions (SA). The conceptual framework integrates these three mediators to explain how managerial attitudes and practices translate into frontline safety outcomes. A quantitative, cross-sectional design was adopted using a structured questionnaire distributed among construction workers, supervisors, and project managers. A total of 352 from 384 valid responses were collected, and the data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) via SmartPLS 4. The findings revealed that MSP does not directly influence WSB but has significant indirect effects through WSA, WSC, and SA. Among these, WSC emerged as the most powerful mediator, followed by WSA and SA, indicating that competency is the most critical driver of safe worker behavior. These results provide robust empirical support for a multidimensional mediation model, highlighting the need for managers to enhance safety behaviors not merely through supervision but through fostering awareness and competency, providing technical training, and implementing proactive safety measures. Theoretically, this study contributes a novel and integrative framework to the occupational safety literature, particularly within underexplored Middle Eastern construction contexts. Practically, it offers actionable insights for safety managers, industry practitioners, and policymakers seeking to improve construction safety performance in alignment with Saudi Vision 2030. Full article

Artificial intelligence technologies, particularly machine learning and computer vision, are being increasingly utilized to preserve, restore, and create immersive virtual experiences with cultural artifacts and sites, thus aiding in conserving cultural heritage and making it accessible to a global audience. This paper examines the performance of Generative Adversarial Networks (GAN), especially Style-Based Generator Architecture (StyleGAN), as a deep learning approach for producing realistic images of Egyptian monuments. We used Sigmoid loss for Language–Image Pre-training (SigLIP) as a unique image–text alignment system to guide monument generation through semantic elements. We also studied truncation methods to regulate the generated image noise and identify the most effective parameter settings based on architectural representation versus diverse output creation. An improved discriminator design that combined noise addition with squeeze-and-excitation blocks and a modified MinibatchStdLayer produced 27.5% better Fréchet Inception Distance performance than the original discriminator models. Moreover, differential evolution for latent-space optimization reduced alignment mistakes during specific monument construction tasks by about 15%. We checked a wide range of truncation values from 0.1 to 1.0 and found that somewhere between 0.4 and 0.7 was the best range because it allowed for good accuracy while retaining many different architectural elements. Our findings indicate that specific model optimization strategies produce superior outcomes by creating better-quality and historically correct representations of diverse Egyptian monuments. Thus, the developed technology may be instrumental in generating educational and archaeological visualization assets while adding virtual tourism capabilities. Full article

Rockfill particle gradation significantly influences mechanical performance in earth–rockfill dam construction, yet on-site screening is often time-consuming, labor-intensive, and structurally invasive. This study proposes a rapid and non-destructive detection method using mobile-based photography and an end-to-end image segmentation approach. An enhanced YOLOv8-seg model with an integrated dual-attention mechanism was pre-trained on laboratory images to accurately segment densely stacked particles. Transfer learning was then employed to retrain the model using a limited number of on-site images, achieving high segmentation accuracy. The proposed model attains a mAP50 of 97.8% (base dataset) and 96.1% (on-site dataset), enabling precise segmentation of adhered and overlapped particles with various sizes. A Minimum Area Rectangle algorithm was introduced to compute the gradation, closely matching the results from manual screening. This method significantly contributes to the automation of construction workflows, cutting labor costs, minimizing structural disruption, and ensuring reliable measurement quality in earth–rockfill dam projects. Full article

Effective earthquake early warning (EEW) is essential for disaster prevention in the built environment, enabling a rapid structural response, system shutdown, and occupant evacuation to mitigate damage and casualties. However, most current EEW systems lack rigorous reliability analyses of their predictive outcomes, limiting their effectiveness in real-world scenarios—especially for on-site warnings, where data are limited and time is critical. To address these challenges, we propose a Bayesian neural network (BNN) framework based on Stein variational gradient descent (SVGD). By performing Bayesian inference, we estimate the posterior distribution of the parameters, thus outputting a reliability analysis of the prediction results. In addition, we incorporate a continual learning mechanism based on elastic weight consolidation, allowing the system to adapt quickly without full retraining. Our experiments demonstrate that our SVGD-BNN model significantly outperforms traditional peak displacement (Pd)-based approaches. In a 3 s time window, the Pearson correlation coefficient R increases by 9.2% and the residual standard deviation $SD$ decreases by 24.4% compared to a variational inference (VI)-based BNN. Furthermore, the prediction variance generated by the model can effectively reflect the uncertainty of the prediction results. The continual learning strategy reduces the training time by 133–194 s, enhancing the system’s responsiveness. These features make the proposed framework a promising tool for real-time, reliable, and adaptive EEW—supporting disaster-resilient building design and operation. Full article

This study aimed to evaluate the feasibility of using serious games for the (tele)rehabilitation of children with disabilities affected by the Ukrainian war. Additionally, it provides requirements for technologies that can be used in war-affected areas. Structured interviews and Likert scale assessments were conducted on-site and remotely with patients of the tertiary care facility in Ukraine. All participants used the telerehabilitation platform for motor and cognitive training. Nine serious games were employed, involving trunk tilts, upper limb movements, and head control. By mid-September 2023, 186 positive user experiences were evident, with 89% expressing interest in continued engagement. The platform’s accessibility, affordability, and therapeutic benefits were highlighted. The recommendations from user feedback informed potential enhancements, showcasing the platform’s potential to provide uninterrupted rehabilitation care amid conflict-related challenges. This study suggests that serious games solutions that suit the sociopolitical and economic context offer a promising solution to rehabilitation challenges in conflict zones. The positive user experiences towards using the platform with serious games indicate its potential in emergency healthcare provision. The findings emphasize the role of technology, particularly serious gaming, in mitigating the impact of armed conflicts on children’s well-being, thereby contributing valuable insights to healthcare strategies in conflict-affected regions. Requirements for technologies tailored to the context of challenging settings were defined. Full article

Anthropogenic noise can have diverse effects on natural ecosystems, but less is known about the degree to which noise can alter organisms in comparison to other disturbances. A variety of frequencies are produced by man-made objects, ranging from high to low frequencies, and we studied infrasound (<20 Hz) produced by wind turbines and trains. We estimated the number, mass and viability of seeds produced by flowers of Plains pricklypear (Opuntia polyacantha Haw.) that were left open to pollinators, hand-pollinated or bagged to exclude pollinators. Each pollination treatment was applied to plants at varying distances from wind turbines and railways (≤25 km). Self-pollinated Opuntia polyacantha and plants within the wind facility produced ≥1.6 times more seeds in the bagged treatments compared to more distant sites. Seed mass and the percent of viable seeds decreased with distance from infrasound. Viability of seeds was >70% for most treatments and sites. If wind facilities, railways and other man-made structures produce infrasound that increases self-pollination, crops and native plants near sources may produce heavier seeds with higher viability in the absence of pollinators, but genetic diversity of plants may decline due to decreased cross-pollination. Full article

Reservoir-induced landslides threaten infrastructures and downstream communities, making continuous deformation monitoring vital. Time-series InSAR, notably the SBAS algorithm, provides high-precision surface-displacement mapping but suffers from voids due to layover/shadow effects and temporal decorrelation. Existing deep-learning approaches often operate on fixed-size patches or ignore irregular spatio-temporal dependencies, limiting their ability to recover missing pixels. With this objective, a hybrid spatio-temporal Graph Attention (ST-GAT) framework was developed and trained on SBAS-InSAR values using 24 influential features. A unified spatio-temporal graph is constructed, where each node represents a pixel at a specific acquisition time. The nodes are connected via inverse distance spatial edges to their K-nearest neighbors, and they have bidirectional temporal edges to themselves in adjacent acquisitions. The two spatial GAT layers capture terrain-driven influences, while the two temporal GAT layers model annual deformation trends. A compact MLP with per-map bias converts the fused node embeddings into normalized LOS estimates. The SBAS-InSAR results reveal LOS deformation, with 48% of missing pixels and 20% located near the Dasu dam. ST D-GAT reconstructed fully continuous spatio-temporal displacement fields, filling voids at critical sites. The model was validated and achieved an overall R² (0.907), ρ (0.947), per-map R² ≥ 0.807 with RMSE ≤ 9.99, and a ROC-AUC of 0.91. It also outperformed the six compared baseline models (IDW, KNN, RF, XGBoost, MLP, simple-NN) in both RMSE and R². By combining observed LOS values with 24 covariates in the proposed model, it delivers physically consistent gap-filling and enables continuous, high-resolution landslide monitoring in radar-challenged mountainous terrain. Full article

Background: Adolescents in Ethiopia, particularly in rural areas, face significant barriers to accessing comprehensive sexual and reproductive health (SRH) services, resulting in poor health outcomes. The youth-friendly health services (YFHS) initiative addresses these challenges by training Health Extension Workers (HEWs) to deliver tailored, age-appropriate care at the primary care level. This study evaluates the cost-effectiveness of YFHS implementation in rural health posts in the Jimma Zone, Ethiopia. Methods: Using an ingredient-based costing approach, costs were analyzed across six health posts, three implementing YFHS and three offering routine services. Health outcomes were modeled using disability-adjusted life years (DALYs) averted, and incremental cost-effectiveness ratios (ICERs) were calculated. Results: Results showed that YFHS reached 9854 adolescents annually at a cost of USD 29,680, compared to 2012.5 adolescents and USD 7519 in control sites. The study showed the ICER of USD 25.50 per DALY averted. The intervention improved health outcomes, including a 27% increase in antenatal care uptake, a 34% rise in contraceptive use, and a 0.065% reduction in abortion-related mortality, averting 52.11 DALYs versus 26.42 in controls. Conclusions: The ICER was USD 25.50 per DALY averted, well below Ethiopia’s GDP per capita, making it highly cost-effective by WHO standards. Scaling YFHS through HEWs offers a transformative, cost-effective strategy to advance adolescent SRH equity and achieve universal health coverage in Ethiopia. Full article

Pile foundations are critical structural elements, and their integrity is essential for ensuring the stability and safety of construction projects. Low-strain pile integrity testing (LSPIT) is widely used for defect detection; however, conventional manual interpretation of reflectograms is both time-consuming and susceptible to human error. This study presents a deep learning-driven approach utilizing transfer learning with convolutional neural networks (CNNs) to automate pile defect detection. A dataset of 328 reflectograms collected from real construction sites, including 246 intact and 82 defective samples, was used to train and evaluate the model. To address class imbalance, oversampling techniques were applied. Several state-of-the-art pretrained CNN architectures were compared, with ConvNeXtLarge achieving the highest accuracy of 98.2%. The accuracy reported was achieved on a dedicated test set using real reflectogram data from actual construction sites, distinguishing this study from prior work relying primarily on synthetic data. The proposed novelty includes adapting pre-trained CNN architectures specifically for real-world pile integrity testing, addressing practical challenges such as data imbalance and limited dataset size through targeted oversampling techniques. The proposed approach demonstrates significant improvements in accuracy and efficiency compared to manual interpretation methods, making it a promising solution for practical applications in the construction industry. The proposed method demonstrates potential for generalization across varying pile lengths and geological conditions, though further validation with broader datasets is recommended. Full article

Extra-pulmonary tuberculosis (EPTB) can affect any organ of the body, producing a wide variety of clinical manifestations that make the diagnosis and treatment of EPTB challenging. The optimum treatment varies depending on the site of EPTB, its severity, and response to treatment. There is often uncertainty about the best management practices, with a significant departure from national guidelines. This study aims to identify gaps and barriers in adhering to the national guidelines for the diagnosis and treatment of EPTB. We included 433 patients having EPTB and followed up at predefined intervals of 2 months, 6 months, 9 months, and 12 months. Questionnaire-based interviews of the treating physician and the patients in different departments were conducted. For confirmatory diagnosis, heavy dependence on clinical-radiological diagnosis without microbiological support was observed, which is a deviation from National Tuberculosis Elimination Programme (NTEP) guidelines and raises concerns about the potential for misdiagnosis and overtreatment. Apart from patient delays, long health system delays in EPTB were observed. The median patient delay, health system delay, and total treatment delay times were 4.2, 4, and 10.1 weeks, respectively. To enhance EPTB diagnosis and management, there is a pressing need for improved access to microbiological testing, enhanced physician training on adherence to NTEP guidelines, and greater utilisation of imaging and histopathological techniques. Full article

Background: Tobacco use is disproportionately high in rural areas, contributing to elevated cancer mortality, yet it often goes untreated due to limited access to care, high poverty and uninsured rates, and co-occurring substance use disorders (SUDs). This study explored the utility of using rapid qualitative analysis (RQA) to guide the adaptation of a tobacco-free workplace program (TFWP) in Texas healthcare centers serving adults with SUDs in medically underserved areas. Methods: From September–December 2023 and May–July 2024, we conducted 11 pre-implementation, virtual semi-structured group interviews focused on adapting the TFWP to local contexts (N = 69); 7 with providers (n = 34) and managers (n = 12) and 4 with patients (n = 23) in 6 healthcare centers. Two qualified analysts independently summarized transcripts, using RQA templates of key domains drawn from interview guides to summarize and organize data in matrices, enabling systematic comparison. Results: The main themes identified were minimal organizational tobacco cessation support and practices, and attitudinal barriers, as follows: (1) the need for program materials tailored to local populations; (2) limited tobacco cessation practices and partial policies—staff requested guidance on enhancing tobacco screenings and cessation delivery, and integrating new interventions; (3) contradictory views on treating tobacco use that can inhibit implementation (e.g., wanting to quit yet anxious that quitting would cause SUD relapse); and (4) inadequate environmental supports—staff requested treating tobacco-use training, patients group cessation counseling; both requested nicotine replacement therapy. Conclusions: RQA identified key areas requiring capacity development through participants’ willingness to adopt the following adaptations: program content (e.g., trainings and tailored educational materials), delivery methods/systems (e.g., adopting additional tobacco care interventions) and implementation strategies (e.g., integrating tobacco cessation practices into routine care) critical to optimizing TFWP fit and implementation. The study findings can inform timely formative evaluation processes to design and tailor similar intervention efforts by addressing site-specific needs and implementation barriers to enhance program uptake. Full article

The integration of unmanned aerial vehicle (UAV) remote sensing and deep learning has emerged as a highly effective strategy for inventorying forest resources. However, the spatiotemporal variability of forest environments and the scarcity of annotated data hinder the performance of conventional supervised deep-learning models. To overcome these challenges, this study has developed efficient tree (ET), a semi-supervised tree detector designed for forest scenes. ET employed an enhanced YOLO model (YOLO-Tree) as a base detector and incorporated a teacher–student semi-supervised learning (SSL) framework based on pseudo-labeling, effectively leveraging abundant unlabeled data to bolster model robustness. The results revealed that SSL significantly improved outcomes in scenarios with sparse labeled data, specifically when the annotation proportion was below 50%. Additionally, employing overlapping cropping as a data augmentation strategy mitigated instability during semi-supervised training under conditions of limited sample size. Notably, introducing unlabeled data from external sites enhances the accuracy and cross-site generalization of models trained on diverse datasets, achieving impressive results with F1, mAP50, and mAP50-95 scores of 0.979, 0.992, and 0.871, respectively. In conclusion, this study highlights the potential of combining UAV-based RGB imagery with SSL to advance tree species identification in heterogeneous forests. Full article

With the continuous development of high-speed electric multiple units (EMUs), vibration issues of vehicles have become increasingly prominent. During operation, the underfloor equipment installed on the carbody is subjected to random multi-point vibrations transmitted from the carbody, inducing significant fatigue damage. This paper presents a comprehensive analysis of multi-channel vibration environment data for various underfloor equipment across different operating speeds obtained through on-site measurements. A spectral synthetic method grounded in statistical principles is then proposed to generate vibration environment spectra for diverse underfloor equipment. Finally, utilizing fatigue analysis in the frequency domain, the fatigue damage to underfloor equipment is assessed under different operational environments. The research results show that the vibration environment spectrum of the underfloor equipment in high-speed EMU trains differs significantly from the vibration spectrum specified in the IEC 61373 standard, especially at high frequencies. Despite this difference in spectral characteristics, the overall vibration energy values of the two spectra are comparable. Additionally, the vibration spectra of different underfloor equipment exhibit variations that can be attributed to their installation positions. As operational speed increases, the fatigue damage to the underfloor equipment exhibits exponential growth. However, the total accumulated fatigue damage remains relatively low, consistently staying below a value of 1. Full article

Groundwater level monitoring is crucial for assessing hydrological responses to climate change and human activities, which pose significant threats to the sustainability of semi-arid aquifers and the cultural heritage they sustain. This study presents an integrated remote sensing and transformer-based deep learning framework that combines diverse geospatial datasets to predict spatiotemporal variations across the plain near the Persepolis and Naqsh-e Rustam archaeological complexes—UNESCO World Heritage Sites situated at the plain’s edge. We assemble 432 synthetic aperture radar (SAR) scenes (2015–2022) and derive vertical ground motion rates greater than −180 mm yr⁻¹, which are co-localized with multisource geoinformation, including hydrometeorological indices, biophysical parameters, and terrain attributes, to train transformer models with traditional deep learning methods. A sparse probabilistic transformer (ConvTransformer) trained on 95 gridded variables achieves an out-of-sample R² = 0.83 and RMSE = 6.15 m, outperforming bidirectional deep learning models by >40%. Scenario analysis indicates that, in the absence of intervention, subsidence may exceed 200 mm per year within a decade, threatening irreplaceable Achaemenid stone reliefs. Our results indicate that attention-based networks, when coupled to synergistic geodetic constraints, enable early-warning quantification of groundwater stress over heritage sites and provide a scalable template for sustainable aquifer governance worldwide. Full article

Surface ozone is a pollutant linked to higher risks of cardiopulmonary diseases with long-term exposure. Timely forecasting of ozone levels helps authorities implement preventive measures to protect public health and safety. However, few studies have been able to reliably provide long-term hourly ozone forecasts due to the complexity of ozone’s diurnal variations. To address this issue, this study constructs a hybrid prediction model integrating improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bi-directional long short-term memory neural network (BiLSTM), and the persistence model to forecast the hourly ozone concentrations for the next continuous 36 h. The model is trained and tested at the Wanshouxigong site in Beijing. The ICEEMDAN method decomposes the ozone time series data to extract trends and obtain intrinsic mode functions (IMFs) and a residual (Res). Fourier period analysis is employed to elucidate the periodicity of the IMFs, which serves as the basis for selecting the prediction model (BiLSTM or persistence model) for different IMFs. Extensive experiments have shown that a hybrid model of ICEEMDAN, BiLSTM, and persistence model is able to achieve a good performance, with a prediction accuracy of R² = 0.86 and RMSE = 18.70 µg/m³ for the 36th hour, outperforming other models. Full article