Search Results (472)

The development of big data analytics in healthcare has created a demand for privacy-conscious and scalable machine learning algorithms that can allow the use of patient information across different healthcare organizations. In this study, the difficulties that come with traditional federated learning frameworks in healthcare sectors, such as scalability, computational effectiveness, and preserving patient privacy for numerous healthcare systems, are discussed. In this work, a new conceptual model known as Hierarchical Federated Learning (HFL) for large, integrated healthcare organizations that include several institutions is proposed. The first level of aggregation forms regional centers where local updates are first collected and then sent to the second level of aggregation to form the global update, thus reducing the message-passing traffic and improving the scalability of the HFL architecture. Furthermore, the HFL framework leveraged more robust privacy characteristics such as Local Differential Privacy (LDP), Gaussian Differential Privacy (GDP), Secure Multi-Party Computation (SMPC) and Homomorphic Encryption (HE). In addition, a Novel Aggregated Gradient Perturbation Mechanism is presented to alleviate noise in model updates and maintain privacy and utility. The performance of the proposed HFL framework is evaluated on real-life healthcare datasets and an artificial dataset created using Generative Adversarial Networks (GANs), showing that the proposed HFL framework is better than other methods. Our approach provided an accuracy of around 97% and 30% less privacy leakage compared to the existing models of FLBM-IoT and PPFLB. The proposed HFL approach can help to find the optimal balance between privacy and model performance, which is crucial for healthcare applications and scalable and secure solutions. Full article

In the era of “carbon dioxide peaking and carbon neutrality”, low-carbon development of road traffic and transportation has now become a rigid demand in China. Considering the fact that socioeconomic and demographic characteristics vary significantly across Chinese cities, proper city-level transportation development strategies should be established. Using detailed data from cities at prefecture level and above in China, this study investigates the spatially heterogeneous effects of various factors on road traffic CO₂ emissions. Another theoretical issue is concerned with the analytic method for zonal CO₂ emission modeling. We combine the concepts of geographically weighted regression (GWR) and machine learning for nonparametric regression, proposing a modified random forest (RF) algorithm, named “geographically weighted random forest” (GWRF). Our empirical analysis indicates that, when an appropriate weight parameter is applied, GWRF is able to achieve significantly superior performance compared to both the traditional RF and GWR methods. Moreover, the influences of various explanatory variables on CO₂ emissions differ across cities. These findings suggest that low-carbon transportation strategies should be customized to reflect regional heterogeneity, rather than relying on a unified national policy. Full article

Rockfalls, among the most common natural disasters, pose risks such as traffic congestion, casualties, and substantial property damage. Guizhou Province, with China’s fourth-longest highway network, features mountainous terrain prone to frequent rockfall incidents annually. Consequently, assessing highway rockfall risks in Guizhou Province is crucial for safeguarding the lives and travel of residents. This study evaluates highway rockfall risk through three key components: susceptibility, hazard, and vulnerability. Susceptibility was assessed using information content and logistic regression methods, considering factors such as elevation, slope, normalized difference vegetation index (NDVI), aspect, distance from fault, relief amplitude, lithology, and rock weathering index (RWI). Hazard assessment utilized a fuzzy analytic hierarchy process (AHP), focusing on average annual rainfall and daily maximum rainfall. Socioeconomic factors, including GDP, population density, and land use type, were incorporated to gauge vulnerability. Integration of these assessments via a risk matrix yielded comprehensive highway rockfall risk profiles. Results indicate a predominantly high risk across Guizhou Province, with high-risk zones covering 41.19% of the area. Spatially, the western regions exhibit higher risk levels compared to eastern areas. Notably, the Bijie region features over 70% of its highway mileage categorized as high risk or above. Logistic regression identified distance from fault lines as the most negatively correlated factor affecting highway rockfall susceptibility, whereas elevation gradient demonstrated a minimal influence. This research provides valuable insights for decision-makers in formulating highway rockfall prevention and control strategies. Full article

3D object detection is a fundamental task in autonomous driving. In recent years, voxel-based methods have demonstrated significant advantages in reducing computational complexity and memory consumption when processing large-scale point cloud data. A representative method, Voxel-RCNN, introduces Region of Interest (RoI) pooling on voxel features, successfully bridging the gap between voxel and point cloud representations for enhanced 3D object detection. However, its robustness deteriorates when detecting distant objects or in the presence of noisy points (e.g., traffic signs and trees). To address this limitation, we propose an enhanced approach named Self-Attention Voxel-RCNN (SA-VoxelRCNN). Our method integrates two complementary attention mechanisms into the feature extraction phase. First, a full self-attention (FSA) module improves global context modeling across all voxel features. Second, a deformable self-attention (DSA) module enables adaptive sampling of representative feature subsets at strategically selected positions. After extracting contextual features through attention mechanisms, these features are fused with spatial features from the base algorithm to form enhanced feature representations, which are subsequently input into the region proposal network (RPN) to generate high-quality 3D bounding boxes. Experimental results on the KITTI test set demonstrate that SA-VoxelRCNN achieves consistent improvements in challenging scenarios, with gains of 2.49 and 1.87 percentage points at Moderate and Hard difficulty levels, respectively, while maintaining real-time performance at 22.3 FPS. This approach effectively balances local geometric details with global contextual information, providing a robust detection solution for autonomous driving applications. Full article

The terminal maneuvering area (TMA) serves as a critical transition zone between upper enroute airways and airports, representing one of the most complex regions for managing high volumes of arrival and departure traffic. This paper presents the multi-route TMA scheduling problem as an optimization challenge aimed at optimizing TMA interventions, such as rerouting, speed control, time-based metering, dynamic minimum time separation, and holding procedures; the objective function minimizes schedule deviations and the accumulated holding time. Furthermore, the problem is formulated as a mixed-integer linear program (MILP) to facilitate finding solutions. A rolling horizon control (RHC) dynamic optimization framework is also introduced to decompose the large-scale problem into manageable subproblems for iterative resolution. To demonstrate the applicability and effectiveness of the proposed scheduling models, a hub airport—Chengdu Tianfu International Airport (ICAO code: ZUTF) in the Cheng-Yu Metroplex—is selected for validation. Numerical analyses confirm the superiority of the proposed models, which are expected to reduce aircraft delays, shorten airborne and holding times, and improve airspace resource utilization. This study provides intelligent decision support and engineering design ideas for the macroscopic-level collaborative optimization framework of the Integrated Arrival–Departure and Surface (IADS) system. Full article

This study assessed the influence of meteorological conditions on particulate matter (PM) concentrations in Campo Grande, Brazil, from May to December 2021. Using statistical analyses, including Pearson’s correlation coefficient and multivariate regression, we analyzed secondary data on PM2.5 and PM10 concentrations and meteorological variables from the Federal University of Mato Grosso do Sul’s Physics Department. Daily PM concentrations complied with Brazil’s National Ambient Air Quality Standards (PQAr). The PM2.5/PM10 ratios averaged 0.436 (hourly) and 0.442 (daily), indicating a mix of fine and coarse particles. Significant positive correlations were found with temperature, while relative humidity showed a negative correlation, reducing PM levels through deposition. Wind speed had no significant impact. Meteorological influences suggest that air quality management should be tailored to regional conditions, particularly addressing local emission sources like vehicular traffic and biomass burning. Full article

Growing concern over anthropogenic underwater noise, highlighted by initiatives like the Marine Strategy Framework Directive (MSFD) and its Technical Group on Underwater Noise (TG Noise), emphasizes regions like the Western Black Sea, where increasing activities threaten marine habitats. This region is experiencing rapid growth in maritime traffic and resource exploitation, which is intensifying concerns over the noise impacts on its unique marine habitats. While machine learning offers promising solutions, a research gap persists in comprehensively evaluating diverse ML models within an integrated framework for complex underwater acoustic data, particularly concerning real-world data limitations like class imbalance. This paper addresses this by presenting a multi-faceted framework using passive acoustic monitoring (PAM) data from fixed locations (50–100 m depth). Acoustic data are processed using advanced signal processing (broadband Sound Pressure Level (SPL), Power Spectral Density (PSD)) for feature extraction (Mel-spectrograms for deep learning; PSD statistical moments for classical/unsupervised ML). The framework evaluates Convolutional Neural Networks (CNNs), Random Forest, and Support Vector Machines (SVMs) for noise event classification, alongside Gaussian Mixture Models (GMMs) for anomaly detection. Our results demonstrate that the CNN achieved the highest classification accuracy of 0.9359, significantly outperforming Random Forest (0.8494) and SVM (0.8397) on the test dataset. These findings emphasize the capability of deep learning in automatically extracting discriminative features, highlighting its potential for enhanced automated underwater acoustic monitoring. Full article

Despite the well-documented health risks of noise pollution, its impact remains overlooked mainly in life cycle assessment (LCA). This study introduces a methodological innovation by integrating both traffic and construction noise into the LCA framework for concrete construction, providing a more holistic and realistic evaluation of environmental and health impacts. By combining building information modeling (BIM) with LCA, the method automates material quantification and assesses both environmental and noise-related health burdens. A key advancement is the inclusion of health-based indicators, such as annoyance and sleep disturbance, quantified through disability-adjusted life years (DALYs). Two scenarios are examined: (1) a comparative analysis of concrete versus timber flooring and (2) end-of-life options (reuse vs. landfill). The results reveal that concrete has up to 7.4 times greater environmental impact than timber, except in land use. When noise is included, its contribution ranges from 7–33% in low-density regions (Darwin) and 62–92% in high-density areas (NSW), underscoring the critical role of local context. Traffic noise emerged as the dominant source, while equipment-related noise was minimal (0.3–1.5% of total DALYs). Timber slightly reduced annoyance but showed similar sleep disturbance levels. Material reuse reduced midpoint environmental impacts by 67–99.78%. Sensitivity analysis confirmed that mitigation measures like double glazing can cut noise-related impacts by 2–10% in low-density settings and 31–45% in high-density settings, validating the robustness of this framework. Overall, this study establishes a foundation for integrating noise into LCA, supporting sustainable material choices, environmentally responsible construction, and health-centered policymaking, particularly in noise-sensitive urban development. Full article

Rapid urbanization and climate change pose significant challenges to air quality in arid metropolitan areas, with critical implications for public health and sustainable development. This study projects the evolution of air pollution in Riyadh, Saudi Arabia, through 2070 using an integrated modeling approach that combines CMIP6 climate projections with localized air quality data. We analyzed daily concentrations of major pollutants (SO₂, NO₂) across 15 strategically selected monitoring stations representing diverse urban environments, including traffic corridors, residential areas, healthcare facilities, and semi-natural zones. Climate data from two Earth System Models (CNRM-ESM2-1 and MPI-ESM1.2) were bias-corrected and integrated with historical pollution measurements (2000–2015) using hierarchical Bayesian statistical modeling under SSP2-4.5 and SSP5-8.5 emission scenarios. Our results revealed substantial deterioration in air quality, with projected increases of 80–130% for SO₂ and 45–55% for NO₂ concentrations by 2070 under high-emission scenarios. Spatial analysis demonstrated pronounced pollution gradients, with traffic corridors (Eastern Ring Road, Northern Ring Road, Southern Ring Road) and densely urbanized areas (King Fahad Road, Makkah Road) experiencing the most severe increases, exceeding WHO guidelines by factors of 2–3. Even semi-natural areas showed significant increases in pollution due to regional transport effects. The hierarchical Bayesian framework effectively quantified uncertainties while revealing consistent degradation trends across both climate models, with the MPI-ESM1.2 model showing a greater sensitivity to anthropogenic forcing. Future concentrations are projected to reach up to 70 μg m⁻³ for SO₂ and exceed 100 μg m⁻³ for NO₂ in heavily trafficked areas by 2070, representing 2–3 times the Traffic corridors showed concentration increases of 21–24% compared to historical baselines, with some stations (R5, R13, and R14) recording projected levels above 4.0 ppb for SO₂ under the SSP5-8.5 scenario. These findings highlight the urgent need for comprehensive emission reduction strategies, accelerated renewable energy transition, and reformed urban planning approaches in rapidly developing arid cities. Full article

The Italian market for non-alcoholic beer is very small, with a volume per capita of around 0.7 L. However, there are interesting prospects for future growth for reasons ranging from strict traffic code rules on the quantity of alcohol ingested to simple curiosity. This research aimed to investigate the willingness of Italian consumers/potential consumers to pay for non-alcoholic beer. To accomplish this, a questionnaire was administered using the Google Forms application. Three hundred and ninety-two people participated in this survey voluntarily and without monetary compensation. A probit regression model was used to estimate the impact of certain sociodemographic characteristics (number of inhabitants of the place of residence, region of residence, age group, gender, education level, employment situation, and annual net income), participants’ consumption habits with respect to alcoholic beer, and participants’ knowledge of and preference for non-alcoholic beers with respect to willingness to pay for non-alcoholic beers. The prices respondents were willing to pay ranged from EUR 1.51 to 2.00 for a 33 cL glass bottle. Only two factors significantly affected (p < 0.1) non-alcoholic beer WTP, namely, “Age” and “Non-alcoholic beer color”. WTP decreased as the age of the respondents increased and was higher for the darker beer. Full article

Nitrogen oxides (NO_X) are important precursors of ozone and secondary aerosols. Accurate and timely NO_X emission estimates are essential for formulating measures to mitigate haze and ozone pollution. Bottom–up and satellite–constrained top–down methods are commonly used for emission inventory compilation; however, they have limitations of time lag and high computational demands. Here, we propose a machine learning model, WOA-XGBoost (Whale Optimization Algorithm–Extreme Gradient Boosting), to retrieve NO_X emissions. We constructed a dataset incorporating satellite observations and conducted model training and validation in the Shandong region with severe NO_X pollution to retrieve high spatiotemporal resolution of NO_X emission rates. The 10–fold cross–validation coefficient of determination (R²) for the NO_X emission retrieval model was 0.99, indicating that WOA-XGBoost has high accuracy. Validation of the model for the other year (2019) showed high agreement with MEIC (Multi–resolution Emission Inventory for China), confirming its strong robustness and good temporal transferability. The retrieved NO_X emissions for 2021–2022 revealed that emission rate hotspots were located in areas with heavy traffic flow. Among 16 prefecture–level cities in Shandong, Zibo exhibited the highest NO_X rate (>1 μg/m²/s), explaining its high NO₂ pollution levels. In the future, priority areas for emission reduction should focus on heavy industry clusters such as Zibo and high traffic urban centers. Full article

Predicting forest trail visitation is essential for sustainable management and policy development, including infrastructure planning, safety operations, and conservation. However, due to numerous informal access points and complex external influences, accurately monitoring visitor numbers remains challenging. This study applied random forest, gradient boosting, and LightGBM models with Bayesian optimization to predict daily visitor counts across six sections of the National Daegwallyeong Forest Trail, incorporating variables such as weather conditions, social media activity, COVID-19 case counts, tollgate traffic volume, and local festivals. SHAP analysis revealed that tollgate traffic volume and weekends consistently increased visitation across all sections. The impact of temperature varied by section: higher temperatures increased visitation in Kukmin Forest, whereas lower temperatures were associated with higher visitation at Seonjaryeong Peak. COVID-19 cases demonstrated negative effects across all sections. By integrating diverse variables and conducting section-level analysis, this study identified detailed visitation patterns and provided a practical basis for adaptive, section- and season-specific management strategies. These findings support flexible measures such as seasonal staffing, congestion mitigation, and real-time response systems and contribute to the advancement of data-driven regional tourism management frameworks in the context of evolving nature-based tourism demand. Full article

This study aimed to evaluate the effects of varying traffic intensities, the time since harvesting, and the interaction between these two factors on the restoration of herbaceous cover on skid trails in the Hyrcanian forests, Northern Iran. Three compartments were selected from two districts within the pure oriental beech (Fagus orientalis Lipsky) stands of Kheyrud Forest, where ground-based timber extraction had occurred 5, 10, and 15 years prior. In each compartment, three skid trails representing low, medium, and high traffic intensities were identified. Control plots were established 10 m away from the trails. A total of 54 systematically selected 1 m × 1 m sample plots were surveyed: 27 on skid trails (three traffic intensities × three time intervals × three replicates) and 27 control plots (matching the same variables). Within each quadrat, all herbaceous plants were counted, identified, and recorded. Our findings revealed that only traffic intensity had a clear significant impact on plant abundance. High traffic intensity led to a pronounced decline in herbaceous cover, with disturbed skid trails showing reduced species diversity or the complete disappearance of certain species in comparison to the control plots. Time since harvesting and its interaction with traffic intensity did not yield statistically significant effects. Disturbance led to a reduction in the quantities of certain species or even their disappearance on skid trails in comparison to the control plots. Given the pivotal role of machinery traffic intensity in determining mitigation strategies, there is a critical need for research on region-specific harvesting techniques and the development of adaptive management strategies that minimize ecological impacts by aligning practices with varying levels of traffic intensity. Full article

Road traffic accidents remain a critical public health concern worldwide, with Poland consistently experiencing high fatality rates—52 deaths per million inhabitants in 2023, compared to the EU average of 46. To investigate the underlying factors contributing to these accidents, we developed a multifactorial dataset integrating 250,000 accident records from 2015 to 2023 with spatially interpolated weather data and sociodemographic indicators. We employed Kriging interpolation to convert point-based weather station data into continuous surfaces, enabling the attribution of location-specific weather conditions to each accident. Following comprehensive preprocessing and spatial analysis, we generated visualizations—including heatmaps and choropleth maps—that revealed distinct regional patterns at the county level. Our preliminary findings suggest that accident occurrence and severity are driven by different underlying factors: while temperature and vehicle counts strongly correlate with total accident numbers, humidity, precipitation, and road infrastructure quality show stronger associations with fatal outcomes. This integrated dataset provides a robust foundation for Bayesian and time-series modeling, supporting the development of evidence-based road safety strategies. Full article

Road traffic accidents pose a substantial global public health burden, resulting in significant fatalities and economic costs. This study employs Bayesian Poisson regression to model traffic accident rates in Poland, focusing on the intricate relationships between weather conditions and socioeconomic factors. Analyzing both yearly county-level and weekly nationwide data from 2020 to 2023, we created four distinct models examining the relationships between accident occurrence and predictors including temperature, humidity, precipitation, population density, passenger car registrations, and road infrastructure. Model evaluation, based on WAIC and PSIS-LOO criteria, demonstrated that integrating both weather and socioeconomic variables enhanced predictive accuracy. Results showed that socioeconomic variables—especially passenger car registrations—were strong predictors of accident rates over longer timeframes and across localized regions. In contrast, weather variables, particularly temperature and humidity, were more influential in explaining short-term fluctuations in nationwide accident counts. These findings provide a statistical foundation for identifying high-risk conditions and guiding targeted interventions. The study supports Poland’s national road safety goals by offering evidence-based strategies to reduce accident-related fatalities and injuries. Full article