Search Results (497)

We propose KoSim-GL, a large-scale vision-based geo-localization dataset for drone positioning in GPS-denied environments. Geo-localization estimates a drone’s location by matching drone-view imagery against a geo-referenced satellite image database, offering a reliable alternative to GPS under conditions such as signal jamming, spoofing, or degradation in dense urban canyons. Although this task is challenging due to the domain gap between drone-view and satellite-view imagery, existing benchmarks are built predominantly around urban environments in the United States and China, leaving South Korea largely unrepresented, despite its distinctive landscape in which mountainous terrain coexists with dense high-rise districts and low-rise residential neighborhoods. To address this gap, we introduce KoSim-GL, constructed from drone-view images captured via an AirSim- and ROS-based flight simulator and satellite images collected through the Google Maps Tile API, covering the urban area of Daejeon, South Korea. Its key feature is a multi-view configuration that simultaneously captures five views, one nadir and four oblique, at each flight position across altitudes from 100 m to 600 m, enabling robust localization even in feature-sparse environments where nadir-only matching is prone to fail. In total, KoSim-GL comprises 2,450,315 drone images and 1704 satellite images. We further provide systematic comparisons against five existing benchmarks and baseline evaluations of ten representative geo-localization models under single- and multi-view settings. Experimental results show that the multi-view configuration substantially improves localization performance; for example, FSRA improves Recall@1 from 44.08% (single-view) to 65.37% (multi-view), a gain of 21.29 percentage points. The dataset is publicly available. Full article

Equipment fault prediction in maglev train systems poses substantial challenges: fault events are inherently rare, class distributions are severely imbalanced, and individual equipment units are subject to complex spatial and functional couplings that single-device statistical approaches fundamentally cannot capture. To address these challenges, this study proposes a Knowledge Graph-driven Graph Neural Network (KG-GNN) framework. A fault knowledge graph encompassing equipment, fault, temporal, and environmental entities is constructed to unify multi-source maintenance data. Graph connectivity is established via three spatial relation types (co-location, co-zone, and co-level), with edge weights derived from Laplacian-smoothed Lift scores quantifying fault co-occurrence strength. A two-layer GATv2Conv-based graph attention network is designed: the first layer employs four-head attention with explicit edge-weight integration to capture heterogeneous neighborhood influences, while the second layer produces compact node embeddings via single-head attention. A Top-20 sparsification strategy suppresses weak-association noise, and training under severe class imbalance is stabilized through Focal Loss and F2-Score-guided early stopping. On the test set, the proposed method achieves an F2-Score of 0.5703, Recall of 0.6825, and AUC-ROC of 0.9329 (single-run evaluation); multi-seed evaluation (5 seeds) yields F2 = 0.5645 ± 0.0035, Recall = 0.6789 ± 0.0095, and AUC-ROC = 0.9298 ± 0.0026, outperforming the MLP baseline by 18.3% in F2-Score and substantially exceeding GCN (F2 = 0.1476 ± 0.0176) and GATConv (F2 = 0.4284 ± 0.0097). Ablation studies confirm the individual contributions of authentic graph topology, precise edge weighting, and graph sparsification to overall performance. Full article

Rail-transit station areas concentrate commercial services, employment, and intensive land development, but their vitality is shaped by multiple built-environment conditions rather than rail accessibility alone. Focusing on 20 stations along the Osaka Metro Midosuji Line in Japan, this study uses Japanese chome units, which are small neighborhood-level address and statistical units, within an 800 m pedestrian catchment as analytical units and measures commercial-service agglomeration intensity, employment intensity, and commercial–employment composite vitality. The composite indicator measures the static co-concentration of commercial-service provision and employment carrying capacity, with pedestrian flow, consumption activity, and dwell time treated as separate dimensions of station-area vitality. Ten station-area environmental variables are examined using ordinary least squares (OLS), Lasso, Random Forest, Back-Propagation (BP) Neural Network, and extreme gradient boosting (XGBoost) models, with Shapley additive explanations (SHAP) applied to interpret variable contributions and nonlinear responses. Results show that nonlinear models generally outperform linear models. Development intensity, officially assessed land price, and network distance to the nearest metro station are the most influential variables, showing threshold, marginal, and non-monotonic effects. Split models indicate that commercial-service agglomeration is more sensitive to rail proximity and street-network conditions, whereas employment intensity is more associated with development intensity and land price. These findings support fine-grained station-area renewal and mixed-function planning. Full article

Static pre-scheduling in inland container depot (ICD)-centered drayage must coordinate tractors, detachable load units, factory loading, and port deadlines before next-day execution. Conventional order-based routing is too rigid for mixed direct haulage, drop-and-pull, relay pickup, street-turn, and buffering operations. This study proposes a task-pooling framework that decomposes logistics orders into atomic tasks and recombines them across tractors in a unified static planning space. A compact route-based MILP is used for reduced-scale calibration, and an enhanced adaptive large neighborhood search (E-ALNS) is developed around ICD-oriented relay recombination and temporal-slack shifting. On a realistic synthetic benchmark with 100 generated order records (90 active executable orders), 60 available tractors, and 330 executable tasks, the proposed method reduces the internal search-ledger value from 42,213.29 to 34,421.22 and the compact ex post blueprint value from 53,802.28 to 47,717.99 relative to the greedy construction baseline. The resulting blueprint preserves an average inter-task slack of 89.86 min and a 5th-percentile slack of 61.73 min. A generic adaptive-neighborhood baseline reaches a slightly lower ex post value of 46,722.48 only with a longer runtime and much lower temporal reserve. The results support a cost–reserve–runtime tradeoff interpretation rather than unconditional cost dominance. Full article

Electroencephalography (EEG) offers a non-invasive and cost-effective means of probing brain activity during language processing; however, prior EEG-based language studies have been limited by small datasets, a predominant focus on native-speaker or speech-unit recognition rather than direct language detection, evaluation on only a small number of experimental settings, and frequent reliance on computationally intensive deep learning models with limited interpretability. The proposed feature engineering models classifies EEG segments by language and task mode. The languages are Arabic and Turkish. The modes are reading and listening. In this study, a signal refers to one fixed-length multi-channel EEG segment (14 channels × 15 s at 128 Hz). A channel refers to one electrode time series within that segment. To address these gaps, we curated a new EEG language detection dataset from 346 participants (98 Arabic and 248 Turkish) recorded in reading and listening modes, yielding 6364 EEG segments. Using this dataset, we proposed DiagPat, an explainable feature engineering (XFE) model that extracts transition table-based features from both EEG channels and signals through diagonal pattern analysis. The model combines DiagPat feature extraction with iterative neighborhood component analysis (INCA) for feature selection, at algorithm-based k-nearest neighbors (tkNN) classifier for prediction, and the Directed Lobish (DLob) symbolic language for explainability. We evaluated the framework across nine classification cases covering language detection, mode detection, and mixed multi-class settings. The proposed DiagPat-driven XFE model achieved more than 90% accuracy in all cases, with accuracies ranging from 92.14% to 99.35%, and generated case-specific cortical connectome diagrams that supported the interpretable characterization of language- and mode-related brain activity. Subject-independent results were also reported using leave-one-subject-out cross-validation (LOSO CV), where LOSO accuracies ranged from 29.75% to 83.50%. Thus, the 10-fold CV results show segment-level performance, whereas the LOSO results show subject-level generalization. Balanced accuracy and macro-F1 are also reported. These findings indicate that DiagPat provides an accurate, lightweight, and explainable framework for EEG-based language detection. Full article

Rapid urbanization has intensified inequalities in the distribution of urban green resources, making green equity a critical concern within the framework of the United Nations Sustainable Development Goals. This study examines Zhangdian District in Zibo City, China, a representative “Whole-Area Park City” pilot area. This study integrates 1 km population density grid data with GIS network analysis, space syntax, population-weighted service pressure assessment, and a location–allocation model. Using these methods, it evaluates four categories of urban parks from the perspectives of spatial distribution, road connectivity, and social equity. The results reveal that vehicle and cycling modes achieved nearly complete 15 min coverage, whereas pedestrian accessibility remained insufficient. Walking accessibility for comprehensive parks reached 77.69%, whereas that of community parks and petty street gardens was below 33%. Population-weighted analysis further suggests that more than 78% of residents, concentrated in dense central–western neighborhoods, are served by only 21% of total park area. The Gini coefficient of per capita park area reached 0.4765, indicating substantial inequality in park green space allocation. After optimization through the addition of 76 new parks, improvements in road connectivity, and construction of a slow-traffic system, the Gini coefficient decreased to 0.4053, representing a 14.9% reduction. Meanwhile, the population below the national standard declined from 78.09% to 40.64%. These findings reflect spatial accessibility and area-based equity, while actual park service value also depends on park quality, facilities, and user behavior. This study provides quantitative evidence for equity-oriented park planning and a replicable framework for sustainable urban green space planning. Full article

Translating fine-resolution air pollution surfaces into health equity assessments requires aggregating exposure to administrative units, yet the equity implications of this choice are rarely tested. This study links annual 300 m nitrogen dioxide (NO₂) surfaces from the New York City Community Air Survey (2009–2023) with childhood asthma emergency department (ED) visit rates across 42 neighborhoods, comparing area-weighted, population-weighted, and residential-weighted aggregation throughout. Strong spatial convergence was observed in both NO₂ and ED burden (Pearson correlations between 2009 baseline levels and Theil–Sen slopes of −0.96 and −0.95). Panel first-difference estimation yielded a significant within-neighborhood association between NO₂ decline and ED rate decline (coefficient 0.022, p-value below 0.05). The most deprived fifth of neighborhoods received 47% of the total avoided ED burden, four times the share of the least deprived fifth. However, NO₂ reductions were nearly equal across poverty quintiles. The pro-poor distribution of health benefits was driven by baseline health inequality, not by differential pollution reduction. The three aggregation methods produced near-identical results for all metrics because within-neighborhood exposure variability was uncorrelated with poverty (r = −0.14). In cities where baseline disease burden is concentrated in disadvantaged communities, broad-based air quality improvement may contribute to pro-poor health gains without targeted intervention. Full article

Air quality affects large urban areas, where rapid urban development and human activities place constant pressure on ecosystems and public health. In this context, large-scale air quality assessment, supported by short-term forecasts, can provide useful information for environmental management and decision-making in urban areas, thus supporting evidence-based urban environmental management. The aim of this work is to design an affordable, smart real-time air pollution monitoring and prediction system for urban planning in overpopulated locations, which is deeply related to community health. The system focuses on real-time monitoring and forecasting of air quality. Prediction tasks were limited to gaseous pollutants CO and CO₂. Measurements were obtained over four months from a low-cost sensor platform installed in a highly populated neighborhood district in Baghdad, Iraq. Air quality prediction of gas concentrations was done using three types of time-series algorithms: Long Short-Term Memory, or LSTM; Gated Recurrent Unit, or GRU; and Temporal Convolutional Network, or TCN, models. Among these, the LSTM architecture showed more stable behavior and a higher predictive ${\mathrm{R}}^2$, ranging from 98.2% to 98.9%. Generally, the findings suggest that combining low-cost sensing technologies with artificial intelligence can offer a feasible and scalable solution for urban air quality monitoring. This approach may support cost-effective strategies for monitoring air quality in resource-constrained urban environments. Full article

Automatic license plate reader (ALPR) cameras and gunshot detection system (GDS) technology represent rapidly expanding forms of surveillance. Despite their prevalence, empirical literature regarding these tools remains limited, particularly concerning their geographic distribution across the United States. This study addresses this gap by conducting a geospatial analysis of crowdsourced ALPR and GDS locations throughout Virginia. Utilizing Geographic Information Systems (GIS), we mapped the concentrations of this technology and analyzed the racial demographic profiles of the most heavily surveilled communities. Our results identify distinct clusters of surveillance technology hubs across Virginia. In these high-intensity areas, surveillance technology is frequently concentrated in and around communities of color. These findings carry an array of implications, including the risk that over-surveilled neighborhoods may disproportionately suffer from the abuse or misuse of these tools. Furthermore, this distribution reflects a historical legacy within the criminal justice system of disproportionately monitoring marginalized populations. The limitations of this analysis are equally revealing: the reliance on crowdsourced data due to a lack of verifiable, publicly accessible coordinates underscores an ongoing lack of transparency. Full article

Coordinated development between new-type urbanization and rural revitalization is important for sustainable urban–rural transformation and balanced regional development in China. Using panel data for 30 provincial-level units from 2014 to 2023, this study examines the spatiotemporal evolution, dynamic transitions, and external drivers of the coupling coordination degree between the two systems. Spatial Markov chains and an interpretable machine-learning framework are used to identify neighborhood effects, nonlinear relationships, and interaction patterns. The results show four main findings. First, the coupling coordination degree increased over the study period, but clear spatial differences and clustering remained. This suggests that coordinated urban–rural development did not advance evenly across regions. Second, the evolution of coordination shows strong state dependence, and neighborhood context is closely related to transition probabilities. Provinces located in high-coordination neighborhoods were more likely to move to higher levels, while provinces in low-coordination neighborhoods were more likely to remain trapped at lower levels. Third, digital inclusive finance and fiscal self-sufficiency were the most important external factors. Both showed clear nonlinear patterns. Per capita electricity consumption and aging rate also showed heterogeneous relationships at different value ranges. Fourth, the interaction results suggest that higher coordination is more likely to emerge when digital finance, fiscal capacity, openness, human capital, and infrastructure improve together, rather than when only one factor expands on its own. The findings indicate that sustainable urban–rural transformation is shaped by spatial dependence, nonlinear changes, and context-specific factor combinations. Beyond their relevance for more targeted urban–rural coordination and place-based sustainability governance in China, these findings also provide a useful reference for other developing countries seeking to address similar urban–rural development challenges. Full article

In the renewal of rural self-built houses, dispersed construction patterns, insufficient design guidance, and resource constraints often lead to tensions between individual building needs and the overall settlement landscape. Grounded in the theory of spatial self-organization, this study proposes a roof interface renewal framework of “Clustering–Collaboration–self-organization,” and takes Dianju Village in Anning City, Yunnan Province, as a case study to explore how limited architectural interventions can address the fragmentation of roof landscapes in rural settlements. This research adopts a mixed-method approach combining ethnographic fieldwork, resident design observation, and post-occupancy evaluation (POE). The POE was conducted with 16 participating households, focusing on residents’ perceptions of roof usability, visual order, material acceptance, opportunities for neighborhood interaction, and maintenance issues. The findings indicate that residents generally perceive that continuous roof treatment, the application of bamboo–timber materials, and adjustable structural units have improved the usability of roof spaces, while enhancing their recognition of the overall village image and the expression of local materials. At the same time, residents’ feedback suggests that the long-term performance of bamboo–timber materials still depends on continuous maintenance and appropriate structural protection. The contribution of this study lies in translating spatial self-organization theory into a participatory and locally adaptive process of rural landscape renewal. Rather than providing a directly replicable roof typology, this case offers exploratory insights into key interface identification, resident negotiation, and localized construction strategies for the renewal of rural self-built houses in developing and transitional contexts. Full article

Background/Objectives: To examine the association of social determinants of health (SDOHs) with primary and cost-related medication nonadherence among adults with diabetes. Methods: A retrospective cross-sectional analysis was conducted using 2021 data from the Medical Expenditure Panel Survey (MEPS), a nationally representative sample of the United States civilian noninstitutionalized population. Adults aged ≥ 18 years with a diagnosis of diabetes in 2021 were included. The outcomes include primary medication nonadherence (no antidiabetic prescriptions filled) and cost-related medication nonadherence (delaying prescriptions due to cost). The exposure variables include SDOHs such as financial stress, food insecurity, transportation barriers, social support, access to medical care in the neighborhood, and healthcare discrimination. Weighted multivariable logistic regression analyses were conducted to assess the association between SDOHs and medication nonadherence. Results: Among 21.9 million patients with diabetes, 6.5% reported cost-related nonadherence and 17.4% exhibited primary nonadherence. Difficulty paying rent or mortgage (OR 2.32, 95% CI: 1.27–4.23), food insecurity (OR 2.13, 95% CI: 1.27–3.58), and transportation barriers (OR = 2.15; 95% CI: 1.20–3.63) were significantly associated with cost-related nonadherence. In the Medicare subgroup, both difficulty paying rent or mortgage (OR = 2.41, 95% CI: 1.03–5.64) and food insecurity (OR = 2.16, 95% CI: 1.18–3.96) significantly increased cost-related nonadherence. Conclusions: Financial strain, food insecurity, and transportation barriers are associated with cost-related nonadherence. These findings suggest considering social and economic factors in strategies supporting diabetes medication adherence across populations, including Medicare beneficiaries. Full article

Firearm-related injuries are the leading cause of death for children, adolescents, and young adults in the United States, yet empirically evaluated court-based intervention models targeting firearm offenders remain rare in the peer-reviewed literature. This exploratory pilot study evaluates the implementation and pilot outcomes of the Violence Intervention Program (VIP), a court-based specialty docket designed to address gun violence through a trauma-informed, multidisciplinary model. This descriptive pilot evaluation utilized administrative court records, program data, and clinical service logs among 77 enrolled participants with felony-level, non-violent gun-related charges. Participants were entirely male, majority Black (87%), with a median age of 22 years, and primarily residents of high-poverty Cleveland, OH neighborhoods. Descriptive statistics and independent-samples t-tests were used to compare service utilization and drug screen outcomes between program participants who successfully completed and those who were unsuccessfully terminated from the program. Successful completion was contingent upon fulfillment of three program phase requirements, including consistent adherence to court-mandated supervision and active engagement in clinical and program services. Of 48 participants who exited the program during the pilot period, 34 successfully completed (67.3%). The one-year recidivism rate was 29.5%. Successful program completers received significantly higher monthly peer mentorship services than those who were unsuccessfully terminated, while counseling dosage and drug screen results did not significantly differ between groups. Findings suggest that multidisciplinary, trauma-informed, court-based models can safely intervene with justice-involved young adults and may serve as a replicable public health strategy for reducing gun violence. Full article

Urban neighborhood parks are essential infrastructure for sustainable cities, supporting physical and mental health, social cohesion, and climate adaptation. Equity-oriented park planning, however, requires accurate identification of residents who can access parks within network-constrained travel time thresholds. Many accessibility studies estimate served populations using coarse administrative zones and areal-weighting assumptions, which can bias results in heterogeneous, vertically developed districts. This study develops a building-based population allocation framework (implemented via a building centroid overlay) that integrates Statistics Korea’s census output areas (2023 Q4 release) with the Ministry of Land, Infrastructure and Transport (MOLIT)’s GIS Integrated Building Information database (2023 Q4 release) and applies it to Yongsan-gu (Yongsan District), Seoul. Park entrances were verified and digitized using street-view imagery available on multiple web map platforms, and walkable service areas (5 and 10 min) were delineated via network analysis. Potential service coverage and unserved population were then estimated under three spatial configurations—administrative dong (neighborhood-level administrative unit in Seoul; hereafter administrative unit), census output area, and building-based allocation—and compared. Under the 10 min scenario, the unserved share reached 24.6% at the administrative unit level but decreased to 5.9% and 4.3% when using census output areas and building-based allocation, respectively. The building-based approach additionally revealed micro-scale clusters of unserved residents near localized pedestrian constraints and boundary-crossing areas that are obscured by zone-based methods. These findings demonstrate the sensitivity of access-based potential service coverage diagnostics to spatial unit choice and population disaggregation and suggest that building-based population allocation can improve the targeting of park pro-vision policies and promote spatial equity in dense, vertically developed cities. Full article

Rail trespassing remains a persistent safety challenge at the system level in the United States, with a 24% increase in incidents within the last decade (2016–2025). Identifying hotspots proactively is difficult due to limited incident data and strong spatial dependencies within the built environment. This study thus creates a ZIP-code–level geospatial analytics framework to identify current and emerging trespassing hotspots across North Carolina by combining land-use composition, rail exposure metrics, and historical Federal Railroad Administration (FRA) trespassing records. Geospatial layers were integrated within a GIS workflow to derive attributes such as rail miles, grade crossings, population density, and land-use types. Exploratory spatial analysis showed significant clustering of trespassing incidents, with Global Moran’s I indicating positive spatial autocorrelation across multiple neighborhood sizes. Permutation z-scores confirmed non-random hotspot formation along major rail corridors. A k-means clustering method also identified four structural risk environments, and a Composite Risk Index (CRI) was developed from weighted, standardized exposure and land-use variables to quantify latent risk, independent of raw casualty counts. Results indicate that clusters characterized by higher rail infrastructure exposure and mixed land-use environments exhibit the highest CRI values and elevated hotspot probabilities. In contrast, clusters with limited rail infrastructure, including predominantly commercial and rural ZIP codes, show substantially lower risk levels. The findings highlight that trespassing risk is more strongly associated with structural exposure conditions than with isolated historical incident counts. The resulting risk surfaces and hotspots provide an interpretable and scalable framework for statewide safety planning, early hotspot detection, and targeted interventions by transportation agencies. Full article