Search Results (619)

This study evaluates the landslide susceptibility of Zonguldak Province, Türkiye, by integrating the Analytical Hierarchy Process (AHP), artificial intelligence (AI) algorithms, and SBAS-InSAR deformation data. Eight environmental and geological parameters—elevation, slope, aspect, lithology, hydrogeology, land use, and distances to rivers and roads—were weighted using AHP and analyzed through 25 AI models. Among them, the Ensemble Bagged Trees (EBT) algorithm achieved the highest predictive accuracy (84%), demonstrating strong adaptability to complex geological datasets. The resulting susceptibility maps were validated using both traditional landslide inventories and InSAR-derived deformation maps, achieving an overall agreement of 83.05%. This dual-validation approach allows for the identification of unrecorded or active slope movements not captured in existing inventories. The combined use of AHP and AI significantly improves model reliability by incorporating both expert judgment and data-driven learning. The study introduces a novel hybrid framework for landslide susceptibility mapping and provides a valuable reference for disaster risk management and spatial planning in regions with complex topography. This study also contributes to sustainability by supporting risk-informed land-use planning, reducing potential economic losses, and enhancing environmental resilience in landslide-prone regions. The proposed framework aligns with sustainable development goals by integrating geospatial technologies and data-driven approaches for long-term hazard mitigation. Full article

The shortage of qualified teachers across Europe has increased interest in flexible and decentralized pathways into teacher education. This study examines pre-service teachers’ background characteristics and programme-choice priorities when selecting between two study formats at a Norwegian university: a blended learning programme and a face-to-face campus-based programme. Survey data from 108 pre-service teachers revealed significant differences between the groups in age, place of residence, region of origin, prior teaching experience, current teaching employment, and confidence in securing a permanent teaching position. Campus-based students were younger, less experienced, and reported lower confidence in obtaining permanent employment than students in the blended learning programme. Three of fifteen choice-related factors differed significantly between study formats, most notably the importance assigned to programme organization, which was rated higher by blended-learning students. No differences were found for geographic location or for eleven content-related factors. In this sample, blended-learning students were more often from rural areas, and they placed greater value on organizational flexibility, suggesting that flexible formats may be particularly relevant for students balancing work, distance, or other commitments. However, this study is cross-sectional, based on a single institution, and cannot determine broader policy implications or effects on regional teacher supply. Longitudinal and multi-institutional research is needed to assess potential long-term outcomes. Full article

To address the bottlenecks of low sample efficiency and poor control accuracy in traditional single-layer reinforcement learning during autonomous driving overtaking, this paper proposes an overtaking decision and control system based on hierarchical reinforcement learning to decouple complex tasks in spatial and temporal dimensions. A heterogeneous two-layer architecture is constructed, where the upper layer adopts the Proximal Policy Optimization algorithm to generate macroscopic discrete decisions, while the lower layer employs Twin Delayed Deep Deterministic Policy Gradient combined with Long Short-Term Memory to achieve smooth continuous control of steering and acceleration by perceiving temporal features of dynamic obstacles. A composite reward mechanism, integrating hard safety constraints and soft efficiency incentives, is designed to balance safety, efficiency, and comfort. Experimental results in complex scenarios with multiple interfering vehicles and random lane-changing behaviors demonstrate that the proposed system improves the training convergence speed by approximately 30% within 500,000 steps compared to single-layer algorithms. In tests across varying traffic densities, the system achieves a 98.3% success rate in medium-density scenarios with a collision rate of only 0.6%. In high-density challenges, the success rate remains above 95%, with the collision rate reduced by about 80% compared to baseline models. Furthermore, the lateral control deviation is strictly limited to within 0.2 m, and the longitudinal safety distance remains stable above 5 m. This system provides a robust, high-efficiency paradigm for autonomous overtaking. Full article

To accurately evaluate flood susceptibility in Shenzhen and support long-term flood control planning, this study develops a GIS-based multi-model machine learning framework. Nine factors—including elevation, slope, and distance to rivers—were selected, with multicollinearity ruled out via Pearson correlation and VIF tests. A balanced sample set comprising 741 historical waterlogging points (2020–2024) and equal non-waterlogging sites was constructed. In addition to comparing five base models (Decision Tree, SVM, Logistic Regression, Naïve Bayes, LDA), the study introduces a voting ensemble for model integration and applies SHAP for both global and local interpretability. Key findings include: (1) improved predictive accuracy and robustness via ensemble learning (AUC = 0.8131), outperforming individual models; (2) flood susceptibility mapping reveals a distinct spatial pattern—higher risk in western coastal areas and lower risk in eastern mountainous zones—with 68.3% of historical waterlogging points located in high-susceptibility zones. The model is trained on waterlogging records from 2020 to 2024, which may not fully capture longer-term climatic or urban dynamics. This work directly supports sustainable urban development by providing a replicable framework for flood risk mitigation that reduces long-term economic and social vulnerabilities. Full article

The rapid development of machine learning, large language models, and related technologies has greatly increased the demand for data storage capacity. Therefore, the role of distributed storage systems in such applications has become more prominent. However, it is inevitable that a single node fails in a distributed storage system during long-term use. Being able to repair failed nodes in a timely manner is extremely important for the stable operation of distributed storage systems, and a specific encoding scheme is required to meet the needs of efficiently repairing failed nodes. This research presents a novel family of binary locally repairable codes (LRCs) developed using multiple disjoint recovery sets constructed based on mutually orthogonal Latin squares (MOLS). The proposed constructions achieve distance optimality under the Singleton-like bound for LRCs with availability. Specifically, the codes are parameterized as $(n=r^2+tr,k=r^2,r,t)$ and $(n=rm+tm,k=rm,r,t)$, where n is the block length, k is the dimension, r is the locality, and t is the availability. These codes achieve minimum distance $d=t+1$, guaranteeing efficient recovery with t disjoint repair sets, each of size r. Compared to existing constructions, the proposed codes offer significant improvements in terms of code rate $\mathcal{R}={\displaystyle \frac{r}{r+t}}$, support for larger block lengths, and reduced finite field size requirements (field size $q=2$). Additionally, a method is introduced to improve the minimum distance of codes with even availability t, constructing codes with parameters $(n+1,k,r,t)$ and $d=t+2$, while preserving optimality. These properties make the proposed codes particularly suitable for distributed storage systems, where efficient and parallel repair of failed nodes is critical. Full article

When a line short-circuit fault occurs in a DC distribution network, the fault current rises quickly and affects a wide range, jeopardizing the safe operation of the system. In order to locate the fault quickly and accurately, this study proposes a fault localization method based on the Variational Mode Decomposition (VMD) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. First, the nonlinear relationship between the intrinsic principal frequency and fault distance is analyzed; then, the intrinsic principal frequency of the faulty traveling wave is extracted by using VMD, and the nonlinear relationship between the spectral energy of the principal frequency of the intrinsic frequency and the fault distance is fitted by training the Bi-LSTM network incorporating the attention mechanism. Finally, in response to the issue that a small amount of fault data in practical engineering is difficult to support the amount of data required for deep learning, a transfer learning method is used to locate the fault in the target domain. A small sample test of the target domain is carried out using the migration learning method. The experimental results show that the proposed method has high localization accuracy and good resistance to over-resistance and noise; compared with the traditional network training, the localization error based on migration learning is smaller, and the network convergence effect is better. Full article

Skeleton-based action recognition is a critical technology for intelligent sports analysis. Although the human skeletal structure exhibits inherent bilateral symmetry, sensor noise on resource-constrained edge devices frequently induces geometric distortion and topological asymmetry. Consequently, achieving a balance between high accuracy and real-time performance remains a significant challenge. To this end, we propose EMS-GCN, an Efficient Multi-scale Shift Graph Convolutional Network that integrates geometric priors. Specifically, we design a Gaussian kernel-driven topology refinement module to mitigate structural noise inherent in sensor data. By leveraging geometric symmetry and Gaussian distances among nodes, this module dynamically constrains graph topology learning, thereby effectively rectifying the structural asymmetry and ambiguity induced by noise. Furthermore, we construct a Multi-scale Shift Linear Attention (MSLA) module to replace computationally intensive temporal convolutions. Leveraging temporal shift invariance, this module captures multi-scale contexts via parameter-free shift operations. Furthermore, we introduce a linear temporal attention mechanism to model global temporal dependencies with linear complexity, effectively resolving the information asymmetry inherent in long-range interactions. Finally, EMS-GCN incorporates a dual-branch attention structure to adaptively calibrate feature responses. Extensive experiments demonstrate that our model maintains high recognition accuracy with only 0.56 M parameters, representing a reduction of over 60% compared to mainstream baselines. These results validate the efficacy of leveraging geometric and temporal symmetries to enhance real-time sports analysis. Full article

International tourism plays an important role in the global service economy, contributing to trade, employment, and regional development. For this reason, identifying the factors that influence tourist flows is an important issue for tourism policy, market strategy, and infrastructure planning. A large body of research has applied gravity models to analyze tourism flows between countries. While this approach provides a clear economic interpretation, it is usually based on linear specifications and may therefore capture only part of the relationships present in tourism data. This study examines the economic and geographic determinants of international tourism flows to Mongolia using a framework that combines a traditional gravity model with machine learning techniques. Mongolia serves as an instructive empirical setting, a landlocked, geographically peripheral destination whose inbound demand determinants have received limited systematic empirical attention. The analysis uses panel data for 27 origin countries covering the period from 2000 to 2024. In the first stage, a gravity model is estimated to assess how tourism flows relate to economic size and geographic distance. The results show that tourism flows tend to increase with the economic size of origin and destination countries, while greater geographical distance is associated with lower tourism flows. The estimated distance elasticity ranges from approximately −1.85 to −2.10 across model specifications, which is larger in absolute terms than the values typically reported in cross-country studies. This result is consistent with the relatively high travel cost barriers associated with Mongolia’s geographic location. These findings are consistent with the distance decay relationship commonly reported in the tourism literature. In the second stage, machine learning algorithms, including Random Forest, LightGBM, and XGBoost, are used as complementary interpretive instruments rather than forecasting tools to explore possible nonlinear relationships among the explanatory variables. To make the results more interpretable, the contribution of individual variables is examined using SHAP (Shapley Additive Explanations). The machine learning results indicate that some relationships in tourism demand may be nonlinear and not fully captured by the linear gravity specification. Specifically, distance sensitivity is approximately 6.5 times greater in nearby markets than in long-haul markets, with a structural inflexion at around 5700 km. Further analysis suggests that the influence of geographical distance is not uniform across all markets. In particular, tourism flows originating from middle-income countries appear to be more sensitive to increases in travel distance than those from higher-income countries. Overall, the findings indicate that economic size and geographical distance remain key determinants of international tourism flows to Mongolia. At the same time, the use of machine learning methods provides additional insight into potential nonlinear patterns in tourism demand. By combining econometric modelling with explainable machine learning techniques, the study offers an integrated analytical perspective for examining international tourism flows at geographically peripheral destinations where standard gravity assumptions may be insufficient. Full article

Background/Objectives: Perirenal fat (PRF) constitutes a critical yet understudied component of the tumor microenvironment in clear cell renal cell carcinoma (ccRCC). While radiomics enables non-invasive tissue characterization, whether PRF-derived features can simultaneously predict both TNM stage and histological grade, and whether optimal peritumoral distances differ between these distinct biological targets, remains unexplored in the literature. Methods: This multi-cohort retrospective study included 474 histopathologically confirmed ccRCC patients from three independent datasets (2007–2023). Automated nnU-Net segmentation delineated tumors and kidneys. Concentric PRF regions were systematically generated at 1–10 mm radial distances, yielding 18 distinct regions of interest. From each ROI, 1409 radiomic features were extracted using PyRadiomics. Sequential feature selection employed correlation filtering, SHAP-guided elimination, and LASSO regularization. Multiple machine learning classifiers underwent hyperparameter optimization with rigorous cross-cohort validation. Results: Systematic ROI screening revealed target-specific optimal distances: 4 mm PRF for TNM staging versus 10 mm PRF for histological grading. For staging, the integrated model (tumor + PRF radiomics + clinical variables) achieved AUC 0.829 (95% CI 0.781–0.877), sensitivity 80.2%, and specificity 67.8%. For grading, the combined model achieved AUC 0.780 (95% CI 0.598–0.962), sensitivity 79.7%, and specificity 63.3%, significantly outperforming all single-compartment models (DeLong p < 0.001). Conclusions: This study establishes that PRF radiomics enables accurate simultaneous non-invasive prediction of both TNM stage and histological grade in ccRCC. The novel discovery that optimal peritumoral distances differ substantially by prediction target (4 mm versus 10 mm) suggests distinct biological underpinnings for stage- and grade-related microenvironmental alterations, with important methodological implications for radiomic model development in oncology. Full article

Accurate trajectory tracking of redundant manipulators is difficult because the controller must simultaneously model local couplings between adjacent joints and global dependencies across the whole kinematic chain. Existing reinforcement learning methods typically employ multilayer perceptrons, which do not explicitly exploit manipulator structure and therefore show limited stability and representation ability in high-dimensional continuous control tasks. This paper proposes GT-TD3, a Graph Transformer-enhanced-Twin Delayed Deep Deterministic Policy Gradient framework, for redundant manipulator trajectory tracking. The proposed actor first converts the raw system state into joint-level node features and uses a graph neural network to extract local kinematic coupling information. A Transformer is then employed to capture long-range dependencies among joints. To strengthen the use of structural priors, topology- and distance-related bias terms are incorporated into the attention mechanism, enabling the network to encode manipulator structure during global feature learning. Experiments on a 7-DoF KUKA iiwa manipulator in PyBullet demonstrate that GT-TD3 outperforms MLP, pure GNN, and pure Transformer baselines in tracking performance. The proposed method achieves more stable training, faster convergence, and smoother and more accurate end-effector motion. The results show that the integration of local graph modeling and structure-aware global attention provides an effective solution for high-precision trajectory tracking of redundant manipulators. Full article

Background/Objectives: Machine learning (ML) models can predict hospital admission from emergency department (ED) triage data with areas under the receiver operating characteristic curve (AUC) exceeding 0.85. Whether incorporating the assigned provider’s identity—as a proxy for unmeasured practice variation—improves prediction has not been systematically studied. We aimed to compare 10 supervised ML classifiers for predicting hospital admission at ED triage, with and without provider identity, and to characterize model reasoning using SHapley Additive exPlanations (SHAP). Methods: We conducted a retrospective cohort study of 186,094 ED visits (2020–2023, training) and 58,151 visits (2024, temporal holdout test) at one academic tertiary-care ED. Ten classifiers spanning linear, distance-based, tree-based, ensemble, probabilistic, and neural network families were each trained in two conditions: baseline (23 triage features) and with provider identity appended. SHAP TreeExplainer was applied to the top-performing models (CatBoost and XGBoost). Results: The admission rate was 31.3% (training) and 31.7% (test). CatBoost achieved the highest baseline AUC of 0.8906 (0.8878–0.8933). Adding provider identity produced negligible AUC changes across all models (ΔAUC range: −0.0029 to +0.0015; all DeLong p > 0.05). SHAP analysis identified ESI level, respiratory rate, temperature, complaint category, and age as the dominant predictors, with clinically intuitive directionality. Conclusions: Provider identity does not meaningfully improve ML prediction of hospital admission beyond standard triage variables. The observed 28-percentage-point variation in provider admission rates is explained by patient case-mix differences than with independent practice pattern effects on prediction. SHAP provides transparent, clinically interpretable explanations suitable for bedside decision support. Full article

In federated learning, multiple clients collaborate to train a global model without exchanging raw data, which addresses issues of data silos and the leakage of data privacy. However, existing federated learning schemes often suffer from high communication overhead and unreliable server-side aggregation. To address these limitations, this paper proposes a verifiable chained federated learning mechanism with Euclidean distance-based grouping, termed VDCG-FL. Grouping is used to improve communication efficiency, while verification ensures the accuracy of aggregated results. Unlike conventional approaches, VDCG-FL groups clients according to their Euclidean distance to the server, thereby reducing communication latency, avoiding long-distance transmissions, and enhancing the stability of model aggregation. Moreover, Lagrange interpolation is used for verification to ensure aggregation correctness while incurring significantly lower computational overhead than traditional cryptographic methods. Extensive experiments demonstrate that VDCG-FL improves aggregation stability under non-IID data distributions while simultaneously reducing communication overhead. Full article

Indonesia faces persistent challenges in crime forecasting and judicial resource management, compounded by chronic underreporting and inconsistent spatial resolution in official crime statistics. In this study, a multi-level spatio-temporal machine learning framework is developed and applied to 95,666 adjudicated crime records from the Supreme Court of Indonesia spanning January 2023 to June 2024. Following the CRISP-DM methodology, a hybrid STL-XGBoost v. 3.2.0 model is trained on a chronological split to forecast daily judicial caseloads, achieving an R² of 0.8070, MAE of 16.52, and sMAPE of 9.76% on the held-out test set. DBSCAN spatial clustering, parameterized via k-distance plot analysis ($\mathrm{ϵ}={0.3}^{\circ }$, $minPts$ = 3) and validated through Jaccard Similarity Index sensitivity analysis, identifies 29 distinct adjudicated crime hubs concentrated along Java and Sumatra’s urban and transit corridors. Comparative analysis of reported versus adjudicated crime data reveals systematic judicial funnel attrition ranging from 199.12% in Riau to 2436.02% in Papua, establishing that adjudicated crime records provide a reliable indicator of judicial workload rather than a comprehensive measure of social deviance. Key limitations, including the 18-month observation window that may not capture long-term policy shifts and the use of city centroids as spatial proxies that introduces a degree of ecological fallacy, are acknowledged. The framework offers a scalable, interpretable decision support tool for evidence-based judicial resource planning across national, provincial, and city scales in Indonesia. Full article

Safe and energy-aware navigation is still difficult for unmanned surface vehicles (USVs), especially in cluttered waters where obstacles, smooth motion, and wind or current effects must be considered at the same time. If these issues are handled separately, the path may become longer and the vehicle may turn more often, which raises propulsion effort and hurts stability. To reduce these problems, a hybrid path planning method called ${\theta }^{\ast }$-APF-Q is proposed, and it combines global planning, learning-based decisions, and local adjustment in a three-layer structure. First, an any-angle ${\theta }^{\ast }$ global planner is employed to generate a near-optimal backbone trajectory by line-of-sight pruning, thereby reducing redundant waypoints and limiting detours. Second, an enhanced tabular Q-learning model is executed in an expanded eight-direction action space, and policy learning is guided by a multi-objective reward that jointly encourages distance reduction, alignment with ocean current and wind-induced forces for energy saving, smooth heading variation to suppress excessive steering, and maintenance of a safety margin near obstacles. Third, an adaptive artificial potential field (APF) module is used for real-time local correction, providing repulsion in high-risk regions and assisting trajectory smoothing to reduce unnecessary turning operations. A decision bias strategy further couples instantaneous APF forces with long-term state–action values, while the influence weight is adaptively adjusted according to environmental complexity. The algorithm is validated on the randomly generated marine grid maps and on the real-world satellite map scenario, with comparisons against a conventional four-direction Q-learning baseline. Across randomized tests, average path length, turning frequency, and the composite energy indicator are reduced by 22.3%, 55.6%, and 26.4%, respectively, and the success rate increases by 16%. The results indicate that integrating global guidance, adaptive learning, and local reactive decision making supports practical, energy-aware USV navigation. Full article

Vertical docking of the autonomous underwater shuttle (AUS) for deep-sea data relay relies heavily on ultra-short baseline (USBL) acoustic positioning, whose measurements can be intermittently unavailable and contaminated by outliers in complex underwater environments. This paper proposes a neural network-enhanced robust navigation framework to improve AUS navigation reliability during acoustically guided vertical docking under USBL outages. First, a model-aided batch maximum a posteriori trajectory estimation method (MA-BMAP) is developed to generate learning quality supervision under sensor-limited conditions. Based on the estimated trajectories, a long short-term memory (LSTM)-based horizontal velocity predictor is integrated into a robust fusion filter with online ocean current estimation, enabling stable state estimation during USBL outages and robust rejection of abnormal USBL measurements. The proposed framework is validated through simulations and field trials in lake and sea environments. In sea trials, during two representative 200 s USBL outage intervals, the end-of-window horizontal position errors are 7.86 m and 4.14 m, respectively, corresponding to AUS-to-docking station distances of 244 m and 51 m. In addition, the introduced USBL outliers are successfully detected and rejected. The results indicate that the proposed method enables accurate and stable navigation during USBL unavailability and rapid recovery once USBL measurements resume, demonstrating its practicality for vertical docking missions. Full article