Search Results (4,442)

Impulsive overtopping generated by dam-break surges is a critical hazard for dikes and flood-protection embankments, especially in reservoirs and mountainous catchments. Unlike classical coastal wave overtopping, which is governed by long, irregular wave trains and usually characterized by mean overtopping discharge over many waves, these dam-break-type events are dominated by one or a few strongly nonlinear bores with highly transient overtopping heights. Accurately predicting the resulting overtopping levels under such impulsive flows is therefore important for flood-risk assessment and emergency planning. Conventional cluster-then-predict approaches, which have been proposed in recent years, often first partition data into subgroups and then train separate models for each cluster. However, these methods often suffer from rigid boundaries and ignore the uncertainty information contained in clustering results. To overcome these limitations, we propose a GMM+MoE framework that integrates Gaussian Mixture Model (GMM) soft clustering with a Mixture-of-Experts (MoE) predictor. GMM provides posterior probabilities of regime membership, which are used by the MoE gating mechanism to adaptively assign expert models. Using SPH-simulated overtopping data with physically interpretable dimensionless parameters, the framework is benchmarked against XGBoost, GMM+XGBoost, MoE, and Random Forest. Results show that GMM+MoE achieves the highest accuracy ($R^2=0.9638$ on the testing dataset) and the most centralized residual distribution, confirming its robustness. Furthermore, SHAP-based feature attribution reveals that relative propagation distance and wave height are the dominant drivers of overtopping, providing physically consistent explanations. This demonstrates that combining soft clustering with adaptive expert allocation not only improves accuracy but also enhances interpretability, offering a practical tool for dike safety assessment and flood-risk management in reservoirs and mountain river valleys. Full article

Urban rail transit networks in developing countries are rapidly expanding, entering a networked operational phase where accurate passenger flow forecasting is crucial for optimizing vehicle scheduling, resource allocation, and transportation efficiency. In the short term, accurate real-time forecasting enables the dynamic adjustment of train headways and crew deployment, reducing average passenger waiting times during peak hours and alleviating platform overcrowding; in the long term, reliable trend predictions support strategic planning, including capacity expansion, station retrofitting, and energy management. This paper proposes a novel hybrid forecasting model, EEMD-TiDE, that combines improved Ensemble Empirical Mode Decomposition (EEMD) with a Time Series Dense Encoder (TiDE) to enhance prediction accuracy. The EEMD algorithm effectively overcomes mode mixing issues in traditional EMD by incorporating white noise perturbations, decomposing raw passenger flow data into physically meaningful Intrinsic Mode Functions (IMFs). At the same time, the TiDE model, a linear encoder–decoder architecture, efficiently handles multi-scale features and covariates without the computational overhead of self-attention mechanisms. Experimental results using Xi’an Metro passenger flow data (2017–2019) demonstrate that EEMD-TiDE significantly outperforms baseline models. This study provides a robust solution for urban rail transit passenger flow forecasting, supporting sustainable urban development. Full article

Background/Objectives: Federated learning (FL) offers a way for healthcare institutions to collaboratively train machine learning models without sharing sensitive patient data. This systematic review aims to comprehensively synthesize the ethical dimensions of FL in healthcare, integrating privacy preservation, algorithmic fairness, governance, and equitable access into a unified analytical framework. The application of FL in healthcare between January 2020 and December 2024 is examined, with a focus on ethical issues such as algorithmic fairness, privacy preservation, governance, and equitable access. Methods: Following PRISMA guidelines, six databases (PubMed, IEEE Xplore, Web of Science, Scopus, ACM Digital Library, and arXiv) were searched. The PROSPERO registration is CRD420251274110. Studies were selected if they described FL implementations in healthcare settings and explicitly discussed ethical considerations. Key data extracted included FL architectures, privacy-preserving mechanisms, such as differential privacy, secure multiparty computation, and encryption, as well as fairness metrics, governance models, and clinical application domains. Results: Out of 3047 records, 38 met the inclusion criteria. The most popular applications were found in medical imaging and electronic health records, especially in radiology and oncology. Through thematic analysis, four key ethical themes emerged: algorithmic fairness, which addresses differences between clients and attributes; privacy protection through formal guarantees and cryptographic techniques; governance models, which emphasize accountability, transparency, and stakeholder engagement; and equitable distribution of computing resources for institutions with limited resources. Considerable variation was observed in how fairness and privacy trade-offs were evaluated, and only a few studies reported real-world clinical deployment. Conclusions: FL has significant potential to promote ethical AI in healthcare, but advancement will require the development of common fairness standards, workable governance plans, and systems to guarantee fair benefit sharing. Future studies should develop standardized fairness metrics, implement multi-stakeholder governance frameworks, and prioritize real-world clinical validation beyond proof-of-concept implementations. Full article

This paper analyzes the implementation of the Geoportal SIG FESBAL–UPM, a Participatory Geographic Information System (PGIS) developed within the Master’s and Doctorate programs in Rural Development Project Planning and Sustainable Management at UPM. The study introduces a model integrated with Project-Based Learning (PBL), the Working With People (WWP) framework, and the CFS-RAI principles to address challenges in responsible food systems. The geoportal designed to be applied at the Food Bank–UPM Chair–FESBAL, acts as an innovative instrument for participation among the different stakeholders enabling the spatialization and analysis of data across social, environmental, and governance dimensions. Functionally, it offers a robust foundation for evidence-based decision-making, systematizes geographic information, and visualizes data via the web, supporting research, training, and community engagement actions. Furthermore, this study details the specific projects and activities developed under the three involved action lines: research, training, and community engagement, identifying strengths and weaknesses in each. The findings affirm that this participatory approach ensures that the proposed solutions are aligned with local needs and priorities, increasing the sustainability and long-term success of the projects implemented through the geoportal. Full article

Gadolinium-based contrast agents (GBCAs) are vital for glioma imaging yet pose safety, cost, and accessibility issues; predicting contrast enhancement from non-contrast MRI via machine learning (ML) provides a safer, economical alternative, as enhancement indicates tumor aggressiveness and informs treatment planning. However, scanner and population variability hinder robust model selection. To overcome this, a stability-aware framework was developed to identify reproducible ML pipelines for predicting glioma contrast enhancement across multicenter cohorts. A total of 1367 glioma cases from four TCIA datasets (UCSF-PDGM, UPENN-GB, BRATS-Africa, BRATS-TCGA-LGG) were analyzed, using non-contrast T1-weighted images as input and deriving enhancement status from paired post-contrast T1-weighted images; 108 IBSI-standardized radiomics features were extracted via PyRadiomics 3.1, then systematically combined with 48 dimensionality reduction algorithms and 25 classifiers into 1200 pipelines, evaluated through rotational validation (training on three datasets, external testing on the fourth, repeated across rotations) incorporating five-fold cross-validation and a composite score penalizing instability via standard deviation. Cross-validation accuracies spanned 0.91–0.96, with external testing yielding 0.87 (UCSF-PDGM), 0.98 (UPENN-GB), and 0.95 (BRATS-Africa), averaging ~0.93; F1, precision, and recall remained stable (0.87–0.96), while ROC-AUC varied (0.50–0.82) due to cohort heterogeneity, with the MI + ETr pipeline ranking highest for balanced accuracy and stability. This framework enables reliable, generalizable prediction of contrast enhancement from non-contrast glioma MRI, minimizing GBCA dependence and offering a scalable template for reproducible ML in neuro-oncology. Full article

The rising incidence of invasive fungal infections (IFIs) and the associated antifungal resistance underscore the need for antifungal stewardship (AFS) programs. Evaluating physicians’ knowledge and practices is crucial for identifying gaps and planning effective AFS interventions. A self-administered questionnaire was distributed to staff and resident physicians at a referral university-affiliated hospital in Greece in November 2025. The survey examined participants’ knowledge on fungal diagnosis and treatment, their prescribing attitudes and practices, and their AFS-related education, knowledge and preferences. In total, 70 physicians (46 residents and 24 staff consultants) participated in the survey from medical departments (63%), surgical departments (30%), and intensive care units (7%). Physicians surveyed demonstrated a low average knowledge score of 36.6% correct answers (SD, 22.7%; range 0% to 90%) regarding IFIs and antifungal agents, and significant variation was observed across different hospital departments. Awareness of risk factors for IFI varied widely, with recognition rates of different factors ranging from 10% to 100% across departments. Many physicians (71%) reported a lack of confidence in prescribing antifungal therapy and reliance on infectious disease experts was common (84%). Most preferred training methods were case-based discussions and printed guidelines. The substantial knowledge gaps and low confidence in prescribing antifungals among physicians highlight the urgent need for education and implementation of local guidelines to optimize antifungal use that might improve patient outcomes. Full article

The rapid advancement of sequencing technologies has led to the generation of complex multi-omics data, which are often high-dimensional, noisy, and imbalanced, posing significant challenges for traditional machine learning methods. The novelty of this work resides in the architecture-level integration of autoencoders with Generative Adversarial Network (GAN) and Conditional Tabular Generative Adversarial Network (CTGAN) models, where the autoencoder is employed for latent feature extraction and noise reduction, while GAN-based models are used for realistic sample generation and class imbalance mitigation in multi-omics cancer datasets. This study proposes a novel framework that combines an autoencoder for dimensionality reduction and a CTGAN for generating synthetic samples to balance underrepresented classes. The process starts with selecting the most discriminative features, then extracting latent representations for each omic type, merging them, and generating new minority samples. Finally, all samples are used to train a neural network to predict specific cancer outcomes, defined here as clinically relevant biomarkers or patient characteristics. In this work, the considered outcome in the bladder cancer is Tumor Mutational Burden (TMB), while the breast cancer outcome is menopausal status, a key factor in treatment planning. Experimental results show that the proposed model achieves high precision, with an average precision of 0.9929 for TMB prediction in bladder cancer and 0.9748 for menopausal status in breast cancer, and reaches perfect precision (1.000) for the positive class in both cases. In addition, the proposed AE–CTGAN framework consistently outperformed an autoencoder combined with a standard GAN across all evaluation metrics, achieving average accuracies of 0.9929 and 0.9748, recall values of 0.9846 and 0.9777, and F1-scores of 0.9922 for bladder and breast cancer datasets, respectively. A comparative fidelity analysis in the latent space further demonstrated the superiority of CTGAN, reducing the average Euclidean distance between real and synthetic samples by approximately 72% for bladder cancer and by up to 84% for breast cancer compared to a standard GAN. These findings confirm that CTGAN generates high-fidelity synthetic samples that preserve the structural characteristics of real multi-omics data, leading to more reliable class balancing and improved predictive performance. Overall, the proposed framework provides an effective and robust solution for handling class imbalance in multi-omics cancer data and enhances the accuracy of clinically relevant outcome prediction. Full article

Deep reinforcement learning (DRL) with self-play has emerged as a promising paradigm for solving combinatorial optimization (CO) problems. The recently proposed Gumbel AlphaZero Plan-to-Play (GAZ PTP) framework adopts a competitive training setup between a learning agent and an opponent to tackle classical CO tasks such as the Traveling Salesman Problem (TSP). However, in complex and multi-constrained environments like the Electric Vehicle Routing Problem (EVRP), standard self-play often suffers from opponent mismatch: when the opponent is either too weak or too strong, the resulting learning signal becomes ineffective. To address this challenge, we introduce Two-Stage Self-Play GAZ PTP (TSS GAZ PTP), a novel DRL method designed to maintain adaptive and effective learning pressure throughout the training process. In the first stage, the learning agent, guided by Gumbel Monte Carlo Tree Search (MCTS), competes against a greedy opponent that follows the best historical policy. As training progresses, the framework transitions to a second stage in which both agents employ Gumbel MCTS, thereby establishing a dynamically balanced competitive environment that encourages continuous strategy refinement. The primary objective of this work is to develop a robust self-play mechanism capable of handling the high-dimensional constraints inherent in real-world routing problems. We first validate our approach on the TSP, a benchmark used in the original GAZ PTP study, and then extend it to the multi-constrained EVRP, which incorporates practical limitations including battery capacity, time windows, vehicle load limits, and charging infrastructure availability. The experimental results show that TSS GAZ PTP consistently outperforms existing DRL methods, with particularly notable improvements on large-scale instances. Full article

Curling presents a challenging continuous-control problem in which shot outcomes depend on long-horizon interactions between complex physical dynamics, strategic intent, and opponent responses. Despite recent progress in applying reinforcement learning (RL) to games and sports, curling lacks a unified environment that jointly supports stable, rule-consistent simulation, structured state abstraction, and scalable agent training. To address this gap, we introduce a comprehensive learning framework for curling AI, consisting of a full-sized simulation environment, a task-aligned Markov decision process (MDP) formulation, and a two-phase training strategy designed for stable long-horizon optimization. First, we propose a novel MDP formulation that incorporates stone configuration, game context, and dynamic scoring factors, enabling an RL agent to reason simultaneously about physical feasibility and strategic desirability. Second, we present a two-phase curriculum learning procedure that significantly improves sample efficiency: Phase 1 trains the agent to master delivery mechanics by rewarding accurate placement around the tee line, while Phase 2 transitions to strategic learning with score-based rewards that encourage offensive and defensive planning. This staged training stabilizes policy learning and reduces the difficulty of direct exploration in the full curling action space. We integrate this MDP and training procedure into a unified Curling RL Framework, built upon a custom simulator designed for stability, reproducibility, and efficient RL training and a self-play mechanism tailored for strategic decision-making. Agent policies are optimized using Soft Actor–Critic (SAC), an entropy-regularized off-policy algorithm designed for continuous control. As a case study, we compare the learned agent’s shot patterns with elite match records from the men’s division of the Le Gruyère AOP European Curling Championships 2023, using 6512 extracted shot images. Experimental results demonstrate that the proposed framework learns diverse, human-like curling shots and outperforms ablated variants across both learning curves and head-to-head evaluations. Beyond curling, our framework provides a principled template for developing RL agents in physics-driven, strategy-intensive sports environments. Full article

Background: Food insecurity among college students is a multidimensional challenge shaped by individual, interpersonal, institutional, community, and policy factors. Although many campuses require or provide meal plans, students may experience food insecurity when barriers related to agency (choice and autonomy), utilization (nutrition security), and availability persist. This study explored how undergraduate students at a private, urban U.S. university experience and navigate the multiple dimensions of food insecurity. Methods: We conducted in-depth, semi-structured interviews via Zoom between December 2024 and January 2025 with n = 22 undergraduate students recruited based on food security status, determined by a Fall 2024 longitudinal survey using the USDA Six-Item Short Form. Transcripts were double-coded by trained research assistants in ATLAS.ti using an inductive codebook. Thematic analyses followed a phronetic, iterative approach, organizing findings within a socio-ecological determinants framework and comparing themes by food security status. Results: We identified nine themes across four domains (individual, interpersonal, institutional and community, and political). At the individual level, constrained personal resources for groceries and cooking, time scarcity leading to skipped meals, and health impacts that detracted from academics emerged as key themes. Interpersonally, reliable family financial support was protective and informal support from peers/coaches filled gaps sporadically for some. At the institutional and community level, dining hall hours misaligned with student schedules, perceived limited variety and nutrition quality reduced food agency and utilization, and transportation impeded use of the sole grocery partner accepting university meal plan benefits. Notably, meal plans including unlimited meal swipes provided stable access but did not guarantee food security when food agency and utilization barriers persisted. Many students relied on campus events for free food; formal assistance (e.g., food pantry) was largely underused. At the policy level, Supplemental Nutrition Assistance Program (SNAP) awareness and enrollment was limited among our sample. Conclusions: Meal plan access alone is insufficient to ensure food security. Campus strategies should extend beyond access to prioritize flexibility, variety, and alignment with students’ schedules and preferences, while strengthening communication and eligibility support for external benefits. Future work should design and evaluate interventions that integrate all dimensions of food security and address institutional policies affecting students’ basic needs. Full article

Background/Objectives: In the modern healthcare landscape, breast cancer remains one of the most prevalent malignancies and a leading cause of mortality among women worldwide. Early and accurate prediction of breast cancer plays a pivotal role in effective diagnosis, treatment planning, and improving survival outcomes. However, due to the complexity and heterogeneity of medical data, achieving high predictive accuracy remains a significant challenge. This study proposes an intelligent hybrid system that integrates traditional machine learning (ML), deep learning (DL), and ensemble learning approaches for enhanced breast cancer prediction using the Wisconsin Breast Cancer Dataset. Methods: The proposed system employs a multistage framework comprising three main phases: (1) data preprocessing and balancing, which involves normalization using the min–max technique and application of the Synthetic Minority Over-sampling Technique (SMOTE) to mitigate class imbalance; (2) model development, where multiple ML algorithms, DL architectures, and a novel ensemble model are applied to the preprocessed data; and (3) model evaluation and validation, performed under three distinct training–testing scenarios to ensure robustness and generalizability. Model performance was assessed using six statistical evaluation metrics—accuracy, precision, recall, F1-score, specificity, and AUC—alongside graphical analyses and rigorous statistical tests to evaluate predictive consistency. Results: The findings demonstrate that the proposed ensemble model significantly outperforms individual machine learning and deep learning models in terms of predictive accuracy, stability, and reliability. A comparative analysis also reveals that the ensemble system surpasses several state-of-the-art methods reported in the literature. Conclusions: The proposed intelligent hybrid system offers a promising, multidisciplinary approach for improving diagnostic decision support in breast cancer prediction. By integrating advanced data preprocessing, machine learning, and deep learning paradigms within a unified ensemble framework, this study contributes to the broader goals of precision oncology and AI-driven healthcare, aligning with global efforts to enhance early cancer detection and personalized medical care. Full article

Current research on landslide susceptibility modeling is often constrained by reliance on conventional topographic and geological features, potentially overlooking the discriminative power of surface material properties derived from multi-source remote sensing. This study aims to enhance the accuracy and reliability of susceptibility assessment by innovatively integrating spectral information and advanced machine learning techniques. Focusing on Chongqing, a landslide-prone mountainous region in China, this work conducted three innovative investigations: it (i) introduced 12 spectral features into the feature set; (ii) systematically evaluated spectral features contribution, redundancy, and set completeness through feature engineering; and (iii) implemented a comprehensive Stacking ensemble framework with multiple meta-learners and enhancement strategies (Bagging and Cross-Training) to identify the optimal integration scheme. The key results show that spectral features provided a significant positive impact, boosting the AUC of tree-based ensemble models by up to 4.52%. The optimal model, a Stacking ensemble with Bagging_XGBoost as the meta-learner, achieved a superior test AUC of 0.8611, outperforming all individual base learners. Furthermore, the spatial analysis revealed a concentration of high and very high susceptibility areas in Engineering Geological Zone I, which represents approximately 38% of such areas. This study provides a replicable framework for enhancing landslide susceptibility mapping through the integration of spectral features and ensemble learning, offering a scientific basis for targeted risk management and mitigation planning in complex mountainous terrains. Full article

Background and Objectives: Posthepatectomy liver failure (PHLF) remains a major cause of morbidity and mortality for patients undergoing major liver resections. Recent research highlights the expanding role of machine learning (ML), a crucial subfield of artificial intelligence (AI), in optimizing risk stratification. The aim of the current study was to review, elaborate on and critically analyze the available literature regarding the use of ML-driven risk prediction models for posthepatectomy liver failure. Materials and Methods: A systematic search was conducted in the PubMed/MEDLINE, Scopus and Web of Science databases. Fifteen studies that trained and validated ML models for prediction of PHLF were further included and analyzed. Results: The available literature supports the value of ML-derived models for PHLF prediction. Perioperative clinical, laboratory and imaging features have been combined in a variety of different algorithms to provided interpretable and accurate models for identifying patients at risk of PHLF. The ML-based algorithms have consistently demonstrated high area under the curve and sensitivity values, surpassing traditionally used risk scores in predictive performance. Limitations include the small sample sizes, heterogeneity in populations included, lack of external validation and a reported poor ability to distinguish between true positive and false positive cases in several studies. Conclusions: Despite the constraints, ML-driven tools, in combination with traditional scoring systems and clinical insight, may enable early and accurate PHLF risk detection, personalized surgical planning and optimization of postoperative outcomes in liver surgery. Full article

Effective predictive maintenance is crucial for ensuring aircraft reliability, reducing operational disruptions, and supporting spare part inventory management in airline operations. However, maintenance data is often sparse, with irregular observations, missing records, and imbalanced failure distributions, making accurate forecasting a significant challenge. This study proposes a data-driven framework for maintenance prediction under sparse observational data. We implement and compare two distinct methodologies: survival analysis via DeepHit for time-to-event prediction, and a latent space classifier with autoencoder backbone. Each method is evaluated on historical aircraft maintenance logs and component installation records, addressing challenges posed by limited and imbalanced datasets. Both models are trained and tested on ten years of maintenance logs and component installation records sourced from an airline MRO (Maintenance, Repair and Overhaul) company that services a fleet of more than 500 aircraft, offering a realistic and scalable setting for fleet-wide maintenance analysis. The latent space classifier demonstrates superior overall performance and consistency across diverse components and prediction horizons compared to DeepHit, which is constrained by its sensitivity to probability thresholds. The encoder-based method effectively transfers knowledge from high-data components to those with sparse maintenance histories, enabling reliable maintenance forecasting and enhanced inventory planning for large-scale airline operations. Full article

Remote sensing enables large-scale, image-based assessments of river dynamics, offering new opportunities for hydrological monitoring. We present a publicly available dataset consisting of 281,024 satellite and aerial images of U.S. rivers, constructed using an Application Programming Interface (API) and the U.S. Geological Survey’s National Hydrography Dataset. The dataset includes images, primary keys, and ancillary geospatial information. We use a manually labeled subset of the images to train models for detecting rapids, defined as areas where high velocity and turbulence lead to a wavy, rough, or even broken water surface visible in the imagery. To demonstrate the utility of this dataset, we develop an image segmentation model to identify rivers within images. This model achieved a mean test intersection-over-union ($IoU$) of 0.57, with performance rising to an actual $IoU$ of 0.89 on the subset of predictions with high confidence (predicted $IoU$ > 0.9). Following this initial segmentation of river channels within the images, we trained several convolutional neural network (CNN) architectures to classify the presence or absence of rapids. Our selected model reached an accuracy and F1 score of 0.93, indicating strong performance for the classification of rapids that could support consistent, efficient inventory and monitoring of rapids. These data provide new resources for recreation planning, habitat assessment, and discharge estimation. Overall, the dataset and tools offer a foundation for scalable, automated identification of geomorphic features to support riverine science and resource management. Full article