Search Results (12,927)

The detection of anomaly energy consumption patterns in smart grid metering systems remains a critical issue. This is due to data imbalance, privacy constraints, and the dynamic nature of consumption patterns. To address these concerns, we present a privacy-preserving and scalable anomaly detection framework named as FedTheftDetect framework. The proposed framework integrates deep learning algorithms into a federated learning (FL) architecture through the incorporation of advanced ensemble classifiers to detect behavioral anomalies in daily consumption patterns. A real-world smart meter dataset with significant class imbalance is used to assess the suggested framework. The dataset had significant preprocessing to identify consumption-related anomalies in behavior. Experimental results demonstrate that the suggested framework outperforms the competitive centralized and distributed models. It achieves significant improvements in Accuracy, Precision, Recall, and F1-score, all of which are close to 0.95, which indicates a great predictive capability and reliability. Full article

Shared e-scooter systems are frequently characterized as zero-emission mobility solutions; however, lifecycle greenhouse gas (GHG) emissions depend on manufacturing, electricity generation, and operational logistics. While conventional life cycle assessment (LCA) studies quantify environmental impacts using static average parameters, they rarely integrate lifecycle emissions into real-time fleet decision-making. This study proposes a formally defined carbon-aware operational framework that integrates ride-level telemetry, time-varying electricity grid carbon intensity, amortized production emissions, and dynamically allocated logistics impacts into a unified optimization architecture. Lifecycle emissions are computed at ride-level granularity and incorporated into charging and rebalancing decisions through a constrained optimization framework. A multi-objective extension is introduced to account for environmental–economic trade-offs. An illustrative simulation of 1000 rides was conducted to evaluate the operational performance of the framework. Under the assumed baseline scenario, the illustrative carbon-aware simulation indicated a potential reduction of up to 24.5% relative to conventional scheduling. Sensitivity analysis across variations in grid carbon intensity, scooter lifetime, energy consumption, and logistics emissions demonstrated reduction outcomes ranging between 18% and 29%, indicating robustness to parameter uncertainty. The study does not present large-scale empirical validation but provides a mathematically formalized decision-support architecture that operationalizes lifecycle assessment within shared micro-mobility fleet management. The results suggest that integrating carbon metrics into operational control may substantially enhance the environmental performance of shared e-scooter systems. Future research should validate the framework using real-world fleet data and incorporate a comprehensive economic assessment. The proposed framework provides a scalable methodological basis for integrating environmental metrics into real-time micro-mobility management and urban sustainability planning. Full article

Short-term traffic load prediction is a fundamental component of intelligent transportation systems (ITSs), supporting real-time monitoring, congestion mitigation, and adaptive traffic management in smart cities. Owing to the dynamic and nonlinear nature of urban traffic, identifying prediction models that align with real-world traffic dynamics remains a key challenge. This study presents a comparative evaluation of data-driven traffic load prediction models using high-resolution one-minute traffic data collected from a major urban roundabout in Jeddah, Saudi Arabia. The evaluated models include regression-based machine learning approaches and recurrent deep learning architectures, which are assessed under consistent preprocessing and evaluation conditions. Model performance is evaluated using standard error metrics and complemented by temporal and residual analyses to examine prediction behavior under different traffic regimes. The optimized GRU model achieved the best predictive accuracy with an RMSE of 149.12 veh/h, followed closely by the optimized LSTM model (RMSE = 150.85 veh/h). The results indicate that while conventional machine learning models can effectively capture overall traffic trends under relatively stable conditions, recurrent deep learning models demonstrate stronger capability in modeling nonlinear temporal dependencies and rapid traffic fluctuations when properly configured. In addition, a variability-based regime analysis was conducted to evaluate model robustness under different traffic demand dynamics, revealing that model performance advantages are context-dependent rather than universal. The findings highlight the importance of systematic comparative evaluation and data-driven model selection for developing reliable traffic prediction components in real-time ITS applications and sustainable urban mobility planning. Full article

Background: Calcitonin, a tumor marker primarily used to diagnose medullary thyroid carcinoma (MTC), can also be elevated in other conditions, complicating diagnosis. This study aims to provide a clinical evaluation of the real-world consequences of unexplained calcitonin elevation. Methods: We conducted a retrospective cohort study of patients with elevated basal calcitonin levels who presented at the Department of General, Visceral, and Transplantation Surgery, University Medical Center Mainz, between January 2015 and March 2025. Additionally, we reviewed electronic health records from 2007 onward for patients with ICD codes indicating calcitonin hypersecretion. Patients with confirmed MTC or genetic syndromes were excluded. Results: Of 345 patients with elevated calcitonin levels, 167 (48%) met the inclusion criteria, and 29 additional patients with calcitonin hypersecretion were identified via ICD, resulting in 167 patients analyzed. More than half of the patients were female (52%), had an average age of 53.9 years and a high prevalence of goiter (86%). Calcitonin levels were slightly elevated (<20 pg/mL) in 81% of cases and were above 50 pg/mL in only 10 patients. Surgery was performed in 77% of patients, mainly to exclude malignancy. Postoperatively, calcitonin normalized in 86% of patients but remained elevated in eight patients. Two of these patients were found to have false-positive results due to assay interference. Follow-up data were incomplete for a substantial proportion of patients, with a median follow-up of 4.6 months. The mortality rate was 4%, with causes unrelated to calcitonin levels. Conclusions: Elevated basal calcitonin levels, especially slightly elevated levels (<20 pg/mL), are common in clinical practice and often do not appear to be related to malignant disease, so careful investigation is required. Persistently elevated calcitonin levels justify further examinations, especially if other explanations can be ruled out. Only a few patients attend follow-up appointments, which makes patient follow-up challenging. Full article

The unchecked and uncontrolled global spread of multidrug-resistant (MDR) bacteria is a serious challenge to healthcare and modern medicine, and demands diagnostic approaches that are rapid, sensitive, multiplexed, and reliable in point-of-care (POC) settings. At the interface of nanomaterials and aptamer-based biosensing, significant advances have been reported. The convergence of portable electrochemical sensing technologies, smartphone-based readout systems, and artificial intelligence (AI)- and machine learning (ML)-based data analysis is also playing a significant role in advancing this area. This perspective reflects on the most recent breakthroughs and translational developments in electrochemical nano-aptasensors for MDR bacterial detection, covering diagnostic targets and translation trends, nanomaterials advancements, aptamer engineering-integration, POC strategies and microfluidics platforms, and novel multimodal strategies that enhance accuracy, reliability, and efficiency in POC testing. Moreover, limitations and knowledge gaps in this area, as well as key considerations for sustainable development, large-scale manufacturing, and deployment of integrated electrochemical nano-aptasensors, are also highlighted. Electrochemical nano-aptasensors can pave the way for the transformation of MDR bacterial diagnosis, but need coordinated translational efforts for POC diagnostic advancements towards real-world applications. Full article

Demand-responsive transit (DRT) requires real-time vehicle assignment under dynamically arriving requests, where each decision may alter multi-stop routes and affect both onboard and newly arriving passengers. However, DRT simulations often face three key limitations: rapidly increasing computational complexity as fleet size and demand grow, insufficient integration of traffic congestion into routing decisions, and limited consideration of passenger-oriented service quality in final vehicle assignment. To address these issues, this study proposes an integrated DRT simulation incorporating three core algorithms: Fréchet Distance-based Candidate Vehicle Selection (FD-CVS), Congestion-Aware Path Planning (CA-PP), and Satisfaction-Aware Vehicle Assignment (SA-VA). FD-CVS reduces computational burden by filtering candidate vehicles based on route similarity. CA-PP extends conventional path planning by incorporating congestion-adjusted travel costs derived from public transportation data. SA-VA determines the final vehicle assignment by jointly evaluating passenger waiting time, in-vehicle travel time, and capacity constraints. The algorithms are implemented within a discrete-event simulation environment using real-world data. Experimental results demonstrate that FD-CVS significantly reduces execution time under high-demand conditions, while SA-VA improves passenger waiting time and acceptance rates. Overall, the proposed three-algorithm framework enables more realistic and computationally efficient DRT system evaluation. Full article

Healthcare fraud poses significant risks to insurance systems, undermining both financial sustainability and equitable access to care. Accurate detection of fraudulent claims is therefore critical to ensuring the integrity of healthcare insurance operations. However, the increasing sophistication of fraud techniques and limited data availability have undermined the performance of traditional detection approaches. To address these challenges, this paper proposes WCGAN-GA-RF, an integrated fraud detection framework that synergistically combines Wasserstein Conditional Generative Adversarial Network with gradient penalty (WCGAN-GP) for synthetic data generation, genetic algorithm-based feature selection (GA-RF) for dimensionality reduction, and Random Forest (RF) for classification. The proposed framework was empirically validated on a real-world dataset of 16,000 healthcare insurance claims from a Chinese healthcare technology firm, characterized by a 16:1 class imbalance ratio ($5.9\%$ fraudulent samples) and 118 original features. Using a stratified $80/20$ train–test split with results averaged over five independent runs, the WCGAN-GA-RF framework achieved a precision of $96.47\pm 0.5\%$, a recall of $97.05\pm 0.4\%$, and an F1-score of $96.26\pm 0.4\%$. Notably, the GA-RF component achieved a $65\%$ feature reduction (from 80 to 28 features) while maintaining competitive detection accuracy. Comparative experiments demonstrate that the proposed approach outperforms conventional oversampling methods, including Random Oversampling (ROS), Synthetic Minority Oversampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN), particularly in handling high-dimensional, severely imbalanced healthcare fraud data. Full article

Environmental scientists are increasingly monitoring therapeutic drugs and their metabolites in water systems, requiring knowledge of human drug metabolism and excretion. Many published studies, however, rely on data from small-scale human metabolism trials, typically involving around six (healthy, young, male) volunteers. Their generalizability to real-world drug users may be limited, potentially biasing environmental monitoring efforts. Here, we leveraged untargeted LC-SWATH/MS pharmacometabolomics data from 283 potential living kidney donors and 688 kidney transplant recipients to characterize the 24 h urinary excretion profiles of two widely used diuretics frequently monitored in wastewater, hydrochlorothiazide and furosemide. Both are expected to be excreted largely unchanged, which our analyses confirmed. For hydrochlorothiazide, however, we also identified (using reference standards) the previously underreported transformation products chlorothiazide and salamide. These findings highlight the relevance and capability of using untargeted metabolomics data from human excreta to provide insights from large, real-world cohorts into which chemicals enter wastewater systems, with both drugs serving as exemplary case studies for analogous analyses of other drugs. In particular, the qualitative information obtained (e.g., accurate mass, retention time, fragment spectra) may inform targeted biomonitoring and highlight cases where consensus-based estimates of excreted drug or metabolite fractions are overestimated. Full article

Global citrus exports rely heavily on temperature-controlled logistics to safeguard fruit quality and minimise postharvest losses. Temperature management remains a critical factor governing citrus quality throughout export logistics. Yet the extent to which historical shipment temperature data can meaningfully predict fruit condition at arrival has never been systematically assessed. This study presents a comprehensive review of how historical temperature records have been used to assess citrus quality within export supply chains, highlighting the lack of longitudinal temperature–quality correlations in existing research. Using PRISMA 2020 guidelines and Kitchenham’s three-phase review framework, 35 relevant peer-reviewed articles published between 2013 and 2025 were analysed. Bibliometric mapping identified dominant research concentrations in experimental cold chain studies and simulation-based approaches, with emerging themes around digital twins and virtual cold chain technologies. The review shows that current research predominantly employs controlled experimental designs and computational simulations to quantify temperature-driven deterioration, including chilling injury, decay rate, and weight loss. Although real-time temperature monitoring in commercial shipments is emerging, temperature deviations are rarely assessed alongside direct quality metrics. Although several studies have examined shipment temperatures alongside arrival-quality outcomes, these analyses are generally limited in duration, scope, or sensor resolution. Consequently, rigorous, multi-year, longitudinal datasets that pair detailed shipment temperature histories with standardised fruit-quality assessments remain largely unavailable, constraining the empirical validation of temperature–quality relationships in real export conditions. This gap significantly limits predictive capability in real-world export contexts. The review highlights the urgent need for a coordinated, long-term data infrastructure that integrates temperature and quality measurements across global citrus supply chains. Establishing such datasets, particularly in major exporting regions such as South Africa, would enable more robust modelling of temperature impacts, support the optimisation of cold chain practices, and contribute to international food loss-reduction goals. Full article

Vehicle–infrastructure cooperative perception (VICP) extends the sensing capability of single-vehicle systems by integrating multi-source information from onboard and roadside sensors, thereby alleviating limitations in sensing range and field-of-view coverage. However, in complex urban environments, the robustness of such systems—particularly in terms of blind-spot coverage and feature representation—is severely affected by both static and dynamic occlusions, as well as distance-induced sparsity in point cloud data. To address these challenges, a 3D object detection framework incorporating point cloud feature enhancement and spatially adaptive fusion is proposed. First, to mitigate feature degradation under sparse and occluded conditions, a Redefined Squeeze-and-Excitation Network (R-SENet) attention module is integrated into the feature encoding stage. This module employs a dual-dimensional squeeze-and-excitation mechanism operating across pillars and intra-pillar points, enabling adaptive recalibration of critical geometric features. In addition, a Feature Pyramid Backbone Network (FPB-Net) is designed to improve target representation across varying distances through multi-scale feature extraction and cross-layer aggregation. Second, to address feature heterogeneity and spatial misalignment between heterogeneous sensing agents, a Spatial Adaptive Feature Fusion (SAFF) module is introduced. By explicitly encoding the origin of features and leveraging spatial attention mechanisms, the SAFF module enables dynamic weighting and complementary fusion between fine-grained vehicle-side features and globally informative roadside semantics. Extensive experiments conducted on the DAIR-V2X benchmark and a custom dataset demonstrate that the proposed approach outperforms several state-of-the-art methods. Specifically, Average Precision (AP) scores of 0.762 and 0.694 are achieved at an IoU threshold of 0.5, while AP scores of 0.617 and 0.563 are obtained at an IoU threshold of 0.7 on the two datasets, respectively. Furthermore, the proposed framework maintains real-time inference performance, highlighting its effectiveness and practical potential for real-world deployment. Full article

This study stems from the need to investigate how GenAI tools, particularly ChatGPT-4o, can support the professional development of mathematics teachers. It explores how Blum’s modeling cycle can serve as a conceptual and operational framework for mathematics teachers’ instructional design when supported by ChatGPT-4o. Drawing on a qualitative case study within a teacher professional development program, the research analyzes how two upper secondary school teachers engaged with ChatGPT-4o to redesign a mathematical task involving probability and real-world contexts. Data include responses to three modeling-related tasks, teachers’ prompts and interactions with ChatGPT-4o, and the final mathematical activity they designed. These materials were analyzed qualitatively according to the modeling cycle and its sub-competencies. The results indicate that the modeling cycle provided teachers with a cognitive and methodological scaffold to guide their interaction with ChatGPT-4o, allowing them to structure, validate, and refine AI-generated ideas through all stages of modeling—from understanding and mathematizing to interpreting and validating. These findings suggest that the modeling cycle can be reinterpreted as a design-oriented framework for integrating ChatGPT-4o in mathematics teacher education. Implications for teacher professional development and future research directions are discussed. Full article

Background: Precision oncology has traditionally relied on genomic biomarkers to guide therapy selection; however, static molecular profiling often fails to predict real-world responses to cytotoxic chemotherapy. Increasing evidence suggests that treatment outcomes are determined by the interaction between tumor-intrinsic biology and host-specific pharmacology. Functional ex vivo platforms, including patient-derived organoids and tumor slice cultures, provide a complementary phenotypic readout of drug sensitivity that reflects tumor architecture and microenvironmental interactions. Methods: This narrative review integrates recent experimental, translational, and clinical evidence on molecular oncodiagnostics combining tumor transcriptomics, germline pharmacogenetics, and ex vivo drug sensitivity testing. Relevant literature was identified through targeted searches of major biomedical databases, focusing on studies describing multi-omic predictive models, functional precision oncology platforms, and patient-derived tumor models. Results: Converging data indicate that integrated oncodiagnostic strategies can improve prediction of chemotherapy response beyond genomics-only approaches. Transcriptomic profiling captures dynamic pathway activity and resistance programs, pharmacogenetic testing informs host-specific toxicity and dosing constraints, and ex vivo assays enable direct phenotypic validation of drug efficacy. Together, these complementary approaches provide a biologically grounded framework for individualized therapy selection. Conclusions: The convergence of molecular profiling and functional phenotyping represents an emerging paradigm in precision oncology. Integrating multi-omic and functional data may enhance treatment prediction and reduce ineffective therapy, although prospective validation and standardization remain necessary for routine clinical implementation. Full article

Island microgrids are highly vulnerable to extreme weather, which threatens operational stability and post-disaster recovery. To address the challenge of widespread power outages caused by typhoons, a novel coordinated framework is proposed which optimizes electric ships as mobile power sources to enhance island microgrid resilience. By integrating a hybrid wind field model with an improved wind-resistant A* algorithm, the framework synergistically optimizes dynamic scenario-aware ship routing and distribution network reconfiguration. The problem is formulated as a mixed-integer second-order cone programming (MISOCP) model. Case studies based on real-world data from Hengsha Island, Shanghai, demonstrate that the proposed dynamic routing strategy significantly outperforms static approaches. Specifically, critical load recovery rates are improved by at least 29% during the navigation-restricted phase and total load curtailment costs are reduced by 31.6%. These findings reveal this significance of integrating spatiotemporal environmental dynamics into optimization frameworks, providing a robust decision-making tool for island grid operators to maintain power supply to critical loads under evolving disaster conditions. Full article

Swallowing is a critical marker of neurological and emotional health. The ability to monitor it continuously and non-invasively, especially through smart ear-worn devices, holds significant promise for clinical applications. Despite this potential, no public audio datasets currently support reliable swallowing sound detection. Existing datasets focus primarily on speech and breathing, offering limited coverage and lacking detailed annotations for swallowing events. To address this gap, we introduce an in-ear audio dataset specifically designed to capture a wide range of verbal and non-verbal sounds. It includes comprehensive labeling focused on swallowing. The dataset was collected from 34 healthy adults (14 females and 20 males) between the ages of 20 and 29. Each participant performed a series of predefined tasks involving both non-verbal and verbal events. Non-verbal tasks included swallowing, clicking, forceful blinking, touching the scalp, and physical movements such as squatting or walking in place. Verbal tasks consisted of speaking (e.g., describing an image). Recordings were conducted in both quiet and noisy environments to better reflect real-world conditions. Data were captured using a combination of in-/outer-ear microphones, a chest belt to record electrocardiogram (ECG), respiration and acceleration signals, and an ultrasound probe to track tongue movement, which served as a reference for swallowing annotation. All signals were precisely synchronized. To ensure high data quality, the recordings were reviewed using both algorithmic analysis and manual inspection. Swallowing events were identified based on ultrasound signals and validated by an expert to guarantee accurate labeling. As a proof of concept that in-ear audio supports swallow classification, we fine-tune a fully connected neural network on YAMNet embeddings plus zero-crossing rate (ZCR) features. Across the completed folds, the model reaches an F1 score of 0.875 ± 0.013. Full article

The growing importance of integrating renewable energy sources (RESs) into mainline railway traction networks stems from the sector’s substantial electricity demand, which is traditionally met by carbon-intensive thermal generation. This paper addresses the potential of wind power to enhance energy efficiency and reduce emissions in rail transport. It details the development of digital models for simulating DC traction power systems (TPSs) coupled with RESs, specifically wind turbines. Given the complexity of TPSs, effective integration requires digital modeling that accounts for their unique properties. The proposed methodology, based on phase coordinate algorithms, offers a universal and comprehensive framework. It enables the identification of various operational modes (normal, emergency, and special) for diverse network components, including traction networks, transmission lines, and transformers. These models were used to simulate real-world train operations, generating data on electrical parameter dynamics and transformer thermal conditions. The results confirm that wind integration can improve energy efficiency, validating the methodology’s practical applicability for RES projects in DC traction networks, including advanced high-voltage systems. Full article