Search Results (8,884)

Background: Antibiotic overuse in hospitals is common and linked to adverse outcomes and antimicrobial resistance. Antimicrobial stewardship programs (ASP) aim to optimize prescribing and require context-specific adaptation. Objectives: To describe the experience of implementing and strengthening ASP in hospitals from six Latin American countries by using an integrated framework. Methods: The intervention included a point-prevalence survey (PPS) of antibiotic use, a baseline checklist, a continuous online education program, and individual facility meetings to share SWOT analyses and recommendations. The latter was performed based on PPS and checklist results. The checklist covers six domains (authorities’ commitment, organization, structure, and accountability; interventions; education and training; monitoring and surveillance; and internal communication). The training program spanned 12–18 months and addressed core ASP components. Results: The PPS across 67 hospitals showed an antibiotic use prevalence of 47.9%, with 63% of prescriptions deemed appropriate. The median checklist score was 61.2%. Among the categories assessed, monitoring and surveillance achieved the highest score (median 75.0; IQR 63.9–84.0), while education received the lowest (median 43.8; IQR 29.7–62.5). A total of 80 country groups and 35 individual hospital meetings were held. Conclusions: An integrated, data-driven framework combining PPS, checklists, individual hospital meetings, and sustained training provides a scalable approach to strengthening ASP in diverse Latin American hospitals, aligning with Pan American Health Organization (PAHO) guidance and global recommendations. Full article

Couples generally manage chronic diseases together and the management takes an emotional toll on both patients and their romantic partners. Consequently, recognizing the emotions of each partner in daily life could provide insight into their emotional well-being in chronic disease management. Currently, the process of assessing each partner’s emotions is manual, time-intensive, and costly. Despite the existence of works on emotion recognition among couples, none of these works have used data collected from couples’ interactions in daily life. In this work, we collected 85 h (1021 5-min samples) of real-world multimodal smartwatch sensor data (speech, heart rate, accelerometer, and gyroscope) and self-reported emotion data (n = 612) from 26 partners (13 couples) managing diabetes mellitus type 2 in daily life. We extracted physiological, movement, acoustic, and linguistic features, and trained machine learning models (support vector machine and random forest) to recognize each partner’s self-reported emotions (valence and arousal). Our results from the best models—balanced accuracies of 63.8% and 78.1% for arousal and valence respectively—are better than the results from (1) chance, (2) prior work that also used data from German-speaking, Swiss-based couples, and (3) partners’ perceptions of each other’s emotions. This work contributes toward building automated emotion recognition systems that would eventually enable partners to monitor their emotions in daily life and enable the delivery of interventions to improve their emotional well-being. Full article

Persistent traffic congestion and the need for efficient traffic monitoring have increased the demand for automated vehicle-analysis systems based on CCTV footage. This study presents a CCTV-based vehicle monitoring system that integrates vehicle detection, tracking, counting, public/private vehicle class prediction, seven-category vehicle-type prediction, vehicle-color recognition, and traffic-state estimation using YOLOv12 and DeepSORT. To reduce manual annotation effort during the initial training stage, a semi-automated method for generating synthetic composite road scenes was developed by combining cropped vehicle images and road-background images. The detector was first trained on 10,000 synthetic images and then sequentially fine-tuned on real CCTV data. Four real-world traffic video clips from Metro Manila were used in the study. Three 5 min clips were used within the staged refinement workflow: the first two for iterative refinement and the third for final post-refinement evaluation of the adapted model. A separate fourth CCTV clip was reserved exclusively for blind evaluation without on-the-fly retraining. The final system achieved average accuracies of 97% for public/private vehicle class prediction, 90% for seven-category vehicle-type prediction, 82% for vehicle-color recognition, and 96.67% for vehicle counting on the final evaluation video. The results show that synthetic pretraining combined with limited real-world fine-tuning can improve performance in CCTV-based vehicle monitoring while reducing the amount of manually labeled real-world data required. The study also discusses the limitations of the current evaluation protocol and the need for broader multi-location testing. Full article

This study estimates daily nitrogen dioxide (NO₂) concentrations at ground level across the Marmara Region of Türkiye at 0.01° resolution. The framework integrates Sentinel-5P (S5P) TROPOspheric Monitoring Instrument (TROPOMI) and GEOS Composition Forecast (GEOS-CF) tropospheric NO₂ vertical column density (VCD) data with meteorological, topographic, land-use, socioeconomic, and temporal features through four tree-based ensemble algorithms trained on 74 ground station observations. Under a temporal split (2019–2022 training, 2023 validation, 2024 testing), S5P-Categorical Boosting (CatBoost) achieved the best performance (Pearson correlation coefficient (R) = 0.706, R² = 0.498, root mean square error (RMSE) = 14.31 µg/m³). Random splitting inflated R by +0.168 due to temporal autocorrelation, while leave-one-station-out and leave-one-province-out cross-validation reduced R to ~0.50 by removing spatial dependence, together revealing the combined effect of temporal and spatial autocorrelation. SHapley Additive exPlanations (SHAP) analysis identified TROPOMI NO₂ VCD, population density, road length, and nighttime light as dominant predictors; population density was the top predictor in the GEOS-CF model, followed by VCD. Concentration maps for 2024 showed that 95.9% of the region’s 26.74 million inhabitants were exposed above the WHO annual air quality guideline of 10 µg/m³, with a population-weighted mean of 21.08 µg/m³. Full article

Accurate landslide susceptibility assessment remains challenging in mountainous regions with complex terrain, heterogeneous geology, and clustered landslide inventories. This study develops a slope–unit–based landslide susceptibility assessment framework for Tongren County, Qinghai Province, China, using a landslide inventory of 217 events, multi–source environmental data, Certainty Factor (CF)–based conditioning–factor analysis, and machine learning models. Eighteen conditioning factors derived from remote sensing, geological survey, and meteorological datasets were extracted at the slope–unit scale, and their collinearity was evaluated using Pearson’s correlation and the Variance Inflation Factor (VIF). Eight models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), AdaBoost, Decision Tree (DT), XGBoost, K–Nearest Neighbors (KNN), and Convolutional Neural Network (CNN)—were evaluated under a 70:30 train/test split. The results show clear performance differences among the tested models: SVM achieved the best overall balance between discrimination and landslide detection (AUC = 0.9489; recall = 0.879). The tested CNN baseline showed relatively weak performance under the current slope–unit–based tabular–data setting. Susceptibility zoning results showed that high– and very–high–susceptibility zones were mainly concentrated along the Longwu River and its tributaries, where middle–elevation dissected terrain, weak lithological materials, river–valley erosion, and human engineering activities spatially coincide. These results provide a practical basis for slope monitoring and land–use planning in Tongren County. Full article

Recent advances in satellite missions, particularly the Landsat, Sentinel, and Gaofen series, have led to the rapid accumulation of high-quality remote sensing data with frequent revisits. As these data have become more widely available, Satellite Image Time Series (SITS) have become an important tool for monitoring Earth surface dynamics. SITS now supports a wide range of applications, including precision agriculture, Land Use/Cover Change (LULCC) monitoring, environmental management, and disaster response. This growth has also promoted the development of advanced SITS classification datasets. However, existing reviews have mainly focused on SITS classification algorithms or specific applications, while systematic comparisons of public SITS benchmark datasets remain limited. This lack of synthesis makes it difficult for researchers to navigate fragmented resources and select datasets that match specific scientific or operational tasks. To address this gap, this paper provides a comprehensive review and analysis of 29 publicly available medium-to-high-resolution SITS classification benchmark datasets released between 2017 and 2025. These datasets are intended for training, testing, and validating land-cover classification algorithms, rather than for direct use as operational map products. We conduct a detailed statistical and comparative analysis of these datasets, focusing on their key characteristics across spectral, temporal, and spatial dimensions, as well as their labeling systems. In addition, this review summarizes the SITS classification algorithms that have been developed and benchmarked using these datasets. Finally, we identify the main challenges in constructing and applying SITS classification datasets and discuss future research directions, particularly in data reconstruction, multimodal fusion, change analysis, and advanced model architectures. This survey provides the research community with a systematic overview of SITS classification benchmark datasets and aims to support continued progress in this rapidly developing field. Full article

Reliable onboard fault detection and diagnosis (FDD) is essential for autonomous small-satellite constellation operations. The satellite telemetry streams are typically high-dimensional, strongly time-correlated, and severely imbalanced. These characteristics make rare but critical faults hard to recognize. To address these issues, this paper proposes an imbalance-aware spatiotemporal diagnostic framework based on three-dimensional convolutional neural networks (3D-CNNs). Multivariate telemetry is first converted into structured spatiotemporal volumes via sliding-window segmentation and grid-based embedding. This enables the model to jointly learn temporal evolution and cross-parameter coupling patterns. A lightweight residual 3D-CNN is developed to enable end-to-end multi-class classification. In addition, a class-balanced focal objective function is introduced to mitigate class-imbalance issues and enhance sensitivity to minority fault modes. The Lumelite series satellite telemetry dataset, comprising 23 fault types, is constructed for training and evaluation. The proposed lightweight residual 3D-CNN is benchmarked against long short-term memory–random forest (LSTM-RF), support vector machine (SVM), 2D-CNN, CNN-LSTM, and residual neural network models. Experimental results show that the proposed algorithm has the highest overall accuracy and Macro-F1 score. It also obtains higher Recall for low-frequency faults. The computational complexity studies indicate that the proposed algorithm has promising potential for real-time satellite health monitoring. Full article

Accurate and timely information on forest disturbance drivers is important for sustainable forest management, global carbon cycle accounting, and climate change response. However, forest disturbance classification is difficult due to two major challenges: limited labeled samples and highly imbalanced disturbance class distribution. In this article, a new framework for multi-type forest disturbance classification based on collaborative semi-supervised learning and sample generation was proposed. First, forest disturbance is detected using long-term remote sensing time series data and disturbance detection algorithms. Spatiotemporal, spectral and terrain features of different disturbance types are extracted. On this basis, to address the problem of imbalanced and small-sample conditions, a collaborative classification strategy is developed. Based on a small number of labeled samples, Support Vector Machine (SVM) and Random Forest (RF) are used to build dual base classifiers. A confident learning (CL) framework is applied to select high-confidence pseudo-labeled samples from unlabeled data. Then, a latent diffusion model (LDM) is introduced to generate high-fidelity pseudo-samples. This increases the sample size and balances the class distribution. Based on the augmented dataset, the dual classifiers are iteratively optimized using a co-training strategy, which improves model generalization under complex conditions. The results show that the proposed framework could generate high-quality pseudo-samples and effectively reduce class imbalance. The overall accuracy (OA) of the proposed framework reaches 93.2%, which is 5.7% and 4.4% higher than single classifier baselines, respectively. After introducing the LDM-based balancing mechanism, performance is further improved by 1.8% compared with the pure semi-supervised framework. This study provides an efficient and reliable solution for large-scale forest ecosystem monitoring. Full article

Machine learning-based intrusion detection systems (IDS) deployed in real-world environments frequently degrade due to concept drift, where evolving traffic patterns invalidate assumptions learned during training. This challenge is especially pronounced in Internet of Things (IoT) environments, where device behavior changes over time due to user interaction, firmware updates, and emerging attack strategies. Prior work introduced FIRCE, a framework that integrates conformal evaluation into streaming IDS pipelines to enable uncertainty-aware drift detection and adaptive retraining. In this journal extension, we present FADES, a framework for adaptive drift estimation that generalizes drift monitoring beyond prediction-space uncertainty by supporting both conformal evaluation and representation-space detectors within a unified streaming architecture. FADES incorporates multiple conformal evaluation variants, including Approximate Cross-Conformal Evaluation, which preserves the statistical structure of cross-conformal evaluation while eliminating repeated model training, as well as an Adaptive Chunking Controller that dynamically balances detection responsiveness and computational cost. We extend prior work through three major contributions: (i) a variance-aware evaluation protocol comprising 375 simulations across multiple seeds and runs, (ii) integration of a contrastive autoencoder-based detector to enable direct comparison between prediction-space and representation-space drift detection, and (iii) expanded evaluation across in-domain and cross-dataset transfer settings using UNSW-NB15, CICIDS2018, and a real-world IoT testbed. Approx-CCE achieves performance comparable to standard cross-conformal evaluation across hundreds of simulations, providing empirical evidence that the statistical benefits of CCE derive primarily from its disjoint calibration partition structure rather than fold-specific model diversity, a finding with implications for conformal evaluation in repeated recalibration settings more broadly. In contrast, representation-space drift detection via CADE incurs substantial computational cost under repeated retraining, limiting its practicality in streaming settings. These findings demonstrate that conformal evaluation provides a statistically grounded and computationally efficient foundation for real-time drift-aware intrusion detection, and that FADES enables flexible, unified evaluation of drift detection strategies under realistic deployment conditions. Full article

High-resolution satellite imagery is pivotal for accurate analysis in remote sensing applications, including land-use monitoring, urban planning, and environmental assessment. However, obtaining such data is often costly and limited. Consequently, super-resolution techniques, such as deep learning models and fine-tuning strategies like LoRA, offer a promising alternative to the critical research challenge, especially given the diversity and large scale of satellite datasets. While deep learning-based super-resolution models have been very promising recently, their effectiveness, efficiency, and scalability across heterogeneous satellite scenes are not well studied. This work studies the performance of representative deep learning Super-Resolution frameworks, including the Enhanced Super-Resolution Generative Adversarial Network. (ESRGAN), Swin Transformer for Image Restoration (SwinIR), and latent diffusion models (LDM), under unified experimental conditions using the WorldStrat dataset. The main goal is to establish whether adaptation strategies for parameter efficiency can boost reconstruction quality while reducing computational and training costs. Toward this goal, we investigate hybrid sequential pipelines, ensemble averaging, and Low-Rank Adaptation (LoRA)–based fine-tuning. The experiments indicate that these pipelines, which use multi-model methods, achieve only marginal performance gains while incurring substantial increases in computational complexity. LoRA-Based Fine-Tuning, by contrast, has demonstrated superiority in enhancing reconstruction accuracy and quality across all model families, despite using only a small percentage of trainable parameters. LoRA-based models demonstrate superiority over multi-model methods in both efficiency and performance. The presented results confirm that LoRA is an effective and accessible technique for high-fidelity satellite-based super-resolution image synthesis. The manuscript identifies LoRA as one of the enabling technologies advancing the state of the art in Deep Learning-based Super Resolution for large-scale satellite-based image synthesis. Full article

The increasing randomness and volatility of renewable energy resources have raised higher demands for circuit breakers. Utilizing monitoring data enables more accurate condition assessment; however, the imbalance between fault and normal samples hampers the performance of machine-learning-based assessment. To address the overfitting and limited diversity of traditional oversampling methods, this paper proposes a Transformer-conditioned CWGAN-GP (TCWGAN-GP) model to generate multi-class fault samples for data augmentation. The generator of the proposed model takes random noise and class labels as input to capture the distribution characteristics of real fault samples. By combining a transformer-based generator to model inter-feature dependencies among 14 monitoring indicators and a WGAN-GP training objective with gradient penalty, the proposed approach improves training stability and synthetic sample quality. Moreover, a three-stage state assessment method based on XGBoost is developed to sequentially assess health status, fault category, and fault severity. Results demonstrate that the proposed method in the paper outperforms conventional data augmentation methods and single-stage classifiers in terms of accuracy, recall, F1-score, and online prediction efficiency. Specifically, the proposed three-stage model achieves an overall assessment accuracy of 93.10%, outperforming the single-stage XGBoost framework. In terms of online efficiency, the initial anomaly detection stage requires only 0.0041 s per sample, which is a substantial reduction compared to the 0.0241 s required by the single-stage model. Furthermore, compared to traditional Random Oversampling (ROS) and SMOTE, the TCWGAN-GP augmentation yields superior evaluation performance on fully balanced datasets, achieving a recall rate of 91.26% and an F1-score of 92.61%. Overall, the proposed TCWGAN-GP and three-stage XGBoost method contributes to addressing data imbalance challenges and improving the accuracy of circuit breaker state assessment. Full article

Intensive pig farming presents substantial challenges for individual health monitoring due to high stocking densities, complex occlusion scenarios, and the need for continuous real-time surveillance. Existing monitoring approaches rely heavily on manual inspection, which is labor-intensive and prone to delayed detection of abnormal behaviors and disease symptoms. This study proposes an embedded intelligent monitoring system integrating a pan-tilt gimbal platform with an improved multi-object tracking and anomaly detection framework for automated pig health surveillance. The system employs a modified Periodfill_DeepSORT algorithm that incorporates a ReID network with appearance features and motion prediction trajectories to maintain identity consistency under occlusion and re-entry scenarios. For anomaly detection, a lightweight YOLOv8-based network was trained on 772 abnormal samples across three behavioral categories: movement abnormalities, postural abnormalities, and disease-related abnormalities. Experimental results demonstrate that the Periodfill_DeepSORT algorithm achieves a Multiple Object Tracking Accuracy (MOTA) of 95.34%, a Multiple Object Tracking Precision (MOTP) of 94.77%, and an IDF1 score of 96.88%, with only 12 identity switches across 2000 frames involving 12 targets—27 fewer than the standard DeepSORT algorithm. In occlusion scenarios, MOTA improved from 61.1% to 78.3%. The anomaly detection network achieves an overall detection accuracy of 94.5%, representing an 8.8 percentage point improvement over the baseline model, with recognition accuracies of 96.2% for movement abnormalities, 94.1% for postural abnormalities, and 92.8% for disease-related abnormalities. The system operates at 90 frames per second on embedded hardware with a power consumption of 3.2 watts and a startup time of approximately 1 s, with gimbal angle errors maintained within 3°. These results demonstrate the system’s effectiveness and practical feasibility for real-time intelligent health monitoring in intensive livestock farming environments. Full article

Monitoring both captive animals and wild populations is necessary to ensure adequate animal welfare and wildlife conservation. Existing monitoring tools, e.g., camera traps, enable surveillance, yet analysis can prove time-consuming and labor-intensive if handled manually. The automated nature of machine learning (ML) reduces observer bias and manual workload and improves assessment capacity of behavioral monitoring tools that are often used by staff at zoological institutions. This study investigated the activity and space use of three captive jaguars (Panthera onca) through automated individual recognition, activity tracking, and heatmap visualization using an ML model trained on video footage. In total, 123.8 h of video footage was recorded of the jaguar enclosure in Randers Regnskov, Tropical Zoo. The ML model analyzed all videos containing jaguars from one day. The model achieved satisfactory performance based on its evaluation metrics (mean average precision, recall, precision, and F1-score). The ML model showed repeated movement tracks within specific enclosure areas. The jaguars exhibited significantly more inactive than active behavior and did not seem to exhibit natural bimodal nocturnal or crepuscular hunter activity patterns. It should be stated that, due to the small sample size of only three jaguars and 24 analyzed hours, this study is a proof-of-concept to demonstrate the potential of ML methods as valuable tools for individual recognition, activity tracking, and monitoring of space use to aid in future animal welfare monitoring. Full article

This paper presents FMECA-VR-0.1 Prototype, a Maintenance 4.0-oriented immersive Virtual Reality (VR)-based training platform that integrates tools in a digital and virtual environment with Failure Modes, Effects, and Criticality Analysis (FMECA) and the Qualitative Risk Criticality Matrix (QRCM) to enhance reliability-oriented maintenance training in the wind energy sector. The methodological framework is aligned with the Maintenance Management Model (MMM) developed by INGEMAN. It is applied to a VESTAS V100–2.0 MW wind turbine operating at the Valle de los Vientos Wind Farm in northern Chile. The study includes the definition of the operational context, subsystem-level criticality assessment, and a detailed FMECA of the blade subsystem, which are integrated as analytical layers within the immersive VR environment. The proposed platform enables users to visualize critical components, analyze physical failure modes, understand associated consequences, and review preventive and corrective maintenance strategies in an interactive 3D scenario. Preliminary qualitative feedback suggests potential improvements in user engagement and conceptual understanding; however, no formal experimental validation has been conducted at this stage. The FMECA-VR-0.1 prototype demonstrates a feasible path for incorporating risk-based engineering logic into immersive training ecosystems. It establishes the foundation for future developments involving digital twins, real-time monitoring data, multi-subsystem modeling, and quantitative assessment of learning performance. Full article

Nitrogen (N) management is critical for optimizing growth and fruit quality in open-field strawberry cultivation, demanding advanced technological solutions for reliable nutrient assessment. However, visual symptom diagnosis, though widely utilized for nutrient monitoring, is inherently subjective and prone to observer bias, resulting in inconsistent and often unreliable assessments. While available accurate tissue analysis is destructive and costly. Nondestructive, in-field imaging techniques such as the normalized difference vegetation index (NDVI) exist but require expensive multispectral imaging systems. To address these limitations, this study developed a streamlined methodology for in-field N status detection using deep learning on standard RGB images. The experiment utilized ‘Yotsuboshi’ strawberries in a randomized complete block design with sufficient nitrogen (T1) and deficient nitrogen (T2) treatments. To mitigate ambient light variability, a key challenge in open-field phenotyping, a low-cost phenotyping cylinder was developed for standardized smartphone image acquisition. Rigorous four-stage annotation criteria were also introduced to classify the nitrogen status in strawberry leaves as NormalN, LowN, or AdvancedLowN, ensuring a high-quality novel dataset. A YOLO11 model trained on this dataset achieved precision, recall, and mAP50 values exceeding 99%. Subsequent testing using the phenotyping cylinder yielded a mAP50 of 87%. In-field validation without a phenotyping cylinder also demonstrated robust performance under diffuse cloudy conditions (82.7% mAP50), outperforming direct sunlight (79% mAP50). Moreover, the model’s classifications of ‘NormalN’ and ‘LowN’ statuses strongly corresponded with NDVI measurements, validating the accuracy of the RGB-based approach. This research demonstrates the significant potential of combining deep learning and phenotyping cylinder to create a rapid, low-cost, nondestructive and reliable tool for in-field nitrogen detection, with possible application across different crops and environmental conditions. Full article