Search Results (9,886)

Telework has expanded rapidly, yet its determinants and temporal dynamics remain insufficiently documented in developing countries. This study examines the evolution of telework in Brazil from 2022 to 2025 using machine learning models applied to nationally representative microdata from the Continuous National Household Sample Survey, based on approximately 210,000 households per reference period. A standardized pipeline was implemented across four time windows, including preprocessing, missing-data handling, class balancing via random under-sampling, feature encoding and normalization, and stratified data splitting with 5-fold cross-validation. Nine classification algorithms were evaluated and hyperparameter-tuned using ANOVA racing, with model performance assessed primarily through the ROC AUC metric. The results indicate consistently high discriminative performance across all analyzed periods (ROC AUC > 0.80). The temporal evaluation further reveals overlapping confidence intervals among the predictive models, indicating statistically comparable performance over time and no evidence of a universally dominant algorithm. Variable-importance analyses show that the set of the eight most relevant predictors remained stable, although their relative rankings changed, with gender increasing in importance in the most recent periods. Overall, telework in Brazil is jointly shaped by sociodemographic and occupational factors, highlighting its selective nature and the relevance of temporal monitoring to inform research and policy. Full article

Coffee, as a perennial commodity crop, plays a crucial role in global agricultural markets, regional livelihoods, and poverty alleviation. Yunnan Province of China (21°8′–29°15′N) represents the northernmost coffee-growing region worldwide, and its production has gained increasing attention in international markets. However, the absence of a spatially explicit and high-resolution coffee distribution dataset has constrained environmental assessment, land-use analysis, and policy-making in this subtropical and marginal growing region. In this study, we developed the first 10 m resolution Arabica coffee distribution dataset for Yunnan Province for the year 2023 using Sentinel-2 optical imagery and Shuttle Radar Topographic Mission (SRTM) terrain data within the Google Earth Engine (GEE) platform. An object-based workflow was implemented to generate spatially coherent mapping units, followed by supervised classification to identify coffee plantations. The resulting map achieved an overall accuracy (OA) of 0.87, with user accuracy (UA), producer accuracy (PA), and F1 score of 0.90, 0.96, and 0.93 for the coffee class, demonstrating its reliability for regional-scale applications. Feature contribution analysis indicates that shortwave infrared (SWIR) and red-edge information, particularly during the dry season, plays an important role in coffee discrimination. These results enhance confidence in the ecological relevance and stability of the mapping framework. The proposed workflow provides a practical and transferable approach for perennial crop mapping in complex mountainous environments. More importantly, the generated high-resolution coffee distribution dataset establishes a spatial baseline for monitoring land-use dynamics, assessing ecological impacts, and supporting sustainable coffee development in southwestern China. Full article

Accurate extraction of crop planting structures is important for crop area and yield estimation, but complex and fragmented cropping patterns with overlapping phenology in the Hetao Irrigation District hinder reliable crop discrimination. This study proposes a hierarchical workflow that integrates vegetation masking with multi-source feature optimization for crop mapping. First, dual-temporal Sentinel-2 imagery (May and August) is used to generate a vegetation region-of-interest(ROI) mask via Otsu thresholding applied to the Normalized Difference Vegetation Index (NDVI), combined with pixel-wise maximum-value fusion to reduce phenology-driven omissions and background interference. Second, within the vegetation mask, Sentinel-2 spectral, vegetation-index, and texture features are combined with Sentinel-1 synthetic aperture radar (SAR) backscatter and SAR texture features to construct a multi-source feature set. Random Forest(RF) feature-importance ranking is used to select an effective feature subset, and four classifiers (RF, support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), and convolutional neural network (CNN)) are compared under the same training/validation setting. The vegetation extraction achieves an overall accuracy of 91% (Kappa = 0.80). Using Sentinel-2 features only, the optimized subset with CNN attains the best performance (overall accuracy = 95%, Kappa = 0.93). Adding Sentinel-1 SAR texture features provides an additional improvement (overall accuracy = 96%, Kappa = 0.94), particularly for classes prone to confusion in fragmented plots. Area proportions derived from the final map are consistent with statistical yearbook data (percentage errors: maize 3.45%, sunflower 2.66%, wheat 0.11%, tomato 0.92%) under the study conditions. This workflow supports practical crop-structure monitoring in complex irrigation districts. Full article

Generative adversarial networks (GANs) are increasingly applied to mitigate extreme class imbalance in intrusion detection systems, yet reported improvements often obscure role augmentation intensity and adversarial stability. This paper presents a controlled ablation study that isolates the impact of adversarial objective choice, augmentation ratio, and training duration on GAN-based minority data augmentation for highly imbalanced tabular cybersecurity data. Using the UWF-ZeekData22 dataset, nine MITRE ATT&CK tactic-versus-benign classification tasks are evaluated under augmentation ratios of 0.25 and 0.50 and training durations of 400 and 800 epochs. Four GAN variants—Vanilla GAN, Conditional GAN (cGAN), WGAN, and WGAN-GP—are assessed using stratified cross-validation and five classical classifiers representing diverse inductive biases. The results reveal consistent structural patterns. Moderate augmentation (r = 0.25) with controlled training (400 epochs) yields the most stable and reliable improvement in minority recall. Wasserstein-based objectives demonstrate superior stability under aggressive augmentation and prolonged training, while conditional GANs frequently exhibit recall collapse in ultra-sparse regimes. Increasing augmentation volume does not uniformly improve performance and may introduce distributional overlaps that degrade linear and margin-based classifiers. Tree-based classifiers remain largely invariant once sufficient minority density is achieved. These findings demonstrate that adversarial calibration is more important than architectural complexity for improving the detection of rare attacks. The study provides practical guidance for designing robust GAN-based augmentation pipelines under extreme cybersecurity class imbalance. Full article

Background/Objectives: Early diagnosis of eye diseases is critically important for enhancing individuals’ quality of life and reducing the risk of vision loss. In this study, a deep learning-based hybrid model called MidFusionEfficientV2 has been proposed to classify eye diseases, including uveitis, conjunctivitis, cataract, eyelid drooping, and normal conditions. Methods: The model presents a dual-branch architecture that combines an RGB image branch with an EfficientNetV2-S architecture and a specialized texture branch based on Local Binary Pattern (LBP) transformation at an intermediate level. Thanks to the Squeeze-and-Excitation (SE) blocks integrated into the LBP branch, channel-based attention mechanisms have been activated, enhancing the prominence of textural features. The features obtained from the RGB and LBP branches were combined at an intermediate level and transferred to the classification stage. Results: Experimental studies on the five-class eye disease dataset from the Mendeley Data platform have shown that the proposed model outperformed six strong models (ResNetV2, ConvNeXt, DenseNet-121, EfficientNet-B1, MobileNetV3 Large, and EfficientNetV2-S) with an accuracy of 98%. Especially in the difficult-to-diagnose uveitis class, recall and F1 scores of 97% and 94%, respectively, were achieved. Conclusions: The results show that a moderate combination of color and texture features significantly improves classification performance, and that MidFusionEfficientV2 offers a reliable and effective solution for the automatic diagnosis of eye diseases. Full article

Background: Deepfakes pose a growing threat to the integrity of visual media, motivating detectors that remain reliable as forgeries become increasingly realistic. Methods: We propose a deepfake detection framework built on CLIP-derived SigLIP-2 vision transformers and a multi-task design that jointly performs (i) classification and (ii) manipulated-region localization when pixel-level supervision is available. We evaluated the approach on three public benchmarks of increasing complexity—HiDF, SID_Set (SIDA), and CiFake—using each dataset’s official partitions where provided (SID_Set uses the predefined train/validation split) and a standardized preprocessing and training pipeline across experiments. Results: On HiDF, our model achieved strong performance on both video and image tracks (AUC up to 0.931 on video and 0.968 on images), yielding large gains relative to previously reported HiDF baselines under their published settings. On SID_Set, the model achieved 99.1% three-class accuracy (real/synthetic/tampered) and produced accurate localization masks for many tampered regions, while we explicitly documented the split protocol and leakage checks to support the validity of the evaluation. On CiFake, the model exceeded 95% accuracy and attained an AUC of 0.986. Conclusions: Overall, the results indicate that SigLIP-2 representations combined with multi-task training can deliver high detection accuracy and interpretable localization on challenging, realistic forgeries, while highlighting the importance of clearly stated evaluation protocols for fair comparison. Full article

Assessing environmental impacts across the full life cycle of buildings is essential for advancing toward a net-zero and regenerative built environment. However, life cycle inventory generation and impact assessment remain methodologically complex and time-intensive, limiting their integration into early design decision-making. This study aims to quantify and reduce the embodied carbon of a regenerated building while optimizing material selection based on environmental performance and circularity potential. An integrated Building Information Modeling–Life Cycle Assessment (BIM–LCA) framework combined with Sensitivity Analysis (SA) was applied within a circular economy perspective. A regenerative building was modeled using BIM, and Industry Foundation Classes (IFC) data were employed to conduct a detailed life cycle assessment to quantify embodied carbon and identify emission hotspots across life cycle stages. The results indicate that material extraction, processing, and manufacturing dominate environmental impacts, contributing more than 85% of total CO₂ emissions. Sensitivity analysis further demonstrates the influence of material choices on overall carbon performance. The findings underscore the importance of evaluating embodied carbon at early design stages to support informed decisions regarding material efficiency, renewability, and recyclability. The proposed BIM–LCA framework provides a scalable, data-driven approach to support early-stage decarbonization strategies and contributes to reducing the carbon footprint of buildings in alignment with net-zero and regenerative design objectives. Full article

The Mam Mayan Christians of Guatemala’s Western Highlands regularly ascend sacred mountains to pray for the precarious migration journey across Mexico and into the United States. This paper describes and explicates the cultural logic connecting mountains, migration, and prayer through an analysis of linguistic practices across three domains: (1) the tacit and habitual reference to mountains in common Mam grammatical form classes, (2) the discourse patterns that link the precarities of migration to mountaintop prayer, and (3) the context for and structure of mountaintop prayer rituals. Taken together, the analysis of these three domains describes a Mam ontology of mountains that render mountaintop prayer the most important venue for facing the precarities of international migration. The paper closes by considering the habitus of Mam Maya Evangelical Christians as a source of Indigenous theological praxis. Full article

Accurate mapping of grass species in biodiverse ecosystems, such as wetlands, is critical for ecological protection. Rapid advancements in remote sensing have established satellite data as a critical tool for wetland grass species mapping; however, its relatively coarse spatial resolution and susceptibility to cloud contamination limit the distinction of co-occurring species at fine scales. While Unmanned Aerial Vehicle (UAV) remote sensing offers high resolution and operational flexibility, relying on single-source features is often insufficient for fine-scale wetland species mapping due to the spectral similarity of co-occurring species. On the other hand, the fusion of multi-source remote sensing features (i.e., spectral, textural, and geometric features) likely provides a promising solution for achieving accurate, fine-scale grass species mapping in biodiverse ecosystems. In this study, we developed a wetland grass species mapping framework integrating spectral, textural, and geometric features derived from UAV RGB and multispectral imagery. Using a dataset of 95,880 image objects representing 24 wetland grass species classes collected in two years in Dajiu Lake National Wetland Park of China, we evaluated three machine learning algorithms—Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost)—across various feature combinations. We found that while spectral features (i.e., red edge, normalized green–red difference index [NGRDI], and normalized difference vegetation index [NDVI]) (related to leaf pigment concentrations and cellular structures) exhibited the highest importance in wetland grass species mapping, textural (i.e., contrast) and geometric features (i.e., aspect ratio) significantly enhanced classification performance as complementary information, yielding improvements of up to 10.5% in overall accuracy (OA) and 0.103 in Macro-F1 scores. Specifically, the fusion of spectral, textural, and geometric features achieved optimal performance with an OA of 81.9% and a Macro-F1 of 0.807. Furthermore, the XGBoost model outperformed SVM and RF, improving OA by 9.4% and 2.8%, and Macro-F1 by 0.08 and 0.035, respectively. By identifying the optimal feature combination and machine learning algorithm, this study establishes an accurate method for wetland grass species mapping, offering new opportunities for ecological assessment and precision conservation in biodiverse landscapes. Full article

Hypertrophic cardiomyopathy (HCM), the most common inherited cardiomyopathy, represents a paradigmatic condition for precision cardiovascular medicine. Once regarded as a monogenic autosomal dominant disorder driven by rare sarcomeric variants, HCM is now recognized as a genetically complex disease characterized by incomplete penetrance, variable expressivity, and heterogeneous clinical trajectories. This review summarizes current evidence on the evolving genetic architecture of HCM, emphasizing the predominant role of definitively validated sarcomeric genes, particularly MYBPC3 and MYH7, and the clinical value of gene panel expansion. Phenotypic variability reflects interactions among variant classes, gene-specific mechanisms, and modifying factors. Differences between missense and truncating variants, haploinsufficiency and poison-peptide effects, allelic imbalance, and age-dependent penetrance contribute to diverse disease expression. Emerging data further support oligogenic inheritance and polygenic modulation, with genome-wide association studies and polygenic risk scores elucidating their contribution to disease susceptibility and variability, especially in genotype-negative patients and carriers of rare variants. We also address genes with emerging evidence and underrecognized pathogenic mechanisms, including deep intronic and splice-altering variants that may explain part of the missing heritability. The importance of distinguishing phenocopies is highlighted, advocating for phenotype-anchored diagnostic pathways integrating clinical assessment, multimodality imaging, and targeted genetic testing. Overall, contemporary data support a targeted, gene-validity-driven approach to genetic testing, where molecular findings primarily inform diagnosis and cascade screening, while risk stratification remains phenotype-led and longitudinal. Future progress will depend on integrative models combining rare variants, polygenic background, imaging, and biomarkers to translate genetic complexity into actionable precision care. Full article

The present study investigates the influence of low temperatures on the starting torque, viscous friction, and power intensity of a precision cycloidal reducer TwinSpin TS 140-115-E-P19-0583. Two types of plastic greases with differing viscosities were compared in the experiment: Castrol TT-1 (low-viscosity, optimised for low-temperature) and Vigo RE-0 (higher viscosity, designated for greater loads). The measurements were taken in a climate chamber in the temperature ranging from +24 °C to −20 °C in the mode accounting for no external load. The results have shown that Castrol TT-1 maintains its beneficial rheological properties at as low as −20 °C, which is manifested in a low starting torque (~0.30 Nm) and low power intensity (~0.33 kW). On the contrary, Vigo RE-0 shows a significant increase in friction: at −20 °C, the starting torque is 1.0–1.1 Nm and the power intensity of the operation increases to consume more than 1.5 kW. The correct choice of lubricant is a critical factor for reliable cold-start behaviour under no-load, internal-loss-dominated conditions. This study provides a rare experimentally verified low-temperature assessment of starting torque, viscous friction, and power intensity in fully assembled TwinSpin precision cycloidal reducers lubricated with greases of markedly different viscosity classes, addressing an important gap in the existing literature. Full article

Facial emotion recognition (FER) is an important component of human–computer interaction and healthcare-oriented affective computing. However, reliable deployment remains difficult in unconstrained settings due to appearance and geometric variability (e.g., pose, illumination, and occlusion), demographic imbalance, and dataset bias. In practice, two additional constraints frequently limit real-world FER systems: the computational overhead of heavy architectures and limited adaptability when data evolve over time, where sequential updates can cause catastrophic forgetting. To address these challenges, we propose the Incremental Attention-Enhanced Network (IAE-Net), a compact single-branch framework built on a DenseNet121 backbone and a cascaded refinement pipeline. The model incorporates Channel Attention (CA) to emphasize expression-relevant feature channels and suppress less informative responses, followed by a deformable attention module (DA) that reduces feature misalignment caused by non-rigid facial motion and pose shifts, thereby improving robustness under geometric variability. For continual deployment, IAE-Net supports class-incremental updates via weight transfer, exemplar replay, and knowledge distillation to improve retention during sequential learning. We evaluate IAE-Net on four widely used benchmarks, FER2013, FERPlus, KDEF, and AffectNet, covering both controlled and in-the-wild conditions under a unified training protocol. The proposed approach achieves accuracies of 79.15%, 92.03%, 99.48%, and 74.20% on FER2013, FERPlus, KDEF, and AffectNet, respectively, with balanced precision, recall, and F1-score trends. These results indicate that IAE-Net provides an efficient and extensible FER framework with potential utility in dynamic real-world and longitudinal healthcare-oriented applications. Full article

Sleep disorders are prevalent in the world, and they lead to severe health issues such as cardiovascular disease and cognitive disabilities. Conventional polysomnography-based diagnosis is based on manual EEG analysis under the supervision of trained specialists, which is time-consuming and may have inter-rater variability. Although the predictions of deep learning (DL) models on the task of sleep classification of EEG have been promising, they, in many cases, do not explain the multiscale, temporal dynamics that physiological signals are characterized by. In this work, a hybrid model that is a combination of CNN and multifractal detrended fluctuation analysis (MF-DFA) was proposed to detect localized temporal features and long-term fractal-based dynamics of single-channel EEG recordings. The performance of the suggested model was tested using two separate polysomnographic datasets: the CAP Sleep Dataset of five-class sleep disorder classification (Healthy, Insomnia, Narcolepsy, PLM, and RBD) and the ISRUC Sleep Dataset on the three-class subject-independent validation. In the CAP dataset, the framework had an accuracy of 86.38%. Cross-dataset transfer to the ISRUC Sleep Dataset, where only the classification head was fine-tuned on a small labeled subset while all feature-extraction layers remained frozen from CAP training, achieved 87.50% accuracy, demonstrating that the learned representations generalize across differing recording protocols, sampling rates, and diagnostic label spaces. The experiments of ablation proved the paramount importance of the MF-DFA features, and the lack of them led to low classification rates. The findings demonstrate the clinical feasibility of applying fractal analysis in conjunction with DL to detect sleep disorders in an automated, generalizable manner, suitable for use in large-scale monitoring and resource-starved clinical environments. Full article

Following bushfires (also known as wildfires), impacted free-living wildlife with welfare or conservation concerns are captured and presented for veterinary assessment where possible. This study represents an in-depth retrospective analysis of the veterinary records of 259 animals in Victoria, Australia, impacted by bushfire in 2019–2020. In total, 35 different species were assessed, including 196 koalas. Multivariable analyses of 126 koalas with complete medical records identified several clinical prognostic factors affecting 6-month survival outcomes. Increased odds of negative outcomes (death or euthanasia) were associated with increasing age (tooth wear class; odds ratio 2.70 for one unit increase), lower body condition score (one-unit decrease OR 7.27), and the earlier animals were presented after the fire event (OR 0.94 for each passing day). In 83 koalas with burn injuries, negative outcomes were also associated with burns more severe than minor (85% survival for minor burns only, compared to 31% survival with moderate or severe burns), and burns to more than 10 digits (12% survival). In burnt koalas, the combination of burn severity and digital involvement appear to be important prognostic factors for long-term outcomes. These findings can support veterinarians to more accurately evaluate prognosis for bushfire-affected koalas during initial assessment and will facilitate the strategic allocation of limited treatment and rehabilitation resources to the animals most likely to recover. The scope of this study was limited to the consideration of health outcomes, with the recognition of health as just one of many factors that must inform decisions about rehabilitating injured wildlife. Full article

In autonomous driving, deep convolutional neural networks face a core conflict between computational efficiency and safety-critical robustness on resource-constrained onboard computing units. Dominant structural pruning, based on weight magnitude or geometric statistics, fails in long-tailed traffic scenarios by equating parameter magnitude with feature importance and pruning critical filters in the tail classes. To address this, we propose a structural pruning framework that evaluates the semantic utility of features using weighted copula entropy rather than relying solely on their magnitude. Our novel approach integrates Elastic Net regularization for inducing sparsity and weighted copula entropy for unbiased information-theoretic feature selection. By incorporating inverse class frequency weighting into empirical Copula estimation, we decouple feature relevance from sample abundance, ensuring the preservation of rare-class discriminators based on their information content rather than occurrence frequency. Furthermore, this metric is embedded into an enhanced max-relevance and min-redundancy algorithm to eliminate semantic redundancy while maintaining representational diversity. Extensive experiments on the BDD100K dataset with YOLOv5l and YOLOv8l architectures demonstrate that, at a 50% pruning rate, the proposed method reduces FLOPs and parameters by nearly 50%, with only 0.09% mAP@0.5 loss for YOLOv5l and 0.14% mAP@0.5 loss for YOLOv8l, while significantly improving the mAP of the extreme tail class Train from 0% to 3.84% and 2.76% to 5.12%, respectively. It achieves a more favorable trade-off between detection accuracy and computational efficiency than mainstream pruning approaches. This work provides a lightweight scheme for autonomous driving perception models and a new information-theoretic perspective for structured network pruning. Full article