Search Results (10,951)

Background: Polyploidization generates extensive gene redundancy, but how duplicated metabolic genes are retained and subsequently diversified remains poorly understood. UDP-glycosyltransferases (UGTs) provide a suitable system for examining this process because they participate in specialized metabolism, plant development, and environmental responses. This study aimed to characterize the retention, expansion, and regulatory divergence of the UGT family in allotetraploid Panax ginseng at subgenome resolution. Methods: We integrated telomere-to-telomere (T2T) genome annotation, phylogenetic and chromosomal analyses, duplication classification, collinearity and Ka/Ks analyses, promoter cis-acting element prediction, developmental co-expression networks, and transcriptomic responses to biotic and abiotic treatments. Results: A total of 212 PgUGT genes were identified, including 104 and 108 members in the A and B subgenomes, respectively. The family exhibited an overall near-mirrored retention pattern between the two subgenomes, accompanied by local copy-number asymmetry. Whole-genome and segmental duplication accounted for 64.2% of the family, and 99.5% of the gene pairs with valid Ka/Ks estimates had values below 1, suggesting pervasive purifying selection. PgUGT-containing co-expression modules were associated with bud, stem, leaf, and fruit developmental conditions, while promoter cis-acting element compositions exhibited member-specific variation. Transcriptional responses to fungal pathogens and abiotic, hormone, and chemical treatments were concentrated in particular members and local gene arrays rather than being coordinated across entire clades or subgenomes. Conclusions: The PgUGT family is characterized by extensive ancestral copy retention accompanied by local copy-number changes and copy-specific regulatory divergence. These findings provide a subgenome-resolved framework for understanding UGT family evolution in allotetraploid ginseng and prioritize candidate PgUGT genes for subsequent functional validation. Full article

Rapid selection of appropriate antimicrobial therapy is important for improving patient outcomes and supporting antimicrobial stewardship, particularly in the context of increasing antimicrobial resistance (AMR). Conventional antimicrobial susceptibility testing (AST), although essential for clinical decision-making, may not provide actionable susceptibility information immediately. This study develops an explainable multi-label machine learning framework for patient-specific antibiotic recommendation based on susceptibility prediction and ranked decision support using routinely collected clinical microbiology data. The framework integrates leakage-controlled preprocessing, microbiological and demographic feature representation, multi-label susceptibility encoding, One-vs-Rest ensemble learning, probability-based antibiotic ranking, statistical evaluation, temporal validation, and SHapley Additive exPlanations (SHAP). The dataset comprised 234 clinical records, of which 196 bacterial/other records were retained for the primary analysis after excluding 38 fungal records. A chronological partition produced 156 development records and 40 temporally held-out test records. Thirty-three antibiotic susceptibility labels were retained based on development-set availability. XGBoost, Random Forest, and LightGBM were evaluated using five-fold out-of-fold (OOF) validation. Random Forest was selected for the final recommendation and explainability analyses based on its overall performance, achieving a Micro-F1 of 0.4204, Macro-F1 of 0.3003, AUROC of 0.7069, AUPRC of 0.3979, and Precision@5 of 0.3962. A leakage-safe local antibiogram was additionally evaluated as a population-level ranking baseline, achieving a Precision@5 of 0.3077. Feature ablation showed that the combination of organism and age produced the highest OOF Micro-F1 (0.4635) and AUROC (0.7186), while the addition of gender and specimen type improved selected ranking measures but did not consistently improve aggregate classification performance. On the temporally held-out test cohort, Random Forest achieved a Micro-F1 of 0.4267, AUROC of 0.7447, AUPRC of 0.4892, and Precision@5 of 0.4350. SHAP analysis was completed for all 33 antibiotic-specific classifiers, providing global and antibiotic-level explanations of model behavior. The framework provides an interpretable approach for ranking potentially susceptible antibiotics at the patient level and is intended as clinical decision support rather than an autonomous prescribing system. Further external and prospective multicentre validation, including dedicated evaluation of challenging cases such as pan-drug resistance, is required before clinical deployment. Full article

Multilingual sentiment analysis remains challenging because of cross-linguistic differences, uneven data availability, and potential shifts in meaning introduced during translation. Rather than proposing a new model, this study examines the performance of translation-based pipelines and ensemble Transformer models in multilingual settings. The primary objective is to investigate differences in downstream sentiment classification performance between translation systems within a consistent evaluation framework. Texts in Arabic, Chinese, French, and Italian are standardized through label harmonization and basic preprocessing and subsequently translated into English using Google Translate and the open-source LibreTranslate. Sentiment classification is performed using three Transformer-based models: DeBERTa-v3, RoBERTa, and BERTweet. The experiments are formulated as a binary polarity-classification task comprising positive and negative instances, with neutral samples excluded because their annotations are not directly comparable across the heterogeneous source datasets. Predictions from the individual models are combined through majority voting without introducing a new ensemble method. Experiments on the resulting binary datasets demonstrate that the ensemble achieves the highest mean weighted F1-score, with low fold-to-fold variation under both translation pipelines. Google Translate yields higher and more consistent classification performance across the evaluated subsets, whereas LibreTranslate exhibits greater variation. Given that the datasets differ in domain and genre, these variations cannot be attributed solely to linguistic differences. Overall, the findings reveal differences in downstream sentiment classification performance between the two translation pipelines and indicate that the ensemble combines high mean performance with low fold-to-fold variation within the evaluated binary setting. Full article

Medical image classification models often struggle to generalise across heterogeneous clinical domains owing to variations in visual characteristics, acquisition conditions, and class imbalance. Existing studies largely address these challenges independently, with limited investigation into their combined impact on classification robustness. This paper proposes a lightweight dual-stream framework based on a pretrained ConvNeXt-Tiny backbone, integrating complementary global semantic and local structural feature representations with imbalance-aware optimisation. Rather than modifying the backbone, the framework enhances feature discrimination through dual-stream processing while incorporating class-balanced focal loss and stratified sampling for minority-class recognition. The framework is evaluated independently on four public datasets spanning dermatology, ophthalmology, and gastrointestinal endoscopy using five-fold cross-validation to assess architectural robustness across heterogeneous domains rather than cross-domain transfer of a single trained model. Experimental results show strong performance across all datasets, achieving AUC values above 0.92. Ablation studies confirm that dual-stream representation learning provides the primary performance gains, while imbalance-aware optimisation further improves robustness under severe class imbalance. These findings demonstrate an effective and practical solution for medical image classification across heterogeneous clinical imaging domains without requiring dataset-specific architectural modifications. Limitations regarding independent per-domain (rather than cross-domain) evaluation, baseline comparability, and incomplete quantitative calibration analysis are discussed explicitly and identified as directions for future work. Full article

Over the past decade, the Punjab plains of Northern India have experienced recurrent flooding driven by hydroclimatic variability, specifically shifts in western disturbances that have intensified monsoon precipitation. Following a devastating flood in 2025, the region remains highly vulnerable to hydrological extremes, a risk further exacerbated by shifting land use and agricultural patterns, geomorphic parameters, and complex fluvial systems. This study assesses flood susceptibility by integrating multi-sensor satellite observations, multi-temporal Sentinel-1 backscatter signals, and refined runoff potential estimates derived from local climate zones, accounting for land cover, soil type, and infiltration characteristics, into machine learning frameworks. The model is trained using a 2025 flood inventory generated from a synthetic aperture radar backscatter threshold ratio. The calibrated frameworks are applied to the 2023 flood events to test independent transferability. The temporal consistency and predictive performance of the models are evaluated using the precision–recall trade-offs, threshold-dependent predicted probability distribution, and Shapley Additive exPlanations (SHAP). Results indicate more balanced classification performance of Random Forest and Extreme Gradient Boosting in comparison to Artificial Neural Network performance that exhibits higher recall with lower precision. The model performance for 2023 models is considered more robust, with greater class separability of 2023 flood events than for 2025. Probability distributions for both events further demonstrate model-dependent threshold behavior, highlighting a trade-off between flood detection sensitivity. SHAP identifies rainfall, soil moisture, runoff, and elevation as the dominant contributors. The analysis further indicates that all model frameworks effectively capture the physical control of hydrological and topographical variability on the temporal flood events. The consistent contribution of hydrological and topographical factors across the two events supports model transferability, while threshold sensitivity, uncertainty, and spatial dependence are important considerations for flood susceptibility modelling. The results reflect a balanced interaction between extreme rainfall, runoff potential, and topographic control in causing periodic floods in the Punjab plains. Full article

Accurate Land Use and Land Cover (LULC) mapping in high-resolution alpine environments is challenging due to complex terrain, heterogeneous vegetation, seasonal snow and ice cover, and the limited spectral information provided by conventional aerial imagery. Although foundation models such as the Segment Anything Model (SAM) effectively capture structural features, their class-agnostic design, limits fine-grained semantic discrimination and typically requires large annotated datasets. This study proposes a multi-modal deep learning framework for alpine LULC mapping using sparse annotations, which would fall under the category of weakly supervised learning. The framework employs a dual-encoder architecture that integrates RGB imagery, six-band multispectral imagery, and custom adapters for spectral indices, and Digital Surface Models (DSMs). A SAM-based encoder extracts geometric and contextual features from RGB imagery, while a dedicated encoder learns complementary spectral representations from multispectral data. To address the boundary uncertainty introduced by sparse supervision, we propose post inference hybrid refinement strategy that combines a Canopy Height Model (CHM) derived from the DSM to improve tree crown delineation with edge-based refinement for low vegetation classes, such as shrubs, and mathematical methods to refine road and building edge delineation with DSMs. Experimental results across fourteen alpine classes highlight that the framework achieves a validation mIoU of 0.777, macro-averaged over the fourteen classes. For the present sensor choice and classification scheme, no comparable multi-modal baseline exists. Thus, results are reported in absolute terms. The present multi-modal data fusion sets the baseline for future scalable alpine LULC mapping applications. Full article

Background/Objectives: Parkinson’s disease (PD) is associated with gait abnormalities that provide quantitative information on motor function. This study developed and evaluated a signal-to-image deep learning framework for distinguishing participants with diagnosed PD from healthy controls using plantar pressure gait signals. Methods: VGRF signals from the PhysioNet Gait in Parkinson’s Disease Database were transformed into RGB images encoding left-foot pressure, right-foot pressure, and the absolute bilateral difference. ResNet50, EfficientNet-B0, ViT-Tiny, and Swin-Tiny were evaluated at three resolutions and compared with 1D-CNN and BiLSTM baselines. Repeated subject-level five-fold cross-validation with three repetitions and participant-level bootstrap analysis were performed. Results: Among RGB models, ViT-Tiny at 384 × 384 achieved a mean accuracy of 77.64%, F1-score of 82.82%, and AUC of 86.40%. In the Swin-Tiny 384 × 384 ablation, the absolute bilateral-difference representation achieved the highest mean AUC (86.68%). However, its participant-level AUC advantage over RGB was not statistically conclusive (ΔAUC = 0.030, 95% CI: −0.011 to 0.068). Conclusions: Signal-derived gait images provide a feasible approach for PD classification, with bilateral-difference information showing potential discriminative value. Full article

High-fidelity continuum models of electrostatically actuated MEMS accurately capture distributed electromechanical interactions but are computationally expensive for repeated simulation, optimization, and real-time applications. This work develops a physics-informed reduced-order modeling framework based on Lie symmetry classification for a nonlinear electrostatic MEMS microplate governed by a fourth-order integro-partial differential equation. The continuum model is recast as an extended canonical system separating local differential operators from nonlocal stretching and capacitive contributions. Lie group classification of the complete boundary value problem shows that the electrostatic singularity, constitutive coefficients, fixed geometry, and clamped boundary conditions suppress nontrivial continuous spatial symmetries in the generic bounded problem, while time translation survives only in the autonomous subclass. The discrete reflection invariances of the centered rectangular device are treated separately to identify invariant functional subspaces for Galerkin projection. A symmetry-preserving reduced-order model is then constructed in the even–even subspace, retaining bending, geometric stretching, pre-stress, capacitive feedback, dielectric inhomogeneity, and fringing field effects. Numerical verification against the high-fidelity continuum model shows close agreement with the FOM for static and transient responses while preserving reflection symmetry and remaining robust under parameter variations. For the nominal configuration, the monomodal Lie-ROM predicts a pull-in voltage of $127.73\mathrm{V}$ versus $128.21\mathrm{V}$ for the FOM, corresponding to an absolute relative error of $0.37\%$ and a signed error of $-0.37\%$. The monomodal formulation substantially reduces computational cost and consistently outperforms a classical lumped-parameter approximation, providing an interpretable and efficient basis for parametric analysis, design optimization, control-oriented modeling, and future digital twin applications. Full article

Background/Objectives: Traditional machine learning metrics often fail to capture the clinical consequences of classification errors, particularly in high-stakes screening applications. When applying task-specific AI tools to human lives, clinicians cannot rely on simple, headline metrics and marketing materials. Impressive accuracy figures can hide dangerous algorithmic shortcuts that collapse when encountering actual patients. This study addresses the gap between statistical performance and clinical utility by evaluating classifiers for prescription opioid misuse using a clinically oriented framework. Methods: Three ensemble models, namely, Cost-Sensitive Bagged Trees (CSBT-Untuned and CSBT-Tuned) and Random Undersampling Boosting (RUSBoost), were trained on National Survey on Drug Use and Health data and assessed using composite metrics integrating clinical priorities and asymmetric error costs. Results: The results demonstrate that while CSBT-Untuned achieved the highest raw accuracy of 86.7%, it missed 61.5% of positive cases. Conversely, the threshold-optimized CSBT-Tuned model achieved enhanced minority class detection and numerically higher Clinical Discriminative Performance Scores under sensitivity-priority scenarios, though its performance remained statistically comparable to RUSBoost given overlapping confidence intervals. Learning curve analysis confirmed stable convergence for the cost-sensitive bagging approach. Conclusions: Before accepting AI tools in patient care, physicians must demand an evaluation report similarly detailed to this manuscript, utilizing this framework as guidance for what an evidence report should demonstrate prior to clinical deployment. Full article

Assessing ecological sustainability in agricultural landscapes requires approaches that integrate land-cover change, its ecological effects, and their spatial determinants. This study analysed changes between 2023 and 2024 across six agricultural landscapes in northern Benin using the Landscape Ecological Sustainability Index (LESI), calculated for 1 km² landscape cells from Human Disturbance Coefficients (HDCs) assigned to satellite-derived land-cover classes. Interannual changes were assessed using ΔLESI, the Wilcoxon signed-rank test, Global Moran’s I, and the Local Indicators of Spatial Association (LISA). The contribution of land-cover transitions to HDC change was quantified and a Monte Carlo sensitivity analysis based on classification accuracy was additionally used to assess the robustness of the observed interannual changes to classification uncertainty, and complementary univariate and bivariate regression models examined the relationships between LESI variations and 11 biophysical and geographical variables, including their pairwise interactions. The interannual comparison between 2023 and 2024 showed a decrease in ecological sustainability in four sites, a slight increase in one, and relative stability in another. Significant spatial autocorrelation was detected in all sites (Moran’s I = 0.44–0.65; p < 0.001). Some spatially limited transitions exerted important effects on HDC change. Sensitivity analysis confirmed that the direction of ΔHDC was robust to classification uncertainty in five of the six landscapes. The low explanatory power of the univariate models (R² ≤ 0.081) indicates that no single variable independently explains the observed changes. The bivariate interaction analyses further showed that some associations were context-dependent, although their explanatory power remained limited, with the best-performing model accounting for only 10.9% of the variation in ΔLESI. This integrated framework provides a reproducible approach for assessing, mapping, and prioritising interannual change of ecological sustainability from remote sensing data to support evidence-based agricultural landscape planning and sustainable land management. Full article

Multi-objective feature selection provides an effective framework for high-dimensional data analysis by jointly considering classification performance and feature subset size. However, redundant and irrelevant features may degrade the quality of the initial search distribution, and population aggregation may reduce the structural diversity of non-dominated feature subsets. To address these issues, this paper proposes PGS-MODE-FS, a prior-guided and structure-aware multi-objective differential evolution method for high-dimensional feature selection. Specifically, feature–class relevance and feature redundancy are integrated into a unified feature importance measure to guide the generation of candidate solutions with different sparsity levels. The same feature-priority information is further used to construct a Top-k activated subspace, in which individuals are assigned to multiple islands according to their structural differences on informative features, thereby promoting diverse evolutionary search. Experiments on 17 public and biomedical datasets, including parameter analysis, comparative experiments, and ablation studies, demonstrate that PGS-MODE-FS achieves competitive performance in solution-set quality, classification accuracy, feature reduction, and computational efficiency. Further diversity analysis shows that the proposed multi-island mechanism effectively preserves structural diversity during evolution. Full article

Early detection of salinity stress is essential for precision agriculture, particularly in scalable, resource-constrained monitoring systems. This study presents a portable sensing module integrating a low-cost metal oxide semiconductor (MOS) sensor array with potential application for edge deployment to detect salinity stress in peppermint. Salinity significantly reduced plant biomass, confirming physiological stress induction. Volatile organic compound (VOC) fingerprints were collected over eleven consecutive days in a controlled enclosure. Sensor signals underwent outlier filtering, normalization, and smoothing, while treatment discrimination was verified using the Kruskal–Wallis test. Thirty-three machine learning models were evaluated using a 75:25 train–test split with five-fold cross-validation. Wide neural network models achieved the highest predictive performance, exceeding 98% test accuracy and a 97% macro F1 score. Feature adequacy analysis showed that six sensors captured the dominant variance required for reliable classification. Considering computational constraints, a bilayered neural network using only six features maintained over 97% accuracy with a memory footprint of 0.008 MB while remaining Pareto optimal. These findings support the feasibility of a compact, computationally efficient, and edge-compatible VOC sensing framework for salinity stress detection in precision agriculture and intelligent crop monitoring. Full article

Built-up expansion is reshaping landscapes across Nepal; however, consistent multi-temporal mapping remains challenging due to rugged terrain, fragmented settlements, and heterogeneous land-cover conditions. This study develops and evaluates a multi-product and terrain-informed workflow in Google Earth Engine for mapping built-up expansion across three physiographically contrasting districts of Nepal: Arghakhanchi, Lalitpur, and Chitwan, from 2017 to 2025. Annual predictor stacks were generated by integrating Sentinel-2 spectral bands and derived indices, Dynamic World built-up probabilities, and SRTM-derived elevation and slope variables. ESRI Global Land Cover datasets were used separately for auxiliary cross-product comparison and assessment of the mapped outputs. Preliminary yearly built-up masks were generated using district- and year-specific Random Forest classifications, followed by the post-classification constraints, and were subsequently integrated through cumulative expansion mapping. Accuracy assessment for 2017, 2021, and 2025 yielded overall accuracy values of 86.4–92.4%, built-up F1-scores of 84.7–91.3%, and Kappa coefficients of 0.81–0.91. Between 2017 and 2025, cumulative built-up extent expanded by 8054.65 ha in Chitwan, 2406.20 ha in Arghakhanchi, and 2215.96 ha in Lalitpur; Arghakhanchi recorded the highest proportional increase (117.6%). The mapped expansion was comparatively dispersed in Arghakhanchi, concentrated within metropolitan and peri-urban areas in Lalitpur, and broader and corridor-oriented in Chitwan. Because previously detected built-up pixels were retained in subsequent cumulative outputs, the resulting extents were non-decreasing by construction and did not represent demolition or other land use reversals. Consequently, annual built-up expansion should not be interpreted as net annual land-cover change. The proposed framework provides a practical and transferable approach for comparative built-up expansion monitoring and urban growth assessment across contrasting physiographic settings. Full article

Multilingual code-switched language identification remains a challenging task due to frequent language alternation, lexical ambiguity, and the limited availability of annotated corpora for low-resource languages. While transformer-based language models have demonstrated strong performance, their computational complexity motivates the exploration of more efficient neuromorphic approaches. This study proposes an optimized Spiking Neural Network (SNN) framework for multilingual code-switched language identification using spike-based neural computation. Text data are preprocessed and represented using Term Frequency–Inverse Document Frequency (TF-IDF) feature vectors, which are transformed into temporal spike trains through a rate-coding mechanism over a fixed simulation window. The encoded spike sequences are processed by a feedforward SNN employing Leaky Integrate-and-Fire (LIF) neurons. Hyperparameters are optimized using Optuna to improve classification performance. The proposed model is evaluated on a balanced multilingual code-switched dataset and compared with classical machine learning models, including Logistic Regression, Support Vector Machine, and Random Forest, as well as deep learning and transformer-based models, including BiLSTM, mBERT, AfroXLMR, and XLM-RoBERTa. Experimental results demonstrate that the optimized SNN achieves an overall classification accuracy of 81%, outperforming the baseline SNN while remaining competitive with several state-of-the-art neural models. Statistical validation using the Friedman and Nemenyi tests confirms significant performance differences among the evaluated classifiers while demonstrating that the optimized SNN performs competitively against several strong baselines. Although transformer models achieve the highest overall accuracy, the proposed SNN offers a computationally efficient neuromorphic alternative that combines temporal spike processing with stable learning behaviour for multilingual code-switched language identification. These findings demonstrate the potential of spike-based neural computing for low-resource multilingual natural language processing and provide a reproducible foundation for future neuromorphic language identification research. Full article

The identification and interpretation of bone surface modifications (BSM) are central to reconstructing early hominin behavior, yet recent shifts by some researchers toward metric quantification face significant epistemological and statistical challenges. This paper critically evaluates the “metric method” proposed by Keevil/Pante et al., arguing that its reliance on continuous, ratio-scale measurements is fundamentally undermined by effector variance—the inherent dimensional mismatch between experimental tools and those in the (assemblage-specific) archaeological record. I demonstrate through statistical analysis that the method’s use of quadratic discriminant analysis (QDA) is compromised by severe multicollinearity (VIF > 5), resulting in unstable models that fail to generalize to fossil contexts, as exemplified by the problematic interpretations of the Grăunceanu (Romania) assemblage. Furthermore, I deconstruct recent critiques against the application of machine learning (ML) in taphonomy, clarifying misconceptions regarding Wolpert’s “no free lunch” theorem and rebutting allegations of data leakage. I contend that ML algorithms, when properly integrated with high-resolution categorical data, provide a more robust and accurate framework for classification of taphonomic datasets. By exposing these methodological biases, I propose a new paradigm for BSM analysis that prioritizes systemic hypothesis testing, objective data generation, and empirical testing/refutation models based on original datasets over speculative arguments and strict metric quantification. Full article