Search Results (3,075)

Rapid assessment of internal fruit quality is essential for fruit grading, postharvest management, and consumer-oriented quality evaluation. Among the quality attributes, soluble solids content (SSC) is a key indicator of citrus sweetness and maturity. Visible and near-infrared (Vis–NIR) spectroscopy provides an effective approach for rapid SSC detection in fruit. However, most existing studies rely on single full-spectrum models or simple band stacking strategies, which limits their ability to fully exploit complementary information among different spectral sub-bands. To address this limitation, a color residual-variance gated attention fusion network (CR-VGAFNet) is proposed for efficient SSC assessment in Hongmeiren. On the independent prediction set, CR-VGAFNet achieved a prediction correlation coefficient (R_P) of 0.7744, a root mean square error of prediction (RMSE_P) of 0.6530 °Brix, and a mean absolute percentage error of prediction (MAPE_P) of 4.83%. These findings suggest the potential of the framework for multi-band spectral fusion. This study provides a new technical perspective for multi-band spectral fusion and rapid fruit quality assessment. Full article

Implicit Neural Representations (INRs) provide a flexible and resolution-independent formulation for continuous signal representation. Despite their strong representation ability, standard INRs usually predict each queried coordinate independently, making it difficult to explicitly exploit the local coherence widely observed in natural signals. For images and volumetric data, neighboring locations often share correlated responses in smooth regions, while sharp variations mainly appear around spatial transitions. Ignoring such local dependency may reduce learning efficiency and weaken the reconstruction of spatially consistent details. To address this limitation, we propose Spatial-Aware Implicit Neural Representation (SA-INR), which enhances INRs by introducing local feature aggregation into the hidden representation space. Motivated by local feature coherence, SA-INR aggregates neighboring coordinate features through a learnable spatial-aware local operator. The aggregation weights are initialized as a uniform mean filter, providing a smooth local bias during early optimization. As training proceeds, the aggregation weights are updated by reconstruction supervision and become adaptive to spatial content. To preserve coordinate-specific information and avoid over-smoothing, the aggregated feature is further integrated with the original feature through a residual connection. Extensive experiments on image representation, CT reconstruction, and image denoising demonstrate that SA-INR consistently improves reconstruction fidelity across different INR backbones and reconstruction tasks. These results suggest that explicitly modeling local feature interaction is an effective way to enhance continuous signal representation. Full article

Online social networks generate large volumes of textual data that reflect users’ opinions, affective expressions, and broader patterns of engagement and social behavior. However, natural language processing approaches frequently examine sentiment, trust-related signals, and behavioral indicators independently, limiting their ability to represent the multidimensional nature of online interaction. This study conducts a systematic comparative evaluation of lexicon-enhanced fine-grained sentiment classification using linguistic, message-level statistical, and lexicon-derived affective information across a common experimental framework. The empirical analysis combines TF–IDF features, word-count information, and sentiment indicators derived from TextBlob, SentiStrength, and VADER, while the broader multi-level organization is used to relate the resulting affective evidence to online social-behavior analysis. Fifteen classical machine learning algorithms and seven deep learning architectures are evaluated on a real-world Twitter dataset containing 41,157 COVID-19-related tweets labeled across five sentiment-intensity classes. The experimental evaluation considers four feature configurations and seven performance metrics, complemented by Friedman and post hoc Wilcoxon signed-rank tests. The results show that TextBlob provides modest improvements, SentiStrength produces broader and more consistent gains, and VADER yields the strongest overall performance. AdaBoost combined with VADER achieves the best results, with 93.16% accuracy, 93.20% macro F1, 93.27% balanced accuracy, and an MCC of 0.913, while the Dense Neural Network is the strongest deep learning model. These results demonstrate that lexicon-derived affective features can substantially strengthen fine-grained sentiment classification, although their effectiveness depends strongly on the learning algorithm used to exploit them. The empirical contribution of this study is confined to fine-grained sentiment classification, while trust-related and attachment-related dimensions are retained as higher-order interpretive constructs rather than directly predicted or empirically validated outcomes. Full article

This paper proposes a Koopman-based stochastic model predictive control (SMPC) approach for unknown nonlinear systems by exploiting partial probabilistic information. Unlike existing Koopman-based SMPC methods that primarily rely on the first- and second-order moments of stochastic Koopman modeling error, the proposed approach further incorporates available support information into the controller design. By jointly utilizing the mean, covariance, and support information of the resulting uncertainty, the chance-constrained optimization problem is reformulated into a tractable deterministic optimization problem with reduced conservatism. Moreover, the proposed approach is theoretically shown to be no more conservative than the corresponding RMPC in terms of constraint tightening under identical constraint requirements. Furthermore, recursive feasibility and closed-loop quadratic stability of the proposed control scheme are established theoretically. Simulation studies on spacecraft attitude control demonstrate that the proposed method reduces the performance index by 6.7% and 17.0% compared with a Koopman-based SMPC using mean and covariance information and RMPC, respectively, while maintaining a comparable average computation time of approximately 0.010 s. Full article

The construction sector contributes significantly to global carbon emissions, prompting a shift toward sustainable engineered timber. However, European hardwood species remain underutilised because current design standards are largely based on research conducted on softwood species. This paper outlines the fundamental principles for designing mechanical timber connections, specifically dowel-type fasteners, by reviewing the European Yield Model and fracture-mechanics approaches for ductile and brittle failure. Through a synthesis of recent experimental investigations on species like European beech, the work identifies critical gaps in current Eurocode 5 (EC5) provisions. The findings demonstrate that EC5 tends to underestimate the load-carrying capacity of many hardwood connections by 33% to 46% and does not explicitly account for brittle mechanisms such as splitting and row shear. Furthermore, the results highlight that connection performance may be significantly increased by factors like dowel-surface roughness, the “rope effect,” and specific assembly requirements such as precise predrilling diameters. This study concludes that existing design frameworks require calibration with hardwood-specific data and improved predictive models to differentiate failure modes. Such adjustments are essential to fully exploit the superior mechanical potential of hardwood species in modern timber construction. Full article

Tobamoviruses (viruses in the genus Tobamovirus, family Virgaviridae) lead to major yield losses in economically important crops around the world. In this review, we go beyond the canonical gene expression framework by integrating recent discoveries of reverse open reading frames (rORFs) on the negative-strand RNA. These rORFs have only been experimentally validated in cucumber green mottle mosaic virus (CGMMV), with predicted sequence-conserved homologs across a subset of the genus, including TMV, ToBRFV, and PMMoV. However, they are not universally present in all tobamoviruses. We systematically dissect the infection cycle—from disassembly and replication to cell-to-cell and systemic movement—with an emphasis on the host factors hijacked at each stage. We synthesize current understanding of plant antiviral immunity, focusing on RNA silencing and NLR receptor-mediated resistance as two pillars of defense, along with the transcription factors and microRNAs that orchestrate these responses. We critically evaluate the experimental evidence for both plant defenses and viral counter-strategies, noting that many mechanistic models derive from limited model systems. We further characterize host genetic resistance and susceptibility factors applicable to crop breeding. These resources include dominant NLR and non-NLR resistance, as well as recessive resistance derived from modified host susceptibility genes. We address how viral mutations, recombination and fitness trade-offs undermine resistance durability. We then evaluate their practical deployment through conventional breeding, the exploitation of quantitative resistance, and genome editing, and outline associated agronomic drawbacks and regulatory constraints. Using ToBRFV as a case study, we analyze its epidemiological traits and assess the current arsenal of surveillance tools, from field diagnostics to remote sensing. Finally, we survey management strategies across a spectrum of maturity. Some approaches, including sanitation protocols and conventionally bred resistant cultivars, have proven effective under field conditions. The first dsRNA-based biopesticide has recently been registered in China, while other biological control agents and low-risk chemical approaches remain largely at the experimental stage. We also discuss the bottlenecks that impede lab-to-field transition and highlight promising solutions such as precision breeding and evolution-oriented cultivar deployment. By bridging molecular virology, epidemiology, and integrated disease management, this review provides a critical, bench-to-field framework for the sustainable control of tobamoviruses. Full article

Exploiting geometrical symmetry to reduce the computational domain is a well-established strategy in finite element analysis. However, its systematic application to coupled piezoelectric modal problems requires that symmetry conditions be satisfied simultaneously by the mechanical and electrical fields. In this work, a parity-based framework is developed for class 6 mm piezoelectric disks and rings. Starting from coupled piezoelastic constitutive equations, the displacement components and electric potential, together with the associated stresses and electric displacements, are classified into eight electromechanical symmetry classes. The corresponding mechanical and electrical boundary conditions are then derived, allowing each symmetry class to be computed independently using only one eighth of the original geometry. Comparison with full-domain finite element calculations shows that the complete set of modes can be recovered and classified with very small frequency differences, while the reduced models achieve a substantially lower computational cost. The framework is subsequently applied to piezoelectric rings with varying outer diameters to track the evolution and degeneracy of modal families and to identify symmetry-equivalent classes. Finally, selected resonances are experimentally tracked through impedance measurements as the ring diameter is varied and compared with harmonic finite element predictions. The proposed approach therefore provides not merely a domain reduction technique but a physically interpretable classification of coupled electromechanical modes that facilitates efficient modal identification and resonance tracking in piezoelectric disks and rings. Full article

Introductory and intermediate electrical-engineering education commonly models fundamental circuit and device parameters, including inductance, capacitance, resistance, permeability, permittivity, conductivity, characteristic impedance, transformer turns ratio, machine constants, amplifier gain, resonant frequency, propagation velocity, and mutual inductance, as numerical constants. While this approximation is valid within the intended small-signal operating regime, it becomes methodologically incomplete when these coefficients exhibit measurable state dependence. This paper presents a comparative audit of thirteen such coefficients by systematically contrasting their textbook formulations with the established engineering literature and interpreting the results through two complementary frameworks: the JCGM GUM-6:2020 measurement-model methodology for omitted effects, and the Heckmann–Nye/Gasik multidomain coupling architecture for multi-axis physical interactions. The analysis demonstrates that mainstream engineering practice routinely exploits state-dependent coefficients without invoking new physical laws, and that relaxing the constant-coefficient assumption naturally introduces physically meaningful terms, including the inductive contribution $I\mathrm{d}L/\mathrm{d}t$, the capacitive counterpart $V\mathrm{d}C/\mathrm{d}t$, and the mutual-inductance term $i_2\mathrm{d}M/\mathrm{d}t$. The principal scientific contribution is the development and experimental validation of a unified theoretical and engineering framework for high-power resonant transformers and orthogonal Metglas AMCC-1000 paraformers. The proposed approach combines a new physics-based modal theory of octave ($2:1$) parametric excitation with simultaneous optimization of magnetic-core resonance, electrical resonance, nonlinear inductance modulation, resonant conductor lengths selected as integer multiples of the operating resonant wavelength, multi-stranded high-frequency Litz-wire windings, resonant capacitor synthesis, and the nonlinear magnetic characteristics of the AMCC-1000 amorphous core. The modal analysis demonstrates how coupled resonant eigenmodes and engineered state-dependent inductance can be used to satisfy the conditions for stable octave parametric excitation. Experimental results obtained from both the symmetric two-leg resonant transformer and the orthogonal paraformer are in close agreement with analytical predictions and numerical simulations, thereby validating both the proposed electromagnetic design methodology and the underlying modal theory. Full article

Complex optimization tasks in data-driven prediction and engineering applications often involve nonlinear, multimodal, and ill-conditioned objective functions. This study proposes an Enhanced Moss Growth Optimization algorithm (EMGO), an improved variant of the baseline MGO framework, to enhance exploratory step-size control and local covariance exploitation. EMGO incorporates two key algorithmic augmentations: a budget-adaptive jump regulation mechanism that balances global dispersal and fine-grained refinement, and a shrinkage-regularized covariance-guided sampling operator with relative eigenvalue flooring to exploit correlation structures among elite individuals without rank deficiency. The proposed algorithm is evaluated on the CEC2017 benchmark suite across 50 and 100 dimensions with 29 test functions, 30 independent runs, and a budget of $3\times {10}^5$ function evaluations per run, compared against ten state-of-the-art optimizers including CMA-ES, L-SHADE, SBO, and baseline MGO. Nonparametric Friedman ranking, Holm-adjusted Wilcoxon signed-rank tests, and runtime-matched analyses demonstrate that EMGO achieves highly competitive performance across high-dimensional landscapes. Furthermore, EMGO is applied to tune support vector regression (SVR) hyperparameters for effluent suspended solid (SS) prediction using the UCI Water Treatment Plant dataset under an expanding-window rolling-origin cross-validation scheme. EMGO-SVR achieves superior predictive accuracy ($\mathrm{RMSE}=5.58\pm 0.64$, $\mathrm{MAE}=3.97\pm 0.46$, $R^2=0.889\pm 0.028$), outperforming standard SVR, tree-based ensembles, and Bayesian optimization baselines. SHAP-based feature importance analysis confirms the physical and process consistency of the model predictions. Full article

Conductive polymer gel materials are inherently susceptible to localized overheating during electrical heating owing to spatially nonuniform conductivity distributions, while their internal three-dimensional temperature fields remain challenging to monitor in real time through noncontact means. Traditional inversion methods, such as Tikhonov-LSQR and TV-ADMM, perform frame-by-frame spatial regularization. The former enforces global smoothness, while the latter preserves sharp edges—but neither exploits the temporal evolution of the temperature field governed by the heat conduction equation, leading to unstable reconstructions in deep regions. To address this limitation, we propose a comprehensive methodology for the calibration, reconstruction, and overheating warning of three-dimensional dynamic temperature fields based on the focused light-field infrared camera. A forward electro-thermal coupled heat conduction model is established to characterize the transient temperature evolution within the gel throughout the heating process. Concurrently, a forward imaging model and its corresponding linear system matrix are constructed for focused light-field infrared imaging, enabling the acquisition of infrared light-field images and subsequent reconstruction of the three-dimensional dynamic temperature field. Furthermore, we develop an ETP-Causal LSQR online inversion algorithm tailored for real-time overheating warning during gel heating. Unlike conventional spatial regularization methods, we incorporate a temporal physical prior: the previous reconstruction is propagated through the heat conduction equation to predict the current temperature field, and this prediction is introduced as a soft constraint into the LSQR solver. The algorithm strictly respects causality, using only current measurements and historical reconstructions. Comparative results demonstrate that the proposed method consistently outperforms conventional Tikhonov-LSQR and TV-ADMM algorithms across multiple aspects, including reconstruction accuracy, noise robustness, physical consistency, cross-operating condition generalization, and computational efficiency, thereby validating the effectiveness and broad applicability of the physically constrained causal inversion framework. Full article

In recent years, U-Net-based architectures have been widely applied to polarimetric synthetic aperture radar (PolSAR) semantic segmentation. However, successive downsampling may lead to the loss of fine spatial details, while conventional U-Net-style decoder directly concatenates encoder features with the corresponding decoder features without explicitly accounting for their semantic discrepancy, potentially introducing redundant or irrelevant information and weakening feature discrimination. To address these limitations, this paper proposes a lightweight complex-valued high-resolution U-Net (CV-HRU-Net) with a complex-valued cross-gated attention (CV-CGA) module for PolSAR semantic segmentation. CV-HRU-Net employs a complex-valued high-resolution network (CV-HRNet) as the encoder to maintain high-resolution representations through parallel multi-resolution streams, while a complex-valued U-Net (CV-U-Net) decoder progressively incorporates multi-resolution high-level semantic features for pixel-wise prediction. To improve encoder–decoder feature interaction, CV-CGA adaptively calibrates the core decoder features using encoder information. Specifically, CV-CGA integrates the Convolutional Block Attention Module, Transformer-style cross-attention with decoder features as queries and encoder features as keys and values, and adaptive gated recalibration to enhance semantic selectivity and boundary representation. Experiments on two airborne and two spaceborne PolSAR datasets demonstrate that the proposed network achieves accurate land-cover segmentation and precise boundary delineation by jointly exploiting polarimetric phase relationships, fine spatial details, and multi-resolution semantic information. Furthermore, CV-CGA substantially improves segmentation accuracy and boundary F1 scores while introducing only marginal model-size overhead. Full article

Diabetic retinopathy (DR) is a major retinal disease that can cause visual impairment and irreversible blindness. Accurate automated DR grading is essential for large-scale screening and timely clinical intervention. However, most existing methods rely primarily on visual features for classification. Moreover, they often overlook the ordinal structure of DR severity and the intra-class phenotypic heterogeneity arising from diverse lesion combinations. To address these issues, based on the semantic prior information provided by RetiZero, we propose a text-guided lesion mining vision–language ordinal classification framework for DR grading. The proposed framework introduces a text-guided cross-layer lesion mining module that exploits semantic response differences between normal-tissue and lesion-related textual prompts, thereby guiding multi-level visual patch features toward lesion regions relevant to DR grading. To explicitly model the ordered progression of DR severity, we design a conditional ordinal regression branch and an ordinal distribution alignment strategy that jointly encourage the predictions to follow the inherent order of DR grades. Moreover, we introduce a multi-center feature constraint to capture diverse intra-grade phenotypic patterns and enhance feature discriminability. Experiments on APTOS 2019 show that the proposed method achieves 86.3% accuracy, 90.6% AUC, and 70.9% Macro-F1, which improved by 2.4, 0.7, and 5.5 percentage points compared to RetiZero. Furthermore, under the standardized leave-one-domain-out protocol of GDRNet, the proposed method achieves the highest reported average accuracy of 58.6% across six public DR datasets, exceeding the reported result of PAF (54.6%) by 4.0 percentage points. Nevertheless, our approach is limited in F1 and AUC metrics, for which GDRNet delivers superior performance. These results suggest that the proposed framework can improve DR grading performance and the cross-dataset generalization ability of the model to a certain extent. Full article

In unmanned aerial vehicle inspection of transmission lines, insulators often exhibit arbitrary orientations and elongated shapes and are frequently embedded in complex backgrounds. Horizontal bounding boxes tend to include substantial redundant regions. Meanwhile, existing oriented object detection methods still suffer from angular discontinuities at periodic boundaries, insufficient geometric supervision for rotated bounding boxes, and difficulties in lightweight deployment. To address these issues, this paper proposes a lightweight oriented object detection model, termed R-YOLOv8-PSGH, which integrates dual-frequency phase-shift encoding and Gaussian geometric supervision. Based on a lightweight R-YOLOv8 architecture, a rotated detection head is developed to decouple the predictions of object categories, bounding-box locations, and orientation angles. To improve the periodic continuity of angle representations and strengthen the geometric constraints on rotated bounding boxes, a dual-frequency phase-shift angle encoding strategy and a Gaussian geometric localization loss are designed. Specifically, the complementary relationship between periodic signals with periods of 180°and 90° is exploited to map orientation angles into continuous phase responses, thereby improving the stability of orientation prediction. Moreover, the spatial structure of each rotated bounding box is modeled as a two-dimensional Gaussian distribution, and overlap consistency, center distance, and shape discrepancy are jointly optimized. In this manner, the orientation representation and bounding-box-level geometric supervision are collaboratively enhanced. Experimental results demonstrate that the proposed method improves the detection accuracy and localization stability of rotated objects while maintaining favorable lightweight deployment capability, providing a new solution for lightweight object detection in complex scenarios. Full article

Low-precision floating-point computation has become central to efficient artificial intelligence, yet its behavior for compact transformer-based hyperspectral imaging (HSI) models remains underexplored. In this work, we present a controlled comparative study of fully quantized training (FQT) and post-training quantization (PTQ) for pixel-wise foreign plastic object (FPO) classification in poultry hyperspectral data. Using a fixed state-of-the-art spatial–spectral transformer backbone, a common mixed-precision strategy, and identical training and inference protocols, we evaluate FP32, FP16, BF16, FP8, and NVFP4 across predictive performance, model compression, training efficiency, and inference efficiency. The results show that mixed-precision FQT remains highly robust across the tested precision spectrum, with all reduced-precision configurations staying within 0.63 percentage points of the FP32 baseline in overall accuracy while consistently outperforming PTQ at matched precisions. Across the evaluated formats, BF16 provides the closest accuracy to FP32, whereas FP8 offers a particularly favorable balance between accuracy preservation and reduced precision, while model compression increases progressively to $3.69\times$ under NVFP4. The computational benefits, however, are strongly workload dependent. Native FP8/FP4 hardware support does not automatically improve training throughput for this compact model at moderate workloads, and the larger training batches required to better utilize low-precision hardware can degrade predictive performance. In contrast, large-batch inference can effectively exploit FP8 and NVFP4 without affecting predictive accuracy. An ablation study further shows that selective retention of numerically sensitive modules in FP32 is essential for stable ultra-low-precision operation. Overall, the findings demonstrate that low precision is a viable but workload-dependent design choice for compact HSI transformers, with FQT providing greater accuracy robustness than PTQ and FP8, offering a favorable overall accuracy–efficiency trade-off. Full article

Recent industry reporting indicates that meantime to exploit has become negative in several observed datasets, implying that exploitation may occur before patch availability for some classes of vulnerabilities. Adversarial use of artificial intelligence (AI) is a documented accelerant of this trend. This paper addresses the operational problem that follows in healthcare cybersecurity: the volume and velocity of vulnerability disclosure exceed human analytic capacity, which leads practitioners to under-prioritize, or defer entirely, individual Common Vulnerabilities and Exposures (CVEs) at precisely the moment their risk is rising. The study develops and evaluates a purposeful information technology artifact intended to resolve this problem within a mid-sized United States healthcare system. The artifact is a three-application automated CVE intelligence, prioritization, and remediation-tracking pipeline implemented in Microsoft Azure Logic Apps, integrating the National Vulnerability Database (NVD), the CISA Known Exploited Vulnerabilities (KEV) catalog, the Microsoft Security Response Center (MSRC) CVRF API, Microsoft Defender, Claroty xDome, Microsoft Security Copilot, and ServiceNow, and operationalizing the four risk factors codified in CISA Binding Operational Directive (BOD) 26-04. In naturalistic operations across six CISA Weekly Vulnerability Summary bulletins, the artifact processed 12,855 unique CVE references and reduced them to 1640 environment-relevant findings, an 87.2 percent exposure-first reduction, before expensive per-CVE enrichment and ticketing. The findings indicate that governed automation demonstrably increases CVE coverage, reduces low-value enrichment volume, and produces a deterministic, BOD 26-04-conformant prioritization that is fully traceable in the SharePoint tracker, where every assigned tier is reconstructable from its KEV, ransomware, xDome-exploited, EPSS, CVSS, and exposure inputs. Because no controlled before-and-after time-and-motion study was conducted and no independent ground-truth exploitation labels were collected, three distinct outcomes remain future validation targets rather than demonstrated results: analyst productivity, comparative predictive prioritization accuracy against independent ground-truth exploitation outcomes, and remediation speed. The contribution reported here is therefore operational scale, coverage, and auditable prioritization traceability, not measured improvement in analyst decision-making or patient-safety outcomes. Full article