Search Results (32,972)

Arid and semi-arid regions are critical to terrestrial ecosystems and regional carbon cycle regulation, directly contributing to peak carbon and carbon neutrality goals. However, the fragmented landscapes in these regions pose significant challenges to conventional pixel-based classification, which often struggles with mixed pixel issues and lacks biophysical interpretability. To address these limitations, this study develops an Ecologically Constrained Deep Learning Autoencoder (ECO-DEAU) framework for sub-pixel land cover mapping by integrating biophysical constraints. Specifically, ECO-DEAU employs spectral indices to extract standard spectral signatures for five primary land cover types, which serve as initial weights to guide the autoencoder in estimating fractional abundances. The model was trained across ten representative landscape zones in the Inner Mongolia section of the Yellow River Basin and validated against high-resolution Gaofen-2 data. Results demonstrated that ECO-DEAU yielded an average $R^2$ of 0.687, reaching a maximum $R^2$ of 0.749 in spatially heterogeneous transition zones, representing a substantial improvement over the baseline unconstrained Deep Autoencoder (DEAU). By effectively resolving the blind source separation problem and improving decomposition accuracy, ECO-DEAU serves as a robust tool for addressing mixed pixel challenges in heterogeneous environments, thereby facilitating large-scale, high-resolution carbon sink monitoring. Full article

Traditional craft education relies heavily on hands-on practice; however, novice learners often struggle with procedural complexity, material behavior, and the tacit knowledge typically transmitted through prolonged apprenticeship. This paper presents an integrated framework that combines semantic Knowledge Graphs (KGs), real-time Finite Element Method (FEM) simulation, and high-fidelity physically based rendering (PBR) to support the teaching, understanding, and preservation of traditional crafts. Craft processes are modelled as ontologically grounded KGs that capture tools, materials, actions, decision points, and common procedural errors through an extensible representation aligned with CIDOC-CRM. These semantic structures drive an interactive FEM-based simulation that enables learners to enact craft actions in a virtual environment while receiving predictive feedback and corrective guidance derived from expert-defined execution parameters. The resulting workpiece states are visualized using PBR techniques, providing perceptually accurate cues essential for assessing surface changes, deformation patterns, and material conditions. The methodology is embedded within an eLearning ecosystem that supports the generation of structured courses, multimodal exemplars, and instructional design informed by Cognitive Load Theory. A use case involving wood and aluminum carving demonstrates the system’s ability to simulate realistic tool–material interactions and produce visually interpretable outcomes. The results indicate that coupling executable semantic knowledge modelling with physically grounded simulation offers a viable pathway toward scalable, safe, and contextually rich craft training while supporting the long-term preservation of domain expertise. Full article

In Social Internet of Vehicles (SIoV) environments, fog computing plays a crucial role in supporting real-time services by reducing the latency inherent in cloud-based architectures. However, fog nodes are typically deployed in physically exposed roadside environments and can be operated by several system operators, making them vulnerable to physical compromise and unauthorized access. Despite these threats, many existing authentication schemes assume fog nodes to be fully trusted or honest-but-curious, allowing them to decrypt transmitted data using a session key shared among vehicles, fog nodes, and cloud servers. To overcome these limitations, this paper proposes a quantum-secure pairwise key agreement scheme that establishes distinct session keys for vehicle–fog, fog–cloud, and vehicle–cloud communications. This design effectively prevents the disclosure of sensitive information even in the event of fog node compromise. Furthermore, Physical Unclonable Functions (PUFs) are employed to mitigate physical capture attacks, while lattice-based cryptography based on the Module Learning with Errors (MLWE) problem is integrated to ensure resistance against quantum computing attacks. The security of the proposed protocol is rigorously validated through formal analysis using AVISPA, BAN logic, and the Real-or-Random (RoR) model, in addition to informal security analysis. Comparative performance evaluations against related schemes demonstrate that the proposed approach achieves a balance between efficiency and security, making it well suited for practical deployment in SIoV environments. Full article

Unsaturated polyester resin (UPR)–quartz composites have become increasingly important in structural, sanitary, and architectural applications. However, their manufacturing processes still rely heavily on empirical knowledge. This review compiles recent developments in materials science, curing kinetics, and digital manufacturing, outlining a pathway toward data-driven, adaptive production of quartz-filled thermosets. The chemical and physical fundamentals of UPR polymerization are summarized, including the influence of initiator systems, filler characteristics, and thermal management on network formation. Challenges associated with highly filled formulations—such as viscosity control, dispersion, shrinkage, and exothermic peak prediction—are discussed in detail. Recent advances in digital twins (DTs) and artificial intelligence (AI) are reviewed, demonstrating how physics-based simulations, machine learning models, and hybrid mechanistic–data-driven approaches improve the prediction of rheology, curing behavior, and quality outcomes in thermoset polymer processes. A practical application example demonstrates the prediction of peak time in quartz–UPR composites using Random Forest and Gradient Boosting ensemble models. Two prediction scenarios are evaluated: Scenario A with gel time by Leave-One-Out cross-validation, and Scenario B without gel time, representing post-mixing and pre-process prediction contexts, respectively. Stratified bootstrap augmentation improves Gradient Boosting in both scenarios. Principal component analysis confirms that the curing process is governed by three independent physical dimensions: curing reactivity, thermal environment and resin thermal state. Full article

Emotion classification is a fundamental task in affective computing, with applications in human–computer interaction, mental health monitoring, and social media analysis. Although most existing methods formulate it as a flat classification problem, emotional expressions are inherently structured and grounded in semantic roles such as the emotion cue, stimulus, experiencer, and target. However, the relative contribution of these roles to emotion inference has not been systematically examined. Unlike prior models, we propose RolEmo, a role-aware framework for emotion classification that explicitly incorporates semantic role information. The framework employs a controlled role-masking strategy to analyze the contribution of individual roles, augments textual representations with external commonsense knowledge to capture implicit affective context, and applies supervised contrastive learning to structure the embedding space by bringing emotionally similar instances closer while separating opposing ones. We evaluate RolEmo on three benchmark datasets annotated with semantic roles. Experimental results demonstrate that RolEmo outperforms the strongest baseline across three datasets by up to $16.4\%$, $25.8\%$, and $23.2\%$ in the Full Text, Only Role, and Without Role settings, respectively. The analysis further indicates that the cue and stimulus roles provide the most reliable signals for emotion classification, with their removal causing performance drops of up to $6.2\%$ in macro f1-score, while experiencer and target roles exhibit more variable effects. These findings highlight the importance of structured semantic modeling and commonsense reasoning for robust and interpretable emotion understanding. Full article

Pricing multi-peril agricultural insurance under compound climate hazards demands a framework that captures stochastic dependence among heterogeneous perils, accommodates non-stationary loss dynamics, and supports adaptive policy optimisation. We demonstrate that backward stochastic differential equations, combined with copula dependence, recurrent neural networks, and reinforcement learning, provide a unifying language for this task; the contribution lies in their principled integration. The dynamic premium is the unique adapted solution of a BSDE whose driver encodes compound-risk dependence through a Student-t copula, forward loss dynamics through a jump-diffusion process, and a green-finance adjustment through an optimal control variable. Within this framework we derive three progressive results by adapting standard BSDE theory to the compound-dependence and policy-control setting. First, existence and uniqueness hold under Lipschitz and square-integrability conditions. Second, a comparison theorem guarantees that a larger correlation matrix yields higher premiums; the degrees-of-freedom effect enters separately through the risk-loading magnitude. Third, the Euler discretisation converges at a rate of one half of the time-step size, with copula estimation, LSTM conditional expectation approximation, and Q-learning HJB solution as sequential components. Applied to eleven Zhejiang cities (2014–2023, $N\times T=110$), in this illustrative application the framework reduces premium variance by 43.5 percent (bootstrap 95% CI: $[38.2\%,48.7\%]$) while maintaining actuarial adequacy with a mean loss ratio of 0.678, though the modest sample size warrants caution in generalising these findings. Each component contributes statistically significant improvements confirmed by the Friedman test at the 0.1 percent significance level. Full article

Global research on social–emotional learning (SEL) demonstrates robust benefits for student well-being and academic outcomes, yet SEL is still largely treated as gender and culturally neutral, with little attention to how it intersects with locally specific constructions of masculinity. We address this gap through a qualitative study in three urban secondary schools in Khyber Pakhtunkhwa, Pakistan, combining focus groups with boys aged 13–16 (n = 18), student interviews (n = 10), and teacher/counsellor interviews (n = 10). Using critical masculinity theory, the sociology of emotions, and transformative SEL, a reflexive thematic analysis identifies four patterns: (i) sadness and fear framed as status risks while anger signals strength, (ii) “switching off” feelings as masculinized emotion work tied to locally valued ideals of sabar (endurance) and izzat (honour), (iii) fragile “islands of care” where privacy and dignity enable conditional vulnerability, and (iv) SEL-like practices fostering empathy but also reinforcing stigma when emotions are labelled unmanly. We argue that SEL is a contested site where masculinities are reproduced and renegotiated, and we propose five findings-grounded design principles, including graduated emotional entry points, anti-ridicule norms, and indirect pedagogy for gender-attentive SEL that reduces stigma and supports non-violent masculinities in Pakistani secondary schooling. Full article

Floating offshore wind turbines (FOWTs) exhibit complex motions under marine environmental loads and frequently undergo coupled oscillations across multiple degrees of freedom (DOFs). Accurate short-term motion prediction of these responses is crucial for operational safety and maintenance. To overcome the limitations of traditional “black-box” models under complex aero-hydrodynamic loads, this study proposes STL–TimesNet–NLinear, a novel physics-informed deep learning framework. The framework utilizes STL decomposition to explicitly decouple motion signals: NLinear captures non-stationary low-frequency slow drifts, while TimesNet extracts multi-periodic wave-frequency responses. The model was evaluated across different platform typologies—a 5 MW semi-submersible and a larger-scale 15 MW Spar-type platform—under various typical operational and extreme environmental conditions. Model performance was evaluated using comparative and ablation experiments. At a prediction-ahead time (PAT) of 5 s, the proposed model achieves coefficients of determination (R²) exceeding 0.95. Even at longer PATs, the R² remains above 0.90, consistently outperforming multiple benchmark models. Compared to traditional recurrent neural networks (e.g., LSTM), it decreases the Mean Absolute Error (MAE) for pitch motion under extreme sea states by 54.7% and increases the R² to 0.9573. Furthermore, the inference latency is only 2.4 ms per step. These findings confirm that the proposed STL–TimesNet–NLinear model provides fast and accurate solutions for the short-term motion response prediction of FOWTs, demonstrating valuable potential applications for enhancing the safety planning of offshore wind turbine operation and maintenance. Full article

Background/Objectives: Federated learning has emerged as a promising paradigm for enabling collaborative artificial intelligence in healthcare while preserving data privacy. However, most existing frameworks focus on isolated tasks and lack integrated pipelines that combine classification, segmentation, explainability, and automated clinical reporting. Methods: This study proposes FedIHRAS, a privacy-preserving federated learning framework designed for multi-institutional radiological analysis. The system integrates multi-task deep learning modules, including pathology classification using a modified ResNet-50 backbone, anatomical segmentation, explainability through Grad-CAM, and automated report generation supported by semantic aggregation using SNOMED CT. The framework employs confidence-weighted aggregation, differential privacy mechanisms, and secure aggregation protocols to ensure privacy and robustness across heterogeneous institutional datasets. Results: Experimental evaluation was conducted across four large-scale chest X-ray datasets representing simulated institutional nodes, totaling approximately 874,000 images. FedIHRAS achieved high diagnostic performance with strong cross-institutional generalization and demonstrated improved robustness under non-IID data distributions. Additional experiments showed favorable communication efficiency, effective privacy–utility trade-offs, and strong agreement with expert radiologist assessments. Conclusion: The proposed FedIHRAS framework demonstrates that federated learning can support scalable, privacy-preserving, and clinically meaningful radiological AI systems. By integrating multi-task learning, explainability, and automated reporting within a unified federated architecture, the framework addresses key limitations of existing approaches and contributes to the development of collaborative AI in healthcare. Full article

Hyperspectral image (HSI) classification faces the challenges of scarce labeled data and severe class imbalance, which limits the effective training and generalization capabilities of models. To address these issues, we propose S2A-Swin, a joint spatial–spectral hybrid Swin Transformer framework. First, we develop a spectral–spatial conditional generative adversarial network (SSC-cGAN), which combines spectral and spatial smoothing regularizers to synthesize class-specific image patches, thus alleviating the problems of data scarcity and class imbalance while maintaining spectral continuity and local spatial structure consistent with real data. Second, we introduce a dimension-aware hybrid Transformer module, which adds local windows along the spectral dimension to the standard spatial window, thereby facilitating cross-dimensional feature interactions and ensuring that each spectral band is modeled using the local spatial context for more efficient joint spatial–spectral modeling. In this module, attention mechanisms for spectral and spatial windows are applied alternately (“cross-sequence” attention mechanisms), the execution order of which is guided by hyperspectral prior knowledge to enhance cross-dimensional representation learning. This module is embedded in the lightweight Swin backbone and extends the traditional spatial window mechanism through spectral window attention, capturing spectral continuity while maintaining spatial structure consistency. Extensive experiments on multiple datasets demonstrate that, compared to mainstream CNN and Transformer baselines on four benchmark datasets, the proposed method achieves overall accuracy (OA) improvements of 2.45%, 7.05%, 5.17%, and 0.85%. Full article

Robotic pipe welding represents a key and rapidly evolving technology for the automation of pipe and pipe-joint welding processes with standard, intersecting, and complex geometries. This review analyses 84 studies published over the past three decades, categorising them into four primary research areas: general pipe welding, intersecting pipes, boiler and tube-to-tubesheet welding, and control and modelling. Two separate comparative analyses were conducted: one within intersecting pipe research and another within the control and modelling category. The aggregated findings reveal consistent, complementary patterns: simulation and laboratory experiments clearly dominate validation methods, while industrial-scale evaluations remain scarce. The results further demonstrate that control strategies, sensor integration, and validation levels are strongly interconnected, collectively determining system performance, reliability, and practical applicability. Despite significant progress, challenges remain, including system integration complexity, limited robustness in variable industrial environments, insufficient real-time adaptive control, and inconsistent quantitative performance evaluation. Further research should prioritise the development of digital twins, human–robot collaboration, multi-sensor fusion, reinforcement learning-based adaptive control, and scalable industrial deployment. This review provides an overview of current progress and outlines key directions for developing intelligent and reliable robotic pipe welding systems. Full article

This work proposes a hybrid Uzbek sentiment analysis model (sometimes referred to as tonality analysis in the local literature) that integrates contextual text representations with named-entity information from an NER module and emoji-based emotional cues that are common in short online messages. To provide a comprehensive baseline comparison, we evaluate seven approaches—SVM, LSTM, mBERT, XLM-RoBERTa-base, mDeBERTa-v3, LaBSE, and the proposed hybrid model—covering both classical machine learning and modern multilingual transformer architectures for low-resource sentiment tasks. The overall pipeline begins with Uzbek-specific text normalization to reduce noise from informal spellings, transliteration variants, and inconsistent apostrophe usage. In parallel, the system performs explicit emoji extraction to capture affective signals that are often expressed non-verbally in social media texts. Next, we construct three complementary feature streams: a context encoder for sentence-level semantics, NER-driven entity features that encode entity mentions and types, and an emotion module that models emoji priors and their interaction with contextual meaning. These streams are fused into a unified representation and fed to a final classifier to predict sentiment polarity. Experiments on an Uzbek test set demonstrate that the hybrid model reaches an F1-score of 0.92, consistently outperforming text-only baselines. The results indicate that entity-aware and emoji-informed features improve robustness under sarcasm/irony, mixed sentiment with multiple targets, and orthographic noise, making the approach suitable for social media analytics, public opinion monitoring, customer feedback triage, and recommendation-oriented text mining. Full article

The modeling and control of photovoltaic and other engineering systems highly depend on the accuracy of parameter identification. However, parameter extraction for photovoltaic equivalent models typically presents a high-dimensional, strongly nonlinear, and multimodal global optimization problem. Traditional analytical or gradient-based methods are sensitive to initial values and easily fall into local optima. To address this issue, this paper proposes a multi-strategy improvement teaching–learning-based optimization algorithm (SNTLBO). A social learning network structure with symmetric interaction topology is introduced into the classical TLBO framework to characterize the knowledge propagation relationships among individuals. Through this symmetric and balanced information exchange mechanism, learners can be guided not only by the teacher but also by multiple neighbors within the network, enabling more diverse and symmetric exploration of the search space and enhancing population diversity and global search capability. Furthermore, a teacher reputation mechanism is constructed, where historical performance is used to weight teacher influence, strengthening the guidance of high-quality solutions and accelerating convergence. Meanwhile, an adaptive teaching factor is designed to dynamically adjust the teaching intensity based on the distance between the teacher and students in the solution space, maintaining a dynamic balance (symmetry) between exploration and exploitation. To evaluate the performance of the proposed algorithm, SNTLBO is systematically compared with 11 advanced optimization algorithms on two benchmark test suites, CEC2017 (30D, 50D) and CEC2022 (10D, 20D). Non-parametric statistical tests are conducted to assess significance. The results demonstrate that SNTLBO shows competitive advantages in terms of convergence speed, solution accuracy, and stability. Finally, SNTLBO is applied to the parameter estimation of single-diode, double-diode, triple-diode, quadruple-diode, and photovoltaic module models. Experimental results show that the proposed algorithm achieves higher identification accuracy and robustness in terms of RMSE, IAE, and I–V/P–V curve fitting, verifying its effectiveness and practical value for complex global optimization and practical engineering applications. Full article

Background/Objectives: People with mobility limitations face disproportionately high rates of chronic health conditions and demonstrate lower adherence to wellness interventions. Digital programs such as MENTOR offer accessible alternatives but often face high rates of attrition. This study applied machine learning (ML) methods to predict adherence to the eight-week MENTOR telewellness program and identify key predictors of participant attendance. Methods: Data were drawn from 1218 adults enrolled in MENTOR (2023–2024). Adherence was defined as the percentage of 40 sessions attended. Baseline demographic, socioeconomic, psychosocial, mindfulness, resilience, health status, and physical activity variables were included as predictors. Following preprocessing and imputation, 13 ML regression models were trained using an 80/20 train–test split. The best-performing model was identified using mean absolute error (MAE), followed by feature selection and SHAP interpretability analyses. Pairwise synergy analysis quantified interactions between top predictors. Results: Model performance was modest overall. Bayesian ridge regression achieved the best performance (MAE 20.98; RMSE 25.26; R² = 0.12). SHAP analyses revealed that education, race, emotional support, Area Deprivation Index, household size, mindfulness, life satisfaction, and disability onset were the strongest predictors of adherence. Higher emotional support, mindfulness, and life satisfaction were associated with greater adherence, while socioeconomic disadvantage predicted lower adherence. Synergy analyses showed the strongest predictive interactions between low education and psychosocial resources (emotional support and life satisfaction). Conclusions: Baseline characteristics alone modestly predicted adherence to a digital wellness program. However, psychosocial and socioeconomic factors emerged as meaningful predictors, underscoring the need for personalized support strategies to reduce dropout among participants with mobility limitations. Full article

On 12 July 2016, the ruling on the South China Sea Arbitration was announced and rapidly drew worldwide attention, turning the event into a major international hotspot. Quantifying the dynamics of such hotspot events and understanding the evolution of media-based inter-actor networks during major shocks are of substantial research interest. Viewing these interactions as dynamic networks, we analyze the time-varying actor interaction structure surrounding the arbitration using the Global Database of Events, Location and Tone (GDELT), a large-scale media-based event database with global coverage since 1979. We extract nearly 30,000 events related to the arbitration from 5 July to 25 July 2016, constructing daily cooperation and conflict networks to quantify structural changes via network size and degree-entropy dynamics. To further reveal actor-level structural roles, we learn node embeddings on each daily network via an entropy-driven graph representation learning scheme and perform embedding-based clustering with automatically selected cluster numbers, visualized via t-SNE. The results show that key dates in the event window are associated with pronounced structural shifts in the networks, including changes in participation breadth, degree-distribution heterogeneity, and clearer differentiation and reconfiguration of actor roles, with distinct patterns between cooperation and conflict networks. These findings demonstrate the potential of massive media event data for characterizing structural responses and actor-role evolution in event-driven inter-actor networks. Full article