Search Results (8,449)

Accurate tropical cyclone (TC) track prediction remains challenging, as numerical models suffer from high computational cost, substantial storage requirements, and physical parameterization uncertainties, while data-driven large AI models depend heavily on training data volume and high-resolution inputs, resulting in prohibitive computational overhead. To address these issues, this paper proposes TCN-GAN-DM, a three-stage deep learning framework based on the China Meteorological Administration (CMA) Tropical Cyclone Best Track Dataset. Specifically, a dual-stream temporal convolutional network (TCN) first extracts temporal features from track and meteorological sequences, respectively. A generative adversarial network (GAN) then takes these features and produces multiple physically plausible candidate tracks via noise injection. Finally, a conditional diffusion model (DM) refines the predicted positions through progressive denoising. Experimental results for TCs in 2024 show that under the fair deterministic comparison using a single fixed candidate, the model achieves a 6 h track error of 49.10 km, which is comparable to CMA-GFS (49.75 km) and HWRF (44.34 km), and substantially lower than the large AI model FuXi (120.44 km). When evaluating the oracle metric (best-of-K, K = 6) as an upper bound of coverage, the model achieves the smallest errors among all models at 6 h (24.04 km) and 12 h (55.81 km). In addition, the proposed model has advantages over CMA-GFS, HWRF, and FuXi in terms of computational resource consumption and hardware deployment cost. However, its mean track error increases more rapidly beyond 12 h, and at lead times of 18 h and 24 h the model is outperformed by HWRF, FuXi, and CMA-GFS, indicating that its current strength lies primarily in short-term prediction. Consequently, the practical utility of TCN-GAN-DM is currently demonstrated for 6–12 h TC track prediction, offering a new solution for disaster prevention and mitigation that balances accuracy and deployment cost at these specific time scales. Full article

The Internet of Vehicles (IoV) is reshaping intelligent transportation through pervasive connectivity, real-time data exchange, cooperative perception, and vehicle–edge–cloud services, while also expanding cybersecurity and privacy risks across heterogeneous cyber–physical environments. This paper presents a PRISMA 2020-informed systematic review of IoV security and privacy protection research. A cross-layer and lifecycle-oriented analytical framework is developed by integrating a four-layer IoV architecture—sensing layer, network access layer, coordinative computing layer, and application layer—with a five-stage data lifecycle covering data collection, transmission, storage, usage, and disposal. Based on this framework, the paper examines representative threat surfaces, vehicle-to-everything (V2X) communication security, public key infrastructure (PKI) based authentication, trust management, privacy-preserving data sharing, intrusion detection, active defense, and AI-assisted security analytics. Privacy-preserving mechanisms, including differential privacy, federated learning, blockchain, homomorphic encryption, and secure multi-party computation, are further compared in terms of deployment layer, lifecycle stage, real-time suitability, and representative performance evidence. In addition, the review discusses the engineering relevance of UNECE WP.29 R155/R156, ISO/SAE 21434, and related national standards, with emphasis on compliance evidence, over-the-air (OTA) governance, supply-chain coordination, and lifecycle cybersecurity management. The review shows that no single protection mechanism can simultaneously satisfy the requirements of real-time performance, scalability, privacy preservation, trustworthiness, and regulatory compliance in dynamic IoV environments. Future research should emphasize lightweight and adaptive protection, cross-layer trust coordination, privacy–utility co-optimization, trustworthy AI-assisted security operations, and evidence-based lifecycle governance. This review provides a structured reference for researchers and a practical basis for secure and privacy-aware IoV system design. Full article

A novel modified generalized Riccati equation mapping neural network-based approach is the basic theme of this study by exploring the nonlinear dynamical characteristics of the the strain wave model’s soliton solutions, which govern wave propagation in micro structured solids. Strain waves are particularly intriguing, since they preserve their form and speed throughout transmission. The nonlinear dynamical behaviors of strain waves may be modeled by partial differential equations in micro structured materials. In the realm of micro structured solids, there exists a class of phenomena that are referred to as micro strain waves. These waves arise in solids possessing intricate internal architectures, including periodic lattices, precisely engineered metamaterials Understanding these waves is key to designing more complex materials and new acoustic technologies. The activation function and the weight function of the neural network are assigned to each input layer, hidden layer and output layer and the neural network itself is a multi-layer computational network. Using the structure of the neural network, every neuron in the first hidden layer is given solutions to the Riccati equation, and the new highly expressive trial functions are generated in a systematic way. In this way, a large variety of exact soliton solutions are obtained, such as bright, dark, kink, and combined solitons as well as periodic and hyperbolic wave profiles. The influence of the essential physical and mathematical parameters is explored systematically using three-dimensional, two-dimensional and contour visualizations, which illustrate how parameter variations lead to changes in the amplitude, shape and stability of the wave structures. The solutions presented reveal the dynamic properties of micro strain solitons which leads to new avenues of investigation in the study of related nonlinear phenomena in micro structured solids. In a broader context, our results highlight the great potential of analytical techniques using neural networks as a powerful and versatile toolset to study complex nonlinear wave models within the applied sciences from acoustics to photonics to smart materials engineering. Full article

Human digital twins (HDTs) are patient-specific computational models that combine medical imaging, physiological measurements and predictive algorithms. They are moving from an exciting concept to a realistic clinical opportunity. The key question is no longer whether HDTs can be built. The key question is which methods are mature enough to support clinical decisions and what is still missing for routine use. This systematic review maps the methodological landscape of HDTs and highlights practical bottlenecks that limit clinical translation. A PRISMA 2020 guided search of PubMed, Scopus, IEEE Xplore, and the Cochrane Library, covering publications from 2016 to 2026, identified 151 eligible studies. Bibliometric mapping and thematic synthesis were used to characterize research clusters, computational paradigms, and collaboration patterns. Three dominant application streams were identified: cardiovascular HDTs for hemodynamic simulation and procedural planning, musculoskeletal HDTs for biomechanics-driven orthopedic innovation, and neurological HDTs integrating neuroimaging with computational neuroscience. Across domains, the strongest technical trend is the rise in hybrid pipelines that combine physics-based simulation, including finite element and computational fluid dynamics models, with machine learning for segmentation, parameter identification, reduced-order modeling, and faster inference. However, reporting of verification, validation, uncertainty quantification, and explicit context of use remains uneven and prospective clinical evidence is still limited. Overall, the literature shows rapid progress toward clinically credible HDTs, while highlighting the need for scalable computation, standardized credibility pipelines, and workflow-integrated platforms to support safe and reproducible clinical adoption. Full article

In hepatocellular carcinoma (HepG2), aberrant histone modifications are closely linked to long non-coding RNA (lncRNA) expression. However, existing computational models lack physical interpretability at specific promoter coordinates. To address this, we developed a position-specific statistical scoring model based on adjacent and next-adjacent nucleotide frequencies. We trained two independent, position-specific matrices representing increased and decreased modification states across 600 bp promoter windows centered on the true signal summits. Finally, ten-fold cross-validation revealed that significant energy differences between sequences with increased and decreased histone signals enable excellent classification performance. These results indicted a strong correlation between the total energy of local DNA structures and histone modification signal. Full article

Background/Objectives: Parkinson’s disease (PD) is increasingly recognized as a multisystem disorder affecting perceptual, emotional, and reward-related processes. While arts-based interventions in PD have primarily focused on active creative arts engagement, it remains unclear whether receptive arts engagement with visual art—how artworks are perceived and evaluated—is altered. Our objective is to determine whether aesthetic evaluation of visual artworks differs in individuals with PD compared to age-matched healthy controls. We further examine whether emotional interpretation, color-emotion associations, and experiential responses to art viewing are altered. Methods: In a cross-sectional case–control study, individuals with PD (n = 87) and age-matched healthy controls (n = 49) completed two online assessments. Participants evaluated 36 artworks from the Vienna Art Picture System in terms of liking, beauty, and subjective art attributes. Objective image-derived features were computed for each artwork. Interpretable machine learning models were used to test whether evaluation patterns predicted diagnostic group and to identify determinants of aesthetic judgments. Participants further completed a color-emotion association task using ambiguous expressive portraits and reported perceived changes in cognitive, emotional, motivational, and physical states following art viewing. Results: Aesthetic evaluation patterns did not support reliable classification of PD status, indicating no systematic group differences in liking, beauty, or attribute-based judgments between PD and controls. Instead, aesthetic judgments were robustly predicted by individual differences and objective artwork properties, including art-historical style, symmetry, complexity, and color-related features, whereas diagnostic group, gender, and age did not contribute to predictions. Emotional interpretation and color-emotion associations were largely comparable between groups, with a single specific deviation in color-emotion mapping. Positive emotions were less frequently associated with pink in people with PD. Self-reported experiential responses to art viewing did not differ significantly between groups. Conclusions: Aesthetic evaluation of visual artworks appears largely preserved in people with PD. These findings suggest that, in digital viewing contexts, substantial adaptation of visual content to make it accessible for people with PD may not be necessary, although subtle perceptual and emotional differences may still be relevant. Efforts may instead be better directed toward addressing practical barriers to visual art engagement. Full article

The evaluation of wearable robotic systems remains a challenge, particularly in real-world environments where laboratory-based methods are impractical. Existing approaches rely on external instrumentation, such as surface electromyography (sEMG) or motion capture, which are difficult to deploy continuously and do not directly measure key internal metrics such as joint loading or spinal forces. This work introduces a new paradigm for exoskeleton evaluation in which biomechanical assessment is embedded directly within the device’s sensing and computational architecture. We present the ExoMetrix system, a platform that integrates onboard sensing, real-time data acquisition, cloud-based processing, and user-facing analytics into a unified workflow for continuous evaluation of human–exoskeleton interaction. Sensor data from the device are streamed and processed using physics-based models. The resulting outputs are translated into estimates of internal biomechanical quantities, including joint torques, spinal compression and shear forces, and muscle loading. By enabling real-time feedback and longitudinal monitoring without external instrumentation, this approach transforms evaluation from an external, episodic process into an embedded and continuous capability, supporting safer and more scalable deployment of exoskeleton technologies. Full article

Centrifugal compressors are critical assets in the oil and gas, petrochemical, and power generation industries, where unplanned downtime results in severe economic and safety consequences. Despite the application of digital twin technology for predictive maintenance, existing approaches struggle to combine accurate degradation modeling with formal assurance evidence that regulators and operators demand before trusting machine learning-augmented systems. This paper proposes a hybrid digital twin framework whose architecture is structured around a formal safety case template, addressing both the accuracy and the trustworthiness challenges simultaneously. The methodology couples a first-principles thermodynamic model with a neural-network residual learner, and the complete system is organized through a design-stage safety case constructed in Goal Structuring Notation. The design stage identifies the requirements for operational deployment. Validation through a simulation study on a one-year synthetic operational dataset shows that the hybrid model reduces root-mean-square prediction error by over 50% for both pressure ratio and polytropic efficiency compared to the physics-only baseline. The anomaly detection module, presented here as a proof of concept, achieves 92% recall in identifying injected faults, and a composite health index tracks the progression of fouling, erosion, and seal wear over the simulated service life. This study is purely theoretical, with no experimental measurements conducted. It demonstrates the structural viability and coherence of the proposed framework within a controlled environment, providing a solid theoretical and computational foundation for future physical validation efforts. These findings provide preliminary evidence that embedding a structured safety argument into the design of a hybrid digital twin is technically feasible and beneficial for building the confidence needed to deploy such systems in safety-critical industrial environments. Full article

Predicting thermal breakthrough and optimizing injection-production parameters are essential for sustainable geothermal development. Traditional hydrothermal coupled simulations in porous media entail substantial computational costs, which limits their use in dense multi-parameter screening. This study develops a physics-constrained surrogate workflow for the Qihe geothermal doublet system by using COMSOL to generate hydrothermal simulation data and a deep neural network (DNN) to emulate the simulator response within a predefined operating domain. The DNN was trained on physics-driven synthetic outputs rather than independent field observations, and a 2.0 °C decrease in production temperature was used as the thermal breakthrough criterion. Under scenario-wise validation, the surrogate model achieved a test-set R² of 0.9995 and an RMSE of 0.0351 °C, indicating accurate approximation of the deterministic simulator response within the bounded parameter space. The surrogate-based global scan identified a favorable operating region near a well spacing of 462 m, a reinjection temperature of 20 °C, and a reinjection rate of 150 m³/h. To evaluate whether this result was affected by sparse well-spacing sampling, additional COMSOL simulations were performed at 430, 440, 450, 460, 462, 470, 480, 490, and 500 m under the same reinjection temperature and rate. These simulator-based validation cases showed a continuous thermal response with increasing well spacing. The 2.0 °C thermal breakthrough time increased from 46 yr at 430 m to 61 yr at 500 m, while the 50-year cumulative heat extraction increased from 6594.2 to 6722.9 TJ. The 430 and 440 m cases experienced thermal breakthrough before the 50-year design life, whereas the 450 m case was close to the design boundary. The 460 and 462 m cases did not reach the 2.0 °C decline threshold within the 50-year design life and retained relatively high heat-extraction efficiency per unit well spacing. Therefore, the engineering recommendation is revised from a single precise optimum to a locally validated spacing interval of approximately 460–462 m under the present equivalent-porous-medium assumption. The proposed workflow does not replace hydrothermal simulation; instead, it provides a rapid screening tool that narrows the design space before targeted simulator verification and field calibration. Full article

This paper provides a systematic synthesis of recent developments in physics-informed neural networks (PINNs) applied to aerospace engineering, with an emphasis on their role in physically consistent surrogate modeling, forward simulation, and inverse parameter estimation. Using a PRISMA-based methodology, the study surveys peer-reviewed works published between 2017 and 2025 across aviation- and space-related domains, including aerodynamics, structural mechanics, aeroelasticity, propulsion, control, structural health monitoring, satellite-orbit prediction, space-debris collision avoidance, and spacecraft radiation-impact modeling. The analysis shows that embedding governing equations, boundary conditions, and observational data into composite loss functions enables PINNs to improve predictive consistency, reduce dependence on dense simulation or experimental datasets, and support parameter identification under sparse or noisy measurements. Attention is given to architectural variants such as XPINNs, cPINNs, gPINNs, operator-learning approaches, and hybrid PINN-CFD/FEM formulations, as well as to training strategies based on adaptive sampling, domain decomposition, transfer learning, and dynamic loss weighting. Reported benefits include reduced approximation error, improved convergence in selected high-gradient or multiphysics problems, and enhanced interpretability compared with purely data-driven models. At the same time, the review identifies persistent open challenges, including scalability to large aerospace domains, sensitivity to loss-weighting and collocation strategies, limited robustness under noise and uncertainty, high computational cost, and the lack of standardized aerospace benchmarks. Overall, the review highlights PINNs as a promising but still developing framework for fast, interpretable, and physically consistent modeling of aircraft and spacecraft systems. Full article

Introduction: Fish skin is the first line of defense against the aquatic environment, acting as a physical, chemical, and immunological barrier. In addition to preventing pathogen entry, the skin and its mucus contribute to osmoregulation, innate immunity, and redox balance. Skin lesions—caused by mechanical damage, parasites, environmental stress, or handling—disrupt this barrier, increasing susceptibility to infections, inflammation, and production losses. Thus, efficient skin regeneration is essential for fish welfare and performance. Nutrition plays a key role in this process by providing substrates for epithelial repair, immune function, and antioxidant defense. Among dietary factors, zinc (Zn) is particularly important due to its involvement in cell proliferation, enzymatic activity, and maintenance of skin integrity. Objective: Our objective is to assess the effectiveness of image-based analysis in quantifying the skin healing process in Atlantic salmon fed diets supplemented with zinc. Methodology: The trial comprised three dietary treatments: a control diet with 42 mg Zn per kg (D1), and two diets supplemented up to 120 mg/kg of zinc, derived from inorganic (D2) or organic (D3) forms. Pit-tagged fish with an initial body weight (78 ± 0.1 g) were fed the diets for 75 days. After 15 days of experimental feeding, a standardized wound lesion (2.5 mm diameter × 0.5 mm depth) was inflicted in deeply anesthetized fish, with a disposable biopsy punch, in the dorsal area. After wound infliction, the fish resumed their normal feeding regime for the rest of the trial days. The progression of skin wound healing was assessed using standardized digital image analysis. High-resolution photographs of individual wounds were collected 8, 16, 24 and 32 days post-wounding. All images were acquired under standardized conditions with the inclusion of ArUco identifiers to enable a subsequent computer-assisted comparison. Morphometric parameters (wound width, diameter, perimeter and area) were used to assess wound contraction and closure over time. In parallel, a semi-quantitative visual scoring system was applied to each wound image to capture qualitative aspects of healing that are not fully described by morphometric data alone. Results: Full data analysis is currently underway, but the first results show beneficial effects of dietary zinc supplementation on the skin regenerative process. Conclusions: The combined use of objective digital measurements and standardized visual scoring enabled a comprehensive evaluation of wound healing progress, bridging quantitative tissue remodeling with biologically relevant phenotypic outcomes. This image-based framework provides a sensitive and reproducible approach for assessing dietary interventions targeting skin regeneration and barrier restoration in Atlantic salmon. Full article

Bitter phytochemicals, including alkaloids, terpenoids, and bitter glycosides, are abundant in medicinal food plants and exhibit well-documented anti-inflammatory, hypoglycemic, and other bioactivities relevant to human health. However, the inherent bitterness of these compounds presents a significant sensory barrier to patient compliance and limits their application as functional food ingredients. This review provides a comprehensive and interdisciplinary synthesis of current knowledge on bitter compounds in medicinal food plants, integrating perspectives from phytochemistry, molecular pharmacology, and sensory science. We summarize the major chemical classes of bitter phytochemicals, critically evaluate methods for their isolation and identification—from classical sensory-guided fractionation to modern computational approaches such as molecular docking and metabolomics—and analyze three principal strategies for bitterness regulation: physical removal, biological transformation, and sensory modulation (including molecular inclusion and TAS2R receptor blocking). We also briefly touch upon the extraoral expression of TAS2Rs and there suggested links to local immune responses and metabolic regulation, noting that this may be relevant to the concept of “taste–bioactivity homology.” The review further highlights ongoing challenges, such as the identification of unknown bitter compounds and the lack of standardized sensory evaluation systems, and outlines possible directions for improving bitterness analysis and regulation in medicinal food plants. Full article

Artificial intelligence (AI) is increasingly influencing nanopharmaceutical development by supporting the transition from empirical formulation screening toward predictive, data-driven, and translationally oriented design. Nanocarrier-based therapeutics are governed by nonlinear relationships among material composition, physicochemical attributes, manufacturing parameters, biological identity, pharmacokinetics, toxicity, and therapeutic performance. In this review, we examine how AI can contribute to nanopharmaceutical development from predictive formulation design to clinical translation. We synthesize current applications of machine learning, deep learning, physics-informed modeling, hybrid mechanistic–AI approaches, and automated optimization workflows, with emphasis on critical quality attribute modeling, multi-objective optimization, design of experiments, quality-by-design, process analytical technology, digital twins, and continuous manufacturing. We also discuss applications involving nano–bio interactions, pharmacokinetics, toxicity, immunogenicity, and precision nanomedicine. AI-based approaches can support rational nanocarrier design, identify nonlinear formulation–property relationships, guide optimization, improve process understanding, and integrate heterogeneous experimental, biological, and manufacturing datasets across diverse nanopharmaceutical platforms. These methods are particularly relevant for modeling protein corona formation, cellular uptake, intracellular trafficking, biodistribution, pharmacokinetics, toxicity, immunogenicity, and patient-specific responses. However, translational implementation remains limited by fragmented datasets, inconsistent reporting standards, limited interpretability, insufficient external validation, uncertain predictions, poorly defined applicability domains, and evolving regulatory expectations for adaptive computational models. Overall, AI should be viewed not only as an optimization tool, but also as a translational framework connecting formulation science, biological prediction, manufacturing control, and clinical implementation. Future progress will depend on standardized data infrastructures, explainable and externally validated models, uncertainty quantification, applicability-domain definition, hybrid mechanistic–AI frameworks, regulatory-ready documentation, and clinically relevant case studies. Full article

The deployment of offshore wind farms (OWFs) has increased impressively over the last decade. While a group of frontrunner countries has led early deployment, the offshore wind sector is expanding to new regions; the Thracian Sea represents a promising area for OWFs deployment due to its favorable wind and wave climate. The successful implementation of OWFs projects depends on a comprehensive understanding of local environmental conditions, with particular emphasis on complex wind–wave interactions quantification, as well as on robust and representative power performance evaluation. In the present paper, hourly environmental data spanning 29 years (1993–2021), including wind and wave parameters, are utilized to quantify joint probability distributions at selected four locations in the Thracian Sea. Corresponding environmental contours are derived and presented using a probabilistic model for given return period. The joint probability distributions of wind and wave conditions are estimated and the environmental contour surfaces for 50- and 100-year return periods are calculated and presented for generic use. Furthermore, the power production of an OWF comprising nine IEA 15 MW turbine units arranged in an orthogonal grid layout is assessed through a numerical model developed in an open access computational tool. The model accounts for key physical processes influencing OWF capacity performance, including wake interactions, atmospheric conditions, turbine control strategies, and layout effects. The results indicate a substantial value of annual energy production and capacity factor for different zones within Thracian Sea achieving a value of 526 GWh and 44%, respectively. The presented results provide practical guidance for OWFs development in the Thracian Sea and contributes to reducing uncertainty in early-stage project planning and future engineering studies. Full article

Incomplete spatio-temporal (ST) data from sensor networks in precision agriculture often limits environmental modeling and decision-making accuracy. To address this, we propose the Spatio-Temporal Conditional Diffusion Framework (ST-CDF), a generative approach for high-fidelity data reconstruction. The framework’s core is a deep denoising network that integrates a Graph Attention Network (GAT) to explicitly model non-Euclidean spatial correlations, a Differential Attention Transformer to capture abrupt temporal dynamics, and an Inverse Discrete Wavelet Transform (IDWT) module to preserve multi-scale signal details. The generative process is constrained by a physics-informed training objective, which injects known physical laws (i.e., the Penman–Monteith equation for reference evapotranspiration, $E{T}_0$) as an inductive bias, ensuring the imputed data maintains physical consistency. For privacy-preserving deployment on resource-constrained IoT devices, we extend the framework with a Federated Cluster-Guided Distillation (Fed-CGD) strategy. We conducted extensive experiments against established methods on two real-world agricultural datasets. ST-CDF demonstrated improved imputation accuracy across evaluated metrics. Its efficacy was most pronounced in the physically-demanding $E{T}_0$ calculation task, where data imputed by ST-CDF at an 80% missing rate achieved a Root Mean Square Error (RMSE) of 0.3485 and a Coefficient of Determination ($R^2$) of 0.7558, outperforming the baseline models. Furthermore, we explore ST-CDF as an explainable (XAI) framework for active agricultural decision support, demonstrating its utility in performing counterfactual simulations of “what-if” interventions, such as irrigation. The findings highlight ST-CDF as an effective, physically-grounded, and interpretable tool for data-driven scientific computation and precision agriculture. Full article