Search Results (3,277)

Cadmium (Cd), a widespread pollutant, is primarily absorbed via diet and smoking. Chronic Cd exposure has been associated with various adverse health effects, including renal tubular and skeletal damage. Urinary Cd concentration accurately reflects cumulative Cd exposure owing to its strong correlation with renal cortical Cd levels. This study evaluated the accuracy of estimated lifetime Cd intake by examining its correlation with urinary Cd levels after soil remediation, an aspect unreported even in the Kakehashi River Basin. A total of 565 men and 450 women were included. Lifetime Cd intake (g) was estimated using an established exposure assessment model that incorporated individual residential history, rice Cd concentrations, and dietary assumptions. Urinary Cd concentrations were determined using inductively coupled plasma mass spectrometry. Linear regression analyses were conducted between lifetime cadmium intake and urinary cadmium concentration. The obtained standardized regression coefficients were 0.49 for men and 0.54 for women (both p < 0.001), indicating strong associations. Despite possible exposure misclassification, these findings support the utility of lifetime cadmium intake as a useful surrogate indicator of cumulative cadmium exposure and provide further evidence for its application in risk assessment and the derivation of tolerable cadmium intake values. Full article

Late gadolinium enhancement (LGE) cardiac magnetic resonance is the reference standard for non-invasive myocardial tissue characterization. Conventional LGE analysis focuses on the presence and extent of fibrosis, yet these measures incompletely describe the spatial complexity of myocardial scar that underpins arrhythmogenesis. Entropy, derived from radiomic analysis of LGE signal-intensity distributions, has emerged as a surrogate marker of myocardial tissue heterogeneity. Mechanistically, heterogeneous fibrosis promotes electrical conduction alterations, and entropy serves as a global descriptor of this complex substrate. A growing body of evidence suggests that higher LGE entropy is associated with increased arrhythmogenicity and major adverse cardiac events. Several studies have shown that this association remains significant after adjustment for conventional clinical and imaging predictors. A smaller number of studies have gone further, demonstrating that incorporation of LGE entropy improves the discriminatory or reclassification performance of established risk-prediction models. This narrative review critically synthesizes the current evidence on LGE-derived entropy, compares methodological approaches and clinical applications, and discusses its principal limitations. After standardization and prospective validation, entropy-based phenotyping may prove useful for individualized risk stratification beyond conventional LGE metrics and guide clinical decision-making. Full article

Dynamic prediction of reservoir water cut supports development-plan optimization and injection-production control. The 3000 scenarios sampled the reservoir-production-control response space, and the surrogate model learned the mapping from input conditions to dynamic responses for rapid prediction of unseen scenarios. We propose a temporally constrained long short-term memory (TC-LSTM) network that augments pointwise fitting with relative first- and second-order temporal-difference penalties. Three consecutive windows are grouped only during training to evaluate these penalties; inference retains the standard shared LSTM forward computation. Across five random-seed runs on independently split INSIM scenarios, Full TC-LSTM achieved MSE = 0.00394 ± 0.00013, MAE = 0.0432 ± 0.0007, RMSE = 0.0628 ± 0.0010, and R² = 0.9214 ± 0.0028. Relative to LSTM, mean MSE decreased by 31.1% and R² increased by 4.54 percentage points. Component ablation showed that grouping alone had negligible effect, first- and second-order penalties were complementary, and temporal weighting produced a further gain. Validation sensitivity supported ε = 10⁻³, α = 0.5, ω = (1/3, 2/3), and λ = 0.01. The results support TC-LSTM as a stable, domain-prior-regularized surrogate within the simulated parameter space. Full article

Open-channel hydraulic analysis often requires repeated solution of implicit nonlinear equations and numerical integration of gradually varied flow (GVF), which can become computationally demanding in inverse, optimization, and sensitivity applications. This study develops a hydraulically informed artificial neural network (ANN) surrogate framework comprising ten independently trained models for normal and critical depths, alternative and conjugate depths, GVF-related water-surface behavior, and profile-based discharge inference. Hydraulic information is introduced through physically meaningful, and where appropriate dimensionless, variables and reference solutions derived from established governing equations or numerical hydraulic models, while ANN optimization remains data driven. Equation-generated test sets quantified surrogate fidelity, whereas HEC-RAS comparisons were treated as numerical hydraulic cross-verification rather than independent physical validation. The forward surrogates reproduced their reference mappings with high accuracy within the represented domains. Benchmarking against Random Forest, support vector regression, and Gaussian Process Regression for Models 1, 5, and 7 showed no universal algorithmic superiority; however, ANN provided a favorable trade-off among accuracy, relative-error robustness, compactness, and repeated-inference efficiency. For Model 7, ANN inference was approximately 249 times faster than conventional GVF calculation, with development cost recovered after about 1.03 × 10⁵ evaluations. Model 9 inferred discharge with a 4.75% error in the profile-based test. Observation-based assessment using 16 historical Missouri River stage–discharge events showed that direct HEC-RAS inversion yielded a MAPE of 44.71%, whereas observation-only ANN and hybrid HEC-RAS-ANN discrepancy correction reduced MAPE to 10.25% and 9.83%, respectively. The framework is therefore a computational complement to established hydraulic equations and numerical models, with broader field validation and explicit uncertainty treatment required for general deployment. Full article

Multi-infeed LCC-HVDC siting requires a static strength test, a finite-fault propagation assessment, and an auditable rule for selecting the subset of candidates that receives detailed electromagnetic-transient (EMT) evaluation. This paper develops a directional fault-response matrix whose row denotes the responding converter bus and whose column denotes the fault-source terminal. A two-infeed derivation, stated for scalar or common-angle impedances and checked numerically for unequal $X/R$ ratios, shows that a stronger inter-bus tie can raise the weaker terminal’s simplified MSCR while increasing the mutual impedance and the cross-terminal fault response. Structural properties of the nonnegative matrix are derived, and a closed-form first-order surrogate calibrated by one pooled least-squares gain screens all 15 four-infeed combinations of six synthetic sites and routes seven candidates (28 single-source switching-EMT runs) to detailed verification. The complete 60-run library is additionally simulated offline and used only as ground truth: the reduced and EMT composite scores have Spearman coefficients of 0.750 over the routed set and 0.911 over all 15 candidates (0.911 under leave-one-candidate-out calibration), the reduced hard screen produces zero false retentions and zero false rejections, and the matrix score is compared with MSCR-only and impedance-ratio MIIF baselines. ABCE is the best verified candidate, with a minimum simplified MSCR of 2.008 and a maximum EMT cross-response of 0.0395 p.u. A 0.05 ohm stress profile activates the transient limit for 9 of the 15 candidates. Element-level error, weight and threshold sensitivity, measured simulation times, and model limitations are reported. The method remains a screening and diagnostic framework rather than a stability law or a proof of global EMT optimality. Full article

Evacuated-tube solar collectors charged with hybrid nanofluids can raise thermal output, but their coupled thermal and hydraulic response depends on many interacting variables, making the design an optimisation rather than a prediction problem. This study recasts it as a constrained, mixed-variable, three-objective task that maximises thermal efficiency and the Nusselt number while minimising pumping power over the hybrid pair, base fluid, weight fraction, component-one share and flow rate, and develops a memetic metaheuristic: the Adaptive Memetic Hybrid (AMH). A histogram gradient-boosted surrogate trained on 54,432 reduced-order runs, with held-out coefficients of determination of at least 0.9999, provides a fast screen, while a continuous reduced-order model validated to within 0.02 percent serves as the objective; the surrogate is accurate off-grid for efficiency but not for pumping power or the Nusselt number. Nine optimisers, comprising four baselines, three recent metaheuristics, and two AMH variants, were validated on twelve ZDT, DTLZ, and constrained problems over thirty trials using the hypervolume, generational distances, and spacing, and analysed with Friedman, Nemenyi, and Holm-corrected Wilcoxon tests. AMH attained the best mean Friedman rank of 3.08 (chi-square 65.7, p = 3.6 × 10⁻¹¹), significantly outperforming the recent methods and NSGA-III and remaining competitive with the strongest classical algorithms. On the collector, the reduced-order front recovers the 1512-design brute-force maximum efficiency to within 0.02 percent and improves the trade-off through continuous flow rates. The study is a deterministic, model-based optimisation process: the surrogate serves as a tool for fast screening and diagnostics, while the reconstructed reduced-order model is the objective for the final continuous optimisation. The collector application has a low effective design dimension, being governed mainly by the base fluid and the loop flow rate, so the decisive separation of the algorithms is established on the benchmark suite rather than on the collector. Experimental validation remains a task for future work. Full article

Hirth couplings connect gas-turbine rotor discs and transmit torque, making them critical to efficient energy conversion and power output. To address the current lack of strength research, limited optimization studies, and inefficient optimization methods for Hirth couplings, a Hirth Coupling Strength Prediction Graph Convolutional Network (HSP-GCN) is proposed for multiple mechanical field reconstruction and structural optimization. HSP-GCN can rapidly reconstruct the displacement, stress, and contact pressure fields on the Hirth tooth surfaces according to structural parameters. Its rapid and accurate performance superiority is demonstrated through comparisons with deep neural network and convolutional neural network models. To the best of our knowledge, this is the first instance that a neural network-based surrogate model has been used for field reconstruction and performance prediction of Hirth couplings. The results show that the field mean absolute errors are below 0.02 for all reconstructed fields except u_x. The relative errors of the maximum von Mises stress and maximum contact pressure are generally within ±5%, with an error of −5.76% observed in one representative case near the boundary of the design space. Meanwhile, a multi-constraint optimization method for Hirth couplings based on HSP-GCN is proposed. The optimized designs reduce the maximum von Mises stress by 15.4%. This study can provide an effective and novel tool for accelerating analysis and optimization. Full article

Rapid prediction of vehicle lift coefficient is an important issue in aerodynamic design. Traditional CFD/DSMC methods have high computational costs. Although commonly used machine-learning surrogate models offer high prediction efficiency, they struggle to provide explicit mathematical expressions. To balance prediction accuracy and model interpretability, this paper introduces the symbolic regression method and establishes an explicit modeling process for the lift coefficient. Using Mach number, angle of attack, and related flow parameters as inputs, validation is conducted on two-dimensional blunt body DSMC data and three-dimensional missile aerodynamic data, with comparisons against linear regression, quadratic polynomial regression, Kriging, random forest, XGBoost, and multilayer perceptron. The results show that symbolic regression can obtain high-precision explicit expressions on the two-dimensional blunt body data and can also build analytical models with certain predictive capability on the three-dimensional missile data with limited samples. Compared with traditional explicit regression methods, symbolic regression does not require a pre-specified fixed functional form; compared with black-box models, its advantage lies in providing interpretable and editable algebraic expressions. The findings indicate that symbolic regression has application potential in rapid explicit modeling of the lift coefficient. Full article

Mobile networks have become targets of sophisticated cyber attacks. Critical vulnerabilities persist in the General Packet Radio Service Tunneling Protocol (GTP). Signature-based Intrusion Detection Systems (IDS) are inadequate against zero day exploits and novel attack patterns, necessitating more adaptive approaches. We propose GTP-AEGIS (Adaptive Ensemble with Gated Input Selection), a hybrid IDS that integrates signature-based detection with a CatBoost gradient boosting classifier via a Selective Heterogeneous Ensemble (SHE) framework. An Input-Dependent Confidence Gate (IDCG) applies a per-sample priority rule over CatBoost, a NearestCentroid Rule Engine (NCRE), and a signature pathway. A real Suricata engine detects attacks with 100% precision but only 69.2% binary recall when run standalone; within the ensemble, the signature role is played by an idealized Signature-Detection Surrogate (SDS), so the reported ensemble gains are upper bounds. On the evaluated GTP-U dataset, GTP-AEGIS reaches accuracy above 90% with 10% of the training data and raises recall for the rare invalid-TEID class from 48.9% to 64.4%; this improvement comes from the signature pathway rather than the NCRE, and the aggregate accuracy gain is not statistically significant after correction for multiple comparisons. All accuracies are obtained under a packet-level split, which a group-aware comparison shows to be optimistic by approximately 19 percentage points. The model flags 81 to 100% of packets from unseen attack families as non-normal, although this does not constitute unknown-class recognition. We report the limits of signature-only detection and of packet-level evaluation alongside the gains. Full article

In the present work, an alternative methodology was developed for the rapid prediction of pressure distributions over wings of low-speed aircraft. A hybrid neural network architecture, named “MARTHA” (Model for Airloads Reconstruction using a Trained Hybrid Architecture), was presented, which is composed of a Multilayer Perceptron and the decoder of an Autoencoder. Three compact representation models—Principal Component Analysis (PCA), Autoencoder (AE), and Variational Autoencoder (VAE)—were systematically evaluated to determine the optimal dimensionality reduction architecture; the AE was selected based on its superior reconstruction accuracy and training stability. The main feature of MARTHA is that it provides predictions of the differential pressure coefficient field in the form of monochrome images, where the pixel intensity directly represents the normalized pressure value. One of the main objectives of developing MARTHA was to create a rapid surrogate model that can approximate vortex lattice method (VLM) simulations in preliminary design and optimization tasks, particularly when thousands of wing configurations need to be evaluated. The key feature of the proposed model is its ability to predict the pressure distribution for trapezoidal wings of various geometries 10¹–10⁴ times faster than numerical models, while maintaining accuracy (R² = 0.9998). The data obtained are presented in a convenient format for their further use in CAE systems of strength analysis. To assess the practical utility of the proposed model, implementation cases were carried out using the finite element software ANSYS 18.2 for three wing configurations not present in the training dataset. The pressure fields predicted by MARTHA were mapped onto the wing meshes, and linear static structural analyses were performed. The obtained Von Mises stress distributions showed good agreement with the corresponding distributions obtained using numerical models. Full article

Robotic multi-seam welding path planning for box-type thin-walled structures faces significant challenges due to multiple constraints, multiple objectives, and its high-dimensional discrete combinatorial nature. To address these issues, a deformation-informed multi-objective path planning method for multi-seam welding (DMOPP) is proposed, comprising a multi-objective formulation and an optimization algorithm. At the modeling level, welding path length and maximum structural deformation are defined as the optimization objectives. Collision-free path planning is used to calculate the path length, while an XGBoost-based surrogate model is developed to establish the mapping between welding path variables and maximum deformation, enabling rapid deformation prediction without computationally expensive finite element simulations. At the optimization level, a modified discrete artificial lemming algorithm (MODALA) is proposed to improve global search capability and convergence stability. Experimental results show that MODALA outperforms the comparison algorithms on benchmark functions and discrete optimization problems, demonstrating its superior optimization performance. The XGBoost surrogate model achieves an R² of 0.8447 and an RMSE of 0.0841 mm, indicating good predictive accuracy. In welding path planning simulations, the proposed method effectively reduces the path length and welding deformation while achieving a favorable trade-off between path efficiency and structural quality. Robotic welding experiments further validate its practical effectiveness. Full article

Scrap charge selection has a significant influence on the thermal balance of the basic oxygen furnace (BOF) process and consequently on the final melt temperature. This paper presents a hybrid deterministic, regression, and machine learning framework for endpoint temperature prediction and steel scrap charge optimization in BOF steelmaking. The proposed methodology combines an existing deterministic BOF simulation model with regression analysis, machine learning surrogate models, and constrained nonlinear optimization. The dataset was constructed from operational records of 180 industrial BOF heats. The masses of seven scrap categories and the target endpoint temperature were obtained from these operational records, whereas the endpoint temperature used as the output for training the machine learning surrogate models was generated by the existing deterministic BOF process model. Three machine learning approaches, namely Support Vector Regression (SVR), Random Forest Regression (RF), and Gaussian Process Regression (GPR), were implemented and evaluated for endpoint temperature prediction using the masses of seven scrap categories and the target endpoint temperature as model inputs. Among the investigated surrogate models, Gaussian Process Regression achieved the best approximation performance, with a test MAE of 10.47 °C, RMSE of 16.38 °C, and $R^2$ = 0.870, and was subsequently used in the optimization framework. In addition, the deterministic BOF simulation model was incorporated into a model-based optimization procedure using the same optimization objective. Both approaches were formulated as constrained optimization problems minimizing the deviation between the predicted and target endpoint temperatures while satisfying the total scrap mass constraint. The proposed framework provides a model-based approach to temperature-oriented scrap charge planning using either a machine learning surrogate model or a detailed deterministic process model. Full article

During CO₂ flooding, unfavorable mobility ratios and interlayer heterogeneity can induce preferential flow through high-permeability intervals, leaving central low-permeability intervals insufficiently swept and rich in remaining oil. To address the strong coupling among composite chemical-plugging parameters and the high computational cost of CMG-STARS simulations for individual candidate strategies, this study proposes an adaptive heterogeneous ensemble surrogate-assisted differential-evolution method (AHES-DE). The method integrates radial basis function, inverse-distance weighting, and ridge-linear surrogate models, whose predictions are dynamically weighted according to leave-one-out cross-validation errors. Explorer, Exploiter, and Robust roles are used for global search, local exploitation, and prediction-risk control, respectively, with differential-evolution offspring generation embedded in the Exploiter role. A stratified one-injector–four-producer conceptual model with a 21 × 21 × 6 grid was used to establish a numerical evaluation workflow comprising CO₂ injection, preferential-channel development, composite chemical plugging, and subsequent displacement. Mobile chemical concentration, adsorbed preformed particle gel (PPG) mass density, water-phase resistance factor, oil saturation at a common termination time, and net economic value (NEV) were used to evaluate treatment performance. Under an equal budget of 150 high-fidelity CMG-STARS evaluations per method, the reported single-seed final best-so-far NEVs were 2.45405 × 10⁹ CNY for AHES-DE, 2.44888 × 10⁹ CNY for differential evolution (DE), and 2.44698 × 10⁹ CNY for Latin hypercube sampling (LHS). The layer-resolved responses indicate more pronounced chemical transport, retention, and resistance development in the upper and lower preferential intervals, while the oil saturation in the central low-permeability interval decreased further after treatment, indicating that flow redistribution facilitated remaining-oil mobilization. A realistic geological model was further used to assess the engineering consistency of the identified flow-control mechanism. Full article

Metabolic dysfunction-associated steatotic liver disease (MASLD) is one of the leading causes of chronic liver disease worldwide, and effective pharmacological therapies remain limited. Pemafibrate (Pema), a selective peroxisome proliferator-activated receptor alpha (PPARα) modulator (SPPARMα), has shown promising therapeutic potential in patients with MASLD and hypertriglyceridemia; however, its underlying mechanisms remain incompletely understood. Here, we investigated the therapeutic effects and molecular mechanisms of Pema using in vitro and in vivo MASLD models and evaluated its clinical relevance in patients with MASLD. In a choline-deficient, L-amino acid-defined, high-fat diet (CDAHFD)-induced MASLD mouse model, Pema dose-dependently ameliorated hepatic steatosis and fibrosis and significantly suppressed the hepatic expression of inflammatory and fibrogenic genes, including TLR4, TNFα, αSMA, and Col1A1. Pema also favorably altered the gut microbiota by increasing the abundance of the phylum Verrucomicrobia, suggesting modulation of the gut–liver axis. In differentiated 3T3-L1 adipocyte-like cells, Pema induced PPARα expression, inhibited insulin-mediated EGR-1 induction, and significantly reduced leptin secretion. Consistent with these findings, serum insulin and leptin levels, as well as the hepatic accumulation of both molecules, were markedly decreased in Pema-treated MASLD mice. Furthermore, in a clinical cohort of 192 patients with MASLD and hypertriglyceridemia, long-term Pema treatment significantly improved liver-related biochemical parameters, insulin resistance, surrogate markers of liver fibrosis, and serum leptin levels. Collectively, these findings demonstrate that Pema attenuates MASLD progression by suppressing leptin-mediated metabolic and inflammatory signaling while improving the gut microenvironment. These results highlight SPPARMα as a promising therapeutic strategy for MASLD and support further clinical investigation of Pema as a disease-modifying treatment targeting the gut–liver axis. Full article

This study proposes a surrogate model, Graph-Structured Physics-Informed Deep Operator Network (GS-PI-DeepONet), to simulate two-dimensional hydrodynamics in a tidal river network. The model was coupled with Graph Convolutional Networks (GCNs) for spatial feature extraction and Long Short-Term Memory (LSTM) network for temporal prediction, with 2D shallow-water equations (2D SWEs) embedded as physical constraints. To handle complex river network topologies, a mapping mechanism was proposed to transform discrete irregular boundaries into differentiable neural network constraints. A dynamic weighting strategy was developed to improve model training efficiency. GS-PI-DeepONet was applied to a river network within the Pearl River Basin in Zhuhai. Trained on high-fidelity Delft3D data, it achieved precise flow field reconstruction and millisecond-level extrapolation predictions, outperforming traditional data-driven models. The model can be a valuable tool for real-time hydrodynamic simulations and flood management strategies in tidal river networks. Full article