Search Results (139)

Transient analyses of liquid-fueled molten salt reactors involve strong coupling among neutronics, delayed neutron precursor transport, thermal–hydraulics, and solid heat transfer, leading to high computational costs for repeated high-fidelity simulations. To enable fast multi-physics prediction at unseen operating conditions, a parametric non-intrusive reduced-order model (ROM) combining proper orthogonal decomposition (POD) and higher-order dynamic mode decomposition (HODMD) is developed. Coupled full-order snapshots generated from an OpenFOAM-based one-eighth symmetric core model based on a simplified MSRE benchmark configuration are used to construct reduced representations for 11 physical fields. The POD truncation rank, HODMD delay dimension, and interpolation model are selected using leave-one-out cross-validation, with polynomial, radial basis function, and Gaussian process regression models considered as interpolation candidates. For unseen parameter points, the model maintains high accuracy in both the interpolation stage and the temporal extrapolation stage. In the temporal extrapolation stage, the highest mean relative $L_2$ error for the inlet-temperature-step case is $2.112\%$, whereas all mean relative $L_2$ errors for the inlet-velocity-step case remain below $0.177\%$. The results indicate that, under the present cases and parameter settings, the proposed framework provides an accurate and rapid surrogate for multi-physics transient prediction. Full article

A large number of reservoirs (or hydropower plants) have been constructed for flood control and energy production in the past several decades in the Yangtze River basin in China. The conventional scheduling rule curves (Scheme A) were designed in the reservoir construction period and did not consider river flow alternation, which needs to be modified to increase comprehensive benefits in the reservoir operation period. In this study, six large-scale cascade reservoirs or mega hydropower systems constructed and operated by the China Yangtze Three Gorges Corporation were selected for this case study. The current joint scheduling plans of cascade reservoirs (Scheme B) were introduced, and a joint scheduling and multi-objective coordinating operation model (Scheme C) was proposed for this mega hydropower system. The Gaussian radial basis functions (GRBFs) were used to fit operation policies of each reservoir, and the Borg multi-objective evolutionary algorithm was selected to optimize three-objective functions for Scheme C. The observed daily flow data series at main hydrometric stations from 2003 to 2025 were used to simulate and compare different operation scheduling schemes. The results show that the performance of joint scheduling of cascade reservoirs (both Schemes B and C) is much better than the single-reservoir scheduling (Schemes A) with overall benefit; Scheme C-best achieves a comprehensive target of decreasing average annual spillway wastewater by 12.82 billion m³ (or a decrease of 28.5%), increasing average annual power generation by 31.02 billion kWh (or an increase of 10.7%), and improving average annual impoundment efficiency rate by 5.0%. The GRBFs can fit reservoir operation policies well, while the Borg multi-objective evolutionary algorithm can quickly converge with high-precision non-dominated solution sets. The proposed joint scheduling and multi-objective coordinating operation model will provide a scientific basis for achieving maximum benefits in flood protection and hydropower generation for the mega hydropower system. Full article

Botnet architectures are evolving rapidly, creating significant threats to global network security. This paper presents a homogeneous Radial Basis Function Neural Network (RBFNN) approach for botnet detection that employs a single, uniform RBFNN architecture with identical basis kernel types across all network components. Utilizing the CTU-13 dataset to extract flow-level packet length distribution features. These features are critical for identifying the distinct signatures of the 30 botnet types in the dataset, thereby enhancing the detection capabilities of our uniform RBF framework. The proposed model was designed to address the challenge of achieving high discriminative capability between Normal and Botnet activities while preserving the low latency needed for real-time deployment. Extensive experiments, including cross-validation and Operating Characteristic (ROC) analysis, show the model is effective, achieving a top classification accuracy of 98.31% and distinguishing well between Botnet and normal activities, with an Area Under the Curve (AUC) of 0.997. Furthermore, Training behavior analysis demonstrated stable convergence across different batch size configurations, highlighting trade-offs between accuracy and computational cost. A batch size of 64 provides an optimal balance between convergence speed and accuracy, with a total training time of 29.62 minutes. Crucially, the assessment of processing speed revealed a latency of 1.0118 microseconds. Such minimal delay validates the architecture’s suitability for high-speed network environments where real-time traffic analysis is imperative. Moreover, confusion matrix analysis further confirmed the reliability of the detection, with a low false-positive rate of nearly 0.018. Overall, the empirical results demonstrate that the homogeneous RBFNN offers an advanced solution for complex botnet detection. Full article

The Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2), equipped with the Advanced Topographic Laser Altimeter System (ATLAS), is capable of acquiring large-scale terrain and forest structural information through photon-counting LiDAR. However, photon point clouds exhibit significant noise variability due to diurnal changes and variations in beam intensity, which undermines the accuracy and stability of terrain and canopy height retrievals in forested regions. To address the limited adaptability of existing methods under daytime/nighttime and strong/weak beam conditions, this study proposes a multi-stage processing framework integrating photon denoising, classification, and quasi-full-waveform reconstruction. First, local statistical features combined with adaptive parameter optimization were employed, applying Gaussian and exponential fitting to denoise daytime strong and weak beams and enhance the signal-to-noise ratio (SNR). Subsequently, an improved random sample consensus (RANSAC) algorithm was introduced to remove residual noise and classify photons under both diurnal and beam-intensity variations. Finally, a radial basis function (RBF) interpolation was used to reconstruct quasi-full-waveform curves for terrain and canopy heights. Compared with the ATL08 product (terrain root mean square error (RMSE): 2.65 m for daytime strong beams and 5.77 m for daytime weak beams), the proposed method reduced RMSE by 0.53 m and 1.30 m, respectively, demonstrating enhanced stability and robustness under low-SNR conditions. For canopy height estimation, all beam types showed high consistency with airborne LiDAR measurements, with the highest correlation achieved for nighttime strong beams (R = 0.90), accompanied by the lowest RMSE (4.82 m) and mean absolute error (MAE = 2.97 m). In comparison, ATL08 canopy height errors for nighttime strong beams were higher (RMSE = 5.67 m; MAE = 4.16 m). Notably, significant improvements were observed for weak beams relative to ATL08. These results indicate that the proposed framework effectively denoises and classifies photon point clouds under diverse daytime/nighttime and strong/weak beam conditions, providing a robust methodological reference for high-precision terrain and forest canopy height estimation in forested regions. Full article

Soft-core Coulomb fluids, exemplified by the two-dimensional Gaussian-charge one-component plasma, serve as fundamental benchmarks for both mathematical theory and computational modeling of coarse-grained dynamics, including stochastic density functional theory, dynamical density functional theory, and dissipative particle dynamics. In these systems, the conventional mean-field description, or the random phase approximation (RPA), is frequently employed due to its analytic simplicity; however, its validity is restricted to weak coupling regimes. Here we demonstrate that Coulomb correlations induce a structural crossover to a strongly correlated liquid where the nearest-neighbor distance saturates rather than decreasing monotonically, a behavior fundamentally incompatible with mean-field predictions. Central to our analysis is the emergence of a universal scaling law: when rescaled by the coupling constant, the short-range direct correlation function (DCF) collapses onto a single curve across the strong coupling regime. Exploiting this universality, we construct a closed-form analytic representation of the DCF using a two-Gaussian basis. This compact form accurately reproduces hypernetted-chain radial distribution functions and structure factors while ensuring exact compliance with thermodynamic sum rules. Beyond theoretical elegance, the proposed kernel offers a computationally efficient alternative to RPA-based approximations, enabling real-space dynamical methods to incorporate strong correlations without modifying long-range smoothed-charge electrostatics. Its analytic transparency bridges rigorous integral equation theory and practical dynamical kernels, additionally providing a physics-informed prior for emerging machine-learning models. Collectively, these results establish a mathematically rigorous testbed for advancing the modeling of strongly correlated soft matter systems. Full article

Kolmogorov–Arnold Networks employ learnable univariate activation functions on edges rather than fixed node nonlinearities. Standard B-spline implementations require $O\left(3KW\right)$ parameters per layer (K basis functions, W connections). We introduce shared Gaussian radial basis functions with learnable centers ${\mu }_k^{\left(l\right)}$ and widths ${\sigma }_k^{\left(l\right)}$ maintained globally per layer, reducing parameter complexity to $O(KW+2LK)$ for L layers—a threefold reduction, while preserving Sobolev convergence rates $O\left(h^{s-\mathrm{\Omega }}\right)$. Width clamping at ${\sigma }_{min}={10}^{-6}$ and tripartite regularization ensure numerical stability. On MNIST with architecture $[784,128,10]$ and $K=5$, RBF-KAN achieves $87.8\%$ test accuracy versus $89.1\%$ for B-spline KAN with $1.4\times$ speedup and 33% memory reduction, though generalization gap increases from $1.1\%$ to $2.7\%$ due to global Gaussian support. Physics-informed neural networks demonstrate substantial improvements on partial differential equations: elliptic problems exhibit a $45\times$ reduction in PDE residual and maximum pointwise error, decreasing from $1.32$ to $0.18$; parabolic problems achieve a $2.1\times$ accuracy gain; hyperbolic wave equations show a $19.3\times$ improvement in maximum error and a $6.25\times$ reduction in $L^2$ norm. Superior hyperbolic performance derives from infinite differentiability of Gaussian bases, enabling accurate high-order derivatives without polynomial dissipation. Ablation studies confirm that coefficient regularization reduces mean error by 40%, while center diversity prevents basis collapse. Optimal basis count $K\in [3,5]$ balances expressiveness and overfitting. The architecture establishes Gaussian RBFs as efficient alternatives to B-splines for learnable activation networks with advantages in scientific computing. Full article

An adaptive and efficient particle swarm optimization (PSO)-based learning algorithm to determine neuron centers in the hidden layer of a radial basis neural network (RBNN) is developed in the present work for regression problems. The proposed PSO–RBNN algorithm searches the entire input domain space to discover optimal neuron centers by solving an optimization problem and aims to overcome the limitation of center selection from the training data. The network is built in a sequential manner using optimal neuron centers until some specified criterion is met, and therefore, it exploits the concept of neuron significance during the learning process. The Gaussian function with a constant spread (also known as width) is chosen as the radial basis function for each neuron. To illustrate the effectiveness of the PSO–RBNN algorithm over the orthogonal least squares (OLS) method (a popular learning algorithm under a similar category, which selects the neuron center from training data), numerical simulations for different types of nonlinear problems of varying dimensions and complexities are conducted. Finally, a comparison with multiple existing algorithms for network design is made using available data. The results show that the RBNN architecture developed with the proposed learning algorithm exhibits superior convergence, displays good generalization ability, and requires a smaller number of neurons, resulting in an efficient and compact network architecture. Full article

Severe convective weather is marked by abrupt onset, rapid evolution, and substantial destructive potential, posing major threats to economic activities and human safety. To address this challenge, this study proposes MRKAN, a multi-parameter prediction algorithm for dual-polarization radar that integrates Mamba, radial basis functions (RBFs), and the Kolmogorov–Arnold Network (KAN). The method predicts radar reflectivity, differential reflectivity, and the specific differential phase, enabling a refined depiction of the dynamic structure of severe convective systems. MRKAN incorporates four key innovations. First, a Cross-Scan Mamba module is designed to enhance global spatiotemporal dependencies through point-wise modeling across multiple complementary scans. Second, a Multi-Order KAN module is developed that employs multi-order $\beta$-spline functions to overcome the linear limitations of convolution kernels and to achieve high-order representations of nonlinear local features. Third, a Gaussian and Inverse Multiquadratic RBF module is constructed to extract mesoscale features using a combination of Gaussian radial basis functions and Inverse Multiquadratic radial basis functions. Finally, a Multi-Scale Feature Fusion module is designed to integrate global, local, and mesoscale information, thereby enhancing multi-scale adaptive modeling capability. Experimental results show that MRKAN significantly outperforms mainstream methods across multiple key metrics and yields a more accurate depiction of the spatiotemporal evolution of severe convective weather. Full article

Electrical discharge machining (EDM) is widely used for machining hard and difficult-to-cut materials; however, the complex and nonlinear nature of the process makes the accurate prediction of key performance indicators challenging, particularly when only limited experimental data are available. In this study, a combined Taguchi design and Gaussian process regression (GPR) modeling framework is proposed to predict the surface roughness (Ra), material removal rate (MRR), and overcut (OC) in die-sinking EDM. An L18 Taguchi orthogonal array was employed to efficiently design experiments involving discharge current, pulse duration, and electrode material. GPR models with an automatic relevance determination (ARD) radial basis function kernel were developed to capture nonlinear relationships and varying parameter relevance. Model performance was evaluated using strict leave-one-out cross-validation (LOOCV). The developed GPR models achieved low prediction errors, with RMSE (MAE) values of 0.54 µm (0.41 µm) for R_a, 1.56 mm³/min (1.21 mm³/min) for MRR, and 0.0065 mm (0.0055 mm) for OC, corresponding to approximately 9.8%, 5.4%, and 5.9% of the respective response ranges. These results confirm stable and reliable predictive accuracy within the investigated parameter domain. Based on the validated surrogate models, multi-objective optimization was performed to identify Pareto-optimal process conditions, revealing graphite electrodes as the dominant choice within the feasible operating region. The proposed approach demonstrates that accurate and robust prediction of EDM performance can be achieved even with compact experimental datasets, providing a practical tool for process analysis and optimization. Full article

Biogas production plays a key role in the development of renewable energy systems; however, forecasting biomethane yield remains challenging due to the nonlinear nature of anaerobic digestion. The objective of this study was to develop a predictive model based on Radial Basis Function Neural Networks (RBF-NN) to approximate biomethane production using operational data from the Przybroda biogas plant in Poland. Two separate models were constructed: (1) the relationship between process temperature and daily methane production, and (2) the relationship between methane fraction and total biogas flow. Both models were trained using Gaussian activation functions, individually adjusted neuron parameters, and a zero-level correction algorithm. The developed RBF-NN models demonstrated high approximation accuracy. For the temperature-based model, root mean square error (RMSE) decreased from 531 m³ CH₄·day⁻¹ to 52 m³ CH₄·day⁻¹, while for the methane-fraction model, RMSE decreased from 244 m³ CH₄·day⁻¹ to 27 m³ CH₄·day⁻¹. The determination coefficients reached R² = 0.99 for both models. These results confirm that RBF-NN provides an effective and flexible tool for modeling complex nonlinear dependencies in anaerobic digestion, even when only limited datasets are available, and can support real-time monitoring and optimization in biogas plant operations. Full article

Time-fractional interface problems arise in systems where interacting materials exhibit memory effects or anomalous diffusion. These models provide a more realistic description of physical processes than classical formulations and appear in heat conduction, fluid flow, porous media diffusion, and electromagnetic wave propagation. However, the presence of complex interfaces and the nonlocal nature of fractional derivatives makes their numerical treatment challenging. This article presents a numerical scheme that combines radial basis functions (RBFs) with the finite difference method (FDM) to solve time-fractional partial differential equations involving interfaces. The proposed approach applies to both linear and nonlinear models with constant or variable coefficients. Spatial derivatives are approximated using RBFs, while the Caputo definition is employed for the time-fractional term. First-order time derivatives are discretized using the FDM. Linear systems are solved via Gaussian elimination, and for nonlinear problems, two linearization strategies, a quasi-Newton method and a splitting technique, are implemented to improve efficiency and accuracy. The method’s performance is assessed using maximum absolute and root mean square errors across various grid resolutions. Numerical experiments demonstrate that the scheme effectively resolves sharp gradients and discontinuities while maintaining stability. Overall, the results confirm the robustness, accuracy, and broad applicability of the proposed technique. Full article

Background/Objectives: Speech produced by individuals with hearing loss differs notably from that of normal-hearing (NH) individuals. Although cochlear implants (CIs) provide sufficient auditory input to support speech acquisition and control, there remains considerable variability in speech intelligibility among CI users. As a result, speech produced by CI talkers often exhibits distinct acoustic characteristics compared to that of NH individuals. Methods: Speech data were obtained from eight cochlear-implant (CI) and eight normal-hearing (NH) talkers, while electroencephalogram (EEG) responses were recorded from 11 NH listeners exposed to the same speech stimuli. Support Vector Machine (SVM) classifiers employing 3-fold cross-validation were evaluated using classification accuracy as the performance metric. This study evaluated the efficacy of Support Vector Machine (SVM) algorithms using four kernel functions (Linear, Polynomial, Gaussian, and Radial Basis Function) to classify speech produced by NH and CI talkers. Six acoustic features—Log Energy, Zero-Crossing Rate (ZCR), Pitch, Linear Predictive Coefficients (LPC), Mel-Frequency Cepstral Coefficients (MFCCs), and Perceptual Linear Predictive Cepstral Coefficients (PLP-CC)—were extracted. These same features were also extracted from electroencephalogram (EEG) recordings of NH listeners who were exposed to the speech stimuli. The EEG analysis leveraged the assumption of quasi-stationarity over short time windows. Results: Classification of speech signals using SVMs yielded the highest accuracies of 100% and 94% for the Energy and MFCC features, respectively, using Gaussian and RBF kernels. EEG responses to speech achieved classification accuracies exceeding 70% for ZCR and Pitch features using the same kernels. Other features such as LPC and PLP-CC yielded moderate to low classification performance. Conclusions: The results indicate that both speech-derived and EEG-derived features can effectively differentiate between CI and NH talkers. Among the tested kernels, Gaussian and RBF provided superior performance, particularly when using Energy and MFCC features. These findings support the application of SVMs for multimodal classification in hearing research, with potential applications in improving CI speech processing and auditory rehabilitation. Full article

Collapsibility is a fundamental geotechnical property of loess that critically affects its engineering behavior. In this study, a comprehensive dataset comprising 9041 experimental records on the physical properties and collapsibility of loess from the Xi’an region was compiled. Six parameters were selected as model inputs: sampling depth (H), water content (w), plastic limit (w_P), plasticity index (I_P), compression coefficient (a_1–2), and compression modulus (E_s). Based on these inputs, prediction models for the loess collapsibility coefficient (δ_s) were developed using Gaussian Process Regression (GPR), Gradient Boosting Machine (GBM), Support Vector Regression (SVR), Radial Basis Function Neural Network (RBFNN), Classification and Regression Tree (CART), and Feature Tokenizer Transformer (FT-Transformer). Among these, GPR demonstrated the best predictive performance, achieving the lowest error (RMSE = 9.88 × 10⁻³) and the highest accuracy (R² = 0.844). Additionally, the coverage proportion of the 95% confidence interval of the GPR predictions reached 0.949. SHapley Additive exPlanations (SHAP) analysis for GPR further revealed that the compression coefficient exerted the greatest influence on δ_s (0.0149), followed by compression modulus (0.0080), water content (0.0068), plasticity index (0.0061), sampling depth (0.0061), and plastic limit (0.0052). The GPR-based prediction model offers significantly higher predictive accuracy than empirical models. The developed models provide a robust technical framework for the rapid estimation of loess collapsibility in the Xi’an region. Full article

This study proposes a data-efficient surrogate modeling approach for predicting hydrostatic transmission (HST) system efficiency in tractors using minimal data. Only 27 samples were selected from a dataset of 5092 measurements based on the minimum, mean, and maximum values of the input variables (input shaft speed, HST ratio, and load), which were used as the training data. A hybrid prediction model combining deep kernel learning and a residual radial basis function surrogate was developed with hyperparameters optimized via Bayesian optimization. For performance verification, the proposed model was compared with Neural Network (NN), Random Forest, XGBoost, Gaussian Process (GP), and Support Vector Regressor (SVR) models trained using 27 samples. As a result, the proposed model achieved the highest prediction accuracy (R² = 0.93, MAPE = 5.94%, RMSE = 4.05). Process, SVM (Support Vector MA). These findings indicate that the proposed approach can be effectively used to predict the overall HST efficiency using minimal data, particularly in situations where experimental data collection is limited. Full article

This paper introduces a novel and efficient approach for Gaussian Splatting in dynamic scenes that leverages symmetry principles for enhanced computational efficiency and visual fidelity. First, we diverge from conventional methods that process static and dynamic regions uniformly by implementing an adaptive separation mechanism. This approach exploits the inherent symmetry-breaking properties between static and dynamic Gaussian points, utilizing motion differentials to identify and isolate dynamic elements. This symmetry-aware partitioning allows for the application of specialized processing techniques to each region type, with static regions benefiting from their temporal symmetry while dynamic regions receive targeted deformation modeling. Second, through this fine-grained partitioning of static and dynamic components guided by symmetry analysis, we achieve more judicious allocation of computational resources. The symmetric treatment of spatially coherent static regions and the focused processing of symmetry-breaking dynamic elements substantially reduce memory requirements and training time while preserving reconstruction quality. This optimization effectively conserves valuable computational resources without compromising visual fidelity. Third, we introduce a sophisticated deformation modeling framework that learns the transformational characteristics of grids composed of multiple Gaussian points. By incorporating radial basis function principles, which inherently preserve local rotational and translational symmetries, our method efficiently encodes complex motion information of dynamic Gaussian points. This symmetry-preserving deformation approach not only enables high-fidelity reconstruction of dynamic regions but also significantly improves the rendering of continuously evolving shadow interactions by maintaining physical consistency. The result is a marked reduction in visual distortion and rendering outputs that demonstrate exceptional correspondence to ground truth imagery across diverse dynamic scenes. Full article