Search Results (3,753)

Dynamic modulus is a key stiffness parameter in the mechanistic–empirical design of asphalt pavements. Traditional laboratory tests are time-consuming and costly, while conventional empirical models fail to characterize the nonlinear viscoelasticity introduced by fibers, and existing machine learning methods suffer from premature hyperparameter convergence and limited interpretability. To address these issues, this study employs an improved black-winged kite algorithm (IBKA) to optimize eXtreme Gradient Boosting (XGBoost) for establishing a dynamic modulus prediction model. Gaussian chaotic mapping, guided pool strategy, and adaptive step size are introduced to enhance global hyperparameter optimization capability. A dataset of 288 samples involving temperature, frequency, strain, and fiber categories is compiled from multi-condition tests. Nested cross-validation and an independent test set are adopted for internal optimization and generalization assessment, with permutation testing (1000 Monte Carlo, p < 0.001) confirming the statistical reliability of the model. The results demonstrate that IBKA–XGBoost delivers excellent accuracy and robustness, achieving an RMSE of 355.1248 MPa and an R² of 0.9966 in NCV and 373.5450 MPa and 0.9955 on the independent test set. It outperforms BKA–XGBoost, four metaheuristic algorithms, and three conventional tuning strategies across nine evaluation metrics; compared with BKA–XGBoost, RMSE decreases by 23.9% and prediction uncertainty U₉₅ narrows by 23.7%. SHAP and PDP analyses identify temperature as the dominant factor, reveal fiber-type differentiation governed by modulus matching and interfacial compatibility, and confirm asymmetric temperature–frequency interactions consistent with the time–temperature superposition principle. The proposed framework facilitates fiber screening and the intelligent refined design of pavement materials. Full article

The automatic segmentation of the heart from echocardiography can significantly improve the efficiency and effectiveness of assessing cardiac function and provide objective and reproducible quantitative evidence for clinical diagnosis, treatment planning, and disease screening. Many excellent results in the community of medical artificial intelligence have been achieved; however, there is still room for improvement, such as the employment of temporal information in echocardiography. In this paper, we propose the Spiking U-Mamba model, which incorporates three novel modules, i.e., MultiStepLIFEncoder, BidirectionalFeatureFusion and FeatureRefinementBlock. MultiStepLIFEncoder encodes static features into spatio-temporal pulse sequences to enhance the model’s boundary resolution capability, while BidirectionalFeatureFusion enables bidirectional interaction and attention enhancement between the Mamba global features and pulse features, and FeatureRefinementBlock further refines the fused features and ensures stable gradient propagation. Two public echocardiography datasets, CAMUS and EchoNet-Dynamic, were employed to evaluate the proposed Spiking U-Mamba model. On the CAMUS dataset, Spiking U-Mamba achieved a Dice coefficient of 90.16% during the ED phase and 90.54% during the ES phase, outperforming other SOTA methods; on the EchoNet-Dynamic dataset, Spiking U-Mamba also performed well. Since the employment of the Spiking Neural Network, the proposed Spiking U-Mamba model achieved a good balance between segmentation accuracy and computational cost. Full article

Flood occurrence in tropical regions is intensifying due to climate variability and land-use change, increasing the need for reliable flood response time estimation. Accurate prediction of flood lag time (TL)—the interval between the centroid of excess rainfall and peak runoff—is critical for flood early warning and water resource planning. However, TL estimation remains challenging in data-scarce regions because of complex interactions among watershed morphology, rainfall characteristics, and runoff generation processes. This study evaluates four machine learning (ML) algorithms—Random Forest (RF), Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—for predicting TL across twenty gauged watersheds in the Blue Nile Basin of Ethiopia. Fourteen physiographic and hydro-climatic watershed characteristics were used as predictors. Among the tested models, XGBoost achieved the highest training performance (R² = 0.98, NSE = 0.96), while RF showed better generalization in the test dataset (R² = 0.77, NSE = 0.70, KGE = 0.71). SVM produced the lowest prediction errors (MAE = 0.95; RMSE = 2.25) but had lower explanatory power (R² = 0.49). To enhance interpretability and practical applicability, ML-based feature importance was used to develop a parsimonious empirical model: TL = 0.8 + 0.011A − 0.023RI, where A is watershed area and RI is rainfall intensity. This model explained 51% of TL variability and retained much of the predictive skill of more complex ML models. The proposed hybrid ML–empirical framework provides a transparent and operational approach for flood response time estimation in tropical highland watersheds. Its broader applicability remains subject to additional watershed-level validation and regional calibration. Full article

In porous media grouting, highly viscous non-Newtonian fluids often trigger viscous fingering (Saffman–Taylor instability) due to adverse mobility ratios, creating fractal-like preferential channels that severely weaken the reinforcement volume. To overcome this, a novel swirl-driven grouting method is proposed. A 2.5D swirl seepage model is established to derive the analytical solution for tangential velocity spatial decay. Integrating the Capillary Bundle and Herschel–Bulkley models elucidates the nonlinear coupling mechanism of centrifugal force and shear-thinning. The swirl flow creates an in situ centrifugal pump, reshaping pressure gradients and triggering a sudden viscosity plunge via extremely high comprehensive shear rates. Furthermore, a modified Saffman–Taylor dispersion relation is constructed and validated via indoor sandbox experiments. Theoretical analysis yields a conditional critical Swirl Number threshold of approximately 0.6 under the tested parameters to suppress the fractal-like evolution of fingering. Experiments demonstrate that exceeding this threshold transitions the grout from preferential seepage to uniform isotropic diffusion. The measured isotropic index is closely enveloped within the 10% theoretical error band. Consequently, the effective projected area experiences a substantial leap of 83.3% due to synergistically enhanced driving forces and reduced medium resistance. This mechanism fundamentally overcomes viscous fingering and suppresses the fractal-like growth tendency of the displacement front, providing a solid theoretical basis for controlling grout diffusion morphology in underground engineering. Full article

Rapid and non-destructive identification of oilseed rape varieties and prediction of leaf Soil Plant Analysis Development (SPAD) value and water content are important for variety evaluation and plant-status monitoring. However, hyperspectral prediction is constrained by small sample size, costly reference measurements, and acquisition-batch differences. Samples were collected over four consecutive days. Day 1 samples were used for training and Wasserstein generative adversarial network with gradient penalty (WGAN-GP) generation. For Days 2–4, 20% of the samples from each day were combined to form a selection-validation set, while the remaining 80% were retained separately as Test sets 1–3. The improved WGAN-GP integrated principal component analysis–Gaussian mixture model (PCA–GMM)-based class assignment, a partial least squares regression (PLSR) consistency loss, physicochemical distribution control, and generated-sample selection. Under single-task modeling, the improved framework enhanced all three tasks across the test sets. On Test set 3, variety accuracy increased from 0.4672 to 0.6100, SPAD root mean square error of prediction (RMSEP) decreased from 6.2201 to 4.6303, and the water-content test-set correlation coefficient (r_p) increased from 0.6803 to 0.7842. The improved multi-task model also enhanced all three tasks. These findings support the framework within the investigated three-variety, four-day leaf setting. Full article

Foam concrete is a lightweight material characterized by low density and moderate mechanical strength, which can be combined with aluminum alloys to form a novel type of column. Such composite members enable rapid assembly, disassembly, and functional reconfiguration in prefabricated structures. However, research on the axial compressive performance of this new column system remains limited. This study investigates the axial behavior of aluminum alloy-foam concrete short columns through a combination of numerical simulation, theoretical analysis, and machine learning prediction enhanced by the SHAP (SHapley Additive exPlanations) interpretability method. A three-dimensional finite element model was developed in ABAQUS to examine the effects of frame thickness, foam concrete strength, and section dimension on load-bearing capacity. The results indicate that the column sectional dimensions have a significant influence on the axial compressive capacity. The foam concrete strength and frame thickness have relatively smaller effects. In addition, the frame thickness can effectively restrain lateral deformation and delay buckling. Based on the confinement mechanism, polynomial fitting, Mander’s model, and a composite column formulation were proposed for axial capacity prediction. Furthermore, eleven machine learning models were trained on 64 simulation datasets 64 independent computational experiments, among which the Gradient Boosting Decision Tree (GBDT) demonstrated the best performance (R² = 0.9984, MAE = 5.97, RMSE = 7.51). SHAP analysis further revealed the relative contributions of key features, showing that section dimension is the most influential parameter, followed by foam concrete strength, while frame thickness contributes the least. These findings not only enhance the theoretical understanding of the load-transfer mechanism of columns but also provide reliable predictive models and analytical formulations for their application in lightweight prefabricated structures. Full article

The negative differential resistance (NDR) effect provides nonlinear control over ionic current and has important potential in ion sensing and information storage. A multiphys-ics numerical model is established using COMSOL Multiphysics 6.3, coupling the Poisson−Nernst−Planck and Navier−Stokes equations to investigate the effects of solution concentration gradient, pore length, pore diameter, and surface charge density on NDR effect. The results indicate that the NDR effect occurs only in the negative voltage range, where concentration gradient diffusion competes with electric field driven migration. The characteristic voltage window stabilizes between −0.2 V and −0.5 V, and the total current reaches a local extremum near −0.2 V. Electromigration dominates in this range and sup-presses Cl⁻ ion diffusion, while K⁺ transport is less affected, resulting in decreased total ionic current. Under baseline conditions, the total current decreases by 26.19%, from −0.42 nA to −0.31 nA. Increasing the concentration gradient, shortening the pore length, enlarging the pore diameter, and reducing the surface charge density enhance local vortices or maintain Cl⁻ diffusion pathways, thereby strengthening NDR characteristics. This study reveals the regulation mechanisms of NDR effect by solution conditions, macropore structures, and surface properties, providing theoretical guidance for tunable ionic current devices. Full article

This study investigates machine learning techniques for predicting the behavior of proton exchange membrane electrolyzers, which are vital for sustainable hydrogen production. This work addresses these challenges by integrating artificial neural networks to develop predictive models capable of capturing the performance of proton exchange membrane electrolyzers with high accuracy. This research utilizes a multi-layer perceptron network architecture, optimized through rigorous data preprocessing, parameter tuning, and error minimization strategies. The dataset used was based on published PEME numerical simulation datasets and encompasses key performance indicators, including stack voltage, water transport, and electrochemical reactions. The trained artificial neural networks models achieved mean squared error values of 3.66 × 10⁻⁵ and 9.75 × 10⁻⁶, with correlation coefficients of 0.99996 and 0.99958, demonstrating near-perfect predictive accuracy. A comparative benchmarking study against alternative regression algorithms revealed that the proposed MLP models significantly outperformed Gradient Boosting and Random Forest by several orders of magnitude, thereby establishing a higher level of persuasiveness and reliability for the developed framework. Average deviation rates of 0.11% and −0.01% further validated model reliability. The novelty of this work lies in its comprehensive approach, which goes beyond isolated metrics by addressing interactions across system parameters. This integrated framework enables enhanced prediction, control, and optimization of proton exchange membrane electrolyzer’s performance, setting a new benchmark for leveraging machine learning in hydrogen energy systems. These findings pave the way for scalable, cost-effective solutions to improve proton exchange membrane electrolyzers’ efficiency and operational reliability. Full article

With the increasing penetration of wind and photovoltaic generation, microgrids are playing an increasingly important role in promoting renewable energy accommodation, enhancing operational flexibility, and enabling low-carbon energy management. However, the strong uncertainty of renewable generation and load demand, together with the coupling effects of electricity, hydrogen, and carbon markets, poses significant challenges to the optimal planning and operation of microgrid energy storage systems. To address these issues, this paper proposes a bi-level optimal sizing framework for an electric–hydrogen hybrid energy storage system (EHH-ESS) in a microgrid under multi-market coupling. First, typical wind–solar–load scenarios are generated using a Wasserstein generative adversarial network with gradient penalty (WGAN-GP), so as to capture the stochastic characteristics and temporal correlations of renewable generation and load demand. Then, a multi-market coupling index (MCI), integrating electricity price, hydrogen price, and carbon price signals, is constructed to characterize time-varying economic and low-carbon operating incentives and to guide coordinated dispatch decisions. On this basis, a bi-level multi-objective optimization model is established. The upper level determines the optimal capacities of battery storage, electrolyzers, fuel cells, and hydrogen tanks, while the lower level performs hourly coordinated operation of the microgrid under multi-market conditions. The model considers annual equivalent total cost, renewable energy curtailment rate, and carbon emissions as objective functions, and is solved using the NSGA-III algorithm. Compared with the no-storage benchmark, the proposed scheme improves the annual operating economics and renewable-energy accommodation under the studied market conditions. The proposed method significantly reduces annual operating cost and improves renewable energy accommodation. However, under the current carbon price and grid emission factor settings, the optimal economic solution increases carbon emissions relative to the baseline, indicating a trade-off between economic arbitrage and low-carbon operation. Full article

Background: Breast cancer brain metastases (BCBMs) exhibit notable receptor discordance between primary tumors and metastases, yet obtaining intracranial biopsies is rarely practical. We created an interpretable deep learning radiogenomic model to predict estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status from MRI scans in BCBM cases. Methods: A total of 241 post-contrast T1-weighted MRIs from 142 patients were analyzed. We developed a mask-free 3D Residual Neural Network (ResNet) ensemble trained directly on cropped, bias-corrected brain images, with comprehensive 3D geometric and intensity augmentations. The model was optimized in a multi-label setting using Asymmetric Focal Loss. Hyperparameters were fine-tuned via Bayesian optimization, and class probabilities were calibrated. Additionally, Integrated Gradients (IG) offered voxel-level saliency maps. Results: Our ResNet ensemble model achieved a micro-averaged AUROC of 0.74 and a macro-averaged AUROC of 0.67. Receptor-specific AUROCs were 0.57 for ER, 0.79 for PR, and 0.64 for HER2. The F1-scores were 0.56, 0.62, and 0.88 for ER, PR, and HER2, respectively. The held-out cohort contained only four HER2-negative patients, so threshold-dependent HER2 metrics are strongly prevalence-driven and AUROC is the more appropriate summary. Qualitatively inspected saliency maps were concentrated on enhancing metastases with limited background attribution. Conclusions: This proof-of-concept study shows that a segmentation-free, interpretable 3D Convolutional Neural Network (CNN) can be trained to capture receptor-associated patterns in post-contrast T1-weighted MRI of BCBMs. Accuracy was modest relative to published radiomics models, and the mask-free, single-sequence design is offered as a methodological contribution rather than a performance gain. These findings are preliminary, do not establish clinical utility, and require validation in larger, multi-center cohorts. Full article

This research aims to investigate and improve the accuracy of porosity prediction in steel ingot casting by leveraging Thercast finite element simulations. In particular, the study refines the Niyama criterion through additional physical parameters and solidification modeling, aiming to reduce shrinkage porosity and enhance the overall mechanical reliability of cast components. Simulation results reveal that a lower thermal conductivity and faster cooling rates exacerbate shrinkage porosity, while a refined Niyama indicator using explicit solid-fraction weighting, with viscosity, alloy composition, and shrinkage accounted for through the underlying THERCAST material model, improves spatial localization of porosity-prone regions in the investigated case. For the investigated configuration, reducing the cooling rate to around 1.25 K/s decreased the extent of the simulated region classified as porosity-prone relative to the reference case. Furthermore, the analytical porosity–strength relation indicates a material-dependent reduction in strength when the porosity fraction exceeds 2%, underscoring the structural significance of internal voids. This study extends the practical interpretation of the classical Niyama criterion by combining solid-fraction weighting with material-dependent thermophysical inputs, addressing gaps in existing shrinkage porosity models. The approach integrates simulation findings with actual casting defects identified through ultrasonic scanning and metallographic analysis. By merging experimental insights with advanced finite element simulations, foundries can better regulate casting conditions, particularly cooling rates and thermal gradients, to minimize porosity. The refined porosity prediction framework aids in process optimization, improved material utilization, and superior quality assurance of steel ingots. Full article

Convective drying of Zingiberaceous roots, particularly ginger (Zingiber officinale), requires a uniform distribution of airflow and temperature to ensure energy efficiency and product quality. However, many drying systems exhibit aerothermal limitations that produce temperature gradients and non-uniform drying conditions. To address this issue, this study proposes a dual-swirl dryer featuring two air inlets: an upper helical inlet and a lower tangential inlet. Both inlet configurations generate swirling airflow patterns that enhance thermal uniformity and increase the residence time of hot air within the drying chamber. The internal flow behavior was investigated using Computational Fluid Dynamics (CFD) simulations in ANSYS Fluent2025 R1 version. A three-dimensional polyhedral mesh was generated to improve computational efficiency and numerical accuracy. Turbulence and recirculation phenomena were modeled using the Realizable k–$ϵ$ turbulence model, while temperature distribution was analyzed through the energy conservation equation. Numerical predictions were experimentally validated using temperature sensors integrated into an automatic control system. The comparison between numerical and experimental results demonstrated that the dual-swirl configuration improves airflow redistribution, reduces thermal stagnation zones, and promotes a more homogeneous temperature field throughout the drying chamber. These findings confirm that the proposed system is an efficient alternative for agro-industrial drying applications. Full article

Predicting customer churn in the telecom sector is critical for retaining subscribers, maintaining brand reputation, and staying ahead of competitors. Losing customers not only reduces revenue but can also weaken long-term market position in a highly competitive industry. While machine learning has been widely used to address this challenge, most traditional approaches depend on centralizing customer data. This raises major concerns about user privacy, data ownership, and compliance with strict regulations such as GDPR. These challenges make it difficult for businesses to fully utilize customer data while safeguarding sensitive information. In this paper, we investigate a privacy-preserving approach to churn prediction that combines federated learning (FL) with differential privacy (DP). Rather than collecting all customer data in a single repository, the investigated framework enables multiple clients to collaboratively train a deep neural network while maintaining data locality during the federated training process. To further enhance privacy protection, we employ Differentially Private Stochastic Gradient Descent (DP-SGD) and add controlled noise to model updates, reducing the possibility of inferring individual data contributions. This work systematically evaluates how different privacy levels, expressed through ε and δ, influence model performance under simulated non-IID client distributions. The experiments analyze the privacy–utility trade-off using multiple evaluation metrics and compare the results with centralized and non-private federated-learning approaches. The findings show that the investigated framework maintains competitive predictive performance across a range of privacy budgets while demonstrating a clear privacy–utility trade-off. Very strict privacy budgets result in substantial performance degradation, particularly for smaller and more imbalanced datasets, whereas moderate privacy budgets maintain competitive predictive performance with limited degradation. This study highlights the potential of privacy-preserving federated learning for practical distributed analytics applications where protecting sensitive data is essential. Full article

Industrial steel property prediction is often constrained by limited labelled data, reducing the effectiveness of conventional machine learning models. This study investigated whether metallurgy-informed feature engineering enhances predictive performance under small-data conditions. A representative set of 300 samples from an industrial low-carbon hot-rolled steel strip dataset (C: 0.02–0.06 wt%; Mn: 0.17–0.38 wt%) was used to derive five physically meaningful descriptors: carbon equivalent (CE), nitrogen-to-aluminum ratio (N/Al), microalloying efficiency index (MEI), thermal processing parameter (TPP), and solid solution strengthening index (SSSI). These descriptors were combined with the original 17 compositional and processing variables to create a 22-feature dataset. Random Forest (RF) and Extreme Gradient Boosting (XGBoost) models were evaluated on an independent 60-sample test set using 5-fold cross-validation. Feature engineering improved the prediction accuracy, with the greatest gain observed for elongation. For XGBoost, the mean percentage error decreased from 3.23% to 3.05%, whereas the test-set R² increased from 0.4935 to 0.5444, representing a 10.3% improvement in the explained variance. For the yield strength, the Random Forest method increased the R² from 0.4744 to 0.4861. Permutation importance and partial dependence analyses identified MEI and TPP as the six most influential predictors across all targets, confirming that the engineered descriptors provide complementary metallurgical information. Learning curve analysis showed slightly higher cross-validation R² values at intermediate training sizes (n = 125–175), indicating modestly improved sample efficiency. These findings establish domain-informed feature engineering as an interpretable and practical strategy for improving machine learning in data-limited steel manufacturing processes. Full article

Residual creases generated during the leather spreading process exhibit highly variable morphologies and irregular feature distributions, causing significant challenges for feature extraction and leading to low localization accuracy. To address these issues, this paper proposes the Dynamic, Cross-Calibrated, and Edge-Enhanced YOLOv8n-Pose (DCE-YOLOv8n-Pose) algorithm. Instead of providing regional approximations, this framework outputs precise spatial coordinates for robotic grasping by integrating three synergistic components in a progressive network flow. First, dynamic snake convolution adaptively perceives the continuous geometric features of elongated creases; subsequently, an efficient multi-scale attention mechanism provides cross-dimensional weight calibration to suppress highly homochromatic background interference and correct spatial misalignments; finally, an edge-enhanced content-aware reassembly of features module preserves high-frequency gradients and prevents feature fracturing during multi-scale fusion. For comprehensive evaluation, a dataset comprising 700 original laboratory images was constructed. To prevent data leakage, the dataset was partitioned into training and validation sets based on individual leather specimens, ensuring that images of the same leather piece do not appear in both sets. Additionally, an independent test set of 500 images collected from an actual processing plant was designed for industrial validation. Experimental results indicate that, at an Intersection over Union (IoU) threshold of 0.5, the DCE-YOLOv8n-Pose model achieves a bounding box mean average precision (mAP@0.5) of 91.8% and a keypoint mAP@0.5 of 85.1%, with a keypoint precision of 87.9%. The computational load is maintained at 9.2 GFLOPs, alongside an inference speed of 114.3 FPS. Furthermore, consistent convergence across four independent training runs substantiates the model’s reliability in reducing missed detection rates and localization deviations. In conclusion, the proposed algorithm demonstrates practical applicability for the visual guidance of automated leather spreading equipment by balancing detection precision and inference speed, thereby offering an effective coordinate reference for subsequent robotic stretching operations. Full article