Search Results (3,340)

Class imbalance severely limits Network Intrusion Detection Systems (NIDSs) for minority Web attack classes: CICIDS2017 contains only 21 SQL Injection instances among 2.27 million benign flows. This study enriches CICIDS2017 with authentic SQL Injection, Cross-Site Scripting (XSS), and Web Brute Force (WBF) traffic captured from a controlled DVWA/XAMPP environment, processed with CICFlowMeter to match the original feature space. An anti-data-leakage protocol (stratified partitioning, post-split normalization, five-fold cross-validation, and a SHA-1 cryptographic membership audit of an 8881 –flow test sub-sample) found no hash collisions between this sub-sample and the evaluation partitions. The framework added 32,670 authentic flows, increasing SQL Injection from 21 to 10,678, XSS from 652 to 13,212, and WBF from 1507 to 10,960. Among four evaluated ensemble models, LightGBM performed best, achieving 99.85% Accuracy, 99.85% F1-score, 99.29% Balanced Accuracy, and 97.87 ± 1.88% in five-fold cross-validation, improving detection rates by 44.9% (XSS), 23.0% (WBF), and 16.6% (SQL Injection) over the original dataset. A volume-matched ablation study showed comparable aggregate accuracy to synthetic balancing methods (SMOTE, SMOTE-Tomek), while geometric diversity analysis confirmed that authentic traffic occupies feature-space regions unreachable by interpolation, and chronological holdout evaluation confirmed generalization to unseen traffic (F1: 98.53–99.90%). Real-traffic enrichment thus offers a practical, more realistic complement to synthetic balancing for minority Web-attack detection. Full article

Potato tuber dry rot is a major postharvest decay caused predominantly by Fusarium spp. During early infection, external symptoms may be absent even when faint internal browning, localized dehydration, and tissue structure changes have begun. Manual inspection, destructive cutting, and culture- or molecular-based assays are therefore poorly suited to rapid, nondestructive, high-throughput screening. We developed a near-infrared hyperspectral imaging method that combines spatial and spectral representations in a dual-branch ResNet12-SE network. The working dataset contained 1725 labeled records (862 healthy and 863 early-infected records); records were assigned to subsets by tuber identifier, and an infected volume ratio below 5% was used as an operational early infection threshold. The calibrated model input was a 224-band, 224 × 224 hyperspectral cube. The spatial branch used a ResNet-12 backbone with spatial squeeze-and-excitation (SE), whereas the spectral branch used spectral SE followed by bidirectional long short-term memory (BiLSTM). The two feature vectors were concatenated for binary classification. In the single-split test, the proposed model achieved 98.22% accuracy, compared with 90.67% for the ResNet-12 baseline and 97.43% for Vision Transformer. Preprocessing, principal component image, local binary pattern, and gray-level co-occurrence matrix analyses provide complementary interpretation of the spectral and spatial responses. The results support the feasibility of hyperspectral screening under the controlled laboratory protocol and define the validation work required before broader deployment. Full article

In compressible moving-domain computations, similar terminal responses can mask energy-input and pressure-transport biases from different origins, preventing physical attribution of modeling differences. A process-resolved model-choice attribution (PMCA) framework is therefore constructed and applied to 28 controlled cases of a 45 mm combustion light gas gun. Flow closure and heat-source normalization volume are varied independently within a shared forward problem. Differences are tracked from energy input through pressure transport and base-pressure work to the ballistic endpoint, and their stability across heat-release amounts and projectile masses is tested. The laminar closure leaves the applied energy unchanged; the first difference arises in pressure transport. Base-pressure work increases by 9.37–10.84%, mainly because temporal coupling between the pressure history and projectile motion is enhanced, rather than because the overall pressure level rises. Fixed-volume normalization first changes energy input: the applied energy exceeds the prescribed value by 3.48–10.81%, controlled by gas-region expansion during heat release. Base-pressure work then increases by 2.49–6.90%, and the two biases are approximately proportional across common conditions. Cross-condition reconstruction shows that the applied energy, pressure histories, and base-pressure work reproduce these differences in held-out conditions, whereas local peak pressures do not exhibit comparable stability. Terminal responses of strongly coupled moving domains are therefore many-to-one mappings of distinct internal transfer processes; terminal agreement does not guarantee agreement in energy input or pressure transport. PMCA advances model comparison for moving-boundary flows with volumetric sources from terminal matching to physical-process consistency checks. Full article

Physical artificial intelligence (PAI) has emerged as a transformative paradigm that integrates AI into physical entities, enabling direct interactions with real-world environments. However, despite rapid expansion across diverse domains, PAI research has remained highly fragmented and failed to provide a comprehensive understanding of its overarching knowledge structure. To address this gap, this study conducted a data-driven systematic review of 317 publications indexed in the Web of Science between September 2020 and October 2025. For the analysis of annual publication volume, the growth trend was assessed using complete calendar-year observations from 2021 to 2024, while the 2025 publication count was reported separately as a partial-year observation through October. Combining bibliometric network analysis with latent Dirichlet allocation topic modeling, we identified seven latent research topics. We integrated these fragmented topics into a unified, three-layered hierarchical architecture encompassing (1) physical interaction and infrastructure, (2) policy learning and control, and (3) cognitive integration and multimodal reasoning. The temporal analysis revealed a distinct evolutionary trajectory, indicating a structural shift from simulation-based, navigation-centric studies toward greater cognitive and multimodal integration and the practical implementation of embodied physical systems. This study provides a quantitative and structural mapping of PAI, offering a foundational framework to inform future interdisciplinary research and technological convergence. Full article

Accurate characterization of stray magnetic fields is essential in high-field devices, where external fields may affect diagnostics and personnel safety. Although finite-element models provide high-fidelity solutions, they may require extensive preprocessing and discretization of large source-free regions, making repeated evaluations costly when the magnetic source is unchanged. This paper proposes a reduced-order equivalent-dipole model that provides an analytical representation of the three-dimensional background stray field after one-time offline calibration. Dipoles are placed at Gauss–Legendre nodes within an auxiliary volume, while symmetry and anti-symmetry conditions are embedded in the source mapping. Their effective moments are identified from magnetic-flux-density data through a regularized linear inverse problem. The method is assessed for the SHiP spectrometer magnet at CERN against a high-fidelity finite-element reference. A controlled comparison of five model orders selects the 125-dipole configuration, reducing the relative vector $L^2$ error on a common three-dimensional evaluation grid from 21.2% for 27 dipoles to 4.59%. An independently generated dense three-dimensional post-selection dataset confirms the accuracy of the selected model, giving a relative vector $L^2$ error of $1.77\%$ for $d_{\mathrm{aux}}\ge 0.50$ m. The complementary dense mid-plane assessment gives $0.95\%$ over the same validity region. Full article

Assessing chart understanding requires distinguishing responses to local visual evidence from associations with a chart’s overall shape. We present Martingale Doppelgänger-Eval, an interventional audit framework that connects executable edit specifications to benchmark generation, validity checks and response estimation. Matched charts support separate measurements of evidence response and regional sensitivity. Each result carries its uncertainty, response coverage and identification status. We characterize conditions for identifying paired effects and specify a sequential procedure for audits that stop after inspecting accumulating evidence. We directly evaluate nine frozen vision–language models on 12,000 pairs generated with the corrected renderer. Complete-pair evidence scores range from 0.4362 to 0.4990, while supervised pixel controls generalize the learned rules to disjoint held-out symbols. A matched volume-only experiment reveals model-specific responses, and magnitude-matched regional edits quantify oracle-region sensitivity separately from the faithfulness of reported regions. The framework links interpretable visual comparisons to the conditions needed for their statistical evaluation. Full article

Rising volumes of agri-food waste highlight the need for innovative valorization strategies that simultaneously reduce environmental burdens and support sustainable agriculture. In this study, eggshell powder (ESP), spirulina powder (SP), and tannic acid (TA)—three low-cost amendments derived from food waste and algal biomass—were combined for the first time to evaluate their effects on the germination of durum wheat (Triticum durum Desf., cv. Vitron ORD). A Box–Behnken design coupled with response surface methodology (RSM) was employed to optimize the formulation across 17 experimental runs, using SP (0.2–1.0 g), ESP (0.4–1.2 g), and TA (0.005–0.015 g) as independent variables. An untreated distilled-water control and an artificial neural network (ANN) model were used for comparison and prediction assessment. Germination percentage varied substantially among treatments, ranging from 10.67% to 82.67%, compared with 48.00% in the untreated control. Formulations containing low SP, moderate-to-high ESP, and low TA mass exceeded the control, whereas high SP mass generally exerted inhibitory effects. The quadratic RSM model showed an excellent fit to the experimental data (R² = 0.9905; adjusted R² = 0.9783). Desirability-function optimization identified an optimal formulation consisting of 0.200 g SP, 0.766 g ESP, and 0.00534 g TA, with a predicted germination rate of 82.68%. The ANN model showed slightly superior predictive performance compared with RSM (R² = 0.99452; MAE = 0.470). Overall, the optimized low-dose SP–ESP formulation with minimal TA substantially enhanced germination relative to the untreated control, demonstrating the potential of combining algal biomass and food-waste-derived materials as a low-cost and environmentally sound strategy for seed priming and agricultural waste valorization. Full article

Background and Objectives: In this investigation, the mineral profile, antioxidant properties, and phenolic composition of tree gum exudates harvested from sour cherry (Prunus cerasus), mahaleb (Prunus mahaleb), and cherry (Prunus avium) were assessed, together with their in vivo diuretic efficacy in a Wistar albino rat model. Materials and Methods: Spectrophotometric quantification of total flavonoids and phenolics relied on aluminum nitrate and Folin–Ciocalteu reagents, respectively. Antioxidant potential was evaluated through radical scavenging tests, copper reduction capacity, and ferric reducing power, whereas ICP-MS was employed for elemental profiling. Rats were assigned to five groups: Control (distilled water), Furosemide (standard drug), PCRWE (group treated with P. cerasus tree gum exudate), PMRWE (group treated with P. mahaleb tree gum exudate), and PARWE (group treated with P. avium tree gum exudate). Urine samples collected at 5 and 24 h post administration were assessed for volume and Na⁺, K⁺, and Cl⁻ electrolyte concentrations to evaluate natriuretic and carbonic anhydrase activities. Results: Tree gum exudates contained rich mineral profiles, high phenolic and flavonoid levels, and strong antioxidant capacities. Cherry and mahaleb tree gum exudates showed low short-term and moderate long-term diuretic activity. In contrast, sour cherry tree gum exudate exhibited moderate short-term and high long-term diuretic activity. Furthermore, tree gum exudates significantly enhanced sodium, and potassium ion excretion compared to furosemide, demonstrating notable natriuretic and carbonic anhydrase activities. Conclusions: Tree gum exudates represent promising bioactive ingredients, antioxidants, or natural preservatives for food products. Specifically, sour cherry tree gum exudate displays significant diuretic and natriuretic potential, positioning it as a promising natural therapeutic agent for fluid balance management. Further research is required to isolate the active compounds and elucidate their specific mechanism on renal function. Full article

Calibration of debris-flow models is important for reproducible hazard mapping, transparent scenario analysis, and risk-informed territorial planning. Reliable calibration of debris-flow models is limited by parameter uncertainty, non-uniqueness, and the loss of spatial information when observations are reduced to scalar targets. This study presents a global–local full-flowfield inversion framework for estimating effective Voellmy friction parameters from complete final-thickness rasters, thereby replacing subjective trial-and-error adjustment with an explicit forward–inverse workflow and a spatially distributed objective function. A two-dimensional finite-volume shallow-flow solver is coupled with a genetic algorithm for bounded global exploration and projected finite-difference gradient descent for local refinement. The composite objective combines thickness, wet footprint, signed boundary distance, and total volume mismatches. The framework was evaluated through controlled parameter recovery, objective profiling, ten-seed repeatability tests, observation perturbations, conditional identifiability analysis, and a controlled Morino–Rendinara back-analysis retrieval test based on a published real-event parameterization and the real terrain. Uniform reference coefficients of 0.10, 0.25, and 0.45 were recovered with a mean absolute error of $1.90\times {10}^{-4}$ and exact wet footprint agreement. Across ten baseline inversions, the standard deviation of the estimate was $1.53\times {10}^{-4}$. Random removal of up to 50% of observation cells had negligible influence, whereas thickness noise and systematic scaling produced larger deviations; at 20% noise, mean IoU remained 0.9861. Prescribing $\xi$ between 250 and 1000 m s⁻² shifted the estimated $\mathsf{\mu }$ from 0.243038 to 0.254628 despite nearly identical final deposits, demonstrating conditional identifiability. In the two-zone experiment, the framework recovered ${\mathsf{\mu }}_{\mathrm{up}}=0.009991$ and ${\mathsf{\mu }}_{\mathrm{down}}=0.100184$, with a held-out RMSE of $4.49\times {10}^{-5}$ m and IoU equal to one. Full-flowfield inversion therefore provides accurate and reproducible event-specific parameter retrieval. Full article

Two-meter-scale true-triaxial hydraulic-fracturing models involve a large monitoring volume, strongly nonuniform microseismic event densities, and substantial vibration and background noise, making conventional fixed-scale clustering or direct geometric fitting prone to cluster fragmentation, event-band mixing, and low-support false planes. To address these limitations, this study proposes an automatic workflow for extracting dominant event planes from noisy microseismic point clouds. After quality control and spatial-boundary screening, nearest-neighbor statistics are used for adaptive density analysis, followed by support-first RANSAC plane fitting and PCA-based parameter refitting. Parameter sensitivity, null-model testing, and subsampling stability are further used to evaluate robustness. Extended synthetic tests demonstrate that the workflow can identify multiple planes under varying noise levels, event densities, plane spacing, and localization errors, while stage constraints are particularly important for separating spatially overlapping event bands. The method was then applied to three 2 m × 2 m × 1 m tight-sandstone fracturing experiments. For each specimen, 3200 high-quality candidate events were retained from approximately 10,000 located events. The extracted dominant subhorizontal event planes showed support fractions of 12.38%, 15.19%, and 11.94%, dips of 0.97°, 0.59°, and 1.83°, and RMS residuals of 10.96, 10.43, and 11.12 mm, respectively. The results indicate that the proposed workflow can consistently extract coherent dominant event planes from high-noise, nonuniform microseismic datasets in large-scale physical models. These planes represent dominant spatial structures of the located events and should not be interpreted directly as actual opened or conductive hydraulic-fracture surfaces. Full article

Global water scarcity necessitates precision irrigation management to optimize the balance between yield, water productivity (WP), and fruit quality. This study employed structural equation modeling (SEM) to explore the relationships between physiological responses, growth indicators, and yield of eight-year-old kiwifruit (Actinidia chinensis, cv. Jin Yan) under drip irrigation. A two-year field experiment (2018–2019) was conducted in a seasonally dry region of Southwest China, including 17 treatments across four growth stages: bud burst to leafing (I), flowering to fruit set (II), fruit expansion (III), and fruit maturation (IV). The treatments included a control (CK) and four irrigation lower limits at different growth stages: low (LL), mild (L), moderate (S), and severe (SS). Compared with CK, I-SS, II-S, III-LL, and IV-LL treatments significantly increased leaf instantaneous water use efficiency (WUEi) by 9.05%, 4.52%, 7.89%, and 9.55% (p < 0.05) respectively. After re-watering, II-L treatment significantly boosted Pn by 13.56% and Tr by 10.12%, leading to a 3.33% improvement in WUEi. Compared with CK, I-SS, and I-S treatments reduced the length of new shoots by 4.02% and 1.18% and the diameter of new shoots by 4.84% and 1.11%, while they increased fruit volume by 5.03% and 8.01%, respectively. I-SS and I-S treatments greatly increased the yield by 0.86–1.68% (p < 0.05), and increased water productivity (WP) by 3.90–4.31% (p < 0.05), respectively. Based on correlation analysis and SEM, kiwifruit yield was directly influenced by gs, leaf relative chlorophyll content, fruit volume, and shoot growth with standardized path coefficients of 0.377, 0.367, 0.546 and −0.04, respectively. For WP, gs, leaf relative chlorophyll content, fruit volume, and shoot growth exhibited direct path coefficients of −0.501, 0.342, 0.315, and 0.508, respectively. The IV-S, IV-SS, and I-SS treatments were consistently identified as the top three performers in both years using TOPSIS method of combining weights based on game theory. The suitable irrigation pattern was irrigation thresholds of 55%FC, 80%FC, 80%FC, and 60% FC for stages I, II, III, and IV, which enhanced the yield and WP of kiwifruit in Southwest China. This study could provide a scientific basis for precise soil moisture regulation of kiwifruit for similar production conditions. Full article

Carbonate reservoirs are typically characterized by well-developed natural fractures, and complex fracture-network geometries can significantly affect the effectiveness and efficiency of acidizing. In this study, a numerical simulation program for acidizing reactive transport in fractured carbonate reservoirs was developed based on a dual-continuum theory coupled with an Embedded Discrete Fracture Model. By decoupling complex fracture characteristics, we systematically investigated the controlling mechanisms of fracture dip angle and feature length ratio (FLR) on wormhole evolution and acidizing efficiency. The results show that fractures with small dip angles favor the development of the main wormhole trunk, whereas fractures with large dip angles redirect wormhole growth and promote the formation of complex branches. Under low FLR conditions, wormhole propagation is primarily governed by matrix heterogeneity, while a higher FLR markedly enhances the influence of fracture dip angle on overall wormhole development. The response of acid breakthrough volume (${\mathrm{PV}}_{\mathrm{BT}}$) to dip angle is strongly regulated by FLR. When FLR < 0.2, ${\mathrm{PV}}_{\mathrm{BT}}$ first increases and then decreases with dip angle, reaching a maximum at 45°, whereas for FLR > 0.2, ${\mathrm{PV}}_{\mathrm{BT}}$ increases approximately linearly with dip angle, indicating a substantial reduction in breakthrough efficiency. This study provides a theoretical basis for optimizing acidizing treatments in heterogeneous fractured carbonate reservoirs. Full article

The interaction of chemicals, nanoparticles, and circulating cells with the endothelium depends on the magnitude of the mechanical shear produced by the flow of blood. When simulating those interactions with microphysiological systems (MPSs), it is critical to reproduce those shear conditions faithfully. For example, unidirectional flow of a specific magnitude keeps the endothelium healthy with normal barrier tissue function, while bidirectional flow mimics disease conditions with compromised barrier function. Additionally, in MPS, recirculating fluid may be necessary to retain tissue-derived factors and metabolites. However, existing MPS designs struggle to achieve medium recirculation of small volumes of liquid with precise flow control. Here, we present an MPS design that is highly versatile and overcomes this limitation. We demonstrate how the device can produce a wide range of fluidic flow rates that can accommodate both low shear conditions suitable for tissues that typically are only exposed to interstitial flow and high shear conditions suitable for barrier tissues that experience blood flow. We demonstrate the device’s functionality by culturing human umbilical vein endothelial cells (HUVEC) and confirming their flow-aligned morphology through immunostaining of the adherens junction protein (VE-cadherin) and actin filaments. Furthermore, we present a mathematical model that can be used to calculate operating parameters for culturing any tissue under optimum conditions. We also discuss how the device can be adjusted to recirculate liquid volumes ranging from 100 µL to 5 mL. This versatile system holds promise for commercial applications, including the investigation of expensive compounds that are limited to very small volume samples such as rare cells (e.g., circulating tumor cells) or engineered therapeutic cells with barrier tissues. By offering precise control over a wide range of flow conditions with medium recirculation of small liquid volumes, our device addresses a critical gap in current MPS technology. Full article

Polymicrobial fracture-related infections (FRIs) underpinned by bacterial biofilms pose therapeutic challenges distinct from those of monomicrobial infection, as interspecies dynamics may alter both antimicrobial response and host tissue injury. This study evaluated systemic and local antibiotic strategies in an ovine FRI model co-inoculated with a polymicrobial Staphylococcus aureus and Pseudomonas aeruginosa biofilm. At 21 days, untreated positive controls retained substantial total bioburden yet paradoxically preserved bone volume and exhibited low osteoclast activity, contrasting with the marked osteolysis previously observed in monomicrobial infection controls using this model. Although untreated controls remained S. aureus predominant, their S. aureus:P. aeruginosa ratio declined from approximately 200:1 at inoculation to 15:1, indicating a progressive ecological shift over time. A systemic levofloxacin plus rifampin regimen more effectively reduced S. aureus than P. aeruginosa. Likewise, all antibiotic-treated groups shifted from an S. aureus-dominant inoculum toward P. aeruginosa predominance, consistent with unequal antimicrobial suppression altering polymicrobial pathogen balance. Single-dose local antibiotic powder and calcium sulfate bead strategies provided inconsistent microbiological benefit and failed to preserve bone. Reloadable local antibiotic delivery reduced S. aureus tissue bioburden and preserved the greatest bone volume among antibiotic-treated groups but the antibiotics selected for delivery did not prevent persistent P. aeruginosa colonization or the shift in pathogen balance. These findings indicate that microbiological burden reduction, residual pathogen composition, and bone preservation may result in distinct treatment outcomes in polymicrobial FRI. This study highlights the need for appropriate antibiotic selection with ecologically informed, dual targeted local and systemic strategies to manage polymicrobial, biofilm-complicated FRIs. Full article

As agricultural commodities become increasingly financialised, reliable soybean futures forecasts are important for risk management and market monitoring. This study examines the main No. 1 soybean futures contract listed on the Dalian Commodity Exchange using a multi-source daily dataset spanning from February 2015 to December 2025. Ten predictors cover domestic price-volume information, cross-market transmission, the macro-financial environment, and supply–demand fundamentals. To address potential look-ahead bias, the forecasting protocol is strictly causal: monthly fundamentals are lagged by one month before daily alignment; Chicago Board of Trade (CBOT) settlement information is matched only from dates strictly preceding the corresponding Dalian Commodity Exchange (DCE) date; Min-Max scalers are fitted on the training sample only; and wavelet denoising, when used, is performed separately within each 60-trading-day historical input window. Models are trained on target dates through 2022, validated on 2023–2024, and evaluated on the fully held-out 2025 sample. Five fixed random seeds, a random-walk benchmark, directional accuracy, and Diebold–Mariano (DM) tests are used to assess robustness. The results show that thediscrete wavelet transform–bidirectional long short-term memory with attention (DWT-BiLSTM-Attention) specification is sensitive to random initialisation and has significantly higher squared forecast loss than the random walk for the five-seed mean forecast. Among the neural-network specifications considered, the DWT-LSTM model provides the lowest mean root mean square error (RMSE) and the smallest RMSE dispersion across seeds, although its predictive accuracy is not statistically different from the random walk. The ablation results further show that causal DWT and the ten-feature specification do not deliver robust incremental gains, while the incremental effects of attention and bidirectionality are not statistically significant. These findings highlight the importance of leakage-controlled preprocessing, strong naive benchmarks, and repeated-seed evaluation in financial time-series forecasting. Full article