Search Results (58)

Hypergraph Neural Networks (HGNNs) have demonstrated exceptional capability in modeling high-order correlations; however, their vulnerability to adversarial attacks remains inadequately addressed due to the limited scope of existing security investigations. The prevailing white-box structural attack, HyperAttack, relies exclusively on gradient-derived information and overlooks the semantic affinities between nodes and hyperedges. This oversight limits attack efficacy because gradient signals can be noisy or ambiguous under certain conditions (e.g., saturated regions or local optima), whereas semantic similarities provide complementary cues that help identify hyperedges whose perturbation more reliably alters the target node’s representation. To mitigate this limitation, this paper introduces a semantic enhanced adversarial attack framework for hypergraph neural networks, termed SE-HyperAttack. Specifically, hyperedge features are first aggregated, and semantic similarity scores are computed based on the feature similarity between target nodes and their incident hyperedges to capture latent semantic correlations. These semantic similarity scores are subsequently integrated with integrated gradient scores via a weighted summation scheme, refining the precision of hyperedge selection. Extensive experiments on two datasets demonstrate that the proposed SE-HyperAttack achieves an optimal average attack success rate (ASR) of 79.4%, showing an improvement of 2.6% over HyperAttack. Ablation studies further ascertain that a semantic weight of 30% yields peak performance, beyond which degradation is observed. Notably, the proposed approach preserves computational efficiency commensurate with HyperAttack, incurring negligible additional overhead. These findings substantiate that the integration of semantic information effectively enhances adversarial attack effectiveness on hypergraph neural networks without compromising efficiency. Full article

This paper presents the mechatronic design, mathematical modeling, parameter identification, and nonlinear position control of an open-architecture biaxial shake table capable of generating base acceleration along two orthogonal horizontal directions. The shake table is tailored for engineering research and education. Addressing the limitations of proprietary “black-box” systems, the platform is constructed using standard industrial components (HLTNC-CNC modules and NEMA 23 BLDC motors) to ensure reproducibility. A core contribution is the characterization of the system’s nonlinear dynamics to enhance tracking fidelity. The mathematical model, derived via the Euler–Lagrange formulation, incorporates viscous and Coulomb friction phenomena, which are critical for accurately reproducing zero-velocity crossings in seismic signals. System parameters are identified using the Recursive Least Squares (RLS) algorithm combined with State Variable Filters (SVFs) to process the regression vector. To enable precise closed-loop performance, a nonlinear state observer incorporating the identified friction dynamics is designed for velocity estimation. Furthermore, a Computed Torque Control (CTC) strategy is synthesized and compared against a conventional Proportional-Velocity (PV) controller. Experimental validations using historical ground motions, including the 1986 Colima earthquake, confirm that the CTC strategy reduces the maximum absolute tracking error by more than 75% compared to the PV approach, bounding the peak error to $0.36\mathrm{mm}$ across both axes. Furthermore, in high-amplitude scenarios, the proposed model-based approach achieved an RMS tracking error reduction of more than 83%. These results validate the proposed platform as a reliable and accessible tool for structural dynamics testing. Full article

Green Total Factor Productivity (GTFP) serves as a pivotal indicator for balancing high-quality economic growth with increasingly stringent environmental regulations. However, empirical evidence regarding whether and how firm-level GTFP is associated with enhanced Environmental, Social, and Governance (ESG) performance in emerging markets remains limited. This study addresses this gap by examining the GTFP–ESG nexus within the macro-context of China’s “Dual-Carbon” goals (aiming for peak carbon emissions by 2030 and carbon neutrality by 2060). Utilizing an unbalanced panel dataset of Chinese A-share listed companies strictly covering the period from 2011 to 2022 (with 2010 data exclusively used for one-period lagged variables), we construct firm-level GTFP metrics using a non-radial SBM-DDF global Malmquist–Luenberger index—incorporating both desirable economic outputs and undesirable environmental emissions—and link them with Huazheng ESG ratings. To ensure robust empirical identification, we employ two-way fixed-effects models with lagged variables, propensity score matching (PSM), and an instrumental variable two-stage least squares (IV-2SLS) approach utilizing the leave-one-out provincial average GTFP as an instrument. The results indicate a significant positive association between GTFP and overall ESG performance, as well as its three sub-pillars. Specifically, a one-standard-deviation increase in GTFP corresponds to a 0.15-standard-deviation increase in the ESG score, a marginal effect of profound economic significance, providing robust associational insights via the IV estimates. Mechanism analyses reframe traditional mediation as descriptive associational pathways, revealing that digital transformation, green innovation, and information transparency serve as significant channels, theoretically demonstrating how resource efficiency translates into social legitimacy. Heterogeneity tests show that this association is more pronounced for non-state-owned enterprises, firms in eastern China, and those with lower financing constraints. These findings unpack the “black box” between technical efficiency and sustainability, providing empirical support for policymakers to align corporate productivity with international disclosure standards (such as the EU’s CSRD). Full article

This study presents a statistically optimized protocol for the green synthesis of gold nanoparticles (Au NPs) using aqueous Kalanchoe pinnata leaf extract (AKPLE). An integrated experimental strategy, transitioning from preliminary one-factor-at-a-time (OFAT) screening to a five-factor Box–Behnken Design, was employed to model and simultaneously optimize two critical optical responses derived from surface plasmon resonance: the peak position (λ_max) and its absorbance intensity. Highly predictive quadratic models (R² > 0.97) revealed that synthesis outcomes are governed by significant nonlinear curvature, with minimal interaction effects. Multi-response optimization via a desirability function identified a harmonized set of conditions (HAuCl₄: 0.44 mM, AKPLE: 3.50% v/v, temperature: 80.6 °C, pH: 7.2, time: 66.7 min) predicted to minimize λ_max at 540 nm while maximizing absorbance to 0.61. Synthesis under these optimized conditions successfully produced spherical, crystalline Au NPs, as confirmed by characterization (average TEM size: 26.3 ± 4.1 nm; zeta potential: –30.45 mV). This work demonstrates that a hybrid OFAT-RSM approach is superior for the precise, multivariate optimization of plant-mediated Au NP synthesis, providing a validated and scalable framework to balance nanoparticle size and plasmonic intensity—an outcome unattainable through conventional OFAT methods. Full article

High-quality Fourier Transform Infrared (FTIR) imaging usually needs extensive signal averaging to reduce noise and drift, which severely limits clinical speed. Deep learning can accelerate imaging by reconstructing spectra from rapid, single-scan inputs. However, separating noise and baseline drift simultaneously without ground truth is an ill-posed inverse problem. Standard black-box architectures often rely on statistical approximations that introduce spectral hallucinations or fail to generalize to unstable atmospheric conditions. To solve these issues, we propose a physics-informed cascade Unet that separates denoising and baseline correction tasks using a new, deterministic Physics Bridge. This architecture forces the network to separate random noise from chemical signals using an embedded SNIP layer to enforce spectroscopic constraints instead of learning statistical approximations. We benchmarked this approach against a standard single Unet and a traditional Savitzky–Golay smoothing followed by SNIP baseline correction workflow. We used a dataset of human hypopharyngeal carcinoma cells (FaDu). The cascade model outperformed all other methods, achieving a 51.3% reduction in RMSE compared to raw single-scan inputs, surpassing both the single Unet (40.2%) and the traditional workflow (33.7%). Peak-aware metrics show that the cascade architecture eliminates spectral hallucinations found in standard deep learning. It also preserves peak intensity with much higher fidelity than traditional smoothing. These results show that the cascade Unet is a robust solution for diagnostic-grade FTIR imaging. It enables imaging speeds 32 times faster than current methods. Full article

Single-Event Burnout (SEB) is one of the most critical failure mechanisms in silicon power MOSFETs operating in radiation environments, particularly under heavy-ion irradiation, and often limits device operation through excessive voltage derating. In this work, SEB robustness of a silicon VDMOS power device is investigated using detailed electro-thermal transient simulations. The study evaluates two complementary device-level modifications: the introduction of a buffer layer between the epitaxial layer and the substrate, which has been reported in the past, and a new approach considering the incorporation of a novel highly doped boron BOX implant within the P-body region. Heavy-ion impacts are simulated using a physically based model implemented in SENTAURUS TCAD, accounting for ion energy deposition, impact position, and thermal effects. The results show that the buffer layer increases the second breakdown voltage and can suppress high-current operating points, while the BOX implant raises the parasitic BJT activation threshold by reducing the P-body resistance. When combined, both modifications lead to a significant reduction in the peak temperature reached during after-impact transients, without introducing measurable degradation of static electrical characteristics. These results demonstrate that combining buffer layer engineering with localized P-body resistance reduction is an effective strategy to improve SEB robustness in silicon VDMOS power devices without relying on excessive derating. Full article

In forensic pathology, accurately estimating the time since injury is essential. Current histological and imaging approaches commonly miss subtle temporal changes, especially in deaths occurring within hours of injury. This review discusses the timing of neuroinflammation after traumatic brain injury and emphasizes possible markers for estimating the time of injury in forensic cases. Promising markers include microglial activation (allograft inflammatory factor 1 and transmembrane protein 119, detectable within 10 min to 2 h), β-amyloid precursor protein accumulation (20–35 min), high-mobility group box 1 translocation (2–6 h), cytokine fluctuations (IL-1β and TNF-α peak between 4 and 24 h, IL-6 shows delayed, extended elevation), sequential leukocyte infiltration (neutrophils from 2 to 48 h, lymphocytes after 3–5 days), blood–brain barrier breakdown markers such as fibrinogen and IgG leakage, loss of tight junction proteins (2–3 h), matrix metalloproteinase-9 activity (peaking at 24–48 h), and reactive astrocytosis with increased glial fibrillary acidic protein levels (from 12 to 24 h onward). The association between injury severity and inflammation is influenced by factors such as age, genetics (e.g., APOE ε4), coexisting conditions, and preexisting inflammation, which reduce the reliability of individual markers. A multiparametric approach may offer the best prospects to improve the accuracy of post-traumatic and post-mortem interval assessment in medicolegal cases. Full article

An integrated methodology was employed, incorporating spray pyrolysis synthesis, gamma irradiation post-treatment, and Box–Behnken statistical optimization. This approach was designed to systematically refine the structural and optical properties of CZTS thin films, with the objective of enhancing their photocatalytic degradation efficiency. At a dose of 5 kGy, gamma irradiation resulted in an approximately 300% increase in crystallite size and improved crystallinity relative to non-irradiated samples. As the irradiation increases, the films exhibited a stronger preferential orientation along the (112) plane, which peaked at 20 kGy. Analysis using the Williamson–Hall method revealed complex microstructural evolution, showing crystallite sizes varying from ~12.48 nm to ~71.27 nm based on the irradiation dose applied. The photocatalytic activity was assessed through the UV-driven degradation of Brun Sella Solid dye, employing H₂O₂ as a co-reactant. The optimization process, guided by the Box–Behnken design which tested parameters such as pH (2 to 14), gamma dose (0 to 20 kGy), and H₂O₂ volume (100 to 500 μL), achieved a remarkable maximum degradation efficiency of 98% under optimal conditions. This study highlights the synergistic combination of controlled defect engineering through gamma irradiation and meticulous parameter optimization establishing a robust framework for the development of high-performance, earth-abundant photocatalysts suitable for environmental remediation applications. Full article

This study presents a hybrid experimental–numerical methodology for the preliminary design and optimization of a CFRP crash box intended for high-performance automotive applications. An initial experimental campaign was conducted on frustum-shaped crash boxes manufactured by Pagani Automobili S.p.A., comparing constant and variable thickness configurations through drop tower impact tests to evaluate energy absorption, crushing stability, and failure mechanisms. A lightweight finite element model was developed in Abaqus/Explicit using shell elements and Hashin-based damage criteria, achieving calibration errors below 10% for most parameters and under 15% for peak forces. Geometric enhancements, including continuous flanges, removal of the top surface, and an internal cruciform reinforcement, significantly improved energy absorption (up to 110%) but introduced trade-offs in stroke efficiency and mean force levels. To mitigate these effects, a genetic algorithm was employed to optimize laminate layup by varying ply orientations, resulting in improved stroke efficiency and reduced peak and average forces while maintaining crushing stability. The proposed approach demonstrates that integrating experimental validation with efficient numerical modeling and optimization accelerates the development of lightweight, high-performance crash absorbers, offering a robust framework for motorsport and automotive applications that balances safety, efficiency, and manufacturability. Full article

This paper presents a novel carbon fiber reinforced polymer (CFRP) crash box design, incorporating numerical analysis and manufacturing aspects. Within the design and analysis phases, a novel numerical methodology is employed to mitigate computational costs in estimating specific energy absorption (SEA). The proposed approach involves a reduction in ply interfaces and modification of pertinent material properties to optimize energy dissipation, achieving more than 50% reduction in simulation time. This methodology is applied to the design of a composite crash box made of unidirectional (UD) carbon/epoxy prepregs, resulting in a new geometry: sun-like shape featuring four sinusoidal arms connected to a central circular core. Subsequent manufacturing and testing reveal a SEA value of 79.46 J/g for designed geometry, surpassing metallic counterparts by a factor of 3 to 4. Furthermore, this study conducts a comparative analysis of energy absorption performance between unidirectional and woven fabric prepregs for the same geometry. Utilizing carbon/epoxy woven fabric (WF) prepregs further enhances the SEA to 89.26 J/g. Finally, the application of edge tapering to the crash box structure is shown to eliminate initial peak loads, thereby preventing excessive deceleration. Full article

Railway passenger flow forecasting plays a critical role in operational efficiency and resource allocation for transportation systems. However, existing deep learning approaches suffer significant performance degradation when facing rare but high-impact events, primarily due to sample scarcity and their inability to distinguish between routine patterns and disruption regimes. To address these challenges, this study introduces EA-ARIMA-Informer, an adaptive forecasting framework that integrates entropy-augmented ARIMA with Informer through an entropy-guided regime-switching mechanism. The passenger flow series is characterized through a multi-dimensional entropy space comprising four complementary measures: Sample Entropy quantifies local regularity and predictability, Permutation Entropy captures the complexity of ordinal dynamics, Transfer Entropy measures causal information flow from external events (holidays, weather) to passenger demand, and the Conditional Entropy Growth Factor (CEGF)—a novel metric introduced herein—detects regime transitions by tracking the rate of uncertainty change between consecutive time windows. These entropy indicators serve dual roles as feature inputs for representation learning and as state identifiers for segmenting the time series into stable and fluctuating regimes with distinct predictability properties. An adaptive dual-path architecture is then designed accordingly: EA-ARIMA handles low-entropy stable regimes where linear seasonality dominates, while EA-Informer processes high-entropy fluctuating regimes requiring nonlinear residual modeling, with CEGF-guided gating dynamically controlling component weights. Unlike conventional black-box gating mechanisms, this entropy-based switching provides physically interpretable signals that explain when and why different model components dominate the forecast. The framework is validated on a large-scale dataset covering nearly 300 Chinese cities over three years (2017–2019), encompassing normal operations, holiday peaks, and extreme weather disruptions. Experimental results demonstrate that EA-ARIMA-Informer achieves a MAPE of 4.39% for large-scale cities and 7.82% for data-scarce small cities (Tier-3), substantially outperforming standalone ARIMA, XGBoost, and Informer, which yield 15.95%, 13.75%, and 12.87%, respectively, for Tier-3 cities. Ablation studies confirm that both entropy-based feature augmentation and CEGF-guided regime switching contribute significantly to these performance gains, establishing a new paradigm for interpretable and adaptive forecasting in complex transportation systems. Full article

Mid-sized Philippine cities commonly rely on fixed-time traffic signal plans that cannot respond to short-term, demand-driven surges, resulting in measurable idle time at stop lines, increased delay, and unnecessary emissions, while adaptive signal control has demonstrated performance benefits, many existing solutions depend on centralized infrastructure and high-bandwidth connectivity, limiting their applicability for resource-constrained local government units (LGUs). This study reports a field deployment of TrafficEZ, a lightweight edge AI signal controller that reallocates green splits locally using traffic-density approximations derived from cabinet-mounted cameras. The controller follows a macroscopic, cycle-level control abstraction consistent with Transportation System Models (TSMs) and does not rely on stationary flow–density–speed (fundamental diagram) assumptions. The system estimates queued demand and discharge efficiency on-device and updates green time each cycle without altering cycle length, intergreen intervals, or pedestrian safety timings. A quasi-experimental pre–post evaluation was conducted at three signalized intersections in El Salvador City using an existing 125 s, three-phase fixed-time plan as the baseline. Observed field results show average per-vehicle delay reductions of 18–32%, with reclaimed effective green translating into approximately 50–200 additional vehicles per hour served at the busiest approaches. Box-occupancy durations shortened, indicating reduced spillback risk, while conservative idle-time estimates imply corresponding CO₂ savings during peak periods. Because all decisions run locally within the signal cabinet, operation remained robust during backhaul interruptions and supported incremental, intersection-by-intersection deployment; per-cycle actions were logged to support auditability and governance reporting. These findings demonstrate that density-driven edge AI can deliver practical mobility, reliability, and sustainability gains for LGUs while supporting evidence-based governance and performance reporting. Full article

Deep neural networks are vulnerable and susceptible to adversarial examples, which can induce erroneous predictions by injecting imperceptible perturbations. Transferability is a crucial property of adversarial examples, enabling effective attacks under black-box settings. Adversarial examples at flat maxima-those around which the loss peaks and grows slowly-have been demonstrated to exhibit higher transferability. Existing methods to achieve flat maxima rely on the gradient of the worst-case loss within the small neighborhood around the adversarial point. However, the neighborhood structure is typically defined as a Euclidean space, which neglects the input space’s information geometry, leading to suboptimal results. In this work, we build upon the idea of flat maxima but extend the neighborhood structure from Euclidean space to the manifold measured by the Fisher metric, which takes into account the information geometry of the data space. In the non-Euclidean case, we search for the worst-case point in the direction of the natural gradient with respect to adversarial examples. The natural gradient adjusts the original gradient using the Fisher information matrix, giving the steepest direction in the manifold. Furthermore, to reduce the computational cost of calculating the Fisher information matrix, we introduce a diagonal approximation of the matrix and propose an empirical Fisher method under the model ensemble setting. Experimental results demonstrate that our proposed manifold extensions significantly enhance attack success rates against both normally and adversarially trained models. In particular, compared to methods relying on the Euclidean metric, our approach demonstrates more efficient performance. Full article

Background/Objectives: Postoperative sensitivity remains a common challenge following direct composite restorations, especially in Class II cavities with deep proximal boxes. The snow-plow and resin-coating techniques have been proposed to improve marginal adaptation and reduce postoperative discomfort; however, comparative clinical data remain limited. This prospective, split-mouth, quasi-experimental study aimed to compare postoperative pain associated with Class II restorations placed using either the snow-plow or resin-coating technique. Methods: This prospective, split-mouth study followed 83 adult patients (aged 18–45 years) who received bilateral Class II composite restorations for one week. The study received ethical approval. Each participant received one restoration using the snow-plow technique and another using the resin-coating approach. Pain intensity was evaluated using a 10-point visual analog scale (VAS) at baseline, 24-h, 72-h, and 1-week postoperatively. Analyses included Wilcoxon signed-rank, Friedman, Chi-square, McNemar, and two-way repeated-measures ANOVA tests. Results: Pain intensity peaked at 24-h for both techniques and declined significantly by 72-h and 1 week (p < 0.001). The snow-plow technique showed slightly lower mean pain scores at 24 and 72 h (p = 0.026 and p = 0.004, respectively), though categorical analyses revealed no significant difference in pain-free or minimal-pain proportions at any interval (p > 0.05). Both techniques showed significant within-group reductions in pain over time (p < 0.001). Conclusions: Both restorative approaches demonstrated similar postoperative pain trajectories, with substantial improvement by one week. While minor differences in early mean pain intensity were observed, these were not clinically significant. The findings suggest that either technique can be effectively employed to achieve satisfactory postoperative comfort when modern adhesive protocols are applied. Clinicians can therefore select either technique based on preference and clinical circumstances, with the expectation of comparable short-term postoperative comfort outcomes. Full article

Harvesting winter jujubes is a key step in production, yet traditional manual approaches are labor-intensive and inefficient. To overcome these challenges, we propose SCC-YOLO, a lightweight method for winter jujube detection, 3D localization, and cross-platform deployment, aiming to support intelligent harvesting. In this study, RGB-D cameras were integrated with an improved YOLOv11 network optimized by ShuffleNetV2, CBAM, and a redesigned C2f_WTConv module, which enables joint spatial–frequency feature modeling and enhances small-object detection in complex orchard conditions. The model was trained on a diversified dataset with extensive augmentation to ensure robustness. In addition, the original localization loss was replaced with DIoU to improve bounding box regression accuracy. A robotic harvesting system was developed, and an Eye-to-Hand calibration-based 3D localization pipeline was implemented to map fruit coordinates to the robot workspace for accurate picking. To validate engineering applicability, the SCC-YOLO model was deployed on both desktop (PyTorch and ONNX Runtime) and mobile (NCNN with Vulkan+FP16) platforms, and FPS, latency, and stability were comparatively analyzed. Experimental results showed that SCC-YOLO improved mAP by 5.6% over YOLOv11, significantly enhanced detection precision and robustness, and achieved real-time performance on mobile devices while maintaining peak throughput on high-performance desktops. Field and laboratory tests confirmed the system’s effectiveness for detection, localization, and harvesting efficiency, demonstrating its adaptability to diverse deployment environments and its potential for broader agricultural applications. Full article