Search Results (296)

Cantilevered unstable rock masses constitute a prevalent geological hazard, with their stability intrinsically governed by the depth of trailing edge cracks. Traditional stability assessment methods, which largely rely on static calculations or displacement monitoring, often suffer from poor timeliness and insufficient early warning capabilities. To address these limitations, this study employs the Extended Finite Element Method (XFEM) to simulate the natural crack propagation trajectory and investigate the associated dynamic response characteristics under loading. The simulation results demonstrate that XFEM effectively captures the natural “vertical-to-oblique” fracture morphology, overcoming the limitations of pre-defined crack models. A critical correlation is established between crack evolution and natural frequency: the first-order natural frequency exhibits a staged decline, characterized by a precipitous drop of approximately 7 Hz during the late stage of fracture development (80–97% depth). Consequently, a “crack evolution–frequency response” model is proposed. This model confirms that natural frequency is a significantly more sensitive indicator of internal damage than displacement, providing a novel theoretical foundation and technical pathway for the early identification and dynamic evaluation of rock mass stability. Full article

Wafer map defect classification plays a critical role in yield monitoring and root-cause analysis in semiconductor manufacturing. Although recent convolutional neural network (CNN)-based approaches have achieved high classification accuracy, most existing models are evaluated primarily on clean datasets and remain vulnerable to unseen perturbations and representation-level variability at test time. In this paper, we propose a hybrid CNN–echo state network (ESN) architecture that integrates spatial feature extraction with sequential aggregation to enhance robustness under input perturbations. The CNN backbone extracts two-dimensional feature maps, which are converted into ordered sequences using a multidirectional scanline strategy and processed by an ESN reservoir. The resulting sequential representations are combined with CNN features through a class-specific adaptive fusion mechanism. Using the defect-only eight-class version of the WM-811K dataset, we systematically evaluate robustness under multiple perturbation scenarios, with particular focus on the clean train/noisy test (CT-NT) setting. To ensure a controlled robustness evaluation aligned with the binary nature of wafer map data, we introduce binary-consistent die-flip perturbations and additionally employ additive Gaussian perturbations as a representation-level stress test. Under clean-data conditions, the proposed model showed a 0.61 pp improvement in test accuracy compared to the ResNet34-based CNN, with notably larger gains for rare classes and defect types exhibiting strong structural patterns. In the clean train/noisy test scenario, where the model was trained on clean wafer map data and evaluated under controlled test-time perturbations, the accuracy of the CNN baseline dropped to 77.59% at $\sigma$ = 0.10, whereas the proposed hybrid model maintained an accuracy of 87.30%, resulting in an absolute improvement of 9.71 pp. Per-class analysis reveals that the robustness gain is class-dependent, with pronounced improvements for defect types exhibiting clear and repetitive structural patterns, such as Loc and Edge-Ring. Further mechanistic analysis demonstrates that the robustness improvement arises from enhanced representation stability and bounded reservoir dynamics, rather than from changes in CNN feature extraction or training regularization. These results demonstrate that the proposed CNN-ESN hybrid architecture provides meaningful advantages in terms of robustness under noisy evaluation conditions without requiring noise-aware training or prior knowledge of perturbation characteristics. Full article

Movie archives still rely on manual cataloging and sparse metadata, limiting fine-grained retrieval, relationship tracing, and reuse under privacy-constrained edge settings. We propose EdgeCineTag-KG, an edge framework using a single video foundation encoder and knowledge-constrained multi-label learning to produce consistent labels and build a queryable movie-archive knowledge graph. The objective jointly models label co-occurrence, mutual exclusion, hierarchy, and temporal consistency to reduce semantic contradictions and label jitter. For deployment, an uncertainty-driven adaptive computation strategy meets real-time constraints with controlled quality loss. Across MovieNet, Condensed Movies, Trailers12k, MMTF-14K, and TVQA, performance improves from 47.8 to 55.6 mAP and from 38.2 to 44.9 Macro-F1 on MovieNet, from 42.1 to 49.3 mAP on Condensed Movies, and from 71.2 to 75.4 mAP on Trailers12k. Knowledge graph quality also improves, with rule violation rate dropping from 6.8% to 2.4% and link prediction MRR rising from 0.248 to 0.312. Under INT8 adaptive inference, the system reaches 5.3 Clip-FPS, 182 ms P95 latency, and 1.9 GB peak memory. This combination improves consistency and retrieval usability without relying on multiple stacked foundation models. These results support reliable, interpretable, and edge-deployable movie archive understanding. Full article

Integrating Software-Defined Networking (SDN) to enhance mobility management in Vehicular Ad Hoc Networks (VANETs) comes with an additional critical risk. Because centralized controllers are single points of failure, they create the risk that the network will be subject to denial-of-service (DoS) attacks during handovers. Most Intrusion Detection and Prevention systems (IDPSs) do not adequately address these risks because they are topology-blind and have excessive processing layers. This article presents a novel Location-Aware SDN-IDPS Framework that employs a hierarchical defense approach to protect vehicular networks against volumetric attacks. This two-plane system operates with the first tier, which uses dynamic host-location mappings to drop spoofed traffic at the switch level (data plane). In contrast, the second tier analyzes confirmed traffic through a Suricata-based engine to identify and respond to complex flood attack patterns. The experimental results from the Mininet-WiFi testbed show that the system provides a significant improvement over the unprotected state, with controller CPU utilization reduced by up to 18 times (from 9.0% to below 0.5%). In addition, the system provides a 2.3 s guaranteed recovery time, service continuity, successful microsecond-level mitigation time, and a packet delivery ratio (PDR) of 99.73% for legitimate safety messages. In control-plane stress testing, the proposed location-aware logic improved throughput stability by approximately 76.26% compared to the baseline. These findings confirm that offloading anti-spoofing logic to the network edge significantly enhances resilience without compromising performance in safety-critical vehicular environments. Full article

The categorization of real-time defects in heterogeneous domains is a long-standing challenge in the field of industrial visual inspection systems, primarily due to significant visual variations and the lack of labelled information in real-world inspection settings. This work presents the Adaptive Attention DropBlock (AADB) framework, a lightweight deep learning framework that was developed to promote cross-domain defect detection using attention-guided regularization. The proposed architecture integrates the Convolutional Block Attention Module (CBAM) and an organized DropBlock-based regularization scheme, creating a unified and robust framework. Although CBAM-based approaches improve localization of defect-related areas and traditional DropBlock provides a generic spatial regularization, neither of them alone is specifically designed to reduce domain overfitting. To address this limitation, AADB combines attention-directed feature refinement with a progressive, transfer-aware dropout policy that promotes the learning of domain-invariant representations. The proposed model is built on a MobileNetV2 base and trained through a two-phase transfer learning regime, where the first phase consists of pretraining on a source domain and the second phase consists of adaptation to a visually dissimilar target domain with constrained supervision. The overall analysis of a metal surface defect dataset (source domain) and an aircraft surface defect dataset (target domain) shows that AADB outperforms CBAM-only, DropBlock-only, and conventional MobileNetV2 models, with an overall accuracy of 91.06%, a macro-F1 of 0.912, and a Cohen’s k of 0.866. Improved feature separability and localization of error are further described by qualitative analyses using Principal Component Analysis (PCA) and Grad-CAM. Overall, the framework provides a practical, interpretable, and edge-deployable solution to the classification of cross-domain defects in the industrial inspection setting. Full article

This paper develops a mechanism of PF-deletion within a probe–goal system that incorporates C-to-T feature inheritance. I propose that the phase head C enters the derivation not only with an edge feature (EF) and agree (φ-)features but also with a delete-feature, which licenses the deletion of an element at PF (PF-deletion). When C-to-T feature inheritance applies, the target of PF-deletion is determined through φ-probing from T; when it does not, it is determined through EF-probing from C. By linking PF-deletion to phase-internal probing, this approach dispenses with pro, traditionally assumed to exist in the lexicon of null subject languages such as Italian, as a theoretical primitive. Crucially, it offers a unified account of the distribution of null arguments in both Italian (a pro-drop language) and German (a topic-drop language), two language types that have traditionally resisted unified analysis under the principles-and-parameters approach. In addition to the synchronic study of the distribution of null arguments, I further argue that diachronic evidence from old languages such as Old French and Old English lends additional support to the proposal, and conclude that whether C-to-T inheritance applies or not is a crucial factor in explaining crosslinguistic variation in null argument phenomena. Full article

This study investigates the seismic performance of reinforced concrete flat slab buildings strengthened with conventional structural elements, including drop panels, edge beams, shear walls, and coupled shear walls. Unlike previous works that examined these elements independently, this research provides an integrated comparative evaluation of several common strengthening approaches under identical modeling and seismic loading conditions, offering clear guidance for practical design optimization. A comparative finite element analysis was conducted using ETABS v20 in accordance with ACI 318-19 and ASCE 7-22 seismic design provisions. Five ten-story building models were developed to assess key response parameters such as story displacement, inter-story drift, column axial forces, diaphragm deformation, and punching shear resistance under gravity and earthquake loading. Results reveal that models incorporating coupled shear walls achieve the greatest improved seismic performance, with up to 50% reduction in story displacement compared to other configurations, while also minimizing column over-compression and lateral drift. Drop panels alone showed a localized improvement in punching resistance, but their global impact on lateral stiffness was limited. However, the combination of drop panels and edge beams produced a synergistic effect, significantly enhancing overall stiffness and controlling drift. Coupled shear walls efficiently redirected lateral forces away from critical slab–column joints, thereby mitigating the risk of punching shear failure. These findings offer practical guidance for structural engineers seeking to optimize the seismic design of flat slab buildings, emphasizing the importance of integrated strengthening strategies in achieving both stiffness and ductility in seismic regions. The findings underline the significance of systematically evaluating conventional strengthening techniques within a unified modeling framework, offering engineers practical insights for improving the seismic behavior of flat slab buildings at the early stage of design. Full article

This study compares three detectors—Single Shot MultiBox Detector (SSD), Faster Region-based Convolutional Neural Network (Faster R-CNN), and Only Look Once v11 (YOLOv11)—for detecting subgrade distress in GPR radargrams. SSD converges fastest but shows weaker detection performance, while Faster R-CNN achieves higher localization accuracy at the cost of slower convergence. YOLOv11 offers the best overall performance. To push YOLOv11 further, we introduce three enhancements: a Multi-Scale Edge Enhancement Module (MEEM), a Multi-Feature Multi-Scale Attention (MFMSA) mechanism, and a hybrid configuration that combines both. On a representative dataset, YOLOv11_MEEM yields a 0.2 percentage-point increase in precision with a 0.2 percentage-point decrease in recall and a 0.3 percentage-point gain in mean Average Precision@0.5:0.95, indicating improved generalization and efficiency. YOLOv11_MFMSA achieves precision comparable to MEEM but suffers a substantial recall drop and slower inference. The hybrid YOLOv11_MEEM+MFMSA underperforms on key metrics due to gradient conflicts. MEEM reduces electromagnetic interference through dynamic edge enhancement, preserving real-time performance and robust generalization. Overall, MEEM-enhanced YOLOv11 is suitable for real-time subgrade distress detection in GPR radargrams. The research findings can offer technical support for the intelligent detection of subgrade engineering while also promoting the resilient development and sustainable operation and maintenance of urban infrastructure. Full article

In order to achieve better accuracy, modern models have become increasingly large, leading to an exponential increase in computational load, making it challenging to apply them to edge computing. Binary neural networks (BNNs) are models that quantize the filter weights and activations to 1-bit. These models are highly suitable for small chips like advanced RISC machines (ARMs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), system-on-chips (SoCs) and other edge computing devices. To design a model that is more friendly to edge computing devices, it is crucial to reduce the floating-point operations (FLOPs). Batch normalization (BN) is an essential tool for binary neural networks; however, when convolution layers are quantized to 1-bit, the floating-point computation cost of BN layers becomes significantly high. This paper aims to reduce the floating-point operations by removing the BN layers from the model and introducing the scaled weight standardization convolution (WS-Conv) method to avoid the significant accuracy drop caused by the absence of BN layers, and to enhance the model performance through a series of optimizations, adaptive gradient clipping (AGC) and knowledge distillation (KD). Specifically, our model maintains a competitive computational cost and accuracy, even without BN layers. Furthermore, by incorporating a series of training methods, the model’s accuracy on CIFAR-100 is 0.6% higher than the baseline model, fractional activation BNN (FracBNN), while the total computational load is only 46% of the baseline model. With unchanged binary operations (BOPs), the FLOPs are reduced to nearly zero, making it more suitable for embedded platforms like FPGAs or other edge computers. Full article

Metal Injection Molding (MIM) enables complex orthodontic-bracket geometries but can introduce surface and geometric discontinuities that act as initiation sites for crevice and pitting corrosion. The effect of acidic, kombucha-like exposure on corrosion and repassivation was assessed for MIM-316L brackets relative to a commercial comparator, and the coupling between surface quality (roughness and wettability) and localized damage at scanning electron microscopy (SEM)-identified hot-spots was examined. Kombucha was characterized by pH and titratable acidity. Surfaces were characterized by SEM, areal roughness metrics (R_a, S_a, S_z, and A2), and wettability by sessile-drop goniometry. Electrochemical behavior in artificial saliva was measured using open-circuit potential and cyclic potentiodynamic polarization (ASTM F2129/G59), and a qualitative magnetic check was included as a pragmatic quality-assurance screen. Exposure in kombucha reduced breakdown and repassivation potentials and increased passive current density, with the strongest effects co-localizing geometric discontinuities. Commercial brackets exhibited markedly poorer surface quality (notably higher S_z), amplifying acidity-driven susceptibility. These findings indicate that, under acidic challenges, surface/geometry quality dominates corrosion behavior; non-magnetic-phase compliance and simple chairside screening (e.g., magnet test), alongside tighter manufacturing controls on roughness and edge finish, should be incorporated into clinical and industrial quality assurance (QA). Full article

To improve the computational efficiency of complex fatigue assessments, this study proposes a framework that integrates high-fidelity finite element analysis (FEA)with ensemble learning for evaluating the fatigue performance of weathering steel welded joints. First, a three-dimensional crack propagation model for cruciform fillet welds was developed on the ABAQUS-FRANC3D platform, with a validation error of less than 20%. Subsequently, a large-scale parametric analysis was conducted. The results indicate that as the stress amplitude increases from 67.5 MPa to 99 MPa, the fatigue life decreases to 40.29% of the baseline value. When the stress amplitude reaches 180 MPa, the fatigue life drops sharply to 14.28% of the baseline. Within the stress ratio range of 0.1 to 0.7, increasing the initial crack size from 0.075 mm to 0.5 mm reduces the fatigue life to between 85.78% and 86.48% of the baseline. Edge cracks, influenced by stress concentration, exhibit approximately 15.2% shorter fatigue life compared to central cracks, while the maximum variation in fatigue life due to crack geometry is only 10.25%. Second, an Extremely Randomized Trees surrogate model constructed based on the simulation data demonstrates excellent performance. Finally, by integrating this model with Paris’s law, the developed prediction framework achieves high consistency with numerical simulation results, with all predicted values falling within the two-standard-deviation interval. This data-driven approach can effectively replace computationally intensive finite element analysis, enabling efficient structural safety assessments. Full article

Interactions between surface water and groundwater in arid regions regulate their response to climate and human impacts. In the salar systems of the Altiplano-Puna plateau (Bolivia, Chile, Argentina), understanding how surface waters connect to groundwater is crucial for accurate modeling and assessment. This study introduces new data and analysis using subsurface thermal profiles and modeling to identify flow patterns and possible surface water links. We document, to our knowledge, for the first time in the literature, deep-seated cooling of the subsurface caused by extreme evaporation rates. The subsurface is cooled by 4–5 degrees Celsius below the mean annual air temperature to depths greater than 50 m, even though groundwater inflow waters are elevated by 10 degrees °C due to geothermal heating. Three thermal zones are observed along the southern edge of Salar de Atacama, with temperature dropping from 28 °C to about 12 °C over 2.5 km. A 2D numerical model of groundwater and heat flow was developed to test various hydrological scenarios and understand the factors controlling the thermal regime. Two flow scenarios at the southern margin were examined: a diffuse flow model with uniform flow and flux to the surface and a focused flow model with preferential discharge at a topographic slope break. Results indicate that the focused flow scenario matches thermal data, with warm inflow water discharging into a transition zone between freshwater and brine, cooling through evaporation, re-infiltration, and surface flow, then re-emerging near lagoons at the halite nucleus margin. This research offers valuable insights into the groundwater hydraulics in the Salar de Atacama and can aid in monitoring environmental changes causally linked to lithium mining and upgradient freshwater extraction. Full article

Traditional routing algorithms optimizing for distance or travel time are inadequate for electric vehicles (EVs), which require energy-aware planning considering battery constraints and charging infrastructure. This work presents an energy-optimal routing system for EVs that integrates personalized consumption modeling with real-time environmental data. The system employs a Long Short-Term Memory (LSTM) neural network to predict State-of-Charge (SoC) consumption from real-world driving data, learning directly from spatiotemporal features including velocity, temperature, road inclination, and traveled distance. Unlike physics-based models requiring difficult-to-obtain parameters, this approach captures nonlinear dependencies and temporal patterns in energy consumption. The routing framework integrates static map data, dynamic traffic conditions, weather information, and charging station locations into a weighted graph representation. Edge costs reflect predicted SoC drops, while node penalties account for traffic congestion and charging opportunities. An enhanced A* algorithm finds optimal routes minimizing energy consumption. Experimental validation on a Nissan Leaf shows that the proposed end-to-end SoC estimator significantly outperforms traditional approaches. The model achieves an RMSE of 36.83 and an $R^2$ of 0.9374, corresponding to a 59.91% reduction in error compared to physics-based formulas. Real-world testing on various routes further confirms its accuracy, with a Mean Absolute Error in the total route SoC estimation of 2%, improving upon the 3.5% observed for commercial solutions. Full article

Melamine-faced particleboards are widely used in interior applications; however, their performance is often limited by the near-surface structure, film adhesion, and edge damage that can be generated during machining and service impacts. Here, model particleboards were produced with 0%, 10%, 20%, and 40% bark content in the face layers and laminated with two melamine films (light and dark décor). Density profiles, mechanical properties (MOR, MOE, internal bond, IB), and laminate adhesion (pull-off) were determined. Edge integrity was evaluated under edge milling, quantified by cumulative tear-out length (ΣL) and the normalized damage index L_i (mm/m) together with tear-out depth, and under edge impact using a 0.5 kg mass dropped from 0.20 m (damage length and indentation depth). All boards were characterized by a typical U-shaped density profile, while increasing bark share reduced surface-layer density differentiation. MOR and MOE decreased significantly only at 40% bark, whereas IB (0.54–0.74 N/mm²) remained unchanged. Bark content significantly affected adhesion (32.76% contribution), whereas film type was not a significant factor. Milling damage depended on laminate: for the dark laminate, bark-containing boards showed much higher L_i (54.82–60.13 mm/m) than the reference (12.26 mm/m); for the light laminate, the lowest L_i occurred at 10% bark (21.24 mm/m). Tear-out depth varied narrowly (≈0.69–1.02 mm), while impact damage length ranged from 6.96 to 8.58 mm. Full article

Beamforming is highly significant for the physical layer of wireless communication systems, for multi-antenna systems such as multiple input multiple output (MIMO) and massive MIMO, since it improves spectral efficiency and reduces interference. Traditional linear beamforming methods such as zero-forcing beamforming (ZFBF) and minimum mean square error (MMSE) beamforming provide closed-form solutions. Yet, their performance drops when they face non-ideal conditions such as imperfect channel state information (CSI), dynamic propagation environment, or high-dimensional system configurations, primarily due to static assumptions and computational limitations. These limitations have led to the rise of deep learning-based beamforming, where data-driven models derive beamforming solutions directly from CSI. By leveraging the representational capabilities of cutting-edge deep learning architectures, along with the increasing availability of data and computational resources, deep learning presents an adaptive and potentially scalable alternative to traditional methodologies. In this work, we unify and systematically compare our two unsupervised learning architectures for uplink receive beamforming: a simple neural network beamforming (NNBF) model, composed of convolutional and fully connected layers, and a transformer-based NNBF model that integrates grouped convolutions for feature extraction and transformer blocks to capture long-range channel dependencies. They are evaluated in a common multi-user single input multiple output (MU-SIMO) system model to maximize sum-rate across single-antenna user equipments (UEs) under 3GPP-compliant channel models, namely TDL-A and UMa. Furthermore, we present a FLOPs-based asymptotic computational complexity analysis for the NNBF architectures alongside baseline methods, namely ZFBF and MMSE beamforming, explicitly characterizing inference-time scaling behavior. Experiments for the simple NNBF are performed under simplified assumptions such as stationary UEs and perfect CSI across varying antenna configurations in the TDL-A channel. On the other hand, transformer-based NNBF is evaluated in more realistic conditions, including urban macro environments with imperfect CSI, diverse UE mobilities, coding rates, and modulation schemes. Results show that the transformer-based NNBF achieves superior performance under realistic conditions at the cost of increased computational complexity, while the simple NNBF presents comparable or better performance than baseline methods with significantly lower complexity under simplified assumptions. Full article