Search Results (3,597)

To investigate the influence of porosity defects and the strengthening effect of bonded iron-based shape memory alloy (Fe-SMA) plates, fatigue tests were conducted on defect-free, porosity-containing, and Fe-SMA-strengthened U-rib butt-welded specimens. A numerical model considering porosity defects and the bonded Fe-SMA plate was also established and validated against the experimental results. The results show that porosity defects significantly increased the local stress level near the crack. Under a load of 60 kN, the stress at the section 2 mm from the crack edge increased from 98 MPa to 139.5 MPa. Meanwhile, the fatigue life decreased from 260 × 10⁴ cycles to 127 × 10⁴ cycles. After Fe-SMA strengthening, the stress decreased to 75.59 MPa, and the fatigue life increased to 326 × 10⁴ cycles, which was 2.57 times that of the unreinforced defective specimen. The Fe-SMA plate did not change the fatigue crack propagation path but effectively slowed crack growth through local stiffness enhancement and activation-induced pre-compressive stress. Parametric analysis further showed that, among the investigated numerical cases, an activation temperature of 200 °C produced the largest predicted strengthening effect. Increasing the pore diameter from 0.5 mm to 2.0 mm reduced the reinforcement effect from 69.45% to 52.98%, and increasing the crack length from 10 mm to 50 mm reduced it from 65.41% to 35.53%. These results indicate that bonded Fe-SMA plates can effectively improve the fatigue performance of U-rib butt-welded joints with porosity defects, especially when applied before excessive crack growth occurs. Full article

Leading-edge tubercles provide a bio-inspired modification for regulating the hydrodynamic performance of marine propellers, but their controllable generation on complex three-dimensional blades remains insufficiently studied. This study develops a parametric modeling method for tubercled leading-edge propellers based on the David Taylor Model Basin (DTMB) 4383 geometry. The method combines B-spline smooth reconstruction with a Gaussian envelope function to control tubercle radial peak position and height. After validation with publicly available open-water experimental data, the computational fluid dynamics (CFD) method is applied to uniform and locally targeted tubercled models. The results show that leading-edge tubercles modify the suction-side low-pressure region and redistribute local blade loading. The radial peak position mainly controls the concentration region of the pressure disturbance, whereas peak height affects its intensity. At the design advance coefficient, moving the target peak from r/R = 0.26 to r/R = 0.92 decreased the thrust coefficient by 0.77% and increased the torque coefficient by 1.75%. For a fixed target position, increasing the maximum amplitude ratio from 0.05 to 0.80 increased the thrust and torque coefficients by 0.25% and 0.88%, respectively. These findings indicate that tubercle design should balance radial position and protrusion height. Full article

Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain and is particularly valuable in medical imaging, where dense annotations are costly and acquisition conditions vary. Cross-modality segmentation remains challenging because modality-dependent intensity and texture shifts alter image appearance, while teacher-generated pseudo-labels are often unreliable near anatomical boundaries. We propose a fractional texture-guided and boundary-aware perturbation-learning framework within a student–teacher scheme. On the source side, soft histogram transfer introduces target-related low-order intensity shifts. A multi-order fractional Gram discrepancy between shallow features of the intensity-transferred source and target images then provides a gradient signal for generating magnitude-normalized, range-clipped perturbations. This discrepancy is used as a perturbation cue rather than a direct alignment loss, exposing the student to target-relevant texture and edge-transition variation while preserving source annotations. On the target side, teacher logits are perturbed only within predicted boundary bands to model local contour uncertainty. Box-counting fractal boundary complexity guides the boundary-band width and logit perturbation scale and, together with predictive entropy, regulates pseudo-label supervision. Across five adaptation tasks, the proposed method achieves three-seed mean ± standard deviation Dice scores of 89.24 ± 0.12% and 82.01 ± 0.10% for cardiac MR→CT and CT→MR, 88.65 ± 0.29% and 90.43 ± 0.22% for abdominal MR→CT and CT→MR, and 84.76 ± 0.25% for bSSFP→LGE adaptation. Within the protocol-aware benchmark comparisons, the proposed method attains the highest average Dice score on four of the five tasks and is within 0.07 percentage points of the highest reported value on abdominal CT→MR. Ablation and operator-replacement studies further indicate that the source- and target-side pathways provide complementary benefits. Because all auxiliary perturbation and reliability-weighting modules are used only during adaptation, deployment requires only the adapted segmentation network, without additional inference-time modules or parameters. Full article

Cloud-dependent irrigation platforms can support remote monitoring, but their use in precision fertigation is limited when local decisions must be made quickly and reliably. Network delay, temporary disconnection, and the use of single-point measurements may all reduce the ability of a system to respond to spatial variation in soil moisture and nutrient demand. In this work, an edge-controlled precision fertigation system was developed by combining multi-parameter soil sensing, spatial task scheduling, and a 6-DOF robotic manipulator. The ESP32 controller runs a preemptive FreeRTOS scheduler, allowing sensor acquisition, inverse-kinematics calculation, and pump actuation to be handled as separate tasks. A Kalman filter was used to smooth soil moisture measurements, and a hysteresis-based control strategy was adopted to reduce false triggering and repeated pump switching. To improve fertigation safety, a hardware–software interlock was added so that fertilizer delivery is always accompanied by water delivery. Hardware-in-the-Loop simulation and a 14-day field deployment were used to evaluate the system. The controller achieved an end-to-end latency of less than 38 ms and maintained operation during network interruptions through cached local parameters. After calibration, the robotic end-effector positioning error was reduced to ±2.4 mm. The hysteresis strategy lowered daily pump cycling by 71%. Based on prototype duty-cycle data and seasonal extrapolation, the projected seasonal water use and fertilizer demand were 44% and 38% lower, respectively, than those estimated for a uniform application. These values should be interpreted as model-based projections rather than direct season-long measurements. During 72 h of continuous operation, no Modbus faults were observed, and RTOS heap fragmentation remained stable. Overall, the results suggest that edge-based deterministic control can provide a practical route for precision fertigation where both spatial variability and intermittent connectivity must be considered. Full article

Archaeological feature detection at complex, mixed-environment sites requires accurate, efficient methods for identifying subtle morphological signatures. This study presents a semi-automated remote sensing pipeline for the detection and delineation of archaeological earthworks at Cahokia Mounds (Illinois, USA), a major Mississippian urban center and UNESCO World Heritage Site. Three LiDAR datasets, two collected via UAV-mounted sensors and one from a piloted aircraft survey, were processed into Digital Terrain Models and transformed into Local Relief Models (LRM). K-means clustering was applied to segment the LRMs into feature classes, followed by contour bounding using the OpenCV library to outline mounds and borrow pits. Additionally, SAR-derived Local Incidence Angle (LIA) rasters from PALSAR-3 and Sentinel-1 were processed through angular deviation mapping to identify slope anomalies associated with archaeological features. Results across all five datasets demonstrate the complementary strengths of LiDAR and SAR: LiDAR excels at resolving elevation-defined features such as mound footprints, while LIA captures directional slope behavior that highlights mound edges, borrow pit rims, and linear features such as causeways. Comparative analysis of LiDAR acquisition frequencies reveals minimal differences in archaeological feature recovery between pulse settings, suggesting that sensor platform choice matters more than power-density tradeoffs for this application. Despite the need for human review to filter modern disturbances and natural false positives, the integrated workflow meaningfully accelerates prospection and reduces interpretive subjectivity. The methods are scalable, site-invariant, and work with open-access data, making them applicable to archaeological landscapes worldwide. Full article

Belt conveyors are essential to continuous material transport systems, and reliable surface defect detection is therefore critical for safe and stable operation. In real industrial environments, defects such as tears, punctures, and localized damage are often small, elongated, and characterized by weak boundary contrast. Complex background interference further increases the difficulty of accurate and reliable detection for real-time defect detectors. To address these challenges, this paper proposes SEDR-Net (Structure-Edge and Detail Reconstruction Network), a YOLOv11n-based network, for this task. The Structural-Edge Fusion Block (SEFBlock), Channel-Spatial Collaborative Attention (CSCA), and Efficient Up-Convolution Block (EUCB) respectively enhance structural-edge representation, suppress redundant background responses, and recover local structures and boundary details. On a public conveyor-belt defect dataset, SEDR-Net achieves 90.8% Recall, with an mAP@0.5 of 92.4% and an mAP@0.5:0.95 of 58.4%, yielding improvements of 4.7, 3.8, and 7.1 percentage points over YOLOv11n, respectively. Meanwhile, SEDR-Net uses 2.42 M trainable parameters and maintains an inference speed of 134.2 FPS, indicating a favorable accuracy–complexity trade-off for real-time inspection. An independent external industrial test set further verifies the cross-scenario robustness and practical applicability of the proposed method under real mining conveyor-belt conditions. Full article

Recent cyber incidents have become increasingly sophisticated through Living-off-the-Land (LotL) techniques that exploit legitimate behavior and multi-stage attacks. This requires advanced reasoning capabilities to discern the attack contexts within fragmented large-scale logs. However, closed network environments with physical network separation (air-gapped), such as national critical infrastructures, restrict the use of high-performance cloud large language models (LLMs), thereby limiting the adoption of cutting-edge artificial intelligence (AI)-based analysis technologies. To overcome these constraints, this study proposes a Local LLM-based intrusion analysis framework that operates independently within closed networks. The proposed framework combines (i) an Offline Knowledge Distillation technique that transfers the analytical reasoning process of external high-performance models to the Local LLM after a security review, and (ii) an AI agent orchestration structure that controls the analysis procedure step-by-step and suppresses hallucinations. Experiments and validation using a public dataset (Atomic Red Team) demonstrated that the proposed model achieved a consistently higher detection accuracy (88.4%) and MITRE Adversarial Tactics, Techniques, and Common Knowledge mapping performance (0.91 F1-Score) than existing general-purpose Local LLMs. Furthermore, the proposed model suppressed hallucination rates to 6.2% through an automated verification mechanism and significantly improved analysis efficiency by refining large-scale logs to focus on core events. This study quantitatively demonstrated that AI-based intrusion incident analysis can be automated using a single graphics processing unit server under controlled evaluation conditions. The proposed framework provides a practical prototype for intelligent security monitoring in closed-network environments. However, the operational performance must be validated in real-world deployments. Full article

Within the domain of Earth observation, tracking terrestrial transitions via high-resolution optical data plays a fundamental role. Nevertheless, current methods face critical challenges, including the difficulty in collaborative modeling of local details and global features and the singularity of bi-temporal difference representation, along with insufficient cross-scale feature communication, thereby constraining both the precision and resilience of models when applied to complicated environments. To solve these problems, we propose LADENet (Locally Adaptive Mamba and Multi-scale Feature Enhancement Network), an innovative framework that synergizes CNN, Transformer, and Mamba paradigms. By leveraging customized local contextual refinement alongside sophisticated hierarchical fusion, this integration delivers highly precise and resilient detection performance. LADENet adopts a weight-sharing multi-level Transformer encoder combined with a sequence reduction mechanism to generate multi-scale global features, achieving precise alignment of bi-temporal features and global context modeling while reducing computational complexity. To realize accurate localization and local enhancement of changed regions, we design a dual spatiotemporal adaptive local feature marking module based on State-Space Scanning (SSS). This module screens high-saliency changed regions through an adaptive scanning strategy, realizes pixel-aligned spatiotemporal feature fusion via cross-temporal state-space scanning, and introduces a sliding window boundary calibration mechanism to alleviate boundary information loss caused by window segmentation. To strengthen the feature representation of changed regions, a dual-branch difference enhancement module is constructed, which collaboratively captures global change trends and fine-grained local features through an attention-enhanced difference branch and a multi-scale convolution concatenation branch, effectively suppressing background interference. To address the semantic gap between cross-scale features, a global cross-scale spatial feature fusion decoder is proposed, which balances local detail preservation and global context perception through the synergy of spatial attention and two-dimensional selective scanning, completing refined multi-scale feature fusion and spatial resolution recovery. To rigorously validate the proposed LADENet, comprehensive experiments were conducted across four widely adopted bi-temporal benchmarks: LEVIR-CD, WHU-CD, CLCD-CD, and GVLM-CD. The presented architecture establishes substantial superiority over existing cutting-edge methodologies across primary evaluation criteria. Specifically, it yields an F1-measure of 91.06% alongside an IoU of 85.28% in the LEVIR-CD tests, while registering 90.51% (F1) and 82.45% (IoU) for WHU-CD. Similarly, robust outcomes are delivered on CLCD-CD (82.15% F1, 72.83% IoU) as well as GVLM-CD (89.12% F1, 77.78% IoU). These results demonstrate that LADENet possesses excellent detection accuracy, boundary delineation capability and generalization performance in diverse and intricate bi-temporal observation environments. Full article

Maritime UAV surveillance requires rapid, accurate identification of small surface targets amidst volatile sea states. Conventional detectors typically degrade under intense wave clutter, variable lighting, and edge computing constraints. To address these limitations, this paper presents YOLOv11-UAV, a compact framework optimized for real-time edge deployment. We introduce an SPPFLSC module integrating large separable kernel attention (LSKA-C) to extend the receptive field with minimal computational overhead. Additionally, an optimized C3k2-EVA block utilizing sparse decomposed large separable kernel attention (SDLSKA) improves feature representation and processing throughput. To refine localization for low-contrast objects, a high-resolution prediction head is integrated into the multi-scale pipeline. Quantitative evaluations on the SeaDronesSee benchmark demonstrate that YOLOv11-UAV yields substantial precision and recall gains, validating its efficacy for airborne maritime reconnaissance. Full article

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving edge intelligence because it enables geographically distributed devices to collaboratively train a shared model without transferring raw data to a central cloud. This capability is particularly valuable for 5G and emerging 6G networks, where edge-native services are required to satisfy stringent latency, bandwidth, and privacy constraints while operating on highly heterogeneous devices and time-varying wireless channels. In practice, however, synchronous FL is often constrained by straggling clients with limited computation capability or unfavorable communication conditions, which increases round latency and reduces overall resource efficiency. To address this challenge, this study develops a rigorously structured framework for dynamic client selection and radio resource allocation in heterogeneous wireless edge environments. Each FL round is formulated as a latency-aware scheduling problem that jointly captures local computation time, uplink transmission time, minimum participation constraints, and resource block assignment. On this basis, we propose a Dynamic Client Selection and Resource Allocation (DCS-RA) method that integrates computation-aware, channel-aware, and fairness-aware scoring with greedy resource block allocation guided by marginal completion time reduction. The study further provides a clear methodological structure, workflow visualization, literature-grounded justification, dataset documentation, and uncertainty-aware result reporting. Under the reported simulation setting with 100 clients and 20 resource blocks, DCS-RA reduces the average round completion time from 1.92 s to 1.55 s on MNIST and from 2.02 s to 1.57 s on CIFAR-10, corresponding to improvements of 19.39% and 22.47%, respectively. Standard deviation reductions of 70.59% and 80.77% further indicate improved round-to-round stability and more reliable training behavior. These results support the central conclusion that lightweight joint scheduling can materially improve wall-clock FL efficiency in heterogeneous 5G/6G edge networks. Full article

Small object detection is fundamentally constrained by the lack of discriminative fine-grained features. Although introducing higher resolution detection scales can improve performance, it also amplifies background noise. In addition, the independently decoupled design of conventional detection heads is insufficient to address the persistent challenges of missed detections and false positives for small objects. To this end, we propose MSIA-YOLO, a YOLOv11-based detector with multi-scale semantic interaction and alignment, optimized from three complementary perspectives: feature modeling, high resolution semantic compensation, and task coordinated alignment. First, Receptive Field Attention Convolution (RFAConv) is integrated into the backbone to enhance critical local details, such as edge and texture cues, via receptive field aware attention. Second, to alleviate fine detail attenuation caused by repeated downsampling, we construct a CHSP-P2 small object detection framework with an additional P2 branch. A scale sequence fusion mechanism is further introduced to perform high resolution semantic compensation through cross scale hybrid inputs. Finally, we design a DTIA-Head (Dynamic Task Interaction and Alignment Head), which promotes joint optimization of classification and localization through dynamic task interaction and spatial alignment. Extensive experiments on the public datasets VisDrone, TinyPerson, and RSOD show that, compared with the YOLOv11n baseline, MSIA-YOLO improves mAP50 by 7.7%, 10.3%, and 1.0%, respectively, while also outperforming several advanced detectors. These results demonstrate the effectiveness and generalization capability of the proposed method in small object, dense object, and complex scene object detection scenarios. Full article

Weeds remain one of the primary constraints on crop productivity, making accurate detection and spatial localization essential for precision weeding systems. Over the past decades, weed detection has evolved from traditional feature-based image processing to deep learning-driven visual recognition, substantially improving detection accuracy under controlled and semi-controlled conditions. However, most existing approaches still follow a weed-centric paradigm in which models are trained to explicitly recognize diverse weed species or weed classes. Such strategies face persistent limitations caused by extreme weed morphological variability, crop-weed similarity, high annotation cost, and spatial-temporal heterogeneity across fields, seasons, and cropping systems. This review therefore reframes weed detection as a broader transition from feature-based vision and direct weed recognition toward crop-guided, context-aware, and decision-oriented intelligence. Specifically, we synthesize the literature from three perspectives: (i) methodological evolution, including handcrafted features, machine learning, deep learning, segmentation, and multimodal sensing; (ii) paradigm transformation, from weed-centric detection to crop-guided inference based on crop structure, crop rows, and non-crop vegetation; and (iii) deployment-oriented integration, including edge devices, latency-accuracy-energy trade-offs, and robotic actuation. We further summarize representative public datasets, method categories, crop-guided studies, and edge-platform reporting requirements. Finally, we outline a decision-aware hybrid framework in which crop-guided perception provides low-latency weed localization, while species-level recognition is conditionally activated when required by herbicide selection, resistance management, or high-risk weed control. This synthesis clarifies both the value and the limitations of crop-guided weed detection and outlines actionable directions for scalable, robust, and field-deployable intelligent weeding systems. Full article

The cascading damage of expressways induced by extreme heavy rainfall presents a persistent threat to transportation safety and regional sustainable development. To investigate the chain-like evolution characteristics of expressway damage caused by heavy rainfall and to identify precise strategies for mitigating disaster risks by breaking the chain. Firstly, directed causal event pairs were extracted, and clustering generalization was performed on disaster events.; the asymmetric Jaccard index was used to calculate edge weights, thereby establishing a directed causal knowledge graph of disaster chain evolution; Secondly, based on systematic risk assessment and chain-breaking priority indicators, we achieved the precise identification and quantification of critical vulnerable links; finally, we selected three typical damage cases—the ‘5·1’ case on the Meida Expressway in Guangdong, the ‘7·19’ case on the Danning Expressway in Shaanxi, and the ‘8·3’ case on the Yakang Expressway in Sichuan—for case validation, and proposed chain-breaking strategies. The research findings indicate that: (1) under specific hazard-forming environment, secondary disasters can supplant the primary causative factors to become the dominant driving nodes in chain evolution; (2) edge vulnerability and source-path diversity loss indicators respectively point to two distinct categories of high-risk edges; the comprehensive chain-breaking index compensates for the assessment blind spots of single indicators through two-dimensional weighting; (3) core vulnerabilities in disaster chains vary significantly across different regions: the Meida Expressway, the Danning Expressway, and the Yakang Expressway correspond to terminal response, pavement control node, and dual vulnerabilities at the source and structural levels, respectively, necessitating tailored chain-breaking strategies adapted to local conditions. These research findings offer a quantitative tool for infrastructure risk governance, contributing to the safety and sustainability of expressway transportation. Full article

Cloud contamination obscures ground objects, interferes with surface reflectance, and disrupts spatial continuity. In thick-cloud regions, surface structures and spectral information are often extensively missing. CNN-based cloud removal methods can recover local textures, but they are less effective at modeling global structures and color consistency over large cloud-covered areas. Transformer-based methods capture long-range dependencies; however, standard self-attention introduces high computational and memory costs for high-resolution remote sensing images. Efficient attention reduces this cost but may weaken edge and texture discriminability. SAR imagery can penetrate clouds and provide surface structural information, yet repeated SAR injections may propagate speckle noise, cross-modal misalignment, and imaging discrepancies through deep restoration layers. To address these issues, this paper proposes DST-SARNet, a dual-stage SAR structural guidance network for optical remote sensing image cloud removal. In this framework, dual-stage refers to two explicit SAR-guidance positions: early structural skeleton guidance at the input side and late high-frequency modulation near the output. The Texture-Aware Asymmetric Retrieval module is placed between these two stages as a bottleneck memory retrieval operation rather than as a third dense SAR injection stage. With this design, SAR provides structural skeletons, readable texture memory, and terminal detail compensation, while the optical branch remains responsible for color, semantics, and spectral appearance recovery. Experiments on the SMILE-CR and SEN12MS-CR datasets show that DST-SARNet effectively restores cloud-contaminated imagery with a compact model scale, demonstrating its potential for efficient SAR-assisted optical cloud removal. Full article

The increasing connectivity of Internet of Things (IoT)-oriented environments has made them more vulnerable to cyberattacks, requiring intrusion-detection systems (IDSs) to ensure their secure and reliable operation. The feature selection (FS) process of an IDS affects its performance, as effective FS can enhance detection accuracy and reduce the computational cost and model complexity. This paper presents Adaptive Hybrid Genetic Algorithm-Simulated Annealing (AHGA-SA) as an FS framework that integrates the global search ability of a genetic algorithm and the local exploitation ability of simulated annealing. AHGA-SA aims to find compact, informative feature subsets in high-dimensional intrusion-detection datasets at an acceptable computational cost while maintaining detection performance. The experimental results on three recent benchmarks demonstrate feature-space reduction, with classification accuracies of 99.04% on IoTID20 (using 12 features), 98.25% on WUSTL-EHMS (using seven features), and 99.18% on Edge-IIoTset (using nine features). The results also demonstrate reduced training and testing times, central processing unit usage, resident set size overhead, and subset size compared to the baseline. Furthermore, Shapley additive explanations, as an explainable artificial intelligence technique, are applied to explain the model’s predictions and to show the contribution of the selected features to the IDS decision-making process. Full article