Search Results (8,569)

This paper presents an analytical model for the hereditary vibrations of a coupled circular plate system interconnected by viscoelastic creep layers. The system is represented as a discrete-continuous chain of thin, isotropic plates with time-dependent material properties. Based on the theory of hereditary viscoelasticity and D’Alembert’s principle, a system of partial integro-differential equations is derived and reduced to ordinary integro-differential equations using Bernoulli’s method and Laplace transforms. Analytical expressions for natural frequencies, mode shapes, and time-dependent response functions are obtained. The results reveal the emergence of multi-frequency vibration regimes, with modal families remaining temporally uncoupled. This enables the identification of resonance conditions and dynamic absorption phenomena. The fractional parameter serves as a tunable damping factor: lower values result in prolonged oscillations, while higher values cause rapid decay. Increasing the kinetic stiffness of the coupling layers raises vibration frequencies and enhances sensitivity to hereditary effects. This interplay provides deeper insight into dynamic behavior control. The model is applicable to multilayered structures in aerospace, civil engineering, and microsystems, where long-term loading and time-dependent material behavior are critical. The proposed framework offers a powerful tool for designing systems with tailored dynamic responses and improved stability. Full article

Collateral status is an important therapeutic indicator for acute ischemic stroke (AIS), yet visual collateral grading remains subjective and suffers from inter-observer variability. To address this limitation, this study automatically extracted binarized vascular morphological features from CTA images and developed a convolutional neural network (CNN) for automated collateral classification. Performance trends were systematically analyzed across diverse hyperparameter combinations to meet different clinical decision needs. A total of 157 AIS patients (median age 65 [⁵⁷,⁵⁸,⁵⁹,⁶⁰,⁶¹,⁶²,⁶³,⁶⁴,⁶⁵,⁶⁶,⁶⁷,⁶⁸,⁶⁹,⁷⁰,⁷¹,⁷²,⁷³,⁷⁴] years; 61.8% were male) were retrospectively enrolled and stratified by Menon score into good (3–5, n = 117) and poor (0–2, n = 40) collateral groups. A total of 192 architectures were established, and three representative model tendencies emerged: a sensitivity-oriented model (AUC = 0.773; sensitivity = 87.18%; specificity = 65.00%), a balanced model (AUC = 0.768; sensitivity = 72.65%; specificity = 77.50%), and a specificity-oriented model (AUC = 0.753; sensitivity = 63.25%; specificity = 85.00%). These results demonstrate that kernel size, the number of filters in the first layer, and the number of convolutional layers are key determinants of performance directionality, allowing tailored model selection depending on clinical requirements. This work highlights the feasibility of CTA-based automated collateral classification and provides a systematic framework for developing models optimized for sensitivity, specificity, or balanced decision-making. The findings may serve as a reference for clinical model deployment and have potential for integration into multi-objective AI systems for endovascular thrombectomy patient triage. Full article

Subsea pipelines are critical lifelines for marine resource development, yet they face severe threats from accidental ship anchor impacts. This study addresses the scientific challenge of quantifying the “protection margin” of artificial rock-dumping layers, moving beyond traditional passive structural response to a “Critical Failure Intervention” logic. Based on the energy criteria of DNV-RP-F107, a critical velocity required to trigger Concrete Weight Coating (CWC) failure for a bare pipe was derived and established as the Safety Factor baseline (S = 1). Two groups of scaled model tests (1:15) were conducted using a Hall anchor to simulate impact scenarios, where impact forces were measured via force sensors beneath the pipeline under varying backfill thicknesses and configurations. Results show that artificial backfill provides a significant protective redundancy; a 10 cm coarse rock layer increases the safety factor to 3.69 relative to the H₀ baseline, while a multi-layer configuration (sand bedding plus coarse rock) elevates S to 27. Analysis reveals a non-linear relationship between backfill thickness and cushioning efficiency, characterized by diminishing marginal utility once a specific thickness threshold is reached. These findings indicate that while thickness is critical for extreme impacts, the protection efficiency optimizes at specific depths, providing a quantifiable framework to reduce small-particle layers in engineering projects without compromising safety. Full article

Five prevention is an important technical means to prevent maloperations in substations, and knowledge extraction from wiring diagrams is the key to intelligent “five prevention logic verification”. To address the error accumulation caused by multimodal object matching in traditional methods, this paper proposes a hierarchical recognition-based approach for topological knowledge extraction. This method establishes a multi-level recognition framework utilizing image tiling, decomposing the wiring diagram recognition task into three hierarchical levels from top to bottom: connection modes, bay types, and switching devices. A depth-first strategy is employed to establish parent–child node relationships, forming an initial topological structure. Based on the recognition results, the proposed approach performs regularized parsing and leverages a bay topology knowledge base to achieve automated matching of inter-device topological relationships. To enhance recognition accuracy, the model incorporates a Swin Transformer block to strengthen global feature perception and adds an ultra-small target detection layer to improve small-object recognition. The experimental results demonstrate that all recognition layers achieve mAP@0.5 exceeding 90%, with an overall precision of 93.9% and a recall rate of 91.7%, outperforming traditional matching algorithms and meeting the requirements for wiring diagram topology knowledge extraction. Full article

Accurate and stable mapping of crop types is fundamental to agricultural monitoring and food security. However, inter-annual phenological shifts driven by variations in air temperature, precipitation, and sowing dates introduce systematic changes in the spectral distributions associated with the same day of year (DOY). As a result, the “date–spectrum–class” mapping learned during training can become misaligned when applied to a new year, leading to increased misclassification and unstable performance. To tackle this problem, we develop TABS-Net (Temporal–Spectral Attentive Block with Space–Time Fusion Network). The core contributions of this study are summarized as follows: (1) we propose an end-to-end 3D CNN framework to jointly model spatial, temporal, and spectral information; (2) we design and embed CBAM3D modules into the backbone to emphasize informative bands and key time windows; and (3) we introduce DOY positional encoding and temporal jitter during training to explicitly align seasonal timing and simulate phenological shifts, thereby enhancing cross-year robustness. We conduct a comprehensive evaluation on a Cropland Data Layer (CDL) subset. Within a single year, TABS-Net delivers higher and more balanced overall accuracy, Macro-F1, and mIoU than strong baselines, including 2D stacking, 1D temporal convolution/LSTM, and transformer models. In cross-year experiments, we quantify temporal stability using inter-annual robustness (IAR); with both DOY encoding and temporal jitter enabled, the model attains IAR values close to one for major crop classes, effectively compensating for phenological misalignment and inter-annual variability. Ablation studies show that DOY encoding and temporal jitter are the primary contributors to improved inter-annual consistency, while CBAM3D reduces crop–crop and crop–background confusion by focusing on discriminative spectral regions such as the red-edge and near-infrared bands and on key growth stages. Overall, TABS-Net combines higher accuracy with stronger robustness across multiple years, offering a scalable and transferable solution for large-area, multi-year remote sensing crop mapping. Full article

Metal additive manufacturing (AM) generates complex microstructures through extreme thermal gradients and rapid solidification, critically influencing mechanical performance and industrial qualification. This review synthesizes recent advances in cellular automata (CA) and phase-field (PF) modeling to predict grain-scale microstructure evolution during AM. CA methods provide computational efficiency, enabling large-domain simulations and excelling in texture prediction and multi-layer builds. PF approaches deliver superior thermodynamic fidelity for interface dynamics, solute partitioning, and nonequilibrium rapid solidification through CALPHAD coupling. Hybrid CA–PF frameworks strategically balance efficiency and accuracy by allocating PF to solidification fronts and CA to bulk grain competition. Recent algorithmic innovations—discrete event-inspired CA, GPU acceleration, and machine learning—extend scalability while maintaining predictive capability. Validated applications across Ni-based superalloys, Ti-6Al-4V, tool steels, and Al alloys demonstrate robust process–microstructure–property predictions through EBSD and mechanical testing. Persistent challenges include computational scalability for full-scale components, standardized calibration protocols, limited in situ validation, and incomplete multi-physics coupling. Emerging solutions leverage physics-informed machine learning, digital twin architectures, and open-source platforms to enable predictive microstructure control for first-time-right manufacturing in aerospace, biomedical, and energy applications. Full article

Background: Diagnosing CNS tumors through MRI is limited by significant variability in scanner hardware, acquisition protocols, and intensity characteristics at clinical centers, resulting in substantial domain shifts that lead to diminished reliability for automated models. Methods: We present a Domain-Adaptive MRI Learning Model (DA-MLM) consisting of an adversarially aligned hybrid 3D CNN–transformer encoder with contrastive regularization and covariance-based feature harmonization. Varying sequence MRI inputs ($T1$, $T1ce$, $T2$, and $FLAIR$) were inputted to multi-scale convolutional layers followed by global self-attention to effectively capture localized tumor structure and long-range spatial context, with domain adaptation that harmonizes feature distribution across datasets. Results: On the BraTS 2020 dataset, we found DA-MLM achieved 94.8% accuracy, 93.6% macro-F1, and 96.2% AUC, improving upon previously established benchmarks by 2–4%. DA-MLM also attained Dice score segmentation of 93.1% (WT), 91.4% (TC), and 89.5% (ET), improving upon 2–3.5% for CNN and transformer methods. On the REMBRANDT dataset, DA-MLM achieved 92.3% accuracy with segmentation improvements of 3–7% over existing U-Net and expert annotations. Robustness testing indicated 40–60% less degradation under noise, contrast shift, and motion artifacts, and synthetic shifts in scanner location showed negligible performance impairment (<0.06). Cross-domain evaluation also demonstrated 5–11% less degradation than existing methods. Conclusions: In summary, DA-MLM demonstrates improved accuracy, segmentation fidelity, and robustness to perturbations, as well as strong cross-domain generalization indicating the suitability for deployment in multicenter MRI applications where variation in imaging performance is unavoidable. Full article

Automated defect detection in printed circuit boards (PCBs) is a critical process for ensuring the quality and reliability of electronic products. To address the limitations of existing detection methods, such as insufficient sensitivity to minor defects and limited recognition accuracy in complex backgrounds, this paper proposes an enhanced YOLOv8 detection framework. The core contribution lies not merely in the integration of the Convolutional Block Attention Module (CBAM), but in a principled and task-specific integration strategy designed to address the multi-scale and low-contrast nature of PCB defects. The complete CBAM is integrated into the multi-scale feature layers (P3, P4, P5) of the YOLOv8 backbone network. By leveraging sequential channel and spatial attention submodules, CBAM guides the model to dynamically optimise feature responses, thereby significantly enhancing feature extraction for tiny, morphologically diverse defects. Experiments on a public PCB defect dataset demonstrate that the proposed model achieves a mean average precision (mAP@50) of 98.8% while maintaining real-time inference speed, surpassing the baseline YOLOv8 model by 9.5%, with the improvements of 7.4% in precision and 12.3% in recall. While the model incurs a higher computational cost (79.4 GFLOPs), it maintains a real-time inference speed of 109.11 FPS, offering a viable trade-off between accuracy and efficiency for high-precision industrial inspection. The proposed model demonstrates superior performance in detecting small-scale defects, making it highly suitable for industrial deployment. Full article

This paper presents the design and optimisation of a low-power embedded sensor-node architecture for real-time environmental monitoring with on-board machine-learning inference. The proposed system integrates heterogeneous sensing elements for air quality and ambient parameters (temperature, humidity, gas concentration, and particulate matter) into a modular embedded platform based on a low-power microcontroller coupled with an energy-efficient neural inference accelerator. The design emphasises end-to-end energy optimisation through adaptive duty-cycling, hierarchical power domains, and edge-level data reduction. The embedded machine-learning layer performs lightweight event/anomaly detection via on-device multi-class classification (normal/anomalous/critical) using quantised neural models in fixed-point arithmetic. A comprehensive system-level analysis, performed via MATLAB Simulink simulations, evaluates inference accuracy, latency, and energy consumption under realistic environmental conditions. Results indicate that the proposed node achieves 94% inference accuracy, 0.87 ms latency, and an average power consumption of approximately 2.9 mWh, enabling energy-autonomous operation with hybrid solar–battery harvesting. The adaptive LoRaWAN communication strategy further reduces data transmissions by ≈88% relative to periodic reporting. The results indicate that on-device inference can reduce network traffic while maintaining reliable event detection under the evaluated operating conditions. The proposed architecture is intended to support energy-efficient environmental sensing deployments in smart-city and climate-monitoring contexts. Full article

In the process of ore drawing using a caving method under interburden conditions, the key to controlling ore dilution lies in the accurate prediction of boundary particle migration trajectories. To address the challenges of high computational costs and complex modeling in traditional numerical simulations, this study designs a dataset construction method. After calibrating parameters using the angle of repose, ore-drawing numerical simulation datasets with interburden (post-defined and pre-defined models) are established. Building upon this foundation, an improved Transformer model is proposed. The model enhances spatiotemporal representation through multi-layer feature fusion embedding, strengthens long-range dependency capture via a reinforced spatiotemporal attention backbone, improves local dynamic modeling capability through optimized decoding at the output stage, and integrates transfer learning to achieve continuous prediction of particle migration. Validation results demonstrate that the model accurately predicts the spatial distribution patterns and collective motion trends of particles, with prediction errors at critical nodes confined to within a single stage and an average estimation error of approximately 4% in interburden regions. The proposed approach effectively overcomes the timeliness bottleneck of traditional interburden ore-drawing simulations, enabling rapid and accurate prediction of boundary particle migration under interburden conditions. Full article

In order to solve the problems of small-target detection in UAV aerial photography, such as small scale, blurred features and complex background interference, this article proposes the ACS-YOLOv8s method to optimize the YOLOv8s network: notably, most small man-made targets in UAV aerial scenes (e.g., small vehicles, micro-drones) inherently possess symmetry, a key geometric attribute that can significantly enhance the discriminability of blurred or incomplete target features, and thus symmetry-aware mechanisms are integrated into the aforementioned improved modules to further boost detection performance. The backbone network introduces an adaptive feature enhancement module, the edge and detail representation of small targets is enhanced by dynamically modulating the receptive field with deformable attention while also capturing symmetric contour features to strengthen the perception of target geometric structures; a cascaded multi-receptive field module is embedded at the end of the trunk to integrate multi-scale features in a hierarchical manner to take into account both expressive ability and computational efficiency with a focus on fusing symmetric multi-scale features to optimize feature representation; the neck is integrated with a spatially adaptive feature modulation network to achieve dynamic weighting of cross-layer features and detail fidelity and, meanwhile, models symmetric feature dependencies across channels to reduce the loss of discriminative information. Experimental results based on the VisDrone2019 data set show that ACS-YOLOv8s is superior to the baseline model in precision, recall, and mAP indicators, with mAP50 increased by 2.8% to 41.6% and mAP50:90 increased by 1.9% to 25.0%, verifying its effectiveness and robustness in small-target detection in complex drone aerial-photography scenarios. Full article

Intercity population flows are playing an increasingly pivotal role in shaping the spatial evolution and structural dynamics of urban networks. Drawing upon Amap Migration Data (2018–2023), this study maps China’s urban networks using social network analysis and identifies their key drivers using a temporal exponential random graph model. The findings reveal three primary insights: First, the overall network exhibits “high connectivity and strong clustering” traits. Enhanced efficiency in intercity resource allocation fosters cross-regional factor flows, resulting in multi-tiered connectivity corridors. Industrial linkages and policy interventions drive the development of a polycentric and clustered configuration. Second, the individual city network exhibits a core–periphery dynamic structure. A diamond-shaped framework dominated by hub cities in the national strategic regions directs factor flows. Development of strategic corridors enables peripheral cities to evolve into secondary hubs by leveraging structural hole advantages, reflecting the continuous interplay between network structure and geo-economic factors. Third, driving factors involve nonlinear interactions within a multi-layered system. Path dependence in topology, gradient potential from nodal attributes, spatial counterbalance between geographic decay laws and multidimensional proximity, and adaptive self-organization are collectively associated with the transition of the urban network toward a multi-tiered synergistic pattern. By revealing the dynamic interplay between network topology and multidimensional driving factors, this study deepens and advances the theoretical connotations of the “Space of Flows” theory, providing an empirical foundation for optimizing regional governance strategies and promoting high-quality coordinated development of Chinese cities. Full article

Within the domain of intelligent picking robotics, fruit recognition and positioning are essential. Challenging conditions such as varying light, occlusion, and limited edge-computing power compromise fruit maturity detection. To tackle these issues, this paper proposes a lightweight algorithm YOLO-ELS based on YOLOv8n. Specifically, we reconstruct the backbone by replacing the bottlenecks in the C2f structure with Edge-Information-Enhanced Modules (EIEM) to prioritize morphological cues and filter background redundancy. Furthermore, a Large Separable Kernel Attention (LSKA) mechanism is integrated into the SPPF layer to expand the effective receptive field for multi-scale targets. To mitigate occlusion-induced errors, a Spatially Enhanced Attention Module (SEAM) is incorporated into the decoupled detection head to enhance feature responses in obscured regions. Finally, the Inner-GIoU loss is adopted to refine bounding box regression and accelerate convergence. Experimental results demonstrate that compared to the YOLOv8n baseline, the proposed YOLO-ELS achieves a 14.8% reduction in GFLOPs and a 2.3% decrease in parameters, while attaining a precision, recall, and mAP@50% of 92.7%, 83.9%, and 92.0%, respectively. When compared with mainstream models such as DETR, Faster-RCNN, SSD, TOOD, YOLOv5s, and YOLO11n, the mAP@50% is improved by 7.0%, 4.7%, 11.4%, 8.6%, 3.1%, and 3.2%. Deployment tests on the NVIDIA Jetson Orin Nano Super edge platform yield an inference latency of 25.2 ms and a detection speed of 28.2 FPS, successfully meeting the real-time operational requirements of automated harvesting systems. These findings confirm that YOLO-ELS effectively balances high detection accuracy with lightweight architecture, providing a robust technical foundation for intelligent fruit picking in resource-constrained greenhouse environments. Full article

Cyberbullying and hate speech increasingly appear in multi-modal social media posts, where images and text are combined in diverse and fast changing ways across platforms. These posts differ in style, vocabulary and layout, and labeled data are sparse and noisy, which makes it difficult to train detectors that are both reliable and deployable under tight computational budgets. Many high performing systems rely on large vision language backbones, full parameter fine tuning, online retrieval or model ensembles, which raises training and inference costs. We present a parameter efficient cross-platform multi-modal transfer learning framework for cyberbullying and hateful content detection. Our framework has three components. First, we perform domain adaptive pretraining of a compact ViLT backbone on in domain image-text corpora. Second, we apply parameter efficient fine tuning that updates only bias terms, a small subset of LayerNorm parameters and the classification head, leaving the inference computation graph unchanged. Third, we use noise aware knowledge distillation from a stronger teacher built from pretrained text and CLIP based image-text encoders, where only high confidence, temperature scaled predictions are used as soft labels during training, and teacher models and any retrieval components are used only offline. We evaluate primarily on Hateful Memes and use IMDB as an auxiliary text only benchmark to show that the deployment aware PEFT + offline-KD recipe can still be applied when other modalities are unavailable. On Hateful Memes, our student updates only 0.11% of parameters and retain about 96% of the AUROC of full fine-tuning. Full article

In marine hydrodynamics, the core of the boundary element method (BEM) lies in the numerical calculation of the free-surface Green’s function. With the rise of artificial intelligence, using neural networks to fit Green’s function has become a new trend, yet most existing studies are confined to fitting Green’s function in infinite water depth. In this paper, a neural network fitting method for a finite-depth Green’s function is proposed. The classical Multilayer Perceptron (MLP) network and the emerging Kolmogorov–Arnold Network (KAN) are employed to conduct global and partition-based fitting experiments. Experiments indicate that the partition-based KAN fitting model achieves higher fitting accuracy, with most regions reaching 4D fitting precision. For large-scale data input, the average time for the model to calculate a single Green’s function value is 0.0868 microseconds, which is significantly faster than the 0.1120 s required by the traditional numerical integration method. These results demonstrate that the KAN can serve as an accurate and efficient model for finite-depth Green’s functions. The proposed KAN-based fitting method not only reduces the computational cost of numerical evaluation of Green’s functions but also maintains high prediction precision, providing an alternative approach to accelerate BEM calculations for floating body hydrodynamic analysis. Full article