Search Results (221)

Ground penetrating radar (GPR) data inversion, especially in parallel-layered homogeneous media with multiple subsurface targets, still faces challenges in accurately reconstructing geometric structures due to weak reflections and complex target–medium interactions. To address these limitations, this paper proposes a novel multi-scale inversion framework named GPRGAN-SCSE (Ground Penetrating Radar Generative Adversarial Network with Spatial-Channel Squeeze and Excitation). Built upon the Pix2Pix Generative Adversarial Network (Pix2PixGAN), the proposed model incorporates a Spatial-Channel Squeeze and Excitation (SCSE) module into a residual U-Net generator to adaptively enhance target features embedded in layered media. Furthermore, a tri-scale discriminator ensemble is designed to enforce structural consistency and suppress layer-induced artifacts. The network is optimized using a composite loss integrating adversarial loss, L1 loss, and gradient difference loss to jointly improve structural continuity and boundary sharpness. Experiments conducted on a simulation dataset of parallel-layered homogeneous media with multiple targets demonstrate that GPRGAN-SCSE substantially outperforms existing inversion networks. The proposed method reduces the MAE by 63.8% and achieves a Structural Similarity Index (SSIM) of 99.96%, effectively improving the clarity of subsurface edges and the fidelity of geometric contours. These results confirm that the proposed framework provides a robust and high-precision solution for non-destructive subsurface imaging under layered media conditions. Full article

Connected and autonomous vehicle (CAV) platoons face the dual challenge of maintaining longitudinal formation stability while ensuring lateral safety in dynamic traffic environments, yet existing control approaches often address these objectives in isolation. This paper proposes a hierarchical cooperative control framework that integrates a differential game-based longitudinal controller with a risk potential field-driven model predictive controller (MPC) for lateral motion. At the coordination control layer, a differential game formulation models inter-vehicle interactions, with analytical solutions derived for both open-loop Nash equilibrium under predecessor-following (PF) topology and an estimated Nash equilibrium under two-predecessor-following (TPF) topology. The motion control layer employs a risk potential field model that quantifies collision threats from surrounding obstacles and road boundaries, guiding the MPC to perform real-time trajectory optimization. A comprehensive co-simulation platform integrating MATLAB/Simulink, Prescan, and CarSim validates the proposed framework across three representative scenarios: ramp merging with aggressive cut-in maneuvers, emergency braking by a preceding obstacle vehicle, and multi-lane cooperative obstacle avoidance involving multiple dynamic obstacles. Across all scenarios, the CAV platoon achieves safe obstacle avoidance through autonomous decision-making, with spacing errors converging to zero and smooth velocity adjustments that ensure both formation stability and ride comfort. The results demonstrate that the proposed framework effectively adapts to diverse and complex traffic conditions. Full article

Understanding the evolution of the atmospheric boundary layer height (BLH) is essential for characterizing air–surface exchange and air pollution processes. This study investigates the consistency and applicability of three BLH retrieval methods based on multi-source remote sensing observations at Beijing Southern Suburb station during autumn–winter 2023. Using Doppler wind lidar (DWL) and microwave radiometer (MWR) data, the Haar wavelet covariance transform (HWCT), vertical velocity variance (Var), and parcel methods were applied, and 10 min averages were used to suppress short-term fluctuations. Statistical analysis shows good overall consistency among the methods, with the strongest correlation between HWCT and Var method (R = 0.62) and average systematic positive bias of 0.4–0.6 km for the parcel method. Case studies under clear-sky, cloudy, and hazy conditions reveal distinct responses: HWCT effectively captures aerosol gradients but fails under cloud contamination, the Var method reflects turbulent dynamics and requires adaptive thresholds, and the Parcel method robustly describes thermodynamic evolution. The results demonstrate that the three methods are complementary in capturing the material, dynamic, and thermodynamic characteristics of the boundary layer, providing a comprehensive framework for evaluating BLH variability and improving multi-sensor retrievals under diverse meteorological conditions. Full article

With rapid advancements in sub-meter satellite and aerial imaging technologies, high-resolution remote sensing imagery has become a pivotal source for geospatial information acquisition. However, current semantic segmentation models encounter two primary challenges: (1) the inherent trade-off between capturing long-range global context and preserving precise local structural details—where excessive reliance on downsampled deep semantics often results in blurred boundaries and the loss of small objects and (2) the difficulty in modeling complex scenes with extreme scale variations, where objects of the same category exhibit drastically different morphological features. To address these issues, this paper introduces MAFMamba, a multi-scale adaptive fusion visual Mamba network tailored for high-resolution remote sensing images. To mitigate scale variation, we design a lightweight hybrid encoder incorporating an Adaptive Multi-scale Mamba Block (AMMB) in each stage. Driven by a Multi-scale Adaptive Fusion (MSAF) mechanism, the AMMB dynamically generates pixel-level weights to recalibrate cross-level features, establishing a robust multi-scale representation. Simultaneously, to strictly balance local details and global semantics, we introduce a Global–Local Feature Enhancement Mamba (GLMamba) in the decoder. This module synergistically integrates local fine-grained features extracted by convolutions with global long-range dependencies modeled by the Visual State Space (VSS) layer. Furthermore, we propose a Multi-Scale Cross-Attention Fusion (MSCAF) module to bridge the semantic gap between the encoder’s shallow details and the decoder’s high-level semantics via an efficient cross-attention mechanism. Extensive experiments on the ISPRS Potsdam and Vaihingen datasets demonstrate that MAFMamba surpasses state-of-the-art Convolutional Neural Network (CNN), Transformer, and Mamba-based methods in terms of mIoU and mF1 scores. Notably, it achieves superior accuracy while maintaining linear computational complexity and low memory usage, underscoring its efficiency in complex remote sensing scenarios. Full article

This work proposes a non-singular fast terminal sliding mode control (NFTSMC) strategy based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm and a nonlinear disturbance observer (NDO) to address the issues of modeling errors, motion disturbances, and transmission friction in robotic manipulators. Firstly, a novel modular serial 5-DOF robotic manipulator configuration is designed, and its kinematic and dynamic models are established. Secondly, a nonlinear disturbance observer is employed to estimate the total disturbance of the system and apply feedforward compensation. Based on boundary layer technology, an improved NFTSMC method is proposed to accelerate the convergence of tracking errors, reduce chattering, and avoid singularity issues inherent in traditional terminal sliding mode control. The stability of the designed control system is proved using Lyapunov stability theory. Subsequently, a deep reinforcement learning (DRL) agent based on the TD3 algorithm is trained to adaptively adjust the control gains of the non-singular fast terminal sliding mode controller. The dynamic information of the robotic manipulator is used as the input to the TD3 agent, which searches for optimal controller parameters within a continuous action space. A composite reward function is designed to ensure the stable and efficient learning of the TD3 agent. Finally, the motion characteristics of three joints for the designed 5-DOF robotic manipulator are analyzed. The results show that compared to the non-singular fast terminal sliding mode control algorithm based on a nonlinear disturbance observer (NDONFT), the non-singular fast terminal sliding mode control algorithm integrating a nonlinear disturbance observer and the Twin Delayed Deep Deterministic Policy Gradient algorithm (TD3NDONFT) reduces the mean absolute error of position tracking for the three joints by 7.14%, 19.94%, and 6.14%, respectively, and reduces the mean absolute error of velocity tracking by 1.78%, 9.10%, and 2.11%, respectively. These results verify the effectiveness of the proposed algorithm in enhancing the trajectory tracking accuracy of the robotic manipulator under unknown time-varying disturbances and demonstrate its strong robustness against sudden disturbances. Full article

Transonic shock buffet, characterized by large-amplitude self-sustained shock oscillations arising from shock wave/boundary layer interactions, poses significant challenges to aircraft handling quality and structural integrity. Conventional control strategies for buffet suppression typically require prior knowledge of unstable steady-state solutions or time-averaged flow fields and are only applicable to fixed-flow conditions, rendering them inadequate for realistic flight scenarios involving time-varying parameters. This study proposes a data-driven adaptive control framework for transonic buffet suppression utilizing localized morphing skin as the actuation mechanism. The control system employs a Multi-Layer Perceptron neural network that dynamically adjusts the local skin height based on lift coefficient feedback, with the target lift coefficient determined through a moving average method. Numerical simulations on the NACA0012 airfoil demonstrate that the optimal actuator configuration—a skin length of 0.2c with maximum deformation positioned at 0.65c—achieves effective buffet suppression with minimal settling time. Beyond this baseline case, the proposed method exhibits robust performance across different flow conditions. Furthermore, the controller successfully suppresses buffet under time-varying flow conditions, including simultaneous variations in Mach number and angle of attack. These results demonstrate the potential of the proposed framework for practical aerospace applications. Full article

This paper presents a unified framework for constructing partially unstructured B-spline transfinite finite elements with arbitrary nodal distributions. Three novel, distinct classes of elements are investigated and compared with older single Coons-patch elements. The first consists of classical transfinite elements reformulated using B-spline basis functions. The second includes elements defined by arbitrary control point networks arranged in parallel layers along one direction. The third features arbitrarily placed boundary nodes combined with a tensor-product structure in the interior. For all three classes, novel macro-element formulations are introduced, enabling flexible and customizable nodal configurations while preserving the partition of unity property. The key innovation lies in reinterpreting the generalized coefficients as discrete samples of an underlying continuous univariate function, which is independently approximated at each station in the transfinite element. This perspective generalizes the classical transfinite interpolation by allowing both the blending functions and the univariate trial functions to be defined using non-cardinal bases such as Bernstein polynomials or B-splines, offering enhanced adaptability for complex geometries and nonuniform node layouts. Full article

Mature soybean pods exhibit high homogeneity in color and texture relative to straw and dead leaves, and instances are often densely occluded, posing significant challenges for accurate field segmentation. To address these challenges, this paper constructs a high-quality field-based mature soybean dataset and proposes an adaptive Transformer-based network, PodFormer, to improve segmentation performance under homogeneous backgrounds, dense distributions, and severe occlusions. PodFormer integrates three core innovations: (1) the Adaptive Wavelet Detail Enhancement (AWDE) module, which strengthens high-frequency boundary cues to alleviate weak-boundary ambiguities; (2) the Density-Guided Query Initialization (DGQI) module, which injects scale and density priors to enhance instance detection in both sparse and densely clustered regions; and (3) the Mask Feedback Gated Refinement (MFGR) layer, which leverages mask confidence to adaptively refine query updates, enabling more accurate separation of adhered or occluded instances. Experimental results show that PodFormer achieves relative improvements of 6.7% and 5.4% in mAP50 and mAP50-95, substantially outperforming state-of-the-art methods. It further demonstrates strong generalization capabilities on real-world field datasets and cross-domain wheat-ear datasets, thereby providing a reliable perception foundation for structural trait recognition in intelligent soybean harvesting systems. Full article

An accurate and reliable extraction of building structures from high-resolution (HR) remote sensing images is an important research topic in 3D cartography and smart city construction. However, despite the strong overall performance of recent deep learning models, limitations remain in handling significant variations in building scales and complex architectural forms, which may lead to inaccurate boundaries or difficulties in extracting small or irregular structures. Therefore, the present study proposes MSA-UNet, a reliable semantic segmentation framework that leverages multiscale feature aggregation and attentive skip connections for an accurate extraction of building footprints. This framework is constructed based on the U-Net architecture, incorporating VGG16 as a replacement for the original encoder structure, which enhances its ability to capture low-discriminative features. To further improve the representation of image buildings with different scales and shapes, a serial coarse-to-fine feature aggregation mechanism was used. Additionally, a novel skip connection was built between the encoder and decoder layers to enable adaptive weights. Furthermore, a dual-attention mechanism, implemented through the convolutional block attention module, was integrated to enhance the focus of the network on building regions. Extensive experiments conducted on the WHU and Inria building datasets validated the effectiveness of MSA-UNet. On the WHU dataset, the model demonstrated a state-of-the-art performance with a mean Intersection over Union (mIoU) of 94.26%, accuracy of 98.32%, F1-score of 96.57%, and mean Pixel accuracy (mPA) of 96.85%, corresponding to gains of 1.41% in mIoU over the baseline U-Net. On the more challenging Inria dataset, MSA-UNet achieved an mIoU of 85.92%, indicating a consistent improvement of up to 1.9% over the baseline U-Net. These results confirmed that MSA-UNet markedly improved the accuracy and boundary integrity of building extraction from HR data, outperforming existing classic models in terms of segmentation quality and robustness. Full article

To address the issues of uneven population initialization, insufficient individual information interaction, and passive boundary handling in the standard Golden Jackal Optimization (GJO) algorithm, while improving the accuracy and efficiency of multilevel thresholding in artistic image segmentation, this paper proposes an improved Golden Jackal Optimization algorithm (MGJO) and applies it to this task. MGJO introduces a high-quality point set for population initialization, ensuring a more uniform distribution of initial individuals in the search space and better adaptation to the complex grayscale characteristics of artistic images. A dual crossover strategy, integrating horizontal and vertical information exchange, is designed to enhance individual information sharing and fine-grained dimensional search, catering to the segmentation needs of artistic image textures and color layers. Furthermore, a global-optimum-based boundary handling mechanism is constructed to prevent information loss when boundaries are exceeded, thereby preserving the boundary details of artistic images. The performance of MGJO was evaluated on the CEC2017 (dim = 30, 100) and CEC2022 (dim = 10, 20) benchmark suites against seven algorithms, including GWO and IWOA. Population diversity analysis, exploration–exploitation balance assessment, Wilcoxon rank-sum tests, and Friedman mean-rank tests all demonstrate that MGJO significantly outperforms the comparison algorithms in optimization accuracy, stability, and statistical reliability. In multilevel thresholding for artistic image segmentation, using Otsu’s between-class variance as the objective function, MGJO achieves higher fitness values (approaching Otsu’s optimal values) across various artistic images with complex textures and colors, as well as benchmark images such as Baboon, Camera, and Lena, in 4-, 6-, 8-, and 10-level thresholding tasks. The resulting segmented images exhibit superior peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and feature similarity (FSIM) compared to other algorithms, more precisely preserving brushstroke details and color layers. Friedman average rankings consistently place MGJO in the lead. These experimental results indicate that MGJO effectively overcomes the performance limitations of the standard GJO, demonstrating excellent performance in both numerical optimization and multilevel thresholding artistic image segmentation. It provides an efficient solution for high-dimensional complex optimization problems and practical demands in artistic image processing. Full article

Detecting fine, weak-textured defects with discontinuous boundaries on complex industrial surfaces is challenging due to interference from background textures and characters, as well as the scarcity of labeled data. To address this issue, we propose YOLO-SR, an engineering modification of YOLO11 tailored to defect segmentation on smart-card surfaces. Rather than introducing a new detection architecture, YOLO-SR reuses the backbone–neck–head design of YOLO11 and only adjusts a few modules to better capture elongated, low-contrast defects. The approach comprises two key components: first, embedding Strip Pooling (SP) within the C3K2 module to form C3K2_SP; second, a Rectangular Self-Calibration Module (RCM) is interposed after the top-level semantic layer. RCM generates rectangular gates to spatially recalibrate local responses, suppressing interference from complex textures and characters. To mitigate data scarcity and distributional bias, a texture-adaptive procedural defect synthesis strategy was developed. This strategy generates defect samples that conform to the background texture statistics of high-quality backgrounds. Experiments on the integrated circuit chip (ICChip) and signature plate (SignPlate) datasets show that YOLO-SR outperforms the YOLO11 baseline. Results indicate that SP and RCM complement each other by integrating directional priors from mid-to-high layers with top-level shape self-calibration. This enhances the visibility and localization stability of elongated defects while maintaining efficient inference. Full article

Coral reefs are integral components of tropical coastal marine ecosystems that have considerable capacity to mitigate extreme flows and marine floods caused by storms and tsunamis. However, limited studies on coral reef efficacy in reducing such flows, coupled with variable roughness coefficient characteristics, hinder their broader utilization in sustainable engineering applications for societal benefit. In this study, we conducted comprehensive experimental investigations to examine flow–coral interactions and the flow energy reduction capabilities of coral reefs. Three-dimensional-printed coral reefs were used to simulate actual coral reefs, providing a scalable and environmentally responsible approach for studying nature-based coastal protection systems. Flow characteristics within the coral reef were investigated through flow depth and velocity measurements taken at the front of, over, and behind the reef. Analysis was performed considering nondimensional parameters, i.e., the Froude number (Fr), the depth effect (DE; ratio of flow depth to coral height), and the size effect (SE; ratio of coral length to coral height), to assess the flow energy reduction under different coral combinations and flow conditions. Spatial variations in flow depth over the reef showed that fast and shallow flows exhibited a reduction gradient toward the back of the reef. The findings revealed a substantial reduction in flow depth and velocity, reaching up to 27.5% and 25%, respectively, at the back boundary of the coral. Two-layered velocity analyses showed that the velocity over the top of corals could be six times higher than that through the coral reef structure for deep flows. Manning’s roughness coefficient varied considerably from 0.03 to 0.26. Overall, this study contributes to sustainable coastal engineering by demonstrating how bio-inspired coral reef structures can be applied to reduce flow energy and enhance coastal resilience in an environmentally adaptive manner. Full article

Water leakage in subway tunnel linings poses significant risks to structural safety and long-term durability, making accurate and efficient leakage detection a critical task. Existing deep learning methods, such as UNet and its variants, often suffer from large parameter sizes and limited ability to capture multi-scale features, which restrict their applicability in real-world tunnel inspection. To address these issues, we propose an Efficient Multi-Scale U-shaped KAN-based Segmentation Network (EMS-UKAN) for detecting water leakage in subway tunnel linings. To reduce computational cost and enable edge-device deployment, the backbone replaces conventional convolutional layers with depthwise separable convolutions, and an Edge-Enhanced Depthwise Separable Convolution Module (EEDM) is incorporated in the decoder to strengthen boundary representation. The PKAN Block is introduced in the bottleneck to enhance nonlinear feature representation and improve the modeling of complex relationships among latent features. In addition, an Adaptive Multi-Scale Feature Extraction Block (AMS Block) is embedded within early skip connections to capture both fine-grained and large-scale leakage features. Extensive experiments on the newly collected Tunnel Water Leakage (TWL) dataset demonstrate that EMS-UKAN outperforms classical models, achieving competitive segmentation performance. In addition, it effectively reduces computational complexity, providing a practical solution for real-world tunnel inspection. Full article

We use deep Physics-Informed Neural Networks (PINNs) to simulate stratified forced convection in plane Couette flow. This process is critical for atmospheric boundary layers (ABLs) and oceanic thermoclines under global warming. The buoyancy-augmented energy equation is solved under two boundary conditions: Isolated-Flux (single-wall heating) and Flux–Flux (symmetric dual-wall heating). Stratification is parameterized by the Richardson number $(R_i\in [-1,1\left]\right),$ representing $\pm 2 °\mathrm{C}$ thermal perturbations. We employ a decoupled model (linear velocity profile) valid for low-Re, shear-dominated flow. Consequently, this approach does not capture the full coupled dynamics where buoyancy modifies the velocity field, limiting the results to the laminar regime. Novel contribution: This is the first deep PINN to robustly converge in stiff, buoyancy-coupled flows ($\mid R_i\mid \le 1$) using residual connections, adaptive collocation, and curriculum learning—overcoming standard PINN divergence (errors $>28\%$). The model is validated against analytical ($R_i=0$) and RK4 numerical ($R_i\ne 0$) solutions, achieving $L_2$ errors $\le 0.009\%$ and $L_{\mathrm{\infty }}$ errors $\le 0.023\%$. Results show that stable stratification $(R_i>0)$ suppresses convective transport, significantly reduces local Nusselt number ($Nu$) by up to $100\%$ (driving $Nu$ towards zero at both boundaries), and induces sign reversals and gradient inversions in thermally developing regions. Conversely, destabilizing buoyancy $(R_i<0)$ enhances vertical mixing, resulting in an asymmetric response: $Nu$ increases markedly (by up to $140\%$) at the lower wall but decreases at the upper wall compared to neutral forced convection. At $5–10\times$ lower computational cost than DNS or RK4, this mesh-free PINN framework offers a scalable and energy-efficient tool for subgrid-scale parameterization in general circulation models (GCMs), supporting SDG 13 (Climate Action). Full article

Accurate trajectory learning and reconstruction represent a core challenge in mobile robotics, particularly in environments affected by sensor noise, drift, and incomplete data. Addressing this challenge is essential for reliable navigation and motion control in real-world Internet of Robotic Things (IoRT) systems. This paper presents a data-driven framework for learning and reconstructing mobile robot trajectories using LSTM autoencoders. Trajectory data were collected from both simulation and real-world experiments with a Unitree GO1 quadruped robot, preprocessed through normalization, sequence padding, and trajectory boundary flags, and then used to train recurrent neural network models. The proposed architecture employs bidirectional LSTM layers and a custom loss function combining reconstruction, velocity, and boundary terms to improve trajectory stability. Experimental results show stable reconstruction accuracy across simulated and real-world datasets, with the position RMSE reduced from 0.92 m to 0.60 m and the yaw MAE improved from 0.49 rad to 0.17 rad on the most complex trajectory. The evaluation was conducted in controlled indoor conditions and offline mode, which defines the current scope of validation. Future work will extend the analysis to larger and more diverse environments and investigate extensions such as attention mechanisms, sensor fusion, and online learning to enhance adaptability in real-world deployment. Full article