Search Results (138)

Synthetic aperture radar (SAR) exhibits all-day and all-weather capabilities, granting it significant application in remote sensing. However, interpreting SAR images requires extensive expertise, making SAR-to-optical remote sensing image translation a crucial research direction. While conditional generative adversarial networks (CGANs) have demonstrated exceptional performance in image translation tasks, their massive number of parameters pose substantial challenges. Therefore, this paper proposes ILF-BDSNet, a compressed network for SAR-to-optical image translation. Specifically, first, standard convolutions in the feature-transformation module of the teacher network are replaced with depthwise separable convolutions to construct the student network, and a dual-resolution collaborative discriminator based on PatchGAN is proposed. Next, knowledge distillation based on intermediate-layer features and channel pruning via weight sharing are designed to train the student network. Then, the bio-inspired dynamic search of channel configuration (BDSCC) algorithm is proposed to efficiently select the optimal subnet. Meanwhile, the pixel-semantic dual-domain alignment loss function is designed. The feature-matching loss within this function establishes an alignment mechanism based on intermediate-layer features from the discriminator. Extensive experiments demonstrate the superiority of ILF-BDSNet, which significantly reduces number of parameters and computational complexity while still generating high-quality optical images, providing an efficient solution for SAR image translation in resource-constrained environments. Full article

The electrification of agricultural equipment is a critical pathway to address the dual challenges of increasing global food production and ensuring sustainable agricultural development. As the core power unit, the permanent magnet synchronous motor (PMSM) drive system faces severe challenges in achieving high performance, robustness, and reliable control in complex farmland environments characterized by sudden load changes, extreme operating conditions, and strong interference. This paper provides a comprehensive review of key technological advancements in PMSM drive systems for agricultural electrification. First, it analyzes solutions to enhance the reliability of power converters, including high-frequency silicon carbide (SiC)/gallium nitride (GaN) power device packaging, thermal management, and electromagnetic compatibility (EMC) design. Second, it systematically elaborates on high-performance motor control algorithms such as Direct Torque Control (DTC) and Model Predictive Control (MPC) for improving dynamic response; robust control strategies like Sliding Mode Control (SMC) and Active Disturbance Rejection Control (ADRC) for enhancing resilience; and the latest progress in fault-tolerant control architectures incorporating sensorless technology. Furthermore, the paper identifies core challenges in large-scale applications, including environmental adaptability, real-time multi-machine coordination, and high reliability requirements. Innovatively, this review proposes a closed-loop intelligent control paradigm encompassing environmental disturbance prediction, control parameter self-tuning, and actuator dynamic response. This paradigm provides theoretical support for enhancing the autonomous adaptability and operational quality of agricultural machinery in unstructured environments. Finally, future trends involving deep AI integration, collaborative hardware innovation, and agricultural ecosystem construction are outlined. Full article

As a vital carrier of China’s intangible cultural heritage, restoring damaged embroidery fabrics is essential for the sustainable preservation of cultural relics. However, existing methods face persistent challenges, such as mask pattern mismatches and restoration size constraints. To address these gaps, this study proposes an embroidery image restoration framework based on enhanced generative adversarial networks (GANs). Specifically, the framework integrates a U-Net generator with a multi-scale discriminator augmented by an attention mechanism and dual-path residual blocks to significantly enhance texture generation. Furthermore, fabric damage was classified into three categories (hole-shaped, crease-shaped, and block-shaped), with complex patterns simulated through dynamic randomization. Grid-based overlapping segmentation and pixel fusion techniques enable arbitrary-dimensional restoration. Quantitative evaluations demonstrated exceptional performance in complex texture restoration, achieving a structural similarity index (SSIM) of 0.969 and a peak signal-to-noise ratio (PSNR) of 32.182 dB. Complementarily, eye-tracking experiments revealed no persistent visual fixation clusters in the restored regions, confirming perceptual reliability. This approach establishes an efficient digital conservation pathway that promotes resource-efficient and sustainable heritage conservation. Full article

Material decomposition in X-ray imaging is essential for enhancing tissue differentiation and reducing the radiation dose, but the clinical adoption of photon-counting detectors (PCDs) is limited by their high cost and technical complexity. To address this, we propose Dual-head Pix2Pix, a PCD-guided deep learning framework that enables simultaneous iodine and bone decomposition from single-energy X-ray projections acquired with conventional energy-integrating detectors. The model was trained and tested on 1440 groups of energy-integrating detector (EID) projections with their corresponding iodine/bone decomposition images. Experimental results demonstrate that the Dual-head Pix2Pix outperforms baseline models. For iodine decomposition, it achieved a mean absolute error (MAE) of 5.30 ± 1.81, representing an ~10% improvement over Pix2Pix (5.92) and a substantial advantage over CycleGAN (10.39). For bone decomposition, the MAE was reduced to 9.55 ± 2.49, an ~6% improvement over Pix2Pix (10.18). Moreover, Dual-head Pix2Pix consistently achieved the highest MS-SSIM, PSNR, and Pearson correlation coefficients across all benchmarks. In addition, we performed a cross-domain validation using projection images acquired from a conventional EID-CT system. The results show that the model successfully achieved the effective separation of iodine and bone in this new domain, demonstrating a strong generalization capability beyond the training distribution. In summary, Dual-head Pix2Pix provides a cost-effective, scalable, and hardware-friendly solution for accurate dual-material decomposition, paving the way for the broader clinical and industrial adoption of material-specific imaging without requiring PCDs. Full article

This work presents a novel Gallium Nitride (GaN) high-electron-mobility transistor (HEMT)-based ultraviolet (UV) photodetector architecture that integrates advanced material and structural design strategies to enhance detection performance and stability under room-temperature operation. This study is conducted as a fully numerical simulation using the Silvaco Atlas platform, providing detailed electrothermal and optoelectronic analysis of the proposed device. The device is constructed on a high-thermal-conductivity silicon carbide (SiC) substrate and incorporates an n-GaN buffer, an indium nitride (InN) channel layer for improved electron mobility and two-dimensional electron gas (2DEG) confinement, and a dual-passivation scheme combining silicon nitride (SiN) and hexagonal boron nitride (h-BN). A p-GaN layer is embedded between the passivation interfaces to deplete the 2DEG in dark conditions. In the device architecture, the metal contacts consist of a 2 nm Nickel (Ni) adhesion layer followed by Gold (Au), employed as source and drain electrodes, while a recessed gate embedded within the substrate ensures improved electric field control and effective noise suppression. Numerical simulations demonstrate that the integration of a hexagonal boron nitride (h-BN) interlayer within the dual passivation stack effectively suppresses the gate leakage current from the typical literature values of the order of ${10}^{-8}$ A to approximately ${10}^{-10}$ A, highlighting its critical role in enhancing interfacial insulation. In addition, consistent with previous reports, the use of a SiC substrate offers significantly improved thermal management over sapphire, enabling more stable operation under UV illumination. The device demonstrates strong photoresponse under 360 nm ultraviolet (UV) illumination, a high photo-to-dark current ratio (PDCR) found at approximately ${10}^6$, and tunable performance via structural optimization of p-GaN width between 0.40 μm and 1.60 μm, doping concentration from $5\times {10}^{16}$ ${\mathrm{cm}}^{-3}$ to $5\times {10}^{18}$ ${\mathrm{cm}}^{-3}$, and embedding depth between 0.060 μm and 0.068 μm. The results underscore the proposed structure’s notable effectiveness in passivation quality, suppression of gate leakage, and thermal management, collectively establishing it as a robust and reliable platform for next-generation UV photodetectors operating under harsh environmental conditions. Full article

Underwater crack detection in dam structures is of significant importance to ensure structural safety, assess operational conditions, and prevent potential disasters. Traditional crack detection methods face various limitations when applied to underwater environments, particularly in high dam underwater environments where image quality is influenced by factors such as water flow disturbances, light diffraction effects, and low contrast, making it difficult for conventional methods to accurately extract crack features. This study proposes a dual-stage underwater crack detection method based on Cycle-GAN and YOLOv11 called Edge-Enhanced Underwater CrackNet (E²UCN) to overcome the limitations of existing image enhancement methods in retaining crack details and improving detection accuracy. First, underwater concrete crack images were collected using an underwater remotely operated vehicle (ROV), and various complex underwater environments were simulated to construct a test dataset. Then, an improved Cycle-GAN image style transfer method was used to enhance the underwater images. Unlike conventional GAN-based underwater image enhancement methods that focus on global visual quality, our model specifically constrains edge preservation and high-frequency crack textures, providing a novel solution tailored for crack detection tasks. Subsequently, the YOLOv11 model was employed to perform object detection on the enhanced underwater crack images, effectively extracting crack features and achieving high-precision crack detection. The experimental results show that the proposed method significantly outperforms traditional methods in terms of crack detection accuracy, edge clarity, and adaptability to complex backgrounds, effectively improving underwater crack detection accuracy (precision = 0.995, F1 = 0.99762, mAP@0.5 = 0.995, and mAP@0.5:0.95 = 0.736) and providing a feasible technological solution for intelligent inspection of high dam underwater cracks. Full article

Video anomaly detection in unconstrained environments remains a fundamental challenge due to the scarcity of labeled anomalous data and the diversity of real-world scenarios. To address this, we propose a novel unsupervised framework that integrates RGB appearance and optical flow motion via a unified GAN-based architecture. The generator features a dual encoder and a GRU–attention temporal bottleneck, while the discriminator employs ConvLSTM layers and residual-enhanced MLPs to evaluate temporal coherence. To improve training stability and reconstruction quality, we introduce DASLoss—a composite loss that incorporates pixel, perceptual, temporal, and feature consistency terms. Experiments were conducted on three benchmark datasets. On XD-Violence, our model achieves an Average Precision (AP) of 80.5%, outperforming other unsupervised methods such as MGAFlow and Flashback. On Hockey Fight, it achieves an AUC of 0.92 and an F1-score of 0.85, demonstrating strong performance in detecting short-duration violent events. On UCSD Ped2, our model attains an AUC of 0.96, matching several state-of-the-art models despite using no supervision. These results confirm the effectiveness and generalizability of our approach in diverse anomaly detection settings. Full article

This study compared the effectiveness of gallium nitride (GaN) with a single carbon-doped (C-doped) buffer layer and a composite carbon/iron-doped (C/Fe-doped) buffer layer within an AlGaN/GaN high-electron-mobility transistor (HEMT). In traditional power devices, Fe-doping has a large memory effect, causing Fe ions to diffuse outwards, which is undesirable in high-power-device applications. In the present study, a C-doped GaN layer was added above the Fe-doped GaN layer to form a composite buffer against Fe ion diffusion. Direct current (DC) characteristics, pulse measurement, low-frequency noise, and variable temperature analysis were performed on both devices. The single C-doped buffer layer in the AlGaN/GaN HEMT had fewer defects in capturing and releasing carriers, and better dynamic characteristics, whereas the composite C/Fe-doped buffers, by suppressing Fe migration toward the channel, showed higher vertical breakdown voltage and lower sheet resistance, and still demonstrated potential for further performance tuning to achieve enhanced semi-insulating behavior. With optimized doping concentrations and layer thicknesses, the dual-layer configuration offers a promising path toward improved trade-offs between leakage suppression, trap control, and dynamic performance for next-generation GaN-based power devices. Full article

Gas leakages pose significant safety risks in urban environments and industrial sectors like the Oil and Gas Industry (OGI), leading to accidents, fatalities, and economic losses. This paper introduces a novel generative AI framework, the Multi-Scale Dual Discriminator Generative Adversarial Network (MSDD-GAN), designed to detect and localize gas leaks by generating thermal images from RGB input images. The proposed method integrates three key innovations: (1) Attention-Guided Masking (AttMask) for precise gas leakage localization using saliency maps and a circular Region of Interest (ROI), enabling pixel-level validation; (2) Multi-scale input processing to enhance feature learning with limited data; and (3) Dual Discriminator to validate the thermal image realism and leakage localization accuracy. A comprehensive dataset from laboratory and industrial environment has been collected using a FLIR thermal camera. The MSDD-GAN demonstrated robust performance by generating thermal images with the gas leakage indications at a mean accuracy of $81.6\%$, outperforming baseline cGANs by leveraging a multi-scale generator and dual adversarial losses. By correlating ice formation in RGB images with the leakage indications in thermal images, the model addresses critical challenges of OGI applications, including data scarcity and validation reliability, offering a robust solution for continuous gas leak monitoring in pipeline. Full article

Total Electron Content (TEC) is a fundamental parameter characterizing the electron density distribution in the ionosphere. Traditional global TEC modeling approaches predominantly rely on mathematical methods (such as spherical harmonic function fitting), often resulting in models suffering from excessive smoothing and low accuracy. While the 1° high-resolution global TEC model released by MIT offers improved temporal-spatial resolution, it exhibits regions of data gaps. Existing ionospheric image completion methods frequently employ Generative Adversarial Networks (GANs), which suffer from drawbacks such as complex model structures and lengthy training times. We propose a novel high-resolution global ionospheric TEC modeling method based on a Dual-Branch Convolutional Neural Network (DB-CNN) designed for the completion and restoration of incomplete 1°-resolution ionospheric TEC images. The novel model utilizes a dual-branch input structure: the background field, generated using the International Reference Ionosphere (IRI) model TEC maps, and the observation field, consisting of global incomplete TEC maps coupled with their corresponding mask maps. An asymmetric dual-branch parallel encoder, feature fusion, and residual decoder framework enables precise reconstruction of missing regions, ultimately generating a complete global ionospheric TEC map. Experimental results demonstrate that the model achieves Root Mean Square Errors (RMSE) of 0.30 TECU and 1.65 TECU in the observed and unobserved regions, respectively, in simulated data experiments. For measured experiments, the RMSE values are 1.39 TECU and 1.93 TECU in the observed and unobserved regions. Validation results utilizing Jason-3 altimeter-measured VTEC demonstrate that the model achieves stable reconstruction performance across all four seasons and various time periods. In key-day comparisons, its STD and RMSE consistently outperform those of the CODE global ionospheric model (GIM). Furthermore, a long-term evaluation from 2021 to 2024 reveals that, compared to the CODE model, the DB-CNN achieves average reductions of 38.2% in STD and 23.5% in RMSE. This study provides a novel dual-branch input convolutional neural network-based method for constructing 1°-resolution global ionospheric products, offering significant application value for enhancing GNSS positioning accuracy and space weather monitoring capabilities. Full article

The extensive deployment of diverse sensors in hospitals has resulted in the collection of various medical time-series data. However, these real-world medical time-series data suffer from limited volume, poor data quality, and privacy concerns, resulting in performance degradation in downstream tasks, such as medical research and clinical decision-making. Existing studies provide generated medical data as a supplement or alternative to real-world data. However, medical time-series data are inherently complex, including temporal data such as laboratory measurements and static event data such as demographics and clinical outcomes, with each patient’s temporal data being influenced by their static event data. This intrinsic complexity makes the generation of high-quality medical time-series data particularly challenging. Traditional methods typically employ Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs), but these methods struggle to generate high-quality static event data of medical time-series data and often lack interpretability. Currently, large language models (LLMs) introduce new opportunities for medical data generation, but they face difficulties in generating temporal data and have challenges in specific domain generation tasks. In this study, we are the first to propose an LLM-based framework for modularly generating medical time-series data, QAMT, which generates quality-assured data and ensures the interpretability of the generation process. QAMT constructs a reliable health knowledge graph to provide medical expertise to the LLMs and designs dual modules to simultaneously generate static event data and temporal data, constituting high-quality medical time-series data. Moreover, QAMT introduces a quality assurance module to evaluate the generated data. Unlike existing methods, QAMT preserves the interpretability of the data generation process. Experimental results show that QAMT can generate higher-quality time-series medical data compared with existing methods. Full article

To resolve the conflict between global structure modeling and local detail preservation in image super-resolution, we propose SwinT-SRGAN, a novel framework integrating Swin Transformer with GAN. Key innovations include: (1) A dual-path generator where Transformer captures long-range dependencies via window attention while CNN extracts high-frequency textures; (2) An end-to-end Detail Recovery Block (DRB) suppressing artifacts through dual-path attention; (3) A triple-branch discriminator enabling hierarchical adversarial supervision; (4) A dynamic loss scheduler adaptively balancing six loss components (pixel/perceptual/high-frequency constraints). Experiments on CelebA-HQ and Flickr2K demonstrate: (1) Very good performance (max gains: 0.71 dB PSNR, 0.83% SSIM, 4.67 LPIPS reduction vs. Swin-IR); (2) Ablation studies validate critical roles of DRB. This work offers a robust solution for high-frequency-sensitive applications. Full article

Deep neural networks have led to a substantial increase in multifaceted classification tasks by making use of large-scale and diverse annotated datasets. However, diverse optical coherence tomography (OCT) datasets in cardiovascular imaging remain an uphill task. This research focuses on improving the diversity and generalization ability of augmentation architectures while maintaining the baseline classification accuracy for coronary atrial plaques using a novel dual-generator and dynamically fused discriminator conditional generative adversarial network (DGDFGAN). Our method is demonstrated on an augmented OCT dataset with 6900 images. With dual generators, our network provides the diverse outputs for the same input condition, as each generator acts as a regulator for the other. In our model, this mutual regularization enhances the ability of both generators to generalize better across different features. The fusion discriminators use one discriminator for classification purposes, hence avoiding the need for a separate deep architecture. A loss function, including the SSIM loss and FID scores, confirms that perfect synthetic OCT image aliases are created. We optimize our model via the gray wolf optimizer during model training. Furthermore, an inter-comparison and recorded SSID loss of 0.9542 ± 0.008 and a FID score of 7 are suggestive of better diversity and generation characteristics that outperform the performance of leading GAN architectures. We trust that our approach is practically viable and thus assists professionals in informed decision making in clinical settings. Full article

Due to the challenges of low resolution and incomplete data in the process of power data collection and transmission and the lack of detail in the power data super-resolution algorithm, this paper proposes a generative adversarial network super-resolution perception model based on a linear attention mechanism. It uses the adversarial training mechanism of generator and discriminator to restore high-resolution power data from low-resolution power data. In the generator, the deep residual network structure is innovatively combined with the multi-scale linear attention mechanism, and the linear rectifier unit that can be dynamically learned is combined to improve the model’s ability to extract power data features. The discriminator employs a multi-scale architecture embedded with a dual-attention module, integrating both global and local features to enhance the model’s ability to capture fine details. Experiments were conducted on a dataset of multiple monitoring points in a city in East China. Experimental results indicate that the proposed Lmla-GAN delivers an overall average SSIM improvement of approximately 6.7% over the four baseline models-Bicubic, SRCNN, SubPixelCNN, and VDSR. Full article

Robust perception of road surface conditions is a critical challenge for the safe deployment of autonomous vehicles and the efficient management of transportation infrastructure. This paper introduces a synthetic data-driven deep learning framework designed to address this challenge. We present a large-scale, procedurally generated 3D synthetic dataset created in Blender, featuring a diverse range of road defects—including cracks, potholes, and puddles—alongside crucial road features like manhole covers and patches. Crucially, our dataset provides dense, pixel-perfect annotations for segmentation masks, depth maps, and camera parameters (intrinsic and extrinsic). Our proposed model leverages these rich annotations in a multi-task learning framework that jointly performs road defect segmentation and depth estimation, enabling a comprehensive geometric and semantic understanding of the road environment. A core contribution is a two-stage domain adaptation strategy to bridge the synthetic-to-real gap. First, we employ a modified CycleGAN with a segmentation-aware loss to translate synthetic images into a realistic domain while preserving defect fidelity. Second, during model training, we utilize a dual-discriminator adversarial approach, applying alignment at both the feature and output levels to minimize domain shift. Benchmarking experiments validate our approach, demonstrating high accuracy and computational efficiency. Our model excels in detecting subtle or occluded defects, attributed to an occlusion-aware loss formulation. The proposed system shows significant promise for real-time deployment in autonomous navigation, automated infrastructure assessment and Advanced Driver-Assistance Systems (ADAS). Full article