Search Results (576)

To address the deficiency of aircraft point cloud training data for low-altitude environment perception systems, a method termed APCG (aircraft point cloud generation) is proposed. APCG can generate aircraft point cloud data in the single photon counting Lidar (SPC-Lidar) system based on information such as aircraft type, position, and attitude. The core of APCG is the aircraft depth image generator, which is obtained through adversarial training of an improved conditional generative adversarial network (cGAN). The training data of the improved cGAN are composed of aircraft depth images formed by spatial sampling and transformation of fine point clouds of 76 types of aircraft and 4 types of drone. The experimental results demonstrate that APCG is capable of efficiently generating diverse aircraft point clouds that reflect the acquisition characteristics of the SPC-Lidar system. The generated point clouds exhibit high similarity to the standard point clouds. Furthermore, APCG shows robust adaptability and stability in response to the variation in aircraft slant range. Full article

Accurate and timely segmentation of liver trauma in computed tomography (CT) images is essential for effective diagnosis and management in emergency medicine. This review examines advancements in liver segmentation techniques from 1993 to 2024, focusing on deep learning models and their impact on improving diagnostic accuracy for liver injuries. Early methods relied on basic image processing, which faced limitations due to noise, intensity variations, and complex abdominal anatomy. The advent of deep learning has transformed this domain, with architectures such as UNet, UNet++, UNet3+, multiscale large kernel (MSLUNet), and Swin-Unet achieving significant improvements in segmentation precision. Additionally, generative adversarial networks (GANs), including conditional GAN and pixel-to-pixel (Pix2Pix) GAN, have further enhanced image quality and detail, addressing deficiencies in traditional methods. This review provides a comparative analysis of these models, highlighting their strengths and limitations in liver injury segmentation. Full article

AI-powered medical imaging faces persistent challenges, such as limited datasets, class imbalances, and high computational costs. To overcome these barriers, we introduce PixMed-Enhancer, a novel conditional GAN that integrates the ghost module into its encoder—a pioneering approach that achieves efficient feature extraction while significantly reducing the computational complexity without compromising the performance. Our method features a hybrid loss function, uniquely combining binary cross-entropy (BCE) and a Structural Similarity Index Measure (SSIM), to ensure pixel-level precision while enhancing the perceptual realism. Additionally, the use of conditional input masks offers unparalleled control over the generation of tumor features, marking a breakthrough in fine-grained dataset augmentation for segmentation and diagnostic tasks. Rigorous testing on diverse datasets establishes PixMed-Enhancer as a state-of-the-art solution, excelling in its realism, structural fidelity, and computational efficiency. PixMed-Enhancer establishes a robust foundation for real-world clinical applications in AI-driven medical imaging. Full article

Silicon Carbide (SiC) and Gallium Nitride (GaN) are revolutionizing power electronics with greater efficiency and durability than Silicon. Nevertheless, their widespread use is limited by reliability challenges, including thermal degradation, defect propagation, and charge trapping, affecting their stability and lifetime. This review explores these reliability issues, comparing empirical and physics-based models for predicting device performance and identifying practical limitations. We also examine strategies to enhance robustness, from material design improvements to advanced testing methods. We propose a demonstrative GaN power circuit topology specifically for demonstrating reliability in real-world conditions. This work highlights key challenges and opportunities in developing more reliable SiC and GaN technologies for future applications. Full article

The increasing adoption of photovoltaic (PV) systems has introduced challenges for grid stability due to the intermittent nature of PV power generation. Accurate forecasting and data quality are critical for effective integration into power grids. However, PV power records often contain missing data due to system downtime, posing difficulties for pattern recognition and model accuracy. To address this, we propose a GAN-based data imputation method tailored for PV power generation. Unlike traditional GANs used in image generation, our method ensures smooth transitions with existing data by utilizing a data-guided GAN framework with quasi-convex properties. To stabilize training, we introduce a gradient penalty mechanism and a single-batch multi-iteration strategy. Our contributions include analyzing the necessity of data imputation, designing a novel conditional GAN-based network for PV data generation, and validating the generated data using frequency domain analysis, t-NSE, and prediction performance. This approach significantly enhances data continuity and reliability in PV forecasting tasks. Full article

A method for the conversion of SAR (Synthetic Aperture Radar) images to optical images can be useful for disaster area detection for the following two reasons: (1) it is easier to detect disaster areas with optical images rather than with SAR images; (2) disasters may occur at night and in rainy and cloudy conditions (SAR images can be acquired in daytime and nighttime as well as all weather conditions). Therefore, it becomes easier to detect disaster areas with optical images converted from SAR images. Using GANs (Generative Adversarial Networks), it is possible to convert SAR images to optical images. In particular, pix2pix and pix2pixHD are used for this purpose. The author proposed spatial resolution-maintained pix2pixHD previously. In this paper, a new method of modifying pix2pixHD with a spatial attention mechanism and an edge enhancement mechanism with a Canny filter in the loss function is proposed, and the proposed method is compared to the pix2pixHD with a spatial attention mechanism and pix2pixHD as well as pix2pix. All of these four methods are compared in terms of the spatial resolution (frequency components) of converted optical images. By experiment, the superiority of the modified pix2pixHD with spatial attention and edge enhancement mechanisms is confirmed for disaster area detection (landslide area detection). Full article

With the help of specific emitter identification (SEI), the control efficiency of the satellite communication systems can be effectively improved by discriminating the individual satellite. In recent years, deep learning has been introduced into SEI to enhance identification performance because of its powerful classification capability. However, classical real-valued neural networks exhibit some limitations in extracting the radio frequency fingerprint (RFF) features from complex signals, limiting the improvement of identification accuracy. Thus, we proposed a complex-valued conditional adversarial generative network (CC-GAN) which can directly deal with complex signals. Through adversarial learning between the generator and the discriminator, the generator implements direct mapping from the dynamic noisy signals to the noise-free signals. In addition, an auxiliary classifier is introduced into the discriminator to make the discriminator able to label the sample, which effectively compress the proposed model. The experimental results for a signal dataset collected in a real environment demonstrated that the proposed model is superior to the traditional denoising methods in denoising performance, which effectively improves the identification accuracy under dynamic noises. Furthermore, the proposed model outperforms other deep learning models in terms of identification performance under various SNRs, which can effectively improve the robustness and adaptability of the SEI system for communication satellites in dynamic noisy environments. Full article

The rapid proliferation of ransomware variants necessitates more effective detection mechanisms, as traditional signature-based methods are increasingly inadequate. These conventional methods rely on manual feature extraction and matching, which are time-consuming and limited to known threats. This study addresses the escalating challenge of ransomware threats in cybersecurity by proposing a novel deep learning model, LSTM-EDadver, which leverages Generative Adversarial Networks (GANs) and Carlini and Wagner (CW) attacks to enhance malware detection capabilities. LSTM-EDadver innovatively generates adversarial examples (AEs) using sequential features derived from ransomware behaviors, thus training deep learning models to improve their robustness and accuracy. The methodology combines Cuckoo sandbox analysis with conceptual lattice ontology to capture a wide range of ransomware families and their variants. This approach not only addresses the shortcomings of existing models but also simulates real-world adversarial conditions during the validation phase by subjecting the models to CW attacks. The experimental results demonstrate that LSTM-EDadver achieves a classification accuracy of 96.59%. This performance was achieved using a dataset of 1328 ransomware samples (across 32 ransomware families) and 519 normal instances, outperforming traditional RNN, LSTM, and GCU models, which recorded accuracies of 90.01%, 93.95%, and 94.53%, respectively. The proposed model also shows significant improvements in F1-score, ranging from 2.49% to 6.64% compared to existing models without adversarial training. This advancement underscores the effectiveness of integrating GAN-generated attack command sequences into model training. Full article

Semiconductors characterized by ultrawide bandgaps (UWBGs), exceeding the SiC bandgap of 3.2 eV and the GaN bandgap of 3.4 eV, are currently under focus for applications in high-power and radio-frequency (RF) electronics, as well as in deep-ultraviolet optoelectronics and extreme environmental conditions. These semiconductors offer numerous advantages, such as a high breakdown field, exceptional thermal stability, and minimized power losses. This study used numerical simulation to investigate, at the material level, the single-particle radiation response of various UWBG semiconductors, such as aluminum gallium nitride alloys (Al_xGa_1−xN), diamond, and β-phase gallium oxide (β-Ga₂O₃), when exposed to ground-level neutrons. Through comprehensive Geant4 simulations covering the entire spectrum of atmospheric neutrons at sea level, this study provides an accurate comparison of the neutron radiation responses of these UWBG semiconductors focusing on the interaction processes, the number and nature of secondary ionizing products, their energy distributions, and the production of electron–hole pairs at the origin of single-event effects (SEEs) in microelectronics devices. Full article

Ophthalmic diseases such as glaucoma, age-related macular degeneration (ARMD), and optic neuritis involve complex molecular and cellular disruptions that challenge current diagnostic and therapeutic approaches. Advanced artificial intelligence (AI) and machine learning (ML) models offer a novel lens to analyze these diseases by integrating diverse datasets, identifying patterns, and enabling precision medicine strategies. Over the past decade, applications of AI in ophthalmology have expanded from imaging-based diagnostics to molecular-level modeling, bridging critical gaps in understanding disease mechanisms. This paper systematically reviews the application of AI-driven methods, including reinforcement learning (RL), graph neural networks (GNNs), Bayesian inference, and generative adversarial networks (GANs), in the context of these ophthalmic conditions. RL models simulate transcription factor dynamics in hypoxic or inflammatory environments, offering insights into disrupted molecular pathways. GNNs map intricate molecular networks within affected tissues, identifying key inflammatory or degenerative drivers. Bayesian inference provides probabilistic models for predicting disease progression and response to therapies, while GANs generate synthetic datasets to explore therapeutic interventions. By contextualizing these AI tools within the broader framework of ophthalmic disease management, this review highlights their potential to transform diagnostic precision and therapeutic outcomes. Ultimately, this work underscores the need for continued interdisciplinary collaboration to harness AI’s potential in advancing the field of ophthalmology and improving patient care. Full article

High-resolution NDVI maps derived from UAV imagery are valuable in precision agriculture, supporting vineyard management decisions such as disease risk and vigor assessments. However, the expense and complexity of multispectral sensors limit their widespread use. In this study, we evaluate Generative Adversarial Network (GAN) approaches—trained on either multispectral-derived or true RGB data—to convert low-cost RGB imagery into NDVI maps. We benchmark these models against simpler, explainable RGB-based indices (RGBVI, vNDVI) using Botrytis bunch rot (BBR) risk and vigor mapping as application-centric tests. Our findings reveal that both multispectral- and RGB-trained GANs can generate NDVI maps suitable for BBR risk modelling, achieving R-squared values between 0.8 and 0.99 on unseen datasets. However, the RGBVI and vNDVI indices often match or exceed the GAN outputs, for vigor mapping. Moreover, model performance varies with sensor differences, vineyard structures, and environmental conditions, underscoring the importance of training data diversity and domain alignment. In highlighting these sensitivities, this application-centric evaluation demonstrates that while GANs can offer a viable NDVI alternative in some scenarios, their real-world utility is not guaranteed. In many cases, simpler RGB-based indices may provide equal or better results, suggesting that the choice of NDVI conversion method should be guided by both application requirements and the underlying characteristics of the subject matter. Full article

N-polar GaN HEMTs feature a natural back-barrier and enable the formation of low-resistance Ohmic contacts, with the potential to suppress short-channel effects and current collapse effects at sub-100 nm gate lengths, rendering them particularly promising for high-frequency communication applications. In this study, N-polar GaN films were grown on C-face SiC substrates with a 4° misorientation angle via MOCVD. By employing a two-step growth process involving LT-GaN or LT-AlGaN, the surface roughness of N-polar GaN films was reduced to varying degrees, accompanied by an improvement in crystalline quality. The growth processes, including surface morphology at each growth stage, such as the AlN nucleation layer, LT-GaN, LT-AlGaN, and the initial 90 nm HT-GaN, were investigated. The results revealed that a high V/III ratio and low-temperature growth conditions for the low-temperature layers, along with the introduction of a minor amount of Al, influenced adatom migration behavior and facilitated the suppression of step bunching. Suppressing step bunching during the initial growth stages was demonstrated to be critical for improving the surface quality and crystalline quality of N-polar GaN films. An N-polar GaN HEMT epitaxial structure was successfully achieved using the optimized surface morphology with a dedicated Fe-doped buffer process. Full article

Cone-Beam Computed Tomography (CBCT) holds significant clinical value in image-guided radiotherapy (IGRT). However, CBCT images of low-density soft tissues are often plagued with artifacts and noise, which can lead to missed diagnoses and misdiagnoses. We propose a new unsupervised CBCT image artifact correction algorithm, named Spatial Convolution Diffusion (ScDiff), based on a conditional diffusion model, which combines the unsupervised learning ability of generative adaptive networks (GAN) with the stable training characteristics of diffusion models. This approach can efficiently and stably achieve CBCT image artifact correction, resulting in clear, realistic CBCT images with complete anatomical structures. The proposed model can effectively improve the image quality of CBCT. The obtained results can reduce artifacts while preserving the anatomical structure of CBCT images. We compared the proposed method with several GAN- and diffusion-based methods. Our method achieved the highest corrected image quality and the best evaluation metrics. Full article

This survey explores recent advances in addressing class imbalance issues for developing machine learning models in precision agriculture, with a focus on techniques used for plant disease detection, soil management, and crop classification. We examine the impact of class imbalance on agricultural data and evaluate various resampling methods, such as oversampling and undersampling, as well as algorithm-level approaches, to mitigate this challenge. The paper also highlights the importance of evaluation metrics, including F1-score, G-mean, and MCC, in assessing the performance of machine learning models under imbalanced conditions. Additionally, the review provides an in-depth analysis of emerging trends in the use of generative models, like GANs and VAEs, for data augmentation in agricultural applications. Despite the significant progress, challenges such as noisy data, incomplete datasets, and lack of publicly available datasets remain. This survey concludes with recommendations for future research directions, including the need for robust methods that can handle high-dimensional agricultural data effectively. Full article

This study tackles the challenge of precise wood log counting, where applications of the proposed methodology can span from automated approaches for materials management, surveillance, and safety science to wood traffic monitoring, wood volume estimation, and others. We introduce an approach leveraging Conditional Generative Adversarial Networks (cGANs) for eucalyptus log segmentation in images, incorporating specialized image processing techniques to handle noise and intersections, coupled with the Connected Components Algorithm for efficient counting. To support this research, we created and made publicly available a comprehensive database of 466 images containing approximately 13,048 eucalyptus logs, which served for both training and validation purposes. Our method demonstrated robust performance, achieving an average ${\mathrm{Accuracy}}_{pixel}$ of 96.4% and ${\mathrm{Accuracy}}_{logs}$ of 92.3%, with additional measures such as F1 scores ranging from 0.879 to 0.933 and IoU values between 0.784 and 0.875, further validating its effectiveness. The implementation proves to be efficient with an average processing time of 0.713 s per image on an NVIDIA T4 GPU, making it suitable for real-time applications. The practical implications of this method are significant for operational forestry, enabling more accurate inventory management, reducing human errors in manual counting, and optimizing resource allocation. Furthermore, the segmentation capabilities of the model provide a foundation for advanced applications such as eucalyptus stack volume estimation, contributing to a more comprehensive and refined analysis of forestry operations. The methodology’s success in handling complex scenarios, including intersecting logs and varying environmental conditions, positions it as a valuable tool for practical applications across related industrial sectors. Full article