Explore the vast range of titles available.

The growing demand for applications based on Generative Adversarial Networks (GANs) has prompted substantial study and analysis in a variety of fields. GAN models have applications in NLP, architectural design, text-to-image, image-to-image, 3D object production, audio-to-image, and prediction. This technique is an important tool for both production and prediction, notably in identifying falsely created pictures, particularly in the context of face forgeries, to ensure visual integrity and security. GANs are critical in determining visual credibility in social media by identifying and assessing forgeries. As the field progresses, a variety of GAN variations arise, along with the development of diverse assessment techniques for assessing model efficacy and scope. The article provides a complete and exhaustive overview of the most recent advances in GAN model designs, the efficacy and breadth of GAN variations, GAN limits and potential solutions, and the blooming ecosystem of upcoming GAN tool domains. Additionally, it investigates key measures like as Inception Score (IS) and Fréchet Inception Distance (FID) as critical benchmarks for improving GAN performance in contrast to existing approaches.

This article tackles the problem of detecting small objects in satellite or aerial remote sensing images by relying on super-resolution to increase image spatial resolution, thus the size and details of objects to be detected. We show how to improve the super-resolution framework starting from the learning of a generative adversarial network (GAN) based on residual blocks and then its integration into a cycle model. Furthermore, by adding to the framework an auxiliary network tailored for object detection, we considerably improve the learning and the quality of our final super-resolution architecture, and more importantly increase the object detection performance. Besides the improvement dedicated to the network architecture, we also focus on the training of super-resolution on target objects, leading to an object-focused approach. Furthermore, the proposed strategies do not depend on the choice of a baseline super-resolution framework, hence could be adopted for current and future state-of-the-art models. Our experimental study on small vehicle detection in remote sensing data conducted on both aerial and satellite images (i.e., ISPRS Potsdam and xView datasets) confirms the effectiveness of the improved super-resolution methods to assist with the small object detection tasks.

In this study, we propose and simulate the design of a non-regrowth staircase channel GaN vertical trench transistor, demonstrating an exceptional threshold and breakdown characteristic for high power and high frequency applications. The unique staircase design provides a variable capacitance through the gate-dielectric-semiconductor interface, which results in a high breakdown voltage of 1.52 kV and maintains a channel on-resistance of 2.61 mΩ∙cm2. Because of the variable length and doping profile in the channel region, this model offers greater flexibility to meet a wide range of device application requirements.

Positron emission tomography (PET) is a widely used imaging modality, providing insight into both the biochemical and physiological processes of human body. Usually, a full dose radioactive tracer is required to obtain high-quality PET images for clinical needs. This inevitably raises concerns about potential health hazards. On the other hand, dose reduction may cause the increased noise in the reconstructed PET images, which impacts the image quality to a certain extent. In this paper, in order to reduce the radiation exposure while maintaining the high quality of PET images, we propose a novel method based on 3D conditional generative adversarial networks (3D c-GANs) to estimate the high-quality full-dose PET images from low-dose ones. Generative adversarial networks (GANs) include a generator network and a discriminator network which are trained simultaneously with the goal of one beating the other. Similar to GANs, in the proposed 3D c-GANs, we condition the model on an input low-dose PET image and generate a corresponding output full-dose PET image. Specifically, to render the same underlying information between the low-dose and full-dose PET images, a 3D U-net-like deep architecture which can combine hierarchical features by using skip connection is designed as the generator network to synthesize the full-dose image. In order to guarantee the synthesized PET image to be close to the real one, we take into account of the estimation error loss in addition to the discriminator feedback to train the generator network. Furthermore, a concatenated 3D c-GANs based progressive refinement scheme is also proposed to further improve the quality of estimated images. Validation was done on a real human brain dataset including both the normal subjects and the subjects diagnosed as mild cognitive impairment (MCI). Experimental results show that our proposed 3D c-GANs method outperforms the benchmark methods and achieves much better performance than the state-of-the-art methods in both qualitative and quantitative measures. •To render the same underlying information between the low-dose and full-dose PET images, a 3D U-net-like deep architecture which can combine hierarchical features by using skip connections is designed as the generator network to synthesize the full-dose image.•To guarantee the synthesized PET image to be close to the real one, we take into account of the estimation error loss in addition to the discriminator feedback to train the generator network.•A concatenated 3D c-GANs based progressive refinement scheme is also proposed to further improve the quality of estimated images.

In various micro‐light‐emitting diode (micro‐LED) display products, near‐eye applications such as AR (augmented reality) and VR (virtual reality) are gaining popularity, driving consumer demand for higher brightness, resolution, and compact size. To address more advanced demands, GaN‐on‐GaN homoepitaxial micro‐LEDs are notable for their low defect density, excellent thermal management, high efficiency, etc. Additionally, the conductivity of the GaN substrate enables the efficient integration of vertical micro‐LEDs, further enhancing performance for near‐eye displays. In this work, GaN‐on‐GaN homoepitaxial platforms to fabricate low‐defect‐density micro‐LEDs are leveraged with superior electrical properties, addressing the limitations of conventional heterogeneous substrates. By replacing traditional ICP (Inductively coupled plasma) mesa etching with fluorine ion implantation for pixel isolation, this study achieves significant reductions in series resistance and enhances optical performance, characterized by sharper pixel edges and a narrowed full width at half maximum (FWHM). Furthermore, the implementation of vertical micro‐LED architectures enables a compact device footprint, facilitating ultra‐dense integration for near‐eye systems. To evaluate performance under practical operating conditions, the effective external quantum efficiency (EQEeffective) is introduced. The ion‐implanted vertical structures demonstrate a substantial improvement in EQEeffective over traditional ICP‐etched devices, underscoring their potential for high‐brightness applications. This work advances high‐resolution, energy‐efficient micro‐LED technologies, offering a scalable pathway for next‐generation AR/VR displays. This work advances micro‐light‐emitting diode (micro‐LED) technology using GaN‐on‐GaN homoepitaxial platforms for low defects. Fluorine ion implantation replaces plasma etching for pixel isolation, reducing series resistance and enhancing optical quality. Vertical architectures enable dense integration. Introduced display effective external quantum efficiency shows gains for high‐brightness augmented/virtual reality applications, offering scalability.

Large-scale mobile traffic data analysis is important for efficiently planning mobile base station deployment plans and public transportation plans. However, the storage costs of preserving mobile traffic data are becoming much higher as traffic increases enormously population density of target areas. To solve this problem, schemes to generate a large amount of mobile traffic data have been proposed. In the state-of-the-art of the schemes, generative adversarial networks (GANs) are used to transform a large amount of traffic data into a coarse-grained representation and generate the original traffic data from the coarse-grained data. However, the scheme still involves a storage cost, since the coarse-grained data must be preserved in order to generate the original traffic data. In this paper, we propose a scheme to generate the mobile traffic data by using conditional-super-resolution GAN (CSR-GAN) without requiring a coarse-grained process. Through experiments using two real traffic data, we assessed the accuracy and the amount of storage data needed. The results show that the proposed scheme, CSR-GAN, can reduce the storage cost by up to 45% compared to the traditional scheme, and can generate the original mobile traffic data with 94% accuracy. We also conducted experiments by changing the architecture of CSR-GAN, and the results show an optimal relationship between the amount of traffic data and the model size.

A small sample size and unbalanced sample distribution are two main problems when data-driven methods are applied for fault diagnosis in practical engineering. Technically, sample generation and data augmentation have proven to be effective methods to solve this problem. The generative adversarial network (GAN) has been widely used in recent years as a representative generative model. Besides the general GAN, many variants have recently been reported to address its inherent problems such as mode collapse and slow convergence. In addition, many new techniques are being proposed to increase the sample generation quality. Therefore, a systematic review of GAN, especially its application in fault diagnosis, is necessary. In this paper, the theory and structure of GAN and variants such as ACGAN, VAEGAN, DCGAN, WGAN, et al. are presented first. Then, the literature on GANs is mainly categorized and analyzed from two aspects: improvements in GAN’s structure and loss function. Specifically, the improvements in the structure are classified into three types: information-based, input-based, and layer-based. Regarding the modification of the loss function, it is sorted into two aspects: metric-based and regularization-based. Afterwards, the evaluation metrics of the generated samples are summarized and compared. Finally, the typical applications of GAN in the bearing fault diagnosis field are listed, and the challenges for further research are also discussed.

In this study, the effects of switching on the two-dimensional electron gas (2-DEG) channel in an E-mode GaN-on-Si HEMT are investigated using a GS-065-004-1-L device that is commercially available for educational practice. A practical prototype with a reduced number of components is proposed, with empirical concepts used to explain its predictive performance when a coreless transformer is series-connected to the E-mode GaN-on-Si HEMT for switching-mode conduction. Conduction modes arising at the p-GaN/n-AlGaN/i-GaN heterojunction in accordance with specifications from the manufacturer’s datasheet were validated using a didactic physical-based model dependent on semiconductor parameters of gallium nitride (GaN). Test circuit-examined waveforms were analyzed, which confirmed that the switching conduction mode of the 2-DEG channel is dependent on physical parameters such as switching operating frequency, temperature, low-field electron mobility, and space charge capacitance.

We studied the impact of Ge-doping on material properties of polycrystalline GaN layers with different Ge percentages of 2%, 5% and 10%. The carrier concentration for the undoped polycrystalline GaN layer is ~ 6 × 10 19 cm − 3 , and the value increases up to ~ 1.1 × 10 21 cm − 3 by the Ge-doping with 5% of Ge. Meanwhile, the electron mobility is the lowest at 98.6 cm 2 /Vs with 5% of Ge. The result is comparable to some reported Ge-doped single crystal GaN layers with the carrier concentration of above 10 20 cm − 3 . Additionally, the surface of the polycrystalline GaN layer changes significantly with the Ge percentage above 5%. In particular, GaN grain protrusions and GaN grain-like rods are observed. It is found that Ge-N related compounds can form on the GaN grain-like rods. The grain protrusions and grain-like rods lead to the broadening of the Raman E 2 peak, indicating that the crystalline properties can be degraded by excessive Ge-doping.