LIVIVO - Search results -

Search results

Result 1 - 10 of total 5904

Article ; Online: GaN-on-Si

Chin Hsia / Deng-Fong Lu

Applied Sciences, Vol 12, Iss 5109, p

Monolithically Integrated All-GaN Drivers for High-Voltage DC-DC Power Conversion

2022 Volume 5109

Abstract: This paper presents a novel integrated half-bridge driver architecture using GaN-on-Si process ... and depletion-mode (D-mode) GaN transistors. The high-side driver circuit adopts the E-stacked E/D ... of the low-side driver. The designed fully integrated GaN driver can output a high-voltage pulse wave ...

Abstract	This paper presents a novel integrated half-bridge driver architecture using GaN-on-Si process for high-speed and high-voltage DC-DC converters. The entire circuit includes only enhancement mode (E-mode) and depletion-mode (D-mode) GaN transistors. The high-side driver circuit adopts the E-stacked E/D-mode (EED) architecture, which can directly drive the gate of the high-side transistor with a low-voltage signal without using an additional level shifter, which simplifies the design and reduces propagation delay. In addition, the low-side power transistor is driven by stacking two D/E-mode devices. This architecture separates the high-side pulse from the low-side drive signal to prevent false triggering of the low-side driver. The designed fully integrated GaN driver can output a high-voltage pulse wave with an operating frequency greater than 1 MHz when the input voltage is greater than 200 V. The rise and fall times of the high-voltage pulse wave operating at a peak voltage of 200 V are 54.4 ns and 57.6 ns, respectively. The experimental results show that the circuit can effectively drive the half-bridge circuit and be applied to a buck converter. The designed buck converter can deliver up to 20.5 W of output power, and the maximum efficiency achieves 90.7%.
Keywords	GaN technology ; high-side driver ; DC-DC conversion ; integrated power converter ; Technology ; T ; Engineering (General). Civil engineering (General) ; TA1-2040 ; Biology (General) ; QH301-705.5 ; Physics ; QC1-999 ; Chemistry ; QD1-999
Subject code	600
Language	English
Publishing date	2022-05-01T00:00:00Z
Publisher	MDPI AG
Document type	Article ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: MultiLoad-GAN

Hu, Yi / Li, Yiyan / Song, Lidong / Lee, Han Pyo / Rehm, PJ / Makdad, Matthew / Miller, Edmond / Lu, Ning

A GAN-Based Synthetic Load Group Generation Method Considering Spatial-Temporal Correlations

2022

Abstract: ... GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution ... of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served ... required for microgrid and distribution system studies. The novelty and uniqueness of the MultiLoad-GAN ...

Abstract	This paper presents a deep-learning framework, Multi-load Generative Adversarial Network (MultiLoad-GAN), for generating a group of synthetic load profiles (SLPs) simultaneously. The main contribution of MultiLoad-GAN is the capture of spatial-temporal correlations among a group of loads that are served by the same distribution transformer. This enables the generation of a large amount of correlated SLPs required for microgrid and distribution system studies. The novelty and uniqueness of the MultiLoad-GAN framework are three-fold. First, to the best of our knowledge, this is the first method for generating a group of load profiles bearing realistic spatial-temporal correlations simultaneously. Second, two complementary realisticness metrics for evaluating generated load profiles are developed: computing statistics based on domain knowledge and comparing high-level features via a deep-learning classifier. Third, to tackle data scarcity, a novel iterative data augmentation mechanism is developed to generate training samples for enhancing the training of both the classifier and the MultiLoad-GAN model. Simulation results show that MultiLoad-GAN can generate more realistic load profiles than existing approaches, especially in group level characteristics. With little finetuning, MultiLoad-GAN can be readily extended to generate a group of load or PV profiles for a feeder or a service area. Comment: Submitted to IEEE Transactions on Smart Grid
Keywords	Electrical Engineering and Systems Science - Signal Processing
Subject code	621
Publishing date	2022-10-03
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: CM-GAN

Zheng, Haitian / Lin, Zhe / Lu, Jingwan / Cohen, Scott / Shechtman, Eli / Barnes, Connelly / Zhang, Jianming / Xu, Ning / Amirghodsi, Sohrab / Luo, Jiebo

Image Inpainting with Cascaded Modulation GAN and Object-Aware Training

2022

Abstract: ... of an image. We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder ... GAN-Inpainting}. ... Comment: 32 pages, 19 figures ...

Abstract	Recent image inpainting methods have made great progress but often struggle to generate plausible image structures when dealing with large holes in complex images. This is partially due to the lack of effective network structures that can capture both the long-range dependency and high-level semantics of an image. We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder with Fourier convolution blocks that extract multi-scale feature representations from the input image with holes and a dual-stream decoder with a novel cascaded global-spatial modulation block at each scale level. In each decoder block, global modulation is first applied to perform coarse and semantic-aware structure synthesis, followed by spatial modulation to further adjust the feature map in a spatially adaptive fashion. In addition, we design an object-aware training scheme to prevent the network from hallucinating new objects inside holes, fulfilling the needs of object removal tasks in real-world scenarios. Extensive experiments are conducted to show that our method significantly outperforms existing methods in both quantitative and qualitative evaluation. Please refer to the project page: \url{https://github.com/htzheng/CM-GAN-Inpainting}. Comment: 32 pages, 19 figures
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	006
Publishing date	2022-03-22
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article: Research on the Reliability of Threshold Voltage Based on GaN High-Electron-Mobility Transistors.

Dai, Pengfei / Wang, Shaowei / Lu, Hongliang

Micromachines

2024 Volume 15, Issue 3

Abstract: With the development of high-voltage and high-frequency switching circuits, GaN high-electron ... have become an important research topic in this field. It has been found that GaN HEMT devices have ...

Abstract	With the development of high-voltage and high-frequency switching circuits, GaN high-electron-mobility transistor (HEMT) devices with high bandwidth, high electron mobility, and high breakdown voltage have become an important research topic in this field. It has been found that GaN HEMT devices have a drift in threshold voltage under the conditions of temperature and gate stress changes. Under high-temperature conditions, the difference in gate contact also causes the threshold voltage to shift. The variation in the threshold voltage affects the stability of the device as well as the overall circuit performance. Therefore, in this paper, a review of previous work is presented. Temperature variation, gate stress variation, and gate contact variation are investigated to analyze the physical mechanisms that generate the threshold voltage (
Language	English
Publishing date	2024-02-25
Publishing country	Switzerland
Document type	Journal Article ; Review
ZDB-ID	2620864-7
ISSN	2072-666X
ISSN	2072-666X
DOI	10.3390/mi15030321
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Article: Coupling of Pyro-Piezo-Phototronic Effects in a GaN Nanowire.

Qin, Guoshuai / Wang, Zhenyu / Wang, Lei / Yang, Kun / Zhao, Minghao / Lu, Chunsheng

Materials (Basel, Switzerland)

2023 Volume 16, Issue 18

Abstract: ... mechanical loading on the electromechanical behavior of a GaN nanowire. The distributions of polarization ... charge, potential, carriers, and electric field in the GaN nanowire are analytically represented by using ...

Abstract	In this paper, we systematically investigate the synergistic regulation of ultraviolet and mechanical loading on the electromechanical behavior of a GaN nanowire. The distributions of polarization charge, potential, carriers, and electric field in the GaN nanowire are analytically represented by using a one-dimensional model that combines pyro-phototronic and piezo-phototronic properties, and then, the electrical transmission characteristics are analyzed. The results suggest that, due to the pyro-phototronic effect and ultraviolet photoexcited non-equilibrium carriers, the electrical behavior of a nano-Schottky junction can be modulate by ultraviolet light. This provides a new method for the function improvement and performance regulation of intelligent optoelectronic nano-Schottky devices.
Language	English
Publishing date	2023-09-17
Publishing country	Switzerland
Document type	Journal Article
ZDB-ID	2487261-1
ISSN	1996-1944
ISSN	1996-1944
DOI	10.3390/ma16186247
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: A GAN-based anomaly detector using multi-feature fusion and selection.

Dai, Huafeng / Wang, Jyunrong / Zhong, Quan / Chen, Taogen / Liu, Hao / Zhang, Xuegang / Lu, Rongsheng

Scientific reports

2024 Volume 14, Issue 1, Page(s) 5259

Abstract: ... established supervised learning methods. GAN-based models which trained in an unsupervised and single feature ...

Abstract	In numerous applications, abnormal samples are hard to collect, limiting the use of well-established supervised learning methods. GAN-based models which trained in an unsupervised and single feature set manner have been proposed by simultaneously considering the reconstruction error and the latent space deviation between normal samples and abnormal samples. However, the ability to capture the input distribution of each feature set is limited. Hence, we propose an unsupervised and multi-feature model, Wave-GANomaly, trained only on normal samples to learn the distribution of these normal samples. The model predicts whether a given sample is normal or not by its deviation from the distribution of normal samples. Wave-GANomaly fuses and selects from the wave-based features extracted by the WaveBlock module and the convolution-based features. The WaveBlock has proven to efficiently improve the performance on image classification, object detection, and segmentation tasks. As a result, Wave-GANomaly achieves the best average area under the curve (AUC) on the Canadian Institute for Advanced Research (CIFAR)-10 dataset (94.3%) and on the Modified National Institute of Standards and Technology (MNIST) dataset (91.0%) when compared to existing state-of-the-art anomaly detectors such as GANomaly, Skip-GANomaly, and the skip-attention generative adversarial network (SAGAN). We further verify our method by the self-curated real-world dataset, the result show that our method is better than GANomaly which only use single feature set for training the model.
Language	English
Publishing date	2024-03-04
Publishing country	England
Document type	Journal Article
ZDB-ID	2615211-3
ISSN	2045-2322 ; 2045-2322
ISSN (online)	2045-2322
ISSN	2045-2322
DOI	10.1038/s41598-024-52378-9
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Book ; Online: IE-GAN

Li, Junjie / Li, Jingyao / Zhou, Wenbo / Lü, Shuai

An Improved Evolutionary Generative Adversarial Network Using a New Fitness Function and a Generic Crossover Operator

2021

Abstract: ... vanishing gradients. The evolutionary generative adversarial network (E-GAN) attempts to alleviate ... However, the evaluation mechanism in the fitness function of E-GAN cannot truly reflect the adaptability of individuals ... of E-GAN only contains mutation operators without considering the crossover operator jointly, isolating ...

Abstract	The training of generative adversarial networks (GANs) is usually vulnerable to mode collapse and vanishing gradients. The evolutionary generative adversarial network (E-GAN) attempts to alleviate these issues by optimizing the learning strategy with multiple loss functions. It uses a learning-based evolutionary framework, which develops new mutation operators specifically for general deep neural networks. However, the evaluation mechanism in the fitness function of E-GAN cannot truly reflect the adaptability of individuals to their environment, leading to an inaccurate assessment of the diversity of individuals. Moreover, the evolution step of E-GAN only contains mutation operators without considering the crossover operator jointly, isolating the superior characteristics among individuals. To address these issues, we propose an improved E-GAN framework called IE-GAN, which introduces a new fitness function and a generic crossover operator. In particular, the proposed fitness function, from an objective perspective, can model the evolutionary process of individuals more accurately. The crossover operator, which has been commonly adopted in evolutionary algorithms, can enable offspring to imitate the superior gene expression of their parents through knowledge distillation. Experiments on various datasets demonstrate the effectiveness of our proposed IE-GAN in terms of the quality of the generated samples and time efficiency. Comment: arXiv admin note: text overlap with arXiv:2101.11186
Keywords	Computer Science - Neural and Evolutionary Computing ; Computer Science - Machine Learning
Subject code	006
Publishing date	2021-07-25
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: Defect-GAN

Zhang, Gongjie / Cui, Kaiwen / Hung, Tzu-Yi / Lu, Shijian

High-Fidelity Defect Synthesis for Automated Defect Inspection

2021

Abstract: ... presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect ... samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement ... that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition ...

Abstract	Automated defect inspection is critical for effective and efficient maintenance, repair, and operations in advanced manufacturing. On the other hand, automated defect inspection is often constrained by the lack of defect samples, especially when we adopt deep neural networks for this task. This paper presents Defect-GAN, an automated defect synthesis network that generates realistic and diverse defect samples for training accurate and robust defect inspection networks. Defect-GAN learns through defacement and restoration processes, where the defacement generates defects on normal surface images while the restoration removes defects to generate normal images. It employs a novel compositional layer-based architecture for generating realistic defects within various image backgrounds with different textures and appearances. It can also mimic the stochastic variations of defects and offer flexible control over the locations and categories of the generated defects within the image background. Extensive experiments show that Defect-GAN is capable of synthesizing various defects with superior diversity and fidelity. In addition, the synthesized defect samples demonstrate their effectiveness in training better defect inspection networks. Comment: Codes will not be released due to confidentiality agreement. Published on WACV 2021. (https://openaccess.thecvf.com/content/WACV2021/papers/Zhang_Defect-GAN_High-Fidelity_Defect_Synthesis_for_Automated_Defect_Inspection_WACV_2021_paper.pdf)
Keywords	Computer Science - Computer Vision and Pattern Recognition
Subject code	530
Publishing date	2021-03-28
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: OPT-GAN

Lu, Minfang / Ning, Shuai / Liu, Shuangrong / Sun, Fengyang / Zhang, Bo / Yang, Bo / Wang, Lin

A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution

2021

Abstract: ... global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies ... that OPT-GAN outperforms other traditional and neural net-based BBO algorithms. ...

Abstract	Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are based on strong and fixed a priori assumptions, such as Gaussianity. However, the complex real-world problems, especially when the global optimum is desired, could be very far from the a priori assumptions because of their diversities, causing unexpected obstacles. In this study, we propose a generative adversarial net-based broad-spectrum global optimizer (OPT-GAN) which estimates the distribution of optimum gradually, with strategies to balance exploration-exploitation trade-off. It has potential to better adapt to the regularity and structure of diversified landscapes than other methods with fixed prior, e.g., Gaussian assumption or separability. Experiments on diverse BBO benchmarks and high dimensional real world applications exhibit that OPT-GAN outperforms other traditional and neural net-based BBO algorithms.
Keywords	Computer Science - Machine Learning ; Computer Science - Neural and Evolutionary Computing
Subject code	006
Publishing date	2021-02-07
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Book ; Online: JDSR-GAN

Gao, Guangwei / Tang, Lei / Wu, Fei / Lu, Huimin / Yang, Jian

Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

2021

Abstract: ... as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked ... JDSR-GAN over some comparable methods which perform the previous two tasks separately. ... Comment: IEEE ...

Abstract	With the growing importance of preventing the COVID-19 virus, face images obtained in most video surveillance scenarios are low resolution with mask simultaneously. However, most of the previous face super-resolution solutions can not handle both tasks in one model. In this work, we treat the mask occlusion as image noise and construct a joint and collaborative learning network, called JDSR-GAN, for the masked face super-resolution task. Given a low-quality face image with the mask as input, the role of the generator composed of a denoising module and super-resolution module is to acquire a high-quality high-resolution face image. The discriminator utilizes some carefully designed loss functions to ensure the quality of the recovered face images. Moreover, we incorporate the identity information and attention mechanism into our network for feasible correlated feature expression and informative feature learning. By jointly performing denoising and face super-resolution, the two tasks can complement each other and attain promising performance. Extensive qualitative and quantitative results show the superiority of our proposed JDSR-GAN over some comparable methods which perform the previous two tasks separately. Comment: IEEE Transactions on Multimedia, 8 pages, 7 figures
Keywords	Computer Science - Computer Vision and Pattern Recognition ; Electrical Engineering and Systems Science - Image and Video Processing
Subject code	006
Publishing date	2021-03-25
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

To top

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED

Full text online

More links

Kategorien

Inter-library loan at ZB MED