检索结果-内蒙古大学图书馆

Frontiers in Optics + Laser Science 2023, FiO, LS 203: Part of Frontiers in Optics + Laser Science 2023

作者： Shandilya, Pradyoth H. Moille, Gregory D'Aguanno, Giuseppe Srinivasan, Kartik Menyuk, Curtis R. Department of Computer Science and Electrical Engineering University of Maryland Baltimore United States Microsystems and Nanotechnology Division NIST Gaithersburg United States

We show that 3-wave equations can be used to accurately model the multicolor solitons that appear in dual-pumped microresonators. These equations can be used to analyze the soliton properties. © Optica Publishing... 详细信息

ISBN: (纸本)9781957171296

关键词： Fourier transforms Laser pumping Microcavities Phase shift Phase velocity Solitons

来源：评论

学校读者我要写书评

暂无评论

Massive Fabrication of Carbon Nanotube Transistors by Surface Tension-Driven Inkjet-Printing Method 5

Massive Fabrication of Carbon Nanotube Transistors by Surfac...

引用

5th IEEE International Conference on Flexible and Printable Sensors and Systems, FLEPS 2023

作者： Park, Soohyun Shin, Minhye Kang, Hongki Lee, Yoonhee Division of Electronics and Information System Daegu42988 Korea Republic of Department of Electrical Engineering and Computer Science Daegu42988 Korea Republic of

ISBN: (纸本)9781665457330

Carbon nanotube field-effect transistors (CNTFETs) have been ideal nanoelectronics in semiconductor technologies with exceptional electrical properties. Scaling the CNT -FET fabrication enables the expansion of the application fields. However, placing nanotubes with uniform alignment and controlled density to the electrode contacts has been the maj or challenge in massive manufacturing. Here, we introduce the in-place inkjet-printing method for fabricating CNTFETs with controlled numbers of connected CNTs at a single CNT level. A picoliter (pL) drop of CNT ink is printed to the pre-patterned electrode arrays in parallel over a four-inch silicon wafer, allowing adaptive manufacturing without additional lithographic processes. Drops form thin films on the metal electrode patterns driven by the surface tension flow, diluting the surface density of CNT on the one-micrometer channel gap and avoiding bundled coffee ring edges. Finally, single CNTs are correctly bridged to the electrodes with high statistical yield. This process enables reproducible and high-throughput single CNT deposition, integrating into the FET manufacturing process, and can be used for versatile nanoelectronics applications, such as biosensors. © 2023 IEEE.

关键词： Carbon nanotubes

来源：评论

学校读者我要写书评

暂无评论

Near-Perfect Coverage Manifold Estimation in Cellular Networks via Conditional GAN

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第2期6卷 97-100页

作者： Mondal, Washim Uddin Goyal, Veni Ukkusuri, Satish V. Das, Goutam Wang, Di Alouini, Mohamed-Slim Aggarwal, Vaneet Purdue University School of Industrial Engineering The School of Civil Engineering West LafayetteIN47907 United States Purdue University School of Civil Engineering West LafayetteIN47907 United States Indian Institute of Technology Kharagpur G. S. Sanyal School of Telecommunications Kharagpur721302 India Purdue University School of Industrial Engineering West LafayetteIN47907 United States King Abdullah University of Science and Technology Computer Electrical and Mathematical Sciences and Engineering Division Thuwal23955-6900 Saudi Arabia

This letter presents a conditional generative adversarial network (cGAN) that translates base station location (BSL) information of any Region-of-Interest (RoI) to location-dependent coverage probability values within a subset of that region, called the region-of-evaluation (RoE). We train our network utilizing the BSL data of India, the USA, Germany, and Brazil. In comparison to the state-of-the-art convolutional neural networks (CNNs), our model improves the prediction error (L1 difference between the coverage manifold generated by the network under consideration and that generated via simulation) by two orders of magnitude. Moreover, the cGAN-generated coverage manifolds appear to be almost visually indistinguishable from the ground truth. © 2019 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Progressive Motion Boosting for Video Frame Interpolation

引用

IEEE Transactions on Multimedia 2023年 25卷 8076-8090页

作者： Xiao, Jing Xu, Kangmin Hu, Mengshun Liao, Liang Wang, Zheng Lin, Chia-Wen Wang, Mi Satoh, Shin'Ichi The School of Computer Science Wuhan University Wuhan430072 China The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The Department of Electrical Engineering the Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430072 China The Digital Content and Media Sciences Research Division National Institute of Informatics Tokyo101-8430 Japan

Video frame interpolation has made great progress in estimating advanced optical flow and synthesizing in-between frames sequentially. However, frame interpolation involving various resolutions and motions remains challenging due to limited or fixed pre-trained networks. Inspired by the success of the coarse-to-fine scheme for video frame interpolation, i.e., gradually interpolating frames of different resolutions, we propose a progressive boosting network (ProBoost-Net) based on a multi-scale framework to achieve flexible recurrent scales and then gradually optimize optical flow estimation and frame interpolation. Specifically, we designed a dense motion boosting (DMB) module to transfer features close to real motion to the decoded features from the later scales, which provides complementary information to refine the motion further. Furthermore, to ensure the accuracy of the estimated motion features at each scale, we propose a motion adaptive fusion (MAF) module that adaptively deals with motions with different receptive fields according to the motion conditions. Thanks to the framework’s flexible recurrent scales, we can customize the number of scales and make trade-offs between computation and quality depending on the application scenario. Extensive experiments with various datasets demonstrated the superiority of our proposed method over state-of-the-art approaches in various scenarios. © 2023 Institute of electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Tuning Small Datasets for a Custom Apple Sorting System based on Deep Learning 4

Tuning Small Datasets for a Custom Apple Sorting System base...

引用

4th International Conference on Transdisciplinary AI, TransAI 2022

作者： Endo, Minori Kawamoto, Pauline N. Shinshu University Department of Electrical and Computer Engineering Nagano Japan Shinshu University Engineering Core Division Nagano Japan

ISBN: (数字)9781665471848

ISBN: (纸本)9781665471848

Farmers around the world strive to pass on the information and agricultural know-how they have collected during a lifetime to the following generation. In discussions with apple orchard farmers in Nagano City, Japan, we find that they struggle with maintaining 'senka', or fruit sorting, procedures in particular because there are fewer and fewer people who can do it and it takes several years of training to sufficiently acquire the skill of judging defects and signs of illness in apples and then correctly categorizing their market grade. To help solve this problem, we are developing a deep learning model to automatically replicate some of this classification work and reduce the burden on farmers. The prototype in our previous work had a classification accuracy of 84.1%, but when we examined the apple images that were misjudged, we found that several of them contained obvious flaws. In this work, we describe how we modified and utilized the small training set we had to assist the model in learning how to make simple judgments. This model has a 96.5% accuracy rate when evaluating apples with visible points of surface damage. © 2022 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

SOUND AND COMPLETE NEURAL NETWORK REPAIR WITH MINIMALITY AND LOCALITY GUARANTEES 10

SOUND AND COMPLETE NEURAL NETWORK REPAIR WITH MINIMALITY AND...

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Fu, Feisi Li, Wenchao Division of System Engineering Boston University United States Department of Electrical and Computer Engineering Boston University United States

We present a novel methodology for repairing neural networks that use ReLU activation functions. Unlike existing methods that rely on modifying the weights of a neural network which can induce a global change in the function space, our approach applies only a localized change in the function space while still guaranteeing the removal of the buggy behavior. By leveraging the piecewise linear nature of ReLU networks, our approach can efficiently construct a patch network tailored to the linear region where the buggy input resides, which when combined with the original network, provably corrects the behavior on the buggy input. Our method is both sound and complete - the repaired network is guaranteed to fix the buggy input, and a patch is guaranteed to be found for any buggy input. Moreover, our approach preserves the continuous piecewise linear nature of ReLU networks, automatically generalizes the repair to all the points including other undetected buggy inputs inside the repair region, is minimal in terms of changes in the function space, and guarantees that outputs on inputs away from the repair region are unaltered. On several benchmarks, we show that our approach significantly outperforms existing methods in terms of locality and limiting negative side effects. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Piecewise linear techniques

来源：评论

学校读者我要写书评

暂无评论

Use of Attention Mechanism for Decoder in Deep Learning-based Image Super Resolution 14

Use of Attention Mechanism for Decoder in Deep Learning-base...

引用

14th International Conference on Information and Communication Technology Convergence, ICTC 2023

作者： Kim, Hyeongyu Choi, Byungchan Nam, Haewoon Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of Lig Nex1 Rf Seeker R and D Yongin Korea Republic of Hanyang University Division of Electrical Engineering Ansan Korea Republic of

ISBN: (纸本)9798350313277

One of major issues in training deep neural network for image super resolution is checkerboard artifact. It degrades the quality and resolution of output images. It usually appears at diagonal edges and curved edges of input images. It can also occur when too much information is compressed and lost during encoding process. To address this issues, we propose U-Net based structure with its decoder reinforced with attention modules for image super resolution task. U-Net structure is used to increase the feature reusability and reduce the loss of information during the encoding process. Attention modules are implemented in decoding layers in order to enhance the capability to produce high resolution output at diagonal edges and curved edges. Our proposed method shows improvements in PSNR and SSIM compared to the existing methods. © 2023 IEEE.

关键词： Deep Neural Networks Image Attention Image Super Resolution

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Simple GPS Code Information-Based Relative Positioning Assistant Algorithm*

引用

Chinese Journal of Electronics 2023年第2期22卷 347-352页

作者： Shenglei Xu Sangsun Lee Division of Electrical and Computer Engineering Hanyang University Seoul South Korea

Many vehicle application services called LBS (Location based services) are currently based on location information, but civil location equipment is either too expensive or the positioning accuracy is not high enough to provide LBS. If each vehicle used as a center can precisely calculate the relative positions of other vehicles, LBS can be more easily provided. Based on this premise, a new method by limiting low-cost GPS receivers and communication satellites into similar environment respectively to calculate the relative position with a higher accuracy is proposed in this study.

关键词： Location awareness Limiting Codes Receivers Satellite communication Global Positioning System

来源：评论

学校读者我要写书评

暂无评论

Observations of radiated and conducted emissions from an Electric Plane charging station

Observations of radiated and conducted emissions from an Ele...

引用

2023 International Symposium on Electromagnetic Compatibility - EMC Europe, EMC Europe 2023

作者： Giri, Manav Sadeghi, Babak Ronnberg, Sarah Johansson, Jonny Ekman, Jonas Luleå University of Technology Electric Power Engineering Division of Energy Science Skellefteå Sweden Luleå University of Technology EISLAB Department of Computer Science Electrical and Space Engineering Luleå Sweden

ISBN: (纸本)9798350324006

The paper reports a set of radiated and conducted emissions recorded at an electric airplane's charging station located in Sweden. The measurement exercise undertaken shows the existence of supraharmonic frequency components exceeding the IEC 61000-2-2 limits in the frequency range 129 to 147 kHz. These components are visible in the radiated emissions recorded at the test site as well. Observations of the measured common mode current offer a possible explanation for the radiated magnetic field recorded at the test site in the sub 150 kHz band. © 2023 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

DualGFL: Federated Learning with a Dual-Level Coalition-Auction Game

arXiv

引用

arXiv 2024年

作者： Chen, Xiaobing Zhou, Xiangwei Zhang, Songyang Sun, Mingxuan Division of Electrical and Computer Engineering Louisiana State University United States Department of Electrical and Computer Engineering University of Louisiana Lafayette United States Division of Computer Science and Engineering Louisiana State University United States

Despite some promising results in federated learning using game-theoretical methods, most existing studies mainly employ a one-level game in either a cooperative or competitive environment, failing to capture the complex dynamics among participants in practice. To address this issue, we propose DualGFL, a novel Federated Learning framework with a Dual-level Game in cooperative-competitive environments. DualGFL includes a lower-level hedonic game where clients form coalitions and an upper-level multi-attribute auction game where coalitions bid for training participation. At the lower-level DualGFL, we introduce a new auction-aware utility function and propose a Pareto-optimal partitioning algorithm to find a Pareto-optimal partition based on clients’ preference profiles. At the upper-level DualGFL, we formulate a multi-attribute auction game with resource constraints and derive equilibrium bids to maximize coalitions’ winning probabilities and profits. A greedy algorithm is proposed to maximize the utility of the central server. Extensive experiments on real-world datasets demonstrate DualGFL’s effectiveness in improving both server utility and client utility. © 2024, CC BY-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：