检索结果-内蒙古大学图书馆

15th IEEE International Conference on ASIC, ASICON 2023

作者： Lin, Jianwen Cai, Linlin Chen, Yutao Zhang, Haoyu Chen, Wangyong Sun Yat-sen University School of Microelectronics Science and Technology Guangzhou510275 China Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510275 China

ISBN: (纸本)9798350312980

As the geometries of transistors continue to scale down, single-event transient (SET) are becoming a major source of soft errors in circuit design. This paper proposes a machine learning method for modeling SET in circuit-level simulations with the high efficiency, since traditional models such as the double exponential model are not coupled with circuit responses. The proposed artificial neural network (ANN) model shows a great prediction accuracy for single-event transient currents in 12nm FinFET technology under different time, linear energy transfer (LET), bias voltage, and strike positions. The trained model can be implemented into SPICE with Verilog-A for circuit-level simulation, and its validity in a 7-stage inverter chain and a 6T SRAM are demonstrated to provide the rapid guidance for radiation reliability. © 2023 IEEE.

关键词： FinFET machine learning neural network Single-event transient

来源：评论

学校读者我要写书评

暂无评论

Broadband single-polarization photonic crystal fiber based on surface plasmon resonance effect

Broadband single-polarization photonic crystal fiber based o...

引用

2022 International Conference on Optical Technology, Semiconductor Materials, and Devices, OTSMD 2022

作者： Liu, Rui Wu, Tiesheng Liu, Yan Zhong, Xu Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing School of Information and Communication Guilin University of Electronic Technology Guilin541004 China Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen518060 China

ISBN: (纸本)9781510663015

We numerically demonstrate a broadband single polarization photonic crystal fiber (PCF) based on surface plasmon resonance effect. The PCF is constructed of multi-layer hexagonal air holes with a silicon core. The inner wall of the two large air holes is coated with gold films for exciting surface plasmon resonances. The transmission characteristics of the fiber are analyzed by the finite-element method. At the wavelength point of 1.55 μm, the confinement losses of the x and y-polarization modes are 1400 dB/m and 15 dB/m, respectively. The severe difference in polarization loss can support the efficient transmission of the y-polarization mode over the range of 1.51-2.24 μm. Only short fiber lengths of 2 cm, the achievable power of the y-polarization mode can be more than 0.5, and the extinction ratio is less than -20dB for the wavelength range. The presented fiber has promising application prospects in polarization-maintaining and high-power laser systems. © 2023 SPIE.

关键词： Nonlinear optics

来源：评论

学校读者我要写书评

暂无评论

Multi-Attention Gate Based U-net for Retinal Vessel Segmentation 12

Multi-Attention Gate Based U-net for Retinal Vessel Segmenta...

引用

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Zhu, Yu Li, Rui Teng, Shenghua Cao, Xinrong Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China College of Computer and Control Engineering Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (纸本)9798350310153

Retinal blood vessel segmentation images can be used to detect and evaluate various cardiovascular and ophthalmic diseases. However, due to the intricate vessel structures and blurred boundaries of vessels, it is a huge challenge to efficiently and accurately segment blood vessels. To deal with the above problems, this paper improves on the U-net by firstly using multi-scale feature convolution with kernels of varying size for feature extraction. Second, a non-local attention mechanism is applied to obtain richer global semantic information. Then multi-attention gate is used in the skip connection part by inputting feature maps of various scales and dimensions and selectively learning the interrelated regions, which improves the segmentation ability of the network model for the tiny structure of blood vessels. Quantitative and qualitative experimental results on two public datasets, DRIVE and CHASE-DB1, demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

A Network Combining CNN and Transformer for Blind Image Super-Resolution 12

A Network Combining CNN and Transformer for Blind Image Supe...

引用

12th International Conference on information Technology in Medicine and Education, ITME 2022

作者： Zhang, Shuhao Li, Zuoyong Teng, Shenghua Zeng, Kun Shandong University of Science and Technology College of Electronic and Information Engineering Qingdao266590 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Fuzhou350121 China

ISBN: (纸本)9798350310153

Blind super-resolution (SR) requires not only estimating blur kernel, but also super-resolving low-resolution image based on estimated blur kernel. Most blind SR methods use convolutional neural networks (CNNs) for kernel estimation, which cannot exploit long-range dependency within image domain, thus failing to predict blur kernel accurately. To address this issue, we propose a network combining CNN and transformer named NCCT for kernel estimation. By modeling local and non-local image priors simultaneously, NCCT outperforms other blind SR methods in terms of kernel estimation accuracy. Moreover, we design a network module named RRFDB for constructing lightweight blind SR network, which runs faster and achieves comparative SR performance with fewer parameters compared with other state-of-the-art blind SR methods. © 2022 IEEE.

关键词： Optical resolving power

来源：评论

学校读者我要写书评

暂无评论

Real-valued Neural Network Nonlinear Equalization with QAM Signal Combined with SSB Modulation 20

Real-valued Neural Network Nonlinear Equalization with QAM S...

引用

20th International Conference on Optical Communications and Networks, ICOCN 2022

作者： Chen, Zhiwei Wang, Wei Zou, Dongdong Yi, Xingwen Li, Zhaohui Li, Fan Ni, Weihao Sun Yat-Sen University School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou510275 China Zhuhai519000 China

Real-valued neural network equalization combined with SSB modulation is proposed in order to mitigate fiber nonlinearity in complex-valued signals without increased complexity, which enables a transmission of 80 Gbit/... 详细信息

ISBN: (数字)9781665458986

ISBN: (纸本)9781665458986

关键词： Quadrature amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

An embedded vertical‐federated feature selection algorithm based on particle swarm optimisation

引用

CAAI Transactions on Intelligence Technology 2023年第3期8卷 734-754页

作者： Yong Zhang Ying Hu Xiaozhi Gao Dunwei Gong Yinan Guo Kaizhou Gao Wanqiu Zhang School of Information and Control Engineering China University of Mining and TechnologyXuzhouChina The Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin UniversityChangchunChina School of Computing University of Eastern FinlandKuopioFinland The Macao Institute of Systems Engineering Macao University of Science and TechnologyTaipaChina

In real life,a large amount of data describing the same learning task may be stored in different institutions(called participants),and these data cannot be shared among par-ticipants due to privacy *** case that different attributes/features of the same instance are stored in different institutions is called vertically distributed *** pur-pose of vertical‐federated feature selection(FS)is to reduce the feature dimension of vertical distributed data jointly without sharing local original data so that the feature subset obtained has the same or better performance as the original feature *** solve this problem,in the paper,an embedded vertical‐federated FS algorithm based on particle swarm optimisation(PSO‐EVFFS)is proposed by incorporating evolutionary FS into the SecureBoost framework for the first *** optimising both hyper‐parameters of the XGBoost model and feature subsets,PSO‐EVFFS can obtain a feature subset,which makes the XGBoost model more *** the same time,since different participants only share insensitive parameters such as model loss function,PSO‐EVFFS can effec-tively ensure the privacy of participants'***,an ensemble ranking strategy of feature importance based on the XGBoost tree model is developed to effectively remove irrelevant features on each ***,the proposed algorithm is applied to 10 test datasets and compared with three typical vertical‐federated learning frameworks and two variants of the proposed algorithm with different initialisation ***-mental results show that the proposed algorithm can significantly improve the classifi-cation performance of selected feature subsets while fully protecting the data privacy of all participants.

关键词： Evolutionary optimization feature selection privacy protection vertical‐federated learning

来源：评论

学校读者我要写书评

暂无评论

Viewpoint Rotation Prediction based Resource-Efficient Holographic Type Communication in EON enabled 6G RAN

Viewpoint Rotation Prediction based Resource-Efficient Holog...

引用

International Conference on Optical Communications and Networks (ICOCN)

作者： Xin Wang Chengyuan Zhang Yafei Wang Xuehua Li Key Laboratory of Information and Communication Systems Ministry of Information Industry and Key Laboratory of Modern Measurement & Control Technology Ministry of Education Beijing Information Science and Technology University (BISTU) Beijing China

A LSTM based viewpoint rotation prediction enabled resource-efficient holographic type communication is investigated in EON enabled 6G RAN. The CensNet enhanced PPO is used for feature extraction based DU-CU deploymen... 详细信息

ISBN: (数字)9798350367652

ISBN: (纸本)9798350367669

关键词： 6G mobile communication Simulation Benchmark testing Prediction algorithms Feature extraction Optical fiber communication Long short term memory

来源：评论

学校读者我要写书评

暂无评论

A Fully Distributed Hybrid control Framework For Non-Differentiable Multi-Agent Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1792-1800页

作者： Xia Jiang Xianlin Zeng Jian Sun Jie Chen Yue Wei the Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081 the Beijing Institute of Technology Chongqing Innovation Center Chongqing 401120China IEEE the School of Electronic and Information Engineering Tongji UniversityShanghai 200082 the Peng Cheng Laboratory Shenzhen 518055China

This paper develops a fully distributed hybrid control framework for distributed constrained optimization *** individual cost functions are non-differentiable and *** on hybrid dynamical systems,we present a distributed state-dependent hybrid design to improve the transient performance of distributed primal-dual first-order optimization *** proposed framework consists of a distributed constrained continuous-time mapping in the form of a differential inclusion and a distributed discrete-time mapping triggered by the satisfaction of local jump *** the semistability theory of hybrid dynamical systems,the paper proves that the hybrid control algorithm converges to one optimal solution instead of oscillating among different *** simulations illustrate better transient performance of the proposed hybrid algorithm compared with the results of the existing continuous-time algorithms.

关键词： Distributed algorithm hybrid framework multiagent network non-differentiable optimization

来源：评论

学校读者我要写书评

暂无评论

Decision Region Partition Aided Maximum Likelihood Sequence Estimation Enabled O-Band 120Gbit/s PAM-4 Transmission with Severe Bandwidth Constraint 20

Decision Region Partition Aided Maximum Likelihood Sequence ...

引用

20th International Conference on Optical Communications and Networks, ICOCN 2022

作者： Ni, Weihao Yin, Mingzhu Zou, Dongdong Wang, Wei Chen, Zhiwei Yi, Xingwen Li, Zhaohui Li, Fan School of Electronics and Information Technology Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Sun Yat-Sen University Guangzhou510275 China Zhuhai519000 China

A simplified MLSE with decision region partition is investigated in a severe bandwidth-limited IM/DD system. Compared to conventional MLSE, the proposed scheme can reduce 93% total computational complexity with neglig... 详细信息

ISBN: (数字)9781665458986

ISBN: (纸本)9781665458986

关键词： Pulse amplitude modulation

来源：评论

学校读者我要写书评

暂无评论

Impedance Modeling and Characteristics Analysis of Grid-Forming Converter 7

Impedance Modeling and Characteristics Analysis of Grid-Form...

引用

7th IEEE Conference on Energy Internet and Energy System Integration, EI2 2023

作者： Liu, Huifang Lei, Yu He, Guoqing Liu, Keke Gao, Liping Ma, Junhua China Electrical Power Research Institute State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems Beijing China School of Information Engineering China University of Geosciences Beijing China

ISBN: (纸本)9798350345094

Grid-forming control (GFM) has been widely applied in academia and industry for its contribution to the stability in weak grid. As GFM has multiple control loops that interact with each other, the dominant factor of impedance characteristics in different frequency bands is still unknown. At the same time, the impact of dynamic response requirements such as bandwidth and phase margin (PM) of each control loop on GFM impedance characteristics in different frequency bands is still unclear. This article first establishes an impedance model of GFM and analyzes the transmission path of small signals in GFM. Then, based on the small signal transmission relationship, the GFM impedance is divided into two parts. One part is dominated by the synchronization loop, and the other part is dominated by the voltage and current loops. Based on this, the influence of each control loop on GFM impedance characteristics is analyzed. Finally, based on the control hardware in the loop simulation platform, experiments were conducted, verifying the correctness of the analysis in this paper. © 2023 IEEE.

关键词： Simulation platform

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：