检索结果-内蒙古大学图书馆

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

CMAC-Based Sliding-Mode control for Large-Scale Fuzzy Descriptor systems

CMAC-Based Sliding-Mode Control for Large-Scale Fuzzy Descri...

引用

2022 IEEE International Conference on Robotics and Biomimetics, ROBIO 2022

作者： Zhong, Zhixiong Shao, Zhenghua Huan, Zhijie Wang, Xingyi Minjiang University Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin150080 China School of Electrical Engineering and Automation Xiamen University of Technology Xiamen361024 China

ISBN: (纸本)9781665481090

This paper addresses the problem of sliding-mode control for large-scale fuzzy descriptor systems subject to unknown uncertainties. First, a CMAC neural network is used to approximate the unknown uncertainties, and the CMAC-based sliding-mode controller is proposed. Then, a compensation technique is employed to eliminate the influence on the approximation error stemmed from CMAC model. We use the gradient-descent method to online tune the parameters of CMAC and the Lyapunov function is introduced to ensure the stability of the closed-loop control system and the CMAC's convergence. Finally, the effectiveness and correctness of the obtained theories are verified by the tracking control of multi-autonomous underwater vehicles (AUVs). © 2022 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

A Deep Convolutional Embedded Clustering Method for Scenario Reduction of Production Simulation 8

A Deep Convolutional Embedded Clustering Method for Scenario...

引用

8th International Conference on Power and Renewable Energy, ICPRE 2023

作者： Peng, Yishu Ye, Lin Li, Pai Gong, Ting China Agricultural University College of Information and Electrical Beijing China China Electric Power Research Institute State Key Laboratory of Operation and Control of Renewable Energy & Storage Systems Beijing China

ISBN: (纸本)9798350328813

Renewable energy has significant seasonal characteristics and random and fluctuating features, which bring great challenges to the planning and operation of power systems. Typical scenarios of production simulation can provide a decision-making basis for the formulation of dispatch and operation modes, which is significant for the planning and operation of the power system. To obtain the representative production simulation scenarios, a method for scenario reduction based on deep convolutional embedded clustering (DCEC) is proposed in this paper. The convolutional self-encoder is used to reduce dimension and extract features from the high-dimensional production simulation data, and input to the clustering layer to obtain the initial clustering centers. A joint loss function combining clustering loss and reconstruction loss is established, and the final clustering results are obtained by iterative update. The clustering evaluation index Calinski-Harabaz index score and Silhouette coefficient are used to analyze the clustering results, and the results verified the validity of the typical scenarios of production simulation obtained by DCEC aggregation. © 2023 IEEE.

关键词： deep learning dimensionality reduction production simulation scenario reduction

来源：评论

学校读者我要写书评

暂无评论

Temporal and Spatial Changes of Forest Leaf Area Index Based on MODIS: A Case Study of Fujian Province 6th

Temporal and Spatial Changes of Forest Leaf Area Index Based...

引用

6th Euro-China Conference on Intelligent Data Analysis and Applications, ECC 2019

作者： Yu, Hua Zheng, Kaiwen Li, Hui Liang, Fengna Zhang, Jinxin Zhang, Fuquan Ocean College Minjiang University Fuzhou350108 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350108 China

ISBN: (纸本)9789811650352

Forest vegetation is an important place for energy conversion and material cycle, and leaf area index (LAI) is an important parameter to describe the process of plant canopy function. In this paper, with the support of computer technology such as VC, the LAI of Fujian Province from 2001 to 2017 was analyzed and studied by using MODIS remote sensing data with 500 m resolution every 8 days. The results showed that the vegetation growth was the most vigorous in the 200–800 m terrain. The evergreen coniferous forest was mainly distributed in the northwest of Fujian Province, while the mixed forest in the interior. The seasonal mean value of LAI for many years reaching 3.5was the highest in the summer and autumn;the second highest was in the spring, with the mean value of LAI reaching 2.0;the lowest was in the winter, with the mean value of LAI reaching 1.5. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy conversion

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：