检索结果-内蒙古大学图书馆

SSRN 2022年

作者： Yang, Jiming Da, Feipeng Southeast University School of Automation Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China

Image classification task often requires a massive amount of data. Learning to adapt when little data is available could be difficult. In this work, a framework named BlendNet is proposed for few-shot learning. Unlike conventional metric-based methods, a classifier blending features from different levels is proposed to assist the framework to obtain better accuracy and generalization performance. To alleviate the variance of the network for classifying the same class of objects, an data augmentation method is exploited to obtain the image representation robustly. Extensive experiments are conducted to validate our method under the meta-learning paradigm using few-shot classification datasets. The experiments demonstrate that our proposed framework provides competitive results on both Omniglot and mini -ImageNet benchmarks. Our code is available at https: // *** / tyolm / BlendNet . © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Joint Radar-Communication Beamforming for CRB-Based Target Localization

Joint Radar-Communication Beamforming for CRB-Based Target L...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Tianhao Mao Jie Yang Le Liang Shi Jin National Mobile Communications Research Laboratory Southeast University Nanjing China Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Purple Mountain Laboratories Nanjing China

ISBN: (数字)9798350387414

ISBN: (纸本)9798350387421

This paper studies the beamformer design for an integrated sensing and communication system where simultaneous communication for multiple downlink users and bistatic sensing for a point target are realized. Firstly, to avoid self-interference in monostatic settings, we establish the bistatic sensing model where the sensing performance is measured by the Cramér-Rao bound (CRB) for the target's coordinates and the communication performance by the signal-to-interference-plus-noise ratio (SINR). We aim to minimize the CRB while ensuring a predefined SINR for each user. Then, we derive a closed-form beamformer for the single-user case that proves near-optimal. For the multi-user case, we introduce a beamformer design algorithm based on semidefinite relaxation and a suboptimal design algorithm based on successive convex approximation with reduced complexity. Finally, numerical results are provided to validate the solutions.

关键词： Location awareness Vehicular and wireless technologies Interference cancellation Coordinate measuring machines Downlink Approximation algorithms Integrated sensing and communication

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

PCDH-based nonlinear H∞control of VSC-HVDC with wind power integrated

引用

Journal of control and Decision 2021年第1期8卷 41-49页

作者： Xingyu Lv Bangjun Lei Shumin Fei Foreign language Teaching Center Guizhou Institute of TechnologyGuiyangPeople’s Republic of China Key Laboratory of Power Dig Data of Guizhou Province School of Electrical and Information EngineeringGuizhou Institute of TechnologyGuiyang 550003People’s Republic of China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast UniversityNanjingPeople’s Republic of China

Based on the port-controlled dissipative Hamiltonian(PCDH)system,a novel nonlinear(NN)H∞control is designed for the wind farm side(WFS)voltage source converter(VSC)of VSC-based high-voltage direct current(VSC-HVDC)transmission system connected large wind ***,the uncertain nonlinear dynamical model of WFS VSC in the VSC-HVDC is established by taking external disturbances and parameter variations into ***,the dissipative Hamiltonian structure of the WFS VSC system is constructed by means of variable ***,on the basis of the obtained dissipative Hamiltonian structure,a NN H∞control is put ***,the simulation results show that the proposed NN H∞control gains the advantage over the interconnection and damping assignment passivity-based(IDA-PB)control.

关键词： VSC-HVDC large wind farm Hamiltonian function method nonlinear H∞control

来源：评论

学校读者我要写书评

暂无评论

Low latency-oriented Reliable Slicing for URLLC services over TDM-PON based Mobile Edge Computing enabled Cloud Radio Access Network 19

Low latency-oriented Reliable Slicing for URLLC services ove...

引用

19th International Conference on Optical Communications and Networks, ICOCN 2021

作者： Wang, Xin Xu, Zhan He, Shanbao School of Information and Communication Engineering Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing100101 China

ISBN: (纸本)9781665424462

The URLLC services have high stringent requirements for high reliability and low latency transmission. The TDM-PON based mobile edge computing (MEC) enabled cloud radio access network (CRAN) is an effective architecture to carry the URLLC services. However, how to ensure reliability and low latency requirements meanwhile decrease the deployment cost will be one of the major challenges in the network planning stage. A mathematical model and a heuristic algorithm are proposed to tackle such challenge towards demands of URLLC services. Simulation results suggest that proposed algorithm shows better performance in terms of low latency transmission than the benchmark algorithm, and achieves the near-optimal solution of MILP with an acceptable time complexity. Besides, impact of key parameters on comparison of different approaches in terms of total transmission latency consumption is also evaluated. © 2021 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Adaptive Load Balancing Routing Algorithm for Low Earth Orbit Satellite Cluster Networks

Adaptive Load Balancing Routing Algorithm for Low Earth Orbi...

引用

International Conference on Computers, Communications, and Systems (ICCCS)

作者： Liming Wang Zhan Xu Ruxin Zhi Jiahui Wang School of Electronics and Communication Engineering Beijing Information Science and Technology University Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Key Laboratory of Modern Measurement and Control Technology Ministry of Education Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

Large-scale satellite networks are a crucial component of future communication systems. However, they pose several challenges to satellite routing design and link recovery. This paper proposes an Adaptive Load Balancing routing algorithm for Low Earth Orbit (LEO) Satellite Cluster Networks (ALBSCN) to meet the needs of large-scale Low Earth Orbit LEO satellite networks. The constellation is divided into clusters, with each cluster maintaining the intra-cluster link state by electing a cluster head. The cluster head computes intra-cluster and inter-cluster routes. Messages are forwarded using inter-cluster multipath routing and intra-cluster routing techniques. We validated the algorithm's performance and compared it with other algorithms in terms of packet delivery delay using simulation. Simulation results indicate that the proposed clustering routing scheme effectively reduced packet loss and end-to-end delay, while also increasing network throughput.

关键词： Satellites Adaptive systems Simulation Clustering algorithms Low earth orbit satellites Packet loss Routing

来源：评论

学校读者我要写书评

暂无评论

Finite-time robust control for transformerless H-bridge cascaded STATCOM with star configuration

引用

Journal of control and Decision 2021年第2期8卷 106-115页

作者： Xingyu Lv Bangjun Lei Shumin Fei Foreign Language Teaching Center Guizhou Institute of TechnologyGuiyangPeople’s Republic of China Key Laboratory of Power Dig Data of Guizhou Province School of Electrical and Information EngineeringGuizhou Institute of TechnologyGuiyang 550003People’s Republic of China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast UniversityNanjingPeople’s Republic of China

This article presents a finite-time robust control(FTRC)of a transformerless STATCOM based on a cascaded multilevel H-bridge converter(CMHC)with star *** FTRC is first proposed for the current loop control of a CMHC-based transformerless STATCOM by using the finite time robust control *** the parameters,perturbations and external disturbances into account and using coordinate transformation method,the nonlinear dynamic model of the CMHC-based transformerless STATCOM is transformed into a standard nonlinear port-controlled dissipative Hamiltonian(PCDH)*** on the PCDH structure,an FTRC is designed for the CMHC-based transformerless STATCOM to improve the transient stability and oscillation damping of power ***,the simulation results demonstrate that the FTRC has better dynamic performance and strong robustness in comparison with the passivity-based control of the CMHC-based transformerless STATCOM.

关键词： Cascaded H-bridge converter transformerless STATCOM finite time robust control oscillations damping transient stability

来源：评论

学校读者我要写书评

暂无评论

H∞ state estimation for delayed neural networks via variable-augmented-based free-weighting matrices method

引用

Journal of the Franklin Institute 2025年第7期362卷

作者： Chang, Xu-Kang He, Yong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China

The issue of H∞ state estimation for neural networks with time-varying delays is investigated in this study. Firstly, an augmented Lyapunov-Krasovskii functional (LKF) with two delay-product-type terms is constructed to enhance the consideration of system state, delay, and delay derivative information. Furthermore, for taking into account more effective information, the LKF is augmented with both single and double integral variables. Accordingly, the LKF derivative becomes a higher-order term that exhibits nonlinear characteristics of the time delay. To solve the nonlinear problem, a variable-augmented-based free-weighting-matrices (VAFWMs) approach is employed to transform the nonlinear term into a linear form and provides more freedom in obtaining less-conservative results. Consequently, two improved H∞ state estimation criteria are derived. Lastly, a numerical example is provided to demonstrate the merits and effectiveness of the presented methods. Meanwhile, to prove the practical viability of the presented methods, this study extends the methods to a real-world quadruple-tank process system. © 2025 The Franklin Institute

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

A Reinforcement Learning Approach for Robust Restoration of Generators in Power System

A Reinforcement Learning Approach for Robust Restoration of ...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Li, Huimiao Yang, Xiaozhou Zhai, Chao Hubei Key Laboratory of Advanced Control and Intelligent Automation Fo Complex Systems China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China Future Resilient Systems Singapore-ETH Centre Create Campus Singapore

ISBN: (纸本)9781665465335

In the past decades, cascading blackouts have caused serious damages to power systems and affected the normal operation of society, so it is crucial to quickly restore the damaged power system to normal state. In this paper, a reinforcement learning (RL) approach is developed to achieve the robust restoration of generators in power systems. Firstly, the performance recovery of damaged power system is modeled as markov decision process, and constraints such as line voltage and active power output of generators are considered. Secondly, a RL algorithm is proposed to search the optimal control strategy for generator units recovery. Based on the proposed restoration approach, Q-learning algorithm is employed to obtain the optimal strategy for power supply of generaors in power grids. Finally, numerical simulations are carried out on IEEE 9-bus system under different scenarios of external disturbances and certainties. The simulation results demonstrate the effectiveness and feasibility of the proposed approach. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Indoor Point Clouds with the Channel Attention Mechanism

Semantic Segmentation of Indoor Point Clouds with the Channe...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Liu, Wei Lu, Yisheng Zhang, Tao Chen, Jun School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geoexploration Ministry of Education Wuhan430074 China

ISBN: (纸本)9781665465335

In recent years, the semantic segmentation of 3D point cloud has received increasing attention the field of computer vision, because 3D point cloud can better reflect our 3D space. Because of the unstructured and disordered characteristics of 3D point cloud data, semantic segmentation of point cloud is still a difficult task. Our network automatically learns the importance of feature channels by adding a channel attention module, which enables the network to obtain better training results. After the channel attention module is fused, the important channels in the features are enhanced, and the unimportant channels are suppressed, making the network training more efficient. In this paper, we propose an indoor point cloud semantic segmentation method combined with channel attention mechanism. The experimental results show that our method achieves better results than other methods. © 2022 IEEE.

关键词： Semantic Segmentation

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：