检索结果-内蒙古大学图书馆

European Control Conference (ECC)

作者： Xin Mao Dan Wang Wei Chen Li Qiu School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen China Division of Decision and Control Systems KTH Royal Institute of Technology Stockholm Sweden Department of Mechanics and Engineering Science State Key Laboratory for Turbulence and Complex Systems Peking University Beijing China Southern University of Science and Technology Shenzhen China Hong Kong University of Science and Technology Hong Kong S.A.R. China

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

In this paper, the output synchronization in large-scale discrete-time networks is examined by utilizing the novel phase tool, where the agent dynamics are allowed to be significantly heterogeneous. The synchronization synthesis problem is formulated and thoroughly investigated, with the goal of characterizing the allowable heterogeneity among the agents to ensure synchronization under a uniform controller. The solvability condition is provided in terms of the phases of the residue matrices of the agents at the persistent modes. When the condition is satisfied, a design procedure is given, producing a low-gain synchronizing controller. Numerical examples are given to illustrate the results.

关键词： Sufficient conditions Europe Heterogeneous networks Synchronization Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Collaborative Fall Detection and Response using Wi-Fi Sensing and Mobile Companion Robot

arXiv

引用

arXiv 2024年

作者： Chen, Yunwang Kang, Yaozhong Zhao, Ziqi Hong, Yue Meng, Lingxiao Meng, Max Q.-H. The Shenzhen Key Laboratory of Robotics Perception and Intelligence Southern University of Science and Technology Shenzhen518055 China The Department of Electrical and Electronic Engineering SUSTech Shenzhen China The School of System Design and Intelligent Manufacturing SUSTech Shenzhen China

This paper presents a collaborative fall detection and response system integrating Wi-Fi sensing with robotic assistance. The proposed system leverages channel state information (CSI) disruptions caused by movements to detect falls in non-line-of-sight (NLOS) scenarios, offering non-intrusive monitoring. Besides, a companion robot is utilized to provide assistance capabilities to navigate and respond to incidents autonomously, improving efficiency in providing assistance in various environments. The experimental results demonstrate the effectiveness of the proposed system in detecting falls and responding effectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Auxiliary Antenna Array Optimization for Mainlobe Interference Suppression systems

Auxiliary Antenna Array Optimization for Mainlobe Interferen...

引用

International Conference on Microwave and Millimeter Wave technology Proceedings

作者： Jiahao Zhang Jin Meng National Key Laboratory of Science and Technology on Vessel Integrated Power System Naval University of Engineering Wuhan CHINA

ISBN: (纸本)9781665482271

Modern radars are sensitive to the aggressive interference, especially the high-power mainlobe interference. By introducing the auxiliary antenna array, and implementing the spatial domain interference cancellation algorithm, the mainlobe interference can be suppressed, while the signal of interest is reserved. The interference cancellation performance is highly related with the auxiliary array design. In this paper, the location, the element number, and the antenna type of the auxiliary array are investigated. It is found that by adding the number of the auxiliary antenna elements, and optimizing the location of the elements, the mainlobe distortion can be successfully reduced in presence of mainlobe interference. In realistic situations, the omnidirectional auxiliary antenna element is more desired than the directional antenna element, considering the cost and coverage.

关键词： Microwave technology Microwave integrated circuits Interference cancellation Millimeter wave technology Radar Radar antennas Microwave antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Federated Reinforcement Learning for RIS-Aided Non-Orthogonal Multiple Access MEC

Federated Reinforcement Learning for RIS-Aided Non-Orthogona...

引用

IEEE Conference on Vehicular technology (VTC)

作者： Zhong Yang Yaxing Li Hongbo Liu Fangmin He National Key Laboratory of Science and Technology on Vessel Integrated Power System Naval University of Engineering Wuhan China

ISBN: (纸本)9781665454698

A novel reconfigurable intelligent surface (RIS) aided non-orthogonal multiple access mobile edge computing (NOMA-MEC) framework is proposed to release the heavy transmission delay of the edge devices (EDs) in next-generation wireless communication networks. We formulate a stochastic optimization problem that jointly optimizes the phase-shifter design of the RIS, the task offloading decision and the computing resource allocation of MEC, to minimize the overall transmission delay of all EDs in a long-term manner. The mathematical solution for the formulated optimization problem is a long-term offline policy which is non-trivial for conventional optimization approaches due to high computational complexity and stringent delay constraint. Therefore, we propose a federated reinforcement learning (FRL) approach for the formulated optimization problem to obtain the optimal solution taking advantages of the computing resource of all EDs. Moreover, a reputation-enabled ED selection scheme is proposed in the FRL approach that takes the task offloading history into consideration. The proposed RIS-aided NOMA-MEC framework is capable of outperforming conventional orthogonal multiple access (OMA) enabled RIS-MEC networks. The proposed FRL scheme achieves a near-optimal performance when the computional task is image classification in the MNIST and the IRIS dataset.

关键词： Wireless communication NOMA Vehicular and wireless technologies Reinforcement learning Delays History Task analysis

来源：评论

学校读者我要写书评

暂无评论

Configuration and Motion Analysis of Orthopedic External Fixation Mechanism with Virtual Motion Center

Configuration and Motion Analysis of Orthopedic External Fix...

引用

International Conference on Mechanical design, ICMD 2021

作者： Su, Peng Li, Shuo Lai, Yuliang Zhang, Li Li, Jian School of Electromechanical Engineering Beijing Information Science and Technology University Beijing100192 China Second Department of Orthopedics The Affiliated Rehabilitation Hospital of National Research Center for Rehabilitation Aids Beijing100176 China Key Laboratory of Rehabilitation Aids Technology and System of the Ministry of Civil Affairs National Research Center for Rehabilitation Technical Aids Beijing100176 China

ISBN: (纸本)9789811673801

Aiming at the surgical requirements of the external fixator for the correction of internal knee varus, there is an urgent clinical need to design a bone external fixation system with precise motion and independently adjustable parameters. Based on the design idea of telecentric mechanism, the orthopaedic mechanism with virtual central motion is innovatively designed based on the theory of rotational volume, and it can rotate around the X and Y axes and move independently along the Z axis, constituting a personalized 2R1T-RCM orthopaedic external fixation robot mechanism. Based on the rotation theory, a modified Kuzbach–Grübler formula is proposed to analyze the degrees of freedom of the mechanism, and determine the motion condition and drive mode of the mechanism. Finally, the virtual central motion characteristics and independent motion function of the mechanism are verified by the motion simulation of the mechanism. The innovative configuration method of the mechanism with medical-industrial integration can meet the requirements of this orthopedic surgery and can also provide a reference for the configuration design of other skeletal orthopedic mechanisms. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

arXiv

引用

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Experimental study on the energy loss from flow and electrical of vanadium battery with constant pump frequency 2

Experimental study on the energy loss from flow and electric...

引用

2023 2nd International Conference on New Energy, Energy Storage and Power Engineering, NESP 2023

作者： Sun, Yanzhao Zou, Tao Li, Dianhong Li, Juntao School of Electrical Engineering and Automation Wuhan University Hubei Wuhan430072 China Big Pawer Electrical Technology Xiangyang Co. Ltd. Hubei Xiangyang441057 China Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle Hubei University of Arts and Science Hubei Xiangyang441053 China Hunan Vanadium Valley New Energy Technology Co. Ltd. Hunan Changsha410116 China

When the vanadium battery was running, pump frequency and current density were two frequently adjusted parameters. When the pump frequency was constant, the main flow-electrical parameter variation needs to be further studied. To this end, a 10 kW vanadium battery was built. When the current density was relatively high during the charge-discharge, the flow-electrical parameters of the cathode and anode including the temperature, flow resistance, turning voltage difference, capacity loss, energy loss and energy efficiency were studied. Besides, the compositions of capacity and energy were introduced, and the loss calculation scheme was proposed. Firstly, in flow analysis, the flow resistance was defined, which represents the flow state of the electrolyte. It was found that the flow resistance was nearly linear with the temperature. Secondly, in electric analysis, the turning voltage difference increased with the current density increasing. For the same current density, the total energy loss of charge was less than the discharge, and the energy loss of bypass was less than the internal resistance. With the current density increasing, the energy efficiency decreased. The research can be provided insight into the optimizing operation for the vanadium battery. © Published under licence by IOP Publishing Ltd.

关键词： Current density

来源：评论

学校读者我要写书评

暂无评论

design and implementation of unmanned aerial vehicle localization and light tracking system

引用

The Journal of China Universities of Posts and Telecommunications 2023年第4期30卷 67-74页

作者： Xu Ming Dong Chen Li Hanlu Luo Qiming Wang Lizi Zhang Wanru Liu Huixin School of Digital Media and Design Arts Beijing University of Posts and TelecommunicationsBeijing 100876China School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and TelecommunicationsBeijing 100876China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China

Unmanned aerial vehicles(UAV)are applied widely and profoundly in various ***,high-precision positioning and tracking in multiple scenarios are the core requirements for UAV *** ensure stable communication of UAVs in denial environments with substantial electromagnetic interference,a systematic solution is proposed based on a deep learning algorithm for target detection and visible light for UAV *** the cost and computational power limitations on the hardware,the you only look once(YOLO)v4-Tiny model is used for static target detection of the UAV *** UAV tracking,and a light tracker that can adjust the angle of emitted light and focus it on the target is used for dynamic tracking ***,achieving the primary conditions of UAV optical communication with good secrecy is also suitable for dynamic *** UAV tracker positions the UAV model by returning the coordinates and calculating the time delay,and then controls the spotlight to target the *** order to facilitate the deployment of deep learning models on hardware devices,the lighter and more efficient model is selected after *** trained model can achieve 99.25%accuracy on the test *** dynamic target detection can reach 20 frames per second(FPS)on a computer with an MX520 graphics processing unit(GPU)and 6 GB of random access memory(RAM).Dynamic target detection on a Jetson Nano can reach 5.4 FPS.

关键词： unmanned aerial vehicles deep learning light tracking target detection unmanned aerial vehicles location unmanned aerial vehicles tracking

来源：评论

学校读者我要写书评

暂无评论

Multi-Resource Allocation for On-Device Distributed Federated Learning systems

Multi-Resource Allocation for On-Device Distributed Federate...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Yulan Gao Ziqiang Ye Han Yu Zehui Xiong Yue Xiao Dusit Niyato The National Key Laboratory of Science and Technology on Communications University of Electronic Science and Technology of China The School of Computer Science and Engineering Nanyang Technological University Singapore Pillar of Information Systems Technology and Design Singapore University of Technology and Design (SUTD) Singapore

ISBN: (纸本)9781665435413

This work poses a distributed multi-resource allocation scheme for minimizing the weighted sum of latency and energy consumption in the on-device distributed federated learning (FL) system. Each mobile device in the system engages the model training process within the specified area and allocates its computation and communication resources for deriving and uploading parameters, respectively, to minimize the objective of system subject to the computation/communication budget and a target latency requirement. In particular, mobile devices are connect via wireless TCP/IP architectures. Exploiting the optimization problem structure, the problem can be decomposed to two convex sub-problems. Drawing on the Lagrangian dual and harmony search techniques, we characterize the global optimal solution by the closed-form solutions to all sub-problems, which give qualitative insights to multi-resource tradeoff. Numerical simulations are used to validate the analysis and assess the performance of the proposed algorithm.

关键词： Wireless communication Training Machine learning algorithms Federated learning Computational modeling Simulation Search methods

来源：评论

学校读者我要写书评

暂无评论

Free Adversarial Training with Layerwise Heuristic Learning 11th

Free Adversarial Training with Layerwise Heuristic Learning

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Zhang, Haitao Shi, Yucheng Dong, Benyu Han, Yahong Li, Yuanzhang Kuang, Xiaohui College of Intelligence and Computing and Tianjin Key Lab of Machine Learning Tianjin University Tianjin China Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Information System Security Beijing China

ISBN: (纸本)9783030873578

Due to the existence of adversarial attacks, various applications that employ deep neural networks (DNNs) have been under threat. Adversarial training enhances robustness of DNN-based systems by augmenting training data with adversarial samples. Projected gradient descent adversarial training (PGD AT), one of the promising defense methods, can resist strong attacks. We propose "free" adversarial training with layerwise heuristic learning (LHFAT) to remedy these problems. To reduce heavy computation cost, we couple model parameter updating with projected gradient descent (PGD) adversarial example updating while retraining the same mini-batch of data, where we "free" and unburden extra updates. Learning rate reflects weight updating speed. Weight gradient indicates weight updating efficiency. If weights are frequently updated towards opposite directions in one training epoch, then there are redundant updates. For higher level of weight updating efficiency, we design a new learning scheme, layerwise heuristic learning, which accelerates training convergence by restraining redundant weight updating and boosting efficient weight updating of layers according to weight gradient information. We demonstrate that LHFAT yields better defense performance on CIFAR-10 with approximately 8% GPU training time of PGD AT and LHFAT is also validated on ImageNet. We have released the code for our proposed method LHFAT at https://***/anonymous530/LHFAT. © 2021, Springer Nature Switzerland AG.

关键词： Deep neural networks

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：