检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Xiaoyu Luo Chongrong Fang Chengcheng Zhao Jianping He The Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China and Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The State Key Laboratory of Industrial Control Technology and Institute of Cyberspace Research Zhejiang University China

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

The data-driven attack strategies recently have received much attention when the full knowledge of the system model is unknown or difficult to be obtained for the adversary. Note that despite the critical parameters of the system model being unavailable for the adversary, the existing data-driven attack methods still depend on the linearity of the unknown system model. In this paper, we design a completely model-free attack strategy where the adversary with limited capability aims to compromise state variables such that the output value follows the expected trajectory. Specifically, we first construct a zeroth-order feedback optimization framework and uninterruptedly use probing signals for real-time measurements. Then, we iteratively update the attack signals along the composite direction of the gradient estimates of the objective function evaluations and the projected gradients. These objective function evaluations can be obtained only by real-time measurements. Furthermore, we characterize the optimality of these solutions via the optimality gap, which is affected by the dimensions of the attack signal, the iterations of solutions, and the convergence rate of the system. Extensive simulations are conducted to show the effectiveness of the proposed attack strategy.

关键词： Networked control systems Computational modeling Current measurement Linear programming Real-time systems Data models Time measurement

来源：评论

学校读者我要写书评

暂无评论

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

arXiv

引用

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Two-dimensional materials for future information technology: status and prospects

引用

Science China(Information Sciences) 2024年第6期67卷 1-147页

作者： Hao QIU Zhihao YU Tiange ZHAO Qi ZHANG Mingsheng XU Peifeng LI Taotao LI Wenzhong BAO Yang CHAI Shula CHEN Yiqi CHEN Hui-Ming CHENG Daoxin DAI Zengfeng DI Zhuo DONG Xidong DUAN Yuhan FENG Yu FU Jingshu GUO Pengwen GUO Yue HAO Jun HE Xiao HE Jingyi HU Weida HU Zehua HU Xinyue HUANG Ziyang HUANG Ali IMRAN Ziqiang KONG Jia LI Qian LI Weisheng LI Lei LIAO Bilu LIU Can LIU Chunsen LIU Guanyu LIU Kaihui LIU Liwei LIU Sheng LIU Yuan LIU Donglin LU Likuan MA Feng MIAO Zhenhua NI Jing NING Anlian PAN Tian-Ling REN Haowen SHU Litao SUN Yue SUN Quanyang TAO Zi-Ao TIAN Dong WANG Hao WANG Haomin WANG Jialong WANG Junyong WANG Wenhui WANG Xingjun WANG Yeliang WANG Yuwei WANG Zhenyu WANG Yao WE... Department of Applied Physics The Hong Kong Polytechnic University Key Laboratory for Micro-Nano Physics and Technology of Hunan Province College of Materials Science and EngineeringHunan University College of Integrated Circuits Zhejiang University Shenzhen Geim Graphene Center Shenzhen Key Laboratory of Layered Materials for Value-Added ApplicationsTsinghua-Berkeley Shenzhen Institute & Institute of Materials ResearchTsinghua Shenzhen International Graduate SchoolTsinghua University State Key Laboratory of Extreme Photonics and Instrumentation College of Optical Science and EngineeringInternational Research Center for Advanced PhotonicsZijingang CampusZhejiang University National Key Laboratory of Materials for Integrated Circuits Shanghai Institute of Microsystem and Information TechnologyChinese Academy of Sciences CAS Key Laboratory of Nanophotonic Materials and Devices & Key Laboratory of Nanodevices and Applications i-LabSuzhou Institute of Nano-Tech and Nano-Bionics (SINANO)Chinese Academy of Sciences College of Chemistry and Chemical Engineering Hunan University Key Laboratory of Quantum State Construction and Manipulation (Ministry of Education) Department of PhysicsRenmin University of China School of Integrated Circuits Beijing National Research Center for Information Science and Technology (BNRist)Tsinghua University School of Electronic Science and Engineering Nanjing University The State Key Discipline Laboratory of Wide Band Gap Semiconductor Technology Shaanxi Joint Key Laboratory of GrapheneSchool of MicroelectronicsXidian University Key Laboratory of Artificial Micro- and Nano-Structures of Ministry of Education School of Physics and TechnologyWuhan University School of Integrated Circuits Huazhong University of Science and Technology Center for Nanochemistry (CNC) Beijing Science and Engineering Center for NanocarbonsBeijing National Laboratory for Molecular SciencesCollege of Chemistry and Molecular EngineeringPeking University State Key Laboratory for Artificial Microstruct

Over the past 70 years, the semiconductor industry has undergone transformative changes,largely driven by the miniaturization of devices and the integration of innovative structures and materials. Two-dimensional(2D) materials like transition metal dichalcogenides(TMDs) and graphene are pivotal in overcoming the limitations of silicon-based technologies, offering innovative approaches in transistor design and functionality, enabling atomic-thin channel transistors and monolithic 3D integration. We review the important progress in the application of 2D materials in future information technology, focusing in particular on microelectronics and optoelectronics. We comprehensively summarize the key advancements across material production, characterization metrology, electronic devices, optoelectronic devices, and heterogeneous integration on silicon. A strategic roadmap and key challenges for the transition of 2D materials from basic research to industrial development are outlined. To facilitate such a transition, key technologies and tools dedicated to 2D materials must be developed to meet industrial standards, and the employment of AI in material growth, characterizations, and circuit design will be essential. It is time for academia to actively engage with industry to drive the next 10 years of 2D material research.

关键词： two-dimensional (2D) materials information technology production technology standardization of characterization microelectronic devices optoelectronic devices multi-functional integration

来源：评论

学校读者我要写书评

暂无评论

Advanced manufacturing of dielectric metadevices

引用

Photonics Insights 2024年第2期3卷 31-70页

作者： Wenhong Yang Junxiao Zhou Din Ping Tsai Shumin Xiao Key Lab of Micro-Nano Optoelectronic Information System Ministry of Industry and Information TechnologyGuangdong Provincial Key Laboratory of Semiconductor Optoelectronic Materials and Intelligent Photonic SystemsHarbin Institute of TechnologyShenzhenChina Department of Electrical Engineering City University of Hong KongHong KongChina The State Key Laboratory of Terahertz and Millimeter Waves City University of Hong KongHong KongChina Centre for Biosystems Neuroscienceand NanotechnologyCity University of Hong KongHong KongChina Pengcheng Laboratory ShenzhenChina

Metasurfaces,composed of two-dimensional nanostructures,exhibit remarkable capabilities in shaping wavefronts,encompassing phase,amplitude,and *** unique proficiency heralds a transformative paradigm shift in the domain of next-generation optics and photonics,culminating in the development of flat and ultrathin optical *** noteworthy is the all-dielectric-based metasurface,leveraging materials such as titanium dioxide,silicon,gallium arsenide,and silicon nitride,which finds extensive application in the design and implementation of high-performance optical devices,owing to its notable advantages,including a high refractive index,low ohmic loss,and ***,the remarkable growth in nanofabrication technologies allows for the exploration of new methods in metasurface fabrication,especially through wafer-scale nanofabrication technologies,thereby facilitating the realization of commercial applications for *** review provides a comprehensive overview of the latest advancements in state-of-the-art fabrication technologies in dielectric metasurface *** technologies,including standard nanolithography[e.g.,electron beam lithography(EBL)and focused ion beam(FIB)lithography],advanced nanolithography(e.g.,grayscale and scanning probe lithography),and large-scale nanolithography[e.g.,nanoimprint and deep ultraviolet(DUV)lithography],are utilized to fabricate highresolution,high-aspect-ratio,flexible,multilayer,slanted,and wafer-scale all-dielectric metasurfaces with intricate ***,we conclude with a perspective on current cutting-edge nanofabrication technologies.

关键词： dielectric meta-devices meta-optics metasurface nanofabrication nanotechnology nanophotonics large/waferscale nanofabrication

来源：评论

学校读者我要写书评

暂无评论

Eco-friendly gas insulating medium for next-generation SF_(6)-free equipment

引用

iEnergy 2023年第1期2卷 14-42页

作者： Yi Li Shuangshuang Tian Linlin Zhong Geng Chen Song Xiao Yann Cressault Yuwei Fu Yu Zheng Christophe Preve Zhaolun Cui Yin Zhang Fanchao Ye Daniel Piccoz Gang Wang Yalong Li Youping Tu Wenjun Zhou Ju Tang Xiaoxing Zhang Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment Hubei University of TechnologyWuhan 430068China School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072China School of Electrical Engi-neering Southeast UniversityNanjing 210096China State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources North China Electric Power UniversityBeijing 102206China LAPLACE(Laboratoire Plasma et Conversion d'Energie) Universitéde ToulouseToulouse 31013France Department of Electrical Engineering Xi’an University of TechnologyXi’an 710048China Schneider Electric Reuil-Malmaison 92500France School of Electric Power Engineering South China University of TechnologyGuangzhou 510006China

Gas-insulated equipment(GIE)that utilizes the most potent greenhouse gas sulfur hexafluoride(SF_(6))as insulation and arc-quenching medium has been widely used in the power *** eco-friendly insulating gas with advanced performance for next-generation SF_(6)-free GIE is significant for the“net-zero”goal and sustainable *** this paper,the utilization,emission,and reduction policies of SF_(6)around the world were summarized ***,we systematically reviewed the latest progress in comprehensive performance evaluation of eco-friendly insulating gas in terms of molecular design,dielectric insulation,arc-quenching,stability and decomposition,materials compatibility,biosafety,***,the representative applications of eco-friendly insulating gas in medium-voltage,high-voltage GIE as well as relevant maintenance-related technologies were ***,the existing challenges and future perspectives were proposed,presenting a roadmap to hopefully steer the development of eco-friendly insulating gas and GIE.

关键词： Eco-friendly insulating gas net-zero dielectric insulation arc-quenching SF_(6)-free gas-insulated equipment(GIE)

来源：评论

学校读者我要写书评

暂无评论

Coevolutionary Framework for Generalized Multimodal Multi-objective Optimization

arXiv

引用

arXiv 2022年

作者： Li, Wenhua Yao, Xingyi Li, Kaiwen Wang, Rui Zhang, Tao Wang, Ling College of Systems Engineering National University of Defense Technology Changsha China Hunan Key Laboratory of Multi-energy System Intelligent Interconnection Technology Changsha410073 China The Department of Automation Tsinghua University Beijing100084 China

Most multimodal multi-objective evolutionary algorithms (MMEAs) aim to find all global Pareto optimal sets (PSs) for a multimodal multi-objective optimization problem (MMOP). However, in real-world problems, decision makers (DMs) may be also interested in local PSs. Also, searching for both global and local PSs is more general in view of dealing with MMOPs, which can be seen as a generalized MMOP. In addition, current state-of-the-art MMEAs exhibit poor convergence on high-dimension MMOPs. To address the above two issues, we present a novel coevolutionary framework (CoMMEA) to better produce both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs. Specifically, the CoMMEA introduces two archives to the search process, and coevolves them simultaneously through effective knowledge transfer. The convergence archive assists the CoMMEA to quickly approaching the Pareto optimal front (PF). The knowledge of the converged solutions is then transferred to the diversity archive which utilizes the local convergence indicator and the ∊-dominance-based method to obtain global and local PSs effectively. Experimental results show that CoMMEA is competitive compared to seven state-of-the-art MMEAs on fifty-four complex MMOPs. Copyright © 2022, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Safe Path Following Control of Autonomous Underwater Vehicles Based on Double Dipole Vector Field

Safe Path Following Control of Autonomous Underwater Vehicle...

引用

Asian Control Conference

作者： Haoliang Wang Tan Li Lootha Loserian Muriatoy Dezhi Yu Pingxin Liu Ai Jichong Daoyi Lu Marine Engineering College Dalian Maritime University Dalian China Department of Automation Shanghai Jiaotong University Shanghai China State Key Laboratory of Maritime Technology and Safety Dalian China Dalian Key Laboratory of Swarm Control and Electrical Technology for Intelligent Ships Dalian China Marine Electrical Engineering College Dalian Maritime University Dalian China Hainan Railway Co. LTD Haikou China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

This paper studies a path following problem of autonomous underwater vehicle (AUV) in complex and harsh working environment. Firstly, a kinematic model of an AUV in the vertical plane is built by constructing an earth coordinate system and a body coordinate system. Secondly, a guidance pitch angle is proposed by using a double dipole vector field, and guidance speeds are designed based on the back-stepping method. Finally, the stability of the proposed control system is proved by Lyapunov stability theory. Simulation results verify the effectiveness of the real-time safe path following control of autonomous underwater vehicles based on double dipole vector field.

关键词： Earth Autonomous underwater vehicles Simulation Kinematics Reliability engineering Vectors Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Generative AI-driven Cross-layer Covert Communication: Fundamentals, Framework and Case Study

arXiv

引用

arXiv 2025年

作者： Liu, Tianhao Liu, Jiqiang Zhang, Tao Wang, Jian Wang, Jiacheng Kang, Jiawen Niyato, Dusit Mao, Shiwen School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing100045 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

Ensuring end-to-end cross-layer communication security in military networks by selecting covert schemes between nodes is a key solution for military communication security. With the development of communication technology, covert communication has expanded from the physical layer to the network and application layers, utilizing methods such as artificial noise, private networks, and semantic coding to transmit secret messages. However, as adversaries continuously eavesdrop on specific communication channels, the accumulation of sufficient data may reveal underlying patterns that influence concealment, and establishing a cross-layer covert communication mechanism emerges as an effective strategy to mitigate these regulatory challenges. In this article, we first survey the communication security solution based on covert communication, specifically targeting three typical scenarios: device-to-device, private network communication, and public network communication, and analyze their application scopes. Furthermore, we propose an end-to-end cross-layer covert communication scheme driven by Generative Artificial Intelligence (GenAI), highlighting challenges and their solutions. Additionally, a case study is conducted using diffusion reinforcement learning to sovle cloud edge internet of things cross-layer secure communication. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Recurrent Attentional Reinforcement Learning for Fault Diagnosis of Hydraulic system

Recurrent Attentional Reinforcement Learning for Fault Diagn...

引用

International Conference on Control, Decision and Information Technologies (CoDIT)

作者： Zhenhui Tang Ru Liu Kang Lou Chaojian Gao Jingcheng Wang SJTU Sanya Yazhou Bay Institute of Deepsea Science and Technology Sanya China Department of Automation Shanghai Jiao Tong University Shanghai China Shanghai Marine Equipment Research Institute Shanghai China Department of Automation the Key Laboratory of System Control and Information Processing Ministry of Education of China and the Shanghai Engineering Research Center of Intelligent Control and Management Shanghai Jiao Tong University Shanghai China Autonomous Systems and Intelligent Control International Joint Research Center Xi'an Technological University Xi'an China

ISBN: (数字)9798350373974

ISBN: (纸本)9798350373981

Recognizing fault types of machinery system is a fundamental but challenging task in industrial application. Although data-driven fault diagnosis method attains remarkable progress by learning fault features automatically, the existing data-driven fault diagnosis pipelines learn non-discriminative feature. To deal with these problems, a new data-driven fault diagnosis method with recurrent attentional module is proposed to find a sequence of informative features by localizing distinguishing time fragments about each individual faults iteratively. The contextual sequence dependency between the localized time fragments is enhanced. Then, the fault types are further predicted on localized time fragments. The proposed framework also explicitly models long-term dependencies among these attentional time fragments to capture historical fault information. Experiments on hydraulic system show that the proposed framework achieves superior diagnosis performance and computation efficiency.

关键词： Fault diagnosis Location awareness Accuracy Computational modeling Pipelines Reinforcement learning Hydraulic systems Computational efficiency Information technology

来源：评论

学校读者我要写书评

暂无评论

Target Assignment Optimization of Heterogeneous Sensor Networks in Urban Environment 39

Target Assignment Optimization of Heterogeneous Sensor Netwo...

引用

39th Chinese Control Conference, CCC 2020

作者： Chen, Chen Zihao, Cheng Wei, Xu Beijing Institute of Technology School of Automation Beijing100081 China State Key Laboratory of Intelligent Control and Decision of Complex System Beijing100081 China

ISBN: (纸本)9789881563903

Preventing and controlling Low-Slow-Small(LSS) targets are problems to be solved due to their good concealment in urban environment. Consequently, the problem of target assignment is studied in this paper. Firstly, a target assignment model based on heterogeneous sensor networks is proposed. The characteristics of LSS targets and the influence of environmental factors such as climate and terrain are considered on this model. At the same time, the detection capabilities of different detection nodes and collaborative tracking capabilities are also considered. Secondly, an intelligent optimization algorithm GSAPSO based on PSO is proposed to maximize tracking effect of the sensors. Finally, the simulations are used to compare the GSAPSO algorithm with the traditional PSO and GAPSO algorithms. The results demonstrate that the proposed algorithm has better tracking effect. © 2020 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Particle swarm optimization (PSO)

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：