检索结果-内蒙古大学图书馆

IEEE Conference on Decision and Control

作者： Xuefei Yang Emilia Fridman Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin China National Key Laboratory of Modeling and Simulation for Complex Systems School of Electrical Engineering Tel-Aviv University Israel

In this article, we introduce a time-delay approach to gradient-based extremum seeking (ES) in the continuous domain for n-dimensional (nD) static quadratic maps. As in the recently introduced (for 2D maps in the continuous domain), we transform the system to the time-delay one (neutral type system). This system is $\mathbf{O}(\varepsilon)$ . ‘perturbation of the averaged linear ODE system. We further explicitly present the neutral system as the linear ODE, where $\mathrm{O}(\varepsilon)$ -terms are considered as disturbances with distributed delays of the length of the small parameter $\varepsilon$ . Quantitative (for uncertain map) and qualitative (for unknown map) practical stability analyses are provided by employing a variation of constants formula that greatly simplifies the results compared to the previously used Lyapunov-Krasovskii (L-K) method. The new approach also simplifies the conditions and improves the results. Examples from the literature illustrate the efficiency of the new approach, allowing essentially large uncertainty of the Hessian matrix with bounds on $\varepsilon$ that are not too small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Knowledge Enhanced Pre-trained Models

arXiv

引用

arXiv 2021年

作者： Yang, Jian Hu, Xinyu Xiao, Gang Shen, Yulong Computer Science and Technology Xidian University Xi’an China National Key Laboratory for Complex Systems Simulation Beijing China

Pre-trained language models learn informative word representations on a large-scale text corpus through self-supervised learning, which has achieved promising performance in fields of natural language processing (NLP) after fine-tuning. These models, however, suffer from poor robustness and lack of interpretability. We refer to pre-trained language models with knowledge injection as knowledge-enhanced pre-trained language models (KEPLMs). These models demonstrate deep understanding and logical reasoning and introduce interpretability. In this survey, we provide a comprehensive overview of KEPLMs in NLP. We first discuss the advancements in pre-trained language models and knowledge representation learning. Then we systematically categorize existing KEPLMs from three different perspectives. Finally, we outline some potential directions of KEPLMs for future research. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Trends and drivers of anthropogenic NOx emissions in China since 2020

引用

Environmental Science and Ecotechnology 2024年第5期21卷 287-293页

作者： Hui Li Bo Zheng Yu Lei Didier Hauglustaine Cuihong Chen Xin Lin Yi Zhang Qiang Zhang Kebin He Shenzhen Key Laboratory of Ecological Remediation and Carbon Sequestration Institute of Environment and EcologyTsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen 518055China State Environmental Protection Key Laboratory of Sources and Control of Air Pollution Complex Beijing 100084China State Environmental Protection Key Laboratory of Environmental Planning and Policy Simulation and Center of Air Quality Simulation and System Analysis Chinese Academy of Environmental PlanningBeijing 100041China Laboratoire des Sciences du Climat et de l’Environnement LSCE/IPSLCEA-CNRS-UVSQUniversite Paris-SaclayGif-sur-YvetteFrance Center for Satellite Application on Ecology and Environment Ministry of Ecology and Environment of ChinaBeijing 100094China Institute of Future Human Habitats Tsinghua Shenzhen International Graduate SchoolTsinghua UniversityShenzhen 518055China Ministry of Education Key Laboratory for Earth System Modeling Department of Earth System ScienceTsinghua UniversityBeijing 100084China State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijing 100084China

Nitrogen oxides(NOx),significant contributors to air pollution and climate change,form aerosols and ozone in the ***,timely,and transparent information on NOx emissions is essential for decision-making to mitigate both haze and ozone ***,a comprehensive understanding of the trends and drivers behind anthropogenic NOx emissions from Chinadthe world's largest emitterdhas been lacking since 2020 due to delays in emissions *** we show a consistent decline in China's NOx emissions from 2020 to 2022,despite increased fossil fuel consumption,utilizing satellite observations as constraints for NOx emission estimates through atmospheric *** reduction is corroborated by data from two independent spaceborne instruments:the TROPOspheric Monitoring Instrument(TROPOMI)and the Ozone Monitoring Instrument(OMI).Notably,a reduction in transport emissions,largely due to the COVID-19 lockdowns,slightly decreased China's NOx emissions in *** subsequent years,2021 and 2022,reductions in NOx emissions were driven by the industry and transport sectors,influenced by stringent air pollution *** satellite-based inversion system developed in this study represents a significant advancement in the real-time monitoring of regional air pollution emissions from space.

关键词： China's NOx emissions Pollution control Socio-economic drivers Atmospheric inversion

来源：评论

学校读者我要写书评

暂无评论

Demo: A Multi-Agent Communication Framework in Cooperative Detection System

Demo: A Multi-Agent Communication Framework in Cooperative D...

引用

IEEE/ACM Symposium on Edge Computing (SEC)

作者： Hongye Gao Yichen Shi Weixiong Rao Qiongmin Ma School of Software Engineering Tongji University Shanghai China National Key Laboratory for Complex Systems Simulation Beijing China

Communication is an effective mechanism to coordinate the be-havior of mobile multi-agents. We propose a general multi-agent communication framework. With help of graph neural networks and reinforcement learning, this framework can provide a coop-erative detection method with more powerful capabilities. In this paper, we demonstrate the configurable co-detection simulation system. Moreover, the evaluation of the multi-agent communication framework validates that the agents can effectively cooperate with each other through decentralized communication, and effectively reduce computation overhead meanwhile with high scalability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Statistics of active and passive scalars in one-dimensional compressible turbulence

引用

Physical Review E 2012年第6期86卷 066307-066307页

作者： Qionglin Ni Shiyi Chen State Key Laboratory of Turbulence and Complex Systems Center for Applied Physics and Technology and Key Laboratory of High Energy Density Physics Simulation Ministry of Education College of Engineering Peking University 100871 Beijing People's Republic of China

Statistics of the active temperature and passive concentration advected by the one-dimensional stationary compressible turbulence at Reλ=2.56×106 and Mt=1.0 is investigated by using direct numerical simulation with all-scale forcing. It is observed that the signal of velocity, as well as the two scalars, is full of small-scale sawtooth structures. The temperature spectrum corresponds to G(k)∝k−5/3, whereas the concentration spectrum acts as a double power law of H(k)∝k−5/3 and H(k)∝k−7/3. The probability distribution functions (PDFs) for the two scalar increments show that both δT and δC are strongly intermittent at small separation distance r and gradually approach the Gaussian distribution as r increases. Simultaneously, the exponent values of the PDF tails for the large negative scalar gradients are qθ=−4.0 and qζ=−3.0, respectively. A single power-law region of finite width is identified in the structure function (SF) of δT; however, in the SF of δC, there are two regions with the exponents taken as a local minimum and a local maximum. As for the scalings of the two SFs, they are close to the Burgers and Obukhov-Corrsin scalings, respectively. Moreover, the negative filtered flux at large scales and the time-increasing total variance give evidences to the existence of an inverse cascade of the passive concentration, which is induced by the implosive collapse in the Lagrangian trajectories.

关键词： TURBULENCE TEMPERATURE COMPUTER simulation GAUSSIAN distribution LAGRANGIAN functions TRAJECTORIES (Mechanics) POWER law (Mathematics)

来源：评论

学校读者我要写书评

暂无评论

Impacts of major volcanic eruptions over the past two millennia on both global and Chinese climates:A review

引用

Science China Earth Sciences 2024年第1期67卷 61-78页

作者： Weiyi SUN Deliang CHEN Guonian LÜ Liang NING Chaochao GAO Renhe ZHANG Bin WANG Jian LIU Key Laboratory for Virtual Geographic Environment Ministry of EducationState Key Laboratory Cultivation Base of Geographical Environment Evolution of Jiangsu ProvinceJiangsu Center for Collaborative Innovation in Geographical Information Resource Development and ApplicationSchool of Geography ScienceNanjing Normal UniversityNanjing 210023China Regional Climate Group Department of Earth SciencesUniversity of GothenburgGothenburg 40530Sweden College of Environmental and Resource Science Zhejiang UniversityHangzhou 310058China Department of Atmospheric and Oceanic Sciences&Institute of Atmospheric Sciences Fudan UniversityShanghai 200437China Department of Atmospheric Sciences and Atmosphere-Ocean Research Center University of Hawaii at ManoaHonoluluHI 96825USA Jiangsu Provincial Key Laboratory for Numerical Simulation of Large Scale Complex Systems School of Mathematical ScienceNanjing Normal UniversityNanjing 210023China Open Studio for the Simulation of Ocean-Climate-Isotope Qingdao National Laboratory for Marine Science and TechnologyQingdao 266237China

Major volcanic eruptions(MVEs)have attracted increasing attention from the scientific *** studies have explored the climatic impact of MVEs over the past two ***,proxy-based reconstructions and climate model simulations indicate divergent responses of global and China’s regional climates to ***,we used multiple data from observations,reconstructions,simulations,and assimilations to summarize the historical facts of MVEs,the characteristics and mechanisms of their climatic impact,and directions for future *** reviewed volcanic datasets and determined intensive MVE periods;these periods corresponded to the years 530–700,1200‒1460,and 1600‒1840 *** tropical MVEs,a substantial cooling effect is observed throughout the globe and China on the interannual-interdecadal time scales but an inconsistent cooling magnitude is detected between reconstructions and *** the first summer after tropical MVEs,a decrease in global and monsoonal precipitation is *** reconstructions and simulations,an increased precipitation is seen for the Yangtze River Basin,while large uncertainties in precipitation changes are present for other regions of *** drought can be induced by frequent eruptions and volcanism superimposed on low solar irradiation and internal *** affect climate directly through the radiative effect and indirectly by modulating internal variability,such as the El Niño‒Southern Oscillation(ENSO)and Atlantic Multidecadal Oscillation(AMO).However,changes in the phase,amplitude,and periodicity of ENSO and AMO after MVEs and the associated mechanisms remain controversial,which could account for model-reconstruction ***,other internal variability,uncertainties in reconstruction methods and aerosol‒climate models,and climate background may also induce model-reconstruction *** gaps and directions for future research are also discussed.

关键词： Major volcanic eruption Climate variability Mechanism Past two millennia Internal variability

来源：评论

学校读者我要写书评

暂无评论

The qqsQ(q=u,d;Q=c,b)tetraquark system in a chiral quark model

引用

Chinese Physics C 2024年第7期48卷 84-105页

作者：杨刚平加伦 Jorge Segovia Department of Physics Zhejiang Normal UniversityJinhua 321004China Department of Physics and Jiangsu Key Laboratory for Numerical Simulation of Large Scale Complex Systems Nanjing Normal UniversityNanjing 210023China Departamento de Sistemas Físicos Químicos y NaturalesUniversidad Pablo de OlavideE-41013 SevillaSpain

The S-wave qqsQ(q=u,d;Q=c,b)tetraquarks,with spin-paritiesJ^(P)=0^(+),1^(+),and 2^(+),in both isoscalar and isovector sectors,are systematically studied using a chiral quark *** meson-meson,diquark-antidiquark,and K-type arrangements of quarks and all possible color wave functions are comprehensively *** four-body system is solved using the Gaussian expansion method,a highly efficient computational ***,a complex-scaling formulation of the problem is established to disentangle bound,resonance,and scattering *** theoretical framework has already been successfully applied in various tetra-and penta-quark *** the complete coupled channel and within the complex-range formulation,several narrow resonances of qqsC and qqsb systems are obtained,in each allowed I(J^(P))-channel,within the energy regions of 2.4-3.4 GeV and 5.7-6.7GeV,*** predicted exotic states,which indicate a richer color structure when going towards multiquark systems beyond mesons and baryons,are expected to be confirmed in future high-energy particle and nuclear experiments.

关键词： quantum chromodynamics quark models

来源：评论

学校读者我要写书评

暂无评论

数据驱动框架下基于基因表达编程的非线性K-L湍流混合模型

引用

Acta Mechanica Sinica 2023年第2期39卷 147-164页

作者：谢寒松赵耀民张又升 Key Laboratory of High Energy Density Physics Simulation Ministry of EducationCenterfor Applied Physics and Technology and College of EngineeringPeking UniversityBeijing 100871China State Key Laboratory for Turbulence and Complex Systems College of EngineeringPeking UniversityBeijing 100871China institute of Applied Physics and Computational Mathematics Beijing 100094China

由Rayleigh-Taylor(RT)、Richtmyer-Meshkov(RM)、Kelvin-Helmholtz(KH)等流体力学界面不稳定性诱导的湍流混合现象广泛存在于自然界和工程问题中,准确预测其演化具有十分重要的意义.考虑到实际问题的高雷诺数及复杂性,在可预见的未来,... 详细信息

由Rayleigh-Taylor(RT)、Richtmyer-Meshkov(RM)、Kelvin-Helmholtz(KH)等流体力学界面不稳定性诱导的湍流混合现象广泛存在于自然界和工程问题中,准确预测其演化具有十分重要的意义.考虑到实际问题的高雷诺数及复杂性,在可预见的未来,雷诺平均(RANS)方法仍将是工程实践中最具可实现性的选择.一般而言,传统RANS混合模型中至关重要的雷诺应力项是基于经典的Boussinesq线性涡粘假设封闭的.然而,这种线性模型无法充分描述在实际工程流动中发挥着重要作用的湍流各向异性特征.相比之下,非线性模型在这方面具有显著优势.本研究首次将基因表达编程(GEP)方法应用于湍流混合问题,发展了数据驱动的非线性K-L湍流混合模型.与常见的“黑箱”型机器学习模型不同,GEP模型显式给出模型方程,从而具有更强的物理可解释性.具体地,本研究基于二阶截断的广义Cayley-Hamilton非线性本构关系,利用GEP方法中的符号回归功能,形式化地给出了待封闭的模型系数与伽利略不变量之间的函数关系.此外,为了保证训练模型的物理性,我们将可实现性原则引入到了惩罚函数中.模型泛化性测试的结果表明:尽管新模型仅利用倾斜RT混合问题训练得到,但对于几个典型的混合问题均具有良好的鲁棒性.与标准的K-L模型相比,新模型不但具有更高的预测精度,而且能够更好地捕捉湍流的物理特性.此外,通过分析显式的封闭模型,本文进一步给出了新模型的预测效果得以提升的原因.

关键词： Turbulent mixing GEP method Nonlinear model Machine learning Interpretable model

来源：评论

学校读者我要写书评

暂无评论

The view growth pattern of user generated videos on YouTube

引用

International Journal of u- and e- Service, Science and Technology 2016年第6期9卷 433-444页

作者： Zhou, Renjie Xia, Dongchen Yin, Yuyu Zhang, Jilin Zhang, Wei College of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory Complex System Modeling and Simulation Ministry of Education Hangzhou China

With the rapid development of social media, video sharing sites like YouTube are getting more and more attention. Discovering the view growth pattern have become interesting topics for researchers as well as advertisers, media companies. In this paper, we analyze two aspects about video view growth pattern of YouTube videos. Firstly, the pattern of aggregated view is studied. It is found that the aggregated view rate peaks in the first few days, and falls quickly in the following days, and then decrease slowly during the consecutive weeks. Finally, the view rate tends to be a constant on the long run. The aggregated view count after a period of two months can be fitted with a linear line. Secondly, the view growth pattern of individual video is explored. The results indicate that the majority of videos peak at the very beginning of videos’ lifetime, and the category of view sources causes the peak is different. The view count of individual video and the view count from each source item also stabilize after a period of two months, and we finally show the referring time and active period of each source item. © 2016 SERSC.

关键词： Growth rate

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：