检索结果-内蒙古大学图书馆

IEEE International Conference on Radar

作者： Hao Li Xueli Fang Lei Zhang Hui Kang Wei Zhang School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China Key Laboratory of complex aviation simulation system Beijing China

ISBN: (纸本)9781665468893

With the emergence of various kinds of complex radar jamming, radar jamming intelligent recognition technology has increasingly become the key to electronic counter-counter measures. To achieve radar jamming open-set recognition with a small number of tagged samples, Generative adversarial network-based pseudolabeled convolutional neural network (GAN-PL-CNN) model is proposed in this paper. Firstly, radar jamming is modelled, and the radar jamming datasets with known and unknown types are established after time-frequency transformation and image processing. Then, the adaptive pseudolabeling method is used to achieve semi-supervised recognition of radar jamming by combining the learning capability of convolutional neural networks and the characteristics of pseudolabeling to increase labeled samples intelligently. Finally, generative adversarial networks are introduced to enhance the recognition ability of the model and the discrimination ability of the unknown type through the game between the generator and the discriminator in the iterative process. Experimental results show that the GAN-PL-CNN model achieves 89.7%-95.1% for known types and 30.7%-86.8% for unknown types at 3%-6% labeling rate. As the number of labeled samples increases, the recognition effect becomes better and has a greater ability to exclude unknown type.

关键词： Adaptation models Time-frequency analysis Radar measurements Neural networks Radar Radar imaging Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Short-Term Traffic Flow Prediction Method Based on Spatio-Temporal Characteristics of complex Road Network

Short-Term Traffic Flow Prediction Method Based on Spatio-Te...

引用

作者： Huawei ZHU Yihao MAO Yiming ZHAO Liyuan SHI Yanli SHAO School of Information and Electrical Engineering Zhejiang University City College Key Laboratory of Complex Systems Modeling and Simulation School of Computer Science and TechnologyHangzhou Dianzi University

With the development of urbanization,the number of residents' motor vehicles has increased sharply,and traffic congestion problem has become increasingly *** construction of Intelligent Traffic system(ITS) has become the main means to alleviate traffic ***-term traffic flow prediction has guiding significance for residents' travel planning and intelligent management of transportation,and has become one of the research hotspots in intelligent transportation ***,A short-term traffic flow prediction method based on the spatio-temporal characteristics of complex road networks is proposed to further improve the prediction accuracy and reduce the prediction ***,a graph convolutional network(GCN) capable of processing non-Euclidean data structures is used to extract the spatial characteristics of traffic flow ***,the long and short-term memory(LSTM) neural network is used to process the time ***,the two are combined to realize the effective processing of the spatio-temporal characteristics of traffic flow *** results on the real traffic flow dataset prove the feasibility and effectiveness of the proposed method,and can provide a basis for intelligent traffic control and smart city construction.

关键词： Traffic Flow Prediction Spatio-temporal GCN LSTM

来源：评论

学校读者我要写书评

暂无评论

Histogram-covering approach to verify model reliability

Histogram-covering approach to verify model reliability

引用

作者： Huang, Chongfu Jia, Dongyun Key Laboratory of Environmental Change and Natural Disaster Ministry of Education of China Beijing Normal University No. 19 Xinjiekouwai Street Beijing 100875 China Research Center for System Simulation and Disaster Modeling Academy of Disaster Reduction and Emergency Management Ministry of Civil Affairs and Ministry of Education

In statistics viewpoint, it is impossible to precisely estimate a probability distribution of a population with a sample whose size is less than the population's size. In general, with histogram method, estimates resulted from different samples are different, whose cover would reflect the scattering of estimates. Meanwhile, a fuzzy probability distribution would reflect the fuzziness of the probability estimate. According to the consistency principle of possibility/probability, we infer that the model used for calculating fuzzy probabilities is reliable if the fuzzy probability distribution is consist with the cover of histograms, which is a class of probability distributions of the probabilities that the event occurs in intervals. In this paper, with simulation results, we verify that the interior-outer-set model is basically reliable. ©2008 Old City Publishing, Inc.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

UAV Swarm Defense based on Shipborne UAV Swarm

UAV Swarm Defense based on Shipborne UAV Swarm

引用

全球智能工业创新大会暨全球创新技术成果转移大会(GIIC2018)——2018智能无人系统大会

作者： WANG Jixin HONG Da WANG Liang Naval Academy Beijing 100161China Key Laboratory of Complex Ship System Simulation Beijing 100161C Naval Academy Beijing 100161China

UAV swarm can be launched from surface,aerial and underwater *** becomes a new threat to warship because of its characteristics such as huge quantity,cooperative search,coordinated path planning,intelligent recognition and precise strike *** paper puts forward a technique of UAV swarm defense based on shipborne UAV *** operational simulation system was developed to analyze hostile UAV swarm defense achieved by traditional shipborne weapons or shipborne UAV swarm of a single *** show that the defense effectiveness of shipborne UAV swarm is significantly superior to traditional weapons while defensing a huge amount of UAV *** effectiveness of shipborne UAV swarm increases with the hit rate of shipborne UAV if the hostile UAV swarm can be detected at long *** not,it increases with the hit rate of shipborne UAV as well as the system reaction speed and launch speed of UAV launcher.

关键词： UAV swarm defense shipborne UAV swarm defense effectiveness operational simulation experiment

来源：评论

学校读者我要写书评

暂无评论

Mechanics of corrugated surfaces by multi-scale modeling

Mechanics of corrugated surfaces by multi-scale modeling

引用

中国力学大会——2013

作者： Duan Huiling State Key Laboratory for Turbulence and Complex System and Department of Mechanics and Aerospace Engineering College of EngineeringPeking University Key Laboratory of High Energy Density Physics Simulation College of EngineerPeking University

We first build a theoretical model to connect the effective surface stress and the surface morphology by using the continuum mechanics method and basic capillary ***, molecular statics simulation is used to estimate the line stress on a rough surface with ***,we established the connections between the surface stress at the continuum level and

关键词： Mechanics of corrugated surfaces by multi-scale modeling

来源：评论

学校读者我要写书评

暂无评论

How Shale Gas will Shape China's Future? an Evaluation Based on Dynamic Energy-CGE Model

引用

Energy Procedia 2017年 105卷 3349-3354页

作者： Shihui Zhang Can Wang Wenjia Cai State Key Joint Laboratory of Environment Simulation and Pollution Control (SKLESPC) and School of Environment Tsinghua University Beijing 100084 China Ministry of Education Key Laboratory for Earth System Modeling and Center for Earth System Science Room S925 Meng Minwei Science Building Tsinghua University Beijing 100084 China

The potential of shale gas development in China is huge but research that assesses the impacts of shale gas development on China's economy and carbon emissions are rare. This paper used a dynamic CGE model with energy and carbon emission modules to evaluate the impacts under different scenarios. The results implied that large scale of shale gas development will stimulate economy, when the supply of shale gas increases by 500% from 2010 to 2030, the GDP in 2030 will be 2.59% higher than BAU scenario; technology change that reduces the costs of shale gas utilization will not further stimulate economic growth on the basis of large scale exploitation, but will improve the diffusion of gas and make the energy structure cleaner therefore contribute the carbon mitigation. Hence, it is important for policy makers to take into account the varied effects of different shale gas promotion approaches.

关键词： Shale Gas low carbon development economy dynamic CGE model

来源：评论

学校读者我要写书评

暂无评论

An Amplification DDoS Attack Defence Mechanism using Reinforcement Learning

An Amplification DDoS Attack Defence Mechanism using Reinfor...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yuantian Zhang Yang Cheng State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing University of Chinese Academy of Sciences Beijing Key Laboratory of Complex Ship System Simulation Beijing China

ISBN: (数字)9781728140346

ISBN: (纸本)9781728140353

Amplification distributed denial of service attacks constitute a rapidly evolving threat in the current Internet, which is difficult to be defended for its camouflage and distributability. Inspired by recent advances in AI, we consider building an intelligent model that learn to defend amplification attacks directly from traffic. Specifically, we design a novel traffic throttling model using reinforcement learning, and the reinforcement learning agent makes the traffic throttling strategy by receiving traffic data. The reward of the model is calculated based on the proportion of the legitimate traffic transmitted, and the action is considered while evaluating the payload of the network. The results of experiments show that the RL method converges quickly and can effectively identify and discard attack traffic after a period training. Furthermore, we compare our proposed approach against a baseline and a conventional port-based approach and we show the superiority of our approach.

关键词： Computer crime Protocols Learning (artificial intelligence) Servers IP networks Internet Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Improving the wetting stability on submersed superhy-drophobic surfaces for drag reduction applications using hierarchical structures

Improving the wetting stability on submersed superhy-drophob...

引用

23rd International Congress of Theoretical and Applied Mechanics

作者： Yahui Xue Shigan Chu Pengyu Lü Huiling Duan State Key Laboratory for Turbulence and Complex System Department of Mechanics and Aerospace EngineeringCollege of EngineeringPeking University Key Laboratory of High Energy Density Physics Simulation(HEDPS) CAPTPeking University

Superhydrophobic surfaces exhibit great potentials for reducing drag in micro-fluidic *** existence of liquid-air interfaces in a large-area fraction on submersed superhydrophobic surfaces is essential for significant... 详细信息

关键词： Improving the wetting stability on submersed superhy-drophobic surfaces for drag reduction applications using hierarchical structures

来源：评论

学校读者我要写书评

暂无评论

FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation

FedAG:A Federated Learning Method Based on Data Importance W...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Xu, Mengchu Zeng, Yan Xue, Meiting Zhang, Ji-Lin Wan, Jian Zhou, Mingyao Wen, Yilin Shi, Yukun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China Hangzhou Dianzi University School of Cyberspace Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

ISBN: (纸本)9798350345384

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms. © 2023 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

Impact of Household Consumption Activities on Energy Consumption in China—Evidence from the Lifestyle Perspective and Input-output Analysis

引用

Energy Procedia 2017年 105卷 3384-3390页

作者： Qun Ding Wenjia Cai Can Wang Ministry of Education Key Laboratory for Earth System Modeling and Center for Earth System Science Room S925 Meng Minwei Science Building Tsinghua University Beijing 100084 China State Key Joint Laboratory of Environment Simulation and Pollution Control (SKLESPC) and School of Environment Tsinghua University Beijing 100084 China

The household sector has become the second largest consumer of final energy, ranking only next to the industrial sector in China. Except for the direct energy consumption of household sector, people's consumption activities also indirectly affect the energy consumption of multiple production sectors. This paper investigates the direct and indirect impact of household consumption activities on energy consumption in China from the consumers’ lifestyle perspective based on the input-output analysis. The results show that China's energy consumption caused by household consumption activities in 2012 accounts for 24.7% of the total finial energy consumption. The indirect energy consumption of household consumption activities is 1.35 times more than the direct energy consumption. Residential activities cause the most indirect energy consumption, while the smelting and pressing industry of ferrous metal is the most energy-consuming industrial sector influenced by household consumption. We also find that the low-carbon pattern and accelerated technological advance can reduce the indirect energy consumption effectively by scenario analysis.

关键词： household consumption energy consumption input-output analysis energy conservation

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：