检索结果-内蒙古大学图书馆

作者： Yifang Ji Guomin Zhang Shengxu Xie Xiulei Wang Command & Control Engineering College Army Engineering University of PLA

Accurately simulating large-scale user behavior is important to improve the similarity between the cyber range and the real network *** Linux Container provides a method to simulate the behavior of large-scale users under the constraints of limited physical *** a container-based virtualization environment,container networking is an important *** evaluate the impact of different networking methods between the containers on the simulation performance,the typical container networking methods such as none,bridge,macvlan were analyzed,and the performance of different networking methods was evaluated according to the throughput and latency *** experiments show that under the same physical resource constraints,the macvlan networking method has the best network performance,while the bridge method has the worst *** result provides a reference for selecting the appropriate networking method in the user behavior simulation process.

关键词： Linux Container Networking Mode Network Performance User Behavior Simulation

来源：评论

学校读者我要写书评

暂无评论

Learning predictive control of wheeled mobile robot with communication delays 3

Learning predictive control of wheeled mobile robot with com...

引用

2024 3rd International Conference on Electrical, control and Information Technology, ECITech 2024

作者： Wu, Ruizhuo Xu, Xin He, Ming Liu, Daxue Zhang, Xinglong College of Intelligence Science and Technology National University of Defense Technology Hunan Changsha410073 China Institute of Command and Control Engineering Army Engineering University Jiangsu Nanjing210007 China

This paper proposed a learning predictive control method for wheeled mobile robots with communication delays. In consideration of the property in the Networked control System (NCS), communication delay was divided into two types: delay from sensor to controller and delay from controller to actuator. For each type of delay, state prediction and state augmentation techniques were utilized respectively to diminish their passive impact on the control of WMR. Then receding horizon reinforcement learning approach was adopted to learn the optimal policy based on the delay compensation. Finally, simulations were performed applying the proposed method to the trajectory tracking of WMR and showed the validity of the proposed scheme. © 2024 Published under licence by IOP Publishing Ltd.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning based Recommend System using stratified sampling 2

Deep Reinforcement Learning based Recommend System using str...

引用

2018 2nd Annual International Conference on Cloud Technology and Communication engineering, CTCE 2018

作者： Zhao, Zhiruo Chen, Xiliang Command and Control Engineering College Army Engineering University No. 1 HaiFu Road Guang Hua Road Qin Huai District Nanjing City Jiangsu Province210007 China

Typically personalized movie recommendation algorithms often adopt a static view of recommend process and only take current rewards into consideration. Thus, they are hard to adapt to the dynamic change of users and items. In this paper, we propose a movie recommend system based on deep reinforcement learning to better accommodate the dynamic property when users' distribution or interest changes. Firstly, we adopt nature DQN algorithm to set up baseline. Second, under the framework of nature DQN, we use Double DQN to solve overestimation and indeed reduce error. Besides, we use stratified sampling rather than random sampling to accelerate convergence. Finally, by testing on Movielens dataset, the experimental results shows that our algorithm is superior to traditional algorithms, and also comparable to the latest algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Research on ldos attack detection and defense mechanism in software defined networks 6th

Research on ldos attack detection and defense mechanism in s...

引用

6th International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2020

作者： Xie, Shengxu Xing, Changyou Zhang, Guomin Wei, Xianglin Hu, Guyu Command and Control Engineering College Army Engineering University of PLA Nanjing210007 China The 63rd Research Institute National University of Defense Technology Nanjing210007 China

ISBN: (纸本)9789811590306

The LDoS (Low rate Denial of Service) attack that aims at exhausting the limited SDN switch buffer resource is hard to detect and degrade network performance seriously. To solve such a problem, this paper proposes an SDN LDoS detection and defense mechanism ADAR (Attack-flow Detection and Attack-port Recognition), which can detect the attack flows based on the collected statistical data, and identify and suppress these attack flows. The experimental results show that ADAR can effectively detect the SDN switch buffer overflow LDoS attacks, and mitigate their impact by using the attack port suppression method. Meanwhile, it can also effectively alleviate the problem of switch buffer overflow caused by the normal traffic burst in the network. © Springer Nature Singapore Pte Ltd 2020.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Optimization design of TS-PID fuzzy controllers based on genetic algorithms

Optimization design of TS-PID fuzzy controllers based on gen...

引用

WCICA 2004 - Fifth World Congress on Intelligent control and Automation, Conference Proceedings

作者： Xiu, Zhihong Ren, Guang Marine Engineering College Dalian Maritime University Dalian Liaoning Province China Department of Command Control Dalian Naval Academy Dalian Liaoning Province China

TS-PID fuzzy controllers are a class of Tagagi-Sugeno (TS) fuzzy controllers whose rule consequences employ PID expressions. The analytical model of typical TS-PID fuzzy controllers is proposed in this paper. It can be used to develop a fast and precise control algorithm in both optimal design and practical use. The essential character of a typical TS-PID fuzzy controller is investigated to be a nonlinear PID controller. Based on genetic algorithms (GA's), an optimal design method of TSPID fuzzy controllers is discussed in detail by means of the analytical model. The simulation results of a marine control system show that a TS-PID fuzzy controller designed via GA's has a good performance.

关键词： Intelligent control

来源：评论

学校读者我要写书评

暂无评论

A High-Performance Extraction Method for Public Opinion on Internet

引用

Wuhan University Journal of Natural Sciences 2007年第5期12卷 902-906页

作者： LI Yanling DAI Guanzhong ZHU Yehang QIN Sen School of Automatic Control Northwestern Polytechnical University Xi＇an 710072 Shaanxi China Department of Computer and Command Automation The Secondary Artillery Engineering College Xi＇an 710025 Shaanxi China

Aiming at the importance of the analysis for public opinion on Internet, the authors propose a high-performance extraction method for public opinion. In this method, the space model for classification is adopted to describe the relationship between words and categories. The combined feature selection method is used to remove noisy words from the original feature space effectively. Then the category weight of words is calculated by the improved formula combining the frequency of words and distribution of words. Finally, the class weights of the not-categorized documents based on the category weight of words are obtained for realizing opinion extraction. Experiment results show that the method has comparatively high classification and good stability.

关键词： opinion extraction text categorization class spacemodel feature selection

来源：评论

学校读者我要写书评

暂无评论

User's Permission Reasoning Method Based on Knowledge Graph Reward Guidance Reinforcement Learning in Data Center 7th

User's Permission Reasoning Method Based on Knowledge Graph ...

引用

7th International Conference on Data Mining and Big Data, DMBD 2022

作者： Pan, Yu Li, Hongmei Li, Wei Liu, Yi Li, Xiang Zheng, Qibin Qin, Wei National University of Defense Technology Changsha410073 China Command and Control Engineering College Army Engineering University of PLA Nanjing210007 China Academy of Military Science Beijing100091 China

ISBN: (纸本)9789811992964

In general, multiple domain cyberspace security assessments are very important for data center security and can be implemented by reasoning user's permissions. However, while existing methods include some information from the physical and social domains, they do not provide a comprehensive representation of cyberspace. Existing reasoning methods are also based on expert given rules, resulting in inefficiency and a low degree of intelligence. To address this challenge, we create a Knowledge Graph (KG) of multiple domain cyberspace in order to provide a standard semantic description of the multiple domain cyberspace. Following that, we proposed a user's permissions reasoning method based on reinforcement learning. All permissions in cyberspace are represented as nodes, and an agent is trained to find all permissions that user can have according to user's initial permissions and cyberspace KG. We set 10 reward setting rules based on the features of cyberspace KG in the reinforcement learning of reward information setting, so that the agent can better locate user's all permissions and avoid blindly finding user's permissions. The results of the experiments showed that the proposed method can successfully reason about user's permissions and increase the intelligence level of the user's permissions reasoning method. At the same time, the F1 value of the proposed method is 6% greater than that of the Translating Embedding (TransE) method. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Real-time mobile robot teleoperation via Internet based on predictive control

引用

中国高等学校学术文摘·机械工程 2008年第3期3卷 299-306页

作者： Shihua WANG Bugong XU YunHui LIU Yeming ZHOU Laboratory of Real-Time Control Through Internet and Fieldbuses College of Automation Science and Engineering South China University of Technology Guangzhou 510640 China Naval Arms Command Academy of Guangzhou Guangzhou 510430 China Laboratory of Real-Time Control Through Internet and Fieldbuses College of Automation Science and Engineering South China University of Technology Guangzhou 510640 China Naval Arms Command Academy of Guangzhou Guangzhou 510430 China Department of Automation and Computer Aided Engineering The Chinese University of Hong Kong Shatin N.T. HK China

A remote control system that can control a mobile robot in real time via the internet is proposed. To compensate for the network delay and counteract its impact on the teleoperation system, a predictive control scheme based on the modified Smith predictor proposed is selected. To ensure the stability and transparency of the system, a dynamic model manager is designed based on the information exchange between the sensors at the mas-ter and slave sides. To precisely predict the time delay, a new timer synchronization algorithm is proposed. To decrease delay- jitter, a new data buffer scheme is per-formed. Force feedback and a virtual predictive display are introduced to enhance the real-time efficiency of tele-operation. The usefulness and effectiveness of the pro-posed method and system are proven by teleoperation experiments via the internet over a long distance.

关键词： teleoperation internet robots predictive con-trol delay algorithm

来源：评论

学校读者我要写书评

暂无评论

Design and Practice of Flipping Classroom under Blended Learning

Design and Practice of Flipping Classroom under Blended Lear...

引用

International Conference on Information Systems and Computer Aided Education (ICISCAE)

作者： Yang Lanjuan Wang Jinshuang Chen Ping Pan Lin Zhao Min Command and Control Engineering College Army Engineering University Nanjing Jiangsu

ISBN: (数字)9781728183046

ISBN: (纸本)9781728194608

Be aimed at the characteristics of the course of Applied Cryptography and the existing problems in teaching, this paper puts forward the application of blended flipped classroom mode in the course to improve teaching, combines the advantages of online learning and offline learning, carries out the curriculum design, and states the core of “blended flipped classroom” from the aspects of teaching process, the role of teachers and students, and the design of learning resources The model is applied in the actual classroom teaching, and the teaching effect and significance of the model are tested.

关键词： Technological innovation Education Online services Cryptography Task analysis Programming profession Information systems

来源：评论

学校读者我要写书评

暂无评论

QMPS: Q-learning based Message Prioritizing and Scheduling Algorithm for Flying Ad hoc Networks

QMPS: Q-learning based Message Prioritizing and Scheduling A...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Jun Li Ming Chen Command & Control Engineering College Army Engineering University Nanjing China

ISBN: (数字)9781728189543

ISBN: (纸本)9781728189550

Flying ad hoc networks have become increasingly important in civilian applications, organized by several autonomous, small, and low-cost drones. Flying ad hoc networks often suffer from the degradation of performance or lost control of UAV node, caused by unexpected increased delay or packet loss of messages. So message scheduling is important to guarantee reliability and performance of flying ad hoc networks. We propose a novel message scheduling algorithm that provides reliable transmission of messages, named Q-learning based message prioritizing and scheduling algorithm (QMPS). First, we classify messages in the flying ad hoc network into two classes: delay-sensitive messages and delay-tolerant messages. Secondly, we design a new reward function based on the message metric and wireless link quality metric. Then, we use a Q-learning algorithm to assign different priorities to messages and then schedule them. Simulation results indicate that our proposed QMPS algorithm can improve flying ad hoc networks' performance under highly dynamic topology.

关键词： Wireless communication Schedules Scheduling algorithms Heuristic algorithms Simulation Dynamic scheduling Ad hoc 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：