检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Hou, Ruibing Ma, Bingpeng Chang, Hong Gu, Xinqian Shan, Shiguang Chen, Xilin Institute of Computing Technology CAS Beijing100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing100049 China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai200031 China

Video person re-identification (re-ID) plays an important role in surveillance video analysis. However, the performance of video re-ID degenerates severely under partial occlusion. In this paper, we propose a novel network, called Spatio-Temporal Completion network (STCnet), to explicitly handle partial occlusion problem. Different from most previous works that discard the occluded frames, STCnet can recover the appearance of the occluded parts. For one thing, the spatial structure of a pedestrian frame can be used to predict the occluded body parts from the unoccluded body parts of this frame. For another, the temporal patterns of pedestrian sequence provide important clues to generate the contents of occluded parts. With the spatio-temporal information, STCnet can recover the appearance for the occluded parts, which can be leveraged with those unoccluded parts for more accurate video re-ID. By combining a re- ID network with STCnet, a video re-ID framework robust to partial occlusion (VRSTC) is proposed. Experiments on three challenging video re-ID databases demonstrate that the proposed approach outperforms the state-of-the-art approaches. Copyright © 2019, The Authors. All rights reserved.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

Time-varying formation control and disturbance rejection for UAV-UGV heterogeneous swarm system

引用

Hangkong Xuebao/Acta Aeronautica et Astronautica Sinica 2020年 41卷

作者： Zhou, Siquan Dong, Xiwang Li, Qingdong Ren, Zhang School of Automation Science and Electrical Engineering Beihang University Beijing100083 China Science and Technology on Aircraft Control Laboratory Beihang University Beijing100083 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China

This paper studies the time-varying formation control and disturbance rejection problems for heterogeneous UAV-UGV swarm system. The UAV-UGV swarm system is designed to achieve the desired time-varying output formation under unknown external disturbances. First, the kinetic and dynamic mathematical models of each UAV/UGV are established. In addition, the cooperative control models for heterogeneous swarm system are constructed by using the algebraic graph theory. Then, a distributed time-varying output formation controller is designed based on the internal model theory. The distributed formation center estimator and disturbance rejection compensator are designed and added to the formation controller. Third, an algorithm is presented to design the formation control parameters, where the feasibility conditions for achieving the time-varying output formation are given. The stability of the closed-loop UAV-UGV swarm system is proved. Finally, a simulation example is provided to demonstrate the effectiveness of the proposed formation control approach. © 2020, Beihang University Aerospace Knowledge Press. All right reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Application of Cognitive Changes Markers for Diagnostics’ Purposes and in Neurofeedback Therapy

引用

IFAC-PapersOnLine 2019年第27期52卷 520-523页

作者： Magda Zolubak Mariusz Pelc Michal Podpora Wojciech Chlewicki Katarzyna Cichon Aleksandra Kawala-Sterniuk Opole University of Technology - Faculty of Electrical Engineering Automatic Control and Informatics ul. Proszkowska 76 45-758 Opole Poland West Pomeranian University of Technology in Szczecin - Faculty of Electrical Engineering ul. Sikorskiego 37 70-313 Szczecin Poland University of Greenwich - Department of Computing and Information Systems - Faculty of Architecture Computing and Humanities Old Royal Naval College Park Row SE10 9LS London UK

Thanks to the automation of diagnostic processes based on the EEG signal and the creation of classifications of various attention disorders based on the analysis of the EEG signals (as diagnostic markers) - it may be possible to refer patients to appropriate specialists and provide them with appropriate neurofeedback-based treatment. The marker method proposed by the authors of the hereof paper is based on analysis of the EEG, which signal can be widely use in screening diagnostics. The proposed solution in this work may be used for neurofeedback or Brain Computer Interfaces (BCI). In this paper the authors presented implementation of markers for the purpose of analysis of some memory disorders and short-time attention disorder. The study is still in progress. Presented results have initial-study character.

关键词： EEG neurofeedback BCI algoritms

来源：评论

学校读者我要写书评

暂无评论

The Prediction of the Epidemic Trend of COVID-19 Using Neural Networks

引用

IFAC-PapersOnLine 2020年第5期53卷 857-862页

作者： Jing Yang Zhen Shen Xisong Dong Xiuqin Shang Wei Li Gang Xiong J. Yang is with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with College of Information Sciences & Technology Beijing University of Chemical Technology Beijing 100029 China. Z. Shen is with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with the Intelligent Manufacturing Center Qingdao Academy of Intelligent Industries Qingdao Shandong 266113 China. X. Dong X. Shang and W. Li are with the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China. G. Xiong is with Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China and also with the Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Dongguan Guangdong 523808 China.

In this paper, a BP neural network and an LSTM network are applied respectively to the prediction of Coronavirus Disease 2019 (COVID-19) in Wuhan, China and South Korea. The methods do not require specific theories of modelling and the predicted values can be obtained as long as the conventional parameters are set. The mean absolute percentage error (MAPE) of all the experiments are below 5% and the values of the determinable coefficient R are all larger than 0.9. The experiments show that the models can fit the actual values well and make relatively accurate predictions. As of March 29, 2020, the cumulative number of confirmed cases in Wuhan is expected to reach 50,068 using BP neural networks and 49,972 using LSTM network, respectively. As of April 13, 2020, the cumulative number of confirmed cases in South Korea is expected to reach 8,862 using BP neural networks and 8,716 using LSTM network, respectively. The models of neural networks are effective in predicting the trend of the COVID-19 epidemic, which is meaningful to prevent and control the epidemic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convergence of message-passing for distributed convex optimisation with scaled diagonal dominance

arXiv

引用

arXiv 2019年

作者： Zhang, Zhaorong Fu, Minyue School of Electrical Engineering and Computing University of Newcastle. University Drive CallaghanNSW2308 Australia School of Automation Guangdong University of Technology Guangdong Key Laboratory of Intelligent Decision and Cooperative Control Guangzhou510006 China

This paper studies the convergence properties the well-known message-passing algorithm for convex optimisation. Under the assumption of pairwise separability and scaled diagonal dominance, asymptotic convergence is established and a simple bound for the convergence rate is provided for message-passing. In comparison with previous results, our results do not require the given convex program to have known convex pairwise components and that our bound for the convergence rate is tighter and simpler. When specialised to quadratic optimisation, we generalise known results by providing a very simple bound for the convergence rate. Copyright © 2019, The Authors. All rights reserved.

关键词： Belief propagation

来源：评论

学校读者我要写书评

暂无评论

Risk-Aware control and Games in engineering

Risk-Aware Control and Games in Engineering

引用

IEEE Conference on Decision and control

作者： Julian Barreiro-Gomez Hamidou Tembine Leonardo Stella Dario Bauso Patrizio Colaneri Learning & Game Theory Laboratory (L&G-Lab) and Center on Stability Instability and Turbulence (SITE) New York University Abu Dhabi (NYUAD) United Arab Emirates Faculty of Electronics Computing and Mathematics University of Derby United Kingdom Jan C. Willems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen The Netherlands Università di Palermo Italy Politecnico di Milano Italy

ISBN: (数字)9781728174471

ISBN: (纸本)9781728174488

We present a brief tutorial on risk-aware control and game theory applied to engineering problems by solving a backward-forward partial-integro differential system composed of the Hamilton-Jacobi-Bellman and Fokker-Planck coupled equations. First, we discuss about the role that risk terms play in the engineering field. Then, both the risk-aware control and game problems are stated and the computation of the corresponding solutions is presented. We mainly focus on a basic propagation regulation of the coronavirus disease by using mean-field-type control. Hence, we discuss other engineering applications that can be addressed by using the same riskaware perspective. Among such applications, we discuss about the electric vehicles, and the bio-inspired collective decision-making.

关键词： Games Game theory Economics COVID-19 Mathematical model Standards Statistics

来源：评论

学校读者我要写书评

暂无评论

An Adaptive control Method for Arterial Signal Coordination Based on Deep Reinforcement Learning*

An Adaptive Control Method for Arterial Signal Coordination ...

引用

International Conference on Intelligent Transportation

作者： Peng Chen Zemao Zhu Guangquan Lu Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Hai Dian District Beijing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Hai Dian District Beijing

ISBN: (纸本)9781538670255

Traffic signal control is a complex problem and it is difficult to determine an optimal strategy to control multi-directional traffic at multiple intersections. Recent years have witnessed numerous successes of deep learning neural networks in the fields of artificial intelligence. Motivated by the dominant performance of neural networks, this study attempts to develop a novel adaptive signal control approach by fusing deep learning (DL) and reinforcement learning (RL), i.e., deep reinforcement learning (DRL), for arterial signal coordination. DRL can considerably improve the ability to deal with large amounts of data processing, systematic perception and expression, which is key to coordinated control of arterial intersections. The proposed algorithm is implemented by utilizing real-time traffic detection data and aims to optimize the hybrid global and local reward functions. The experimental results obtained by traffic simulation software SUMO demonstrate the advantage of the proposed approach, as well as its efficiency and effectiveness compared with fixed-time and actual signal control methods.

关键词： Aerospace electronics Machine learning Adaptive control Traffic control Roads Optimization

来源：评论

学校读者我要写书评

暂无评论

Behavioural Approach to Network Anomaly Detection for Resource-Constrained System – Presentation of the Novel Solution – Preliminary Study

引用

IFAC-PapersOnLine 2019年第27期52卷 121-126页

作者： Mariusz Pelc Dawid Galus Magda Zolubak Stepan Ozana Wojciech Chlewicki Katarzyna Cichon Michal Podpora Aleksandra Kawala-Sterniuk Opole University of Technology – Faculty of Electrical Engineering Automatic Control and Informatics ul. Proszkowska 76 45-758 Opole Poland University of Greenwich – Department of Computing and Information Systems – Faculty of Architecture Computing and Humanities Old Royal Naval College Park Row SE10 9LS London UK VSB – Technical University Ostrava – FEECS Department of Cybernetics and Biomedical Engineering Ostrava Czech Republic West Pomeranian University of Technology in Szczecin – Faculty of Electrical Engineering ul. Sikorskiego 37 70-313 Szczecin Poland

In this paper some preliminary results of network anomaly detection for resource-constrained systems have been presented. All described algorithms are embedded into a three-tier system application. The presented solution is a response to nowadays trends in computer/network security domain that indicate gradual shifting from signature-based anomaly detection typically based on some selected statistical measures toward systems that are based on behavioural analysis of computer systems and/or networks. The presented system requirements, explain relevant terminology as well as we include some selected results and their analysis. The solution is potentially destined for very resource-constrained systems (IoT specifically), all tests were carried out in an example network to additionally analyse their effect of the presented approach on the computer resources.

关键词： Network Anomaly Detection Behavioural Analysis Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Entanglement swapping for Bell states and Greenberger-Horne-Zeilinger states in qubit systems

arXiv

引用

arXiv 2019年

作者： Ji, Zhaoxu Fan, Peiru Zhang, Huanguo Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan430072 China China Industrial Control Systems Cyber Emergency Response Team Beijing100040 China

We introduce a class of two-level multi-particle Greenberger-Horne-Zeilinger (GHZ) states, and study entanglement swapping between two systems for Bell states and the class of GHZ states in qubit systems, respectively. We give the formulas for the entanglement swapping of Bell states and GHZ states in any number of qubit systems. We further consider entanglement swapping between any number of Bell states and between any number of the introduced GHZ states, and propose a series of entanglement swapping schemes in a detailed way. We illustrate the applications of such schemes in quantum information processing by proposing quantum protocols for quantum key distribution, quantum secret sharing and quantum private comparison. Copyright © 2019, The Authors. All rights reserved.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

A synchronization method for local applications of EtherCAT master-slave in open CNC system

A synchronization method for local applications of EtherCAT ...

引用

2018 IEEE International Conference on Information and Automation, ICIA 2018

作者： Li, Beibei Lin, Hu Sun, Shujie Zheng, Liaomo School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang Liaoning Province China School of Electromechanical and Automotive Engineering Yantai University Yantai Shandong Province China

ISBN: (纸本)9781538680698

A synchronization method for local applications of EtherCAT master-slave is proposed in this paper. Firstly, initial shift time is defined according to the communication structure of EtherCAT master-slave in open CNC system. Then, the initial shift time and clock rate ratio between master clock and reference clock is calculated for initialization of SYNC0 signal. After that, master's cycle remaining time is defined for adjusting the master cycle time. Finally, reference shift time and measuring shift time is defined and calculated. The time difference of them is used as the basis for compensating the cycle remaining time. The master's cycle time is adjusted by compensating the cycle remaining time and the synchronization of local applications of EtherCAT master-slave is realized by adjusting the master's cycle. Experimental results showed that good synchronization effect of local applications of EtherCAT master-slave can be achieved in open CNC system. © 2018 IEEE.

关键词： Synchronization

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：