检索结果-内蒙古大学图书馆

IEEE/CAA Journal of Automatica Sinica 2017年第1期4卷 1-5页

作者： Fei-Yue Wang Jie Zhang Qinglai Wei Xinhu Zheng Li Li IEEE State Key Laboratory of Management and Control for Complex Systems(SKL-MCCS) Institute of AutomationChinese Academy of Sciences(CASIA) School of Computer and Control Engineering University of Chinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences(SKL-MCCSCASIA) Qingdao Academy of Intelligent Industries Department of Computer Science and Engineering University of Minnesota Department of Automation Tsinghua University

Deep reinforcement learning is a focus research area in artificial intelligence. The principle of optimality in dynamic programming is a key to the success of reinforcement learning methods. The principle of adaptive dynamic programming ADP is first presented instead of direct dynamic programming DP , and the inherent relationship between ADP and deep reinforcement learning is developed. Next, analytics intelligence, as the necessary requirement, for the real reinforcement learning, is discussed. Finally, the principle of the parallel dynamic programming, which integrates dynamic programming and analytics intelligence, is presented as the future computational intelligence. © 2014 Chinese Association of automation.

关键词： Artificial intelligence Neural networks Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Ensemble of Extreme Learning Machines for Regression

Ensemble of Extreme Learning Machines for Regression

引用

Data Driven control and Learning systems (DDCLS)

作者： Atmane Khellal Hongbin Ma Qing Fei School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology China

ISBN: (纸本)9781538626191

Regression, as a particular task of machine learning, performs a vital part in data-driven modeling, by finding the connections between the system state variables without any explicit knowledge about the system, using a collection of input-output data. To enhance the prediction performance and maximize the training speed, we propose a fully learnable ensemble of Extreme Learning Machines (ELMs) for regression. The developed approach learns the combination of different individual models, using the ELM algorithm, which is applied to minimize both the prediction error and the norm of the network parameters, which leads to higher generalization performance under Bartlett's theory. Moreover, the average based ELM ensemble may be viewed as a particular case of our model. Extensive experiments on many standard regression benchmark datasets have been carried out, and comparison with different models has been performed. The experimental findings confirm that the proposed ensemble can reach competitive results in term of the generalization performance, and the training speed. Furthermore, the influence of different hyper parameters on the performance, in term of the prediction error and the training speed, of the developed model has been investigated to provide a meaningful guideline to practical applications.

关键词： Computational modeling Training Mathematical model Predictive models Neural networks Prediction algorithms Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Leader-Following Consensus of Multi-Agent systems with Dynamic Leader and Measurement Noises 36

Leader-Following Consensus of Multi-Agent Systems with Dynam...

引用

第36届中国控制会议

作者： Yunpeng Wang Yunchun Xie Long Cheng Beijing Institute of Control Engineering Science and Technology on Space Intelligent Control Laboratory State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781538629185

This paper studies a leader-following consensus problem of multi-agent systems with a dynamic *** is assumed that the leader moves along a polynomial trajectory with respect to time,while followers have first-order integral *** follower is equipped with the positioning system and ranger finder sensor to measure its own position and the relative positions with its *** measured information is corrupted by measurement *** first study a specials case of leader-following consensus problem（tracking problem）,then we extend the results to the general *** is assumed that leader’s velocity is unknown to all *** deal with this challenge,the least square is used to estimate leader’s *** on the estimated velocity and measured information,a consensus protocol is *** is proved that the proposed protocol can solve the mean square leader-following consensus problem under some mild *** simulation examples are also presented to demonstrate the effectiveness of the proposed protocol.

关键词： Leader-Following Consensus Mutli-Agent systems Dynamic Leader Measurement Noise Least Square Method

来源：评论

学校读者我要写书评

暂无评论

Distributed Full Order Sliding Mode control for Finite-time Attitude Synchronization and Tracking of Spacecraft

Distributed Full Order Sliding Mode Control for Finite-time ...

引用

第37届中国控制会议

作者： Nsubuga Latifu Zhuoyue Song Chao Duan Zhen Li Housheng Su Qinghe Wu Xiangdong Liu State Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of Technology Key Laboratory of Drive and Control of Servo Motion System Ministry of Industry and Information Technology School of Automation Huazhong University of Science and Technology

This paper investigates a distributed finite-time attitude synchronization and tracking problem of multiple spacecraft when a time varying reference signal is available to only a subset of group *** Rodrigues parameters are used for attitude representation.A two layer sliding mode surface with fast non-singular terminal sliding mode surface（FNTSMS） as the inner layer and terminal sliding mode surface（TSMS） as the outer layer is used to create a full order sliding mode *** proposed distributed attitude coordination control law guarantees attitude synchronization and tracking as long as their exists atleast one spacecraft that has a direct access to the virtual leader’s time varying ***-time stability of the closed loop system is guaranteed by Lyapunov-based stability *** results are presented to validate the performance of the proposed control strategy.

关键词： Attitude synchronization Attitude tracking Finite-time Full-order sliding mode（FOSM） Distributed control

来源：评论

学校读者我要写书评

暂无评论

A four-stage localization method for epileptic seizure onset zones

引用

IFAC-PapersOnLine 2017年第1期50卷 4412-4417页

作者： Wan T. Wu M. Lai X. Wan X. She J. Du Y. School of Automation China University of Geosciences Wuhan Hubei 430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan Hubei 430074 China School of Engineering Tokyo University of Technology Hachioji Tokyo 192-0982 Japan School of Automation Guangdong University of Technology Guangzhou Guangdong 510006 China

This paper presents a four-stage localization method for epileptic seizure onset zones (SOZs). This method combines the advantages of both the Shannon-entropy-based complex Morlet wavelet transform (SE-CMWT) and adaptive-genetic-algorithm-based matching pursuit (AGA-MP) methods to achieve satisfactory localization performance. The Hilbert transform method is used to identify events of interest. The SE-CMWT-based power spectral density method is applied to acquire channels of interest (CoIs). By using the Morlet wavelets as the dictionary elements, the AGA-MP method combined with Morlet wavelets is developed to detect high-frequency oscillations (HFOs) on CoIs with faster speed and higher accuracy than the AGA-MP method. And the characteristics of HFOs are used to localize SOZs based on the half-maximum method. A comparison shows that our method has higher sensitivity and specificity than four existing methods. © 2017

关键词： Epilepsy Four-stage localization method High-frequency oscillation (HFO) Seizure onset zone (SOZ)

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of RFID based Smart Shopping Booth

Design and Implementation of RFID based Smart Shopping Booth

引用

International Conference on Information Science and control Engineering (ICISCE)

作者： Ehtisham Lodhi Fenghua Zhu Zeeshan Lodhi Qasim Saleem Gang Xiong FeiYue Wang The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of Sciences Beijing China Department of Electrical and Computer Engineering COMSATS University Islamabad Pakistan School of Automation Science and Electrical Engineering Beihang University Beijing China The Cloud Computing Center Chinese Academy of Sciences Dongguan China Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728157122

ISBN: (纸本)9781728157139

In this modern era, technology has advanced to such an extent to make our daily life more proficient and convenient. This paper presents the design and implementation of vending machine (VM) for students, which operates on radio frequency identification technology (RFID). Hence, it turns the VM into smart shopping booth (SSB). The SSB gives the access only through RFID card and vend different products according to the desire of student. The SSB is equipped with RFID reader and student identity card that holds the RFID tag. When the student identity card is scanned for verification and then after selecting the required products, will be dispensed off if a student has available balance in his/her identity card and SMS will be sent to students about remaining balance in their cards by GSM technology. The programming for controller is done by using proton IDE language. The SSB is the customized idea of vending machine and it attempts to resolve various issues that appeared in coin/note based VM. The student identity card RFID based technology is a breakthrough towards a paperless and cashless environment. Moreover, it is very beneficial in saving the precious time of students due to fast paced life and also user friendly. RFID based SSB also improved the communication and sensing capabilities of VM. Hence, our suggested approach outperforms in all aspects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Relation Model of Burden Operation and State Variables of Blast Furnace Based on Low Frequency Feature Extraction*

引用

IFAC-PapersOnLine 2017年第1期50卷 13796-13801页

作者： Zhang, Kexin Wu, Min An, Jianqi Cao, Weihua Liu, Zhentao Ning, Fulong School of Automation China University of Geosciences Wuhan430074 China Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Faculty of Engineering China University of Geosciences wuhan430074 China Department of Computer Science School of Computing Tokyo Institute of Technology Yokohama226-8502 Japan

In the blast furnace ironmaking process, the running state of the blast furnace can be directly adjusted by the burden operation. Therefore, the explicit relation between the burden operation and the running state variables is vital for the blast furnace operators. However, the state variables of the blast furnace are affected by many factors and the burden matrix is complicated. In this paper, a support vector regression(SVR) predicting model based on low frequency feature extraction is proposed to solve these problems. First, the low frequency components of state variables time series which are mostly affected by the burden operation are extracted. Then, the dimensions of the burden matrix are reduced by a devised simple expression method. Finally, the relation model based on SVR is proposed to predict the values of the expected state variables according to the simplified burden matrix and the value of initial state variables. The simulation on real factory data indicates that the model reflects the accurate quantitative relation between the burden operation and the state variables. © 2017

关键词： Blast furnaces Blast furnace practice Extraction Feature extraction Support vector regression Blast furnace iron making Blast furnace operators burden operation Initial state variables Low frequency components Relation models State variables Support vector regression (SVR)

来源：评论

学校读者我要写书评

暂无评论

Coalition formation based on a task-oriented collaborative ability vector

引用

Frontiers of Information Technology & Electronic Engineering 2017年第1期18卷 139-148页

作者： Hao FANG Shao-lei LU Jie CHEN Wen-jie CHEN School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems

Coalition formation is an important coordination problem in multi-agent systems, and a proper description of collaborative abilities for agents is the basic and key precondition in handling this problem. In this paper, a model of task-oriented collaborative abilities is established, where five task-oriented abilities are extracted to form a collaborative ability vector. A task demand vector is also described. In addition, a method of coalition formation with stochastic mechanism is proposed to reduce excessive competitions. An artificial intelligent algorithm is proposed to compensate for the difference between the expected and actual task requirements, which could improve the cognitive capabilities of agents for human commands. Simulations show the effectiveness of the proposed model and the distributed artificial intelligent algorithm.

关键词： Collaborative vector Task allocation Multi-agent system Coalition formation Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Event-Trigger Extended Kalman Filter Design for Distributed Generation Network with Limited Communication 36

Event-Trigger Extended Kalman Filter Design for Distributed ...

引用

第36届中国控制会议

作者： Xing Xin Luyu Li Sen Li Zhen Li Jian Li Zhen Chen Xiangdong Liu Beijing Institute of Electronic System Engineering School of Automation & Key Laboratory for Intelligent Control & Decision on Complex Systems Beijing Institute of Technology

ISBN: (纸本)9781538629185

For distributed generation(DG) network, it is important to estimate the real-time states. The information-centric networking(ICN) is established to take charge of the communication of DG network. However, the assumption of ideal communication between sensors and the estimation center cannot be guaranteed due to the communication constraints of ICN with the increasing DG network. A conventional algorithm, which reduces the communication burden in ICN, is to drop the observation of each smart grid in a random way. However, the accuracy of this algorithm recession decays rapidly with the increasing drop rate. To guarantee an appropriate estimation accuracy when the drop rate increases, this paper introduces the event-trigger strategy into the estimation algorithm. An event-trigger extended kalman filter(ET-EKF) is established in this paper to adapt the nonlinearity of DG system. ET-EKF reduces the communication burden and achieves an appropriate estimation accuracy at the same time. Finally, its feasibility and performance are demonstrated using the standard IEEE 39-bus system with phasor measurement units(PMUs).

关键词： Event-trigger extended Kalman filter(ET-EKF) real-time estimation distributed generation network smart grids phasor measurement unit(PMU)

来源：评论

学校读者我要写书评

暂无评论

A NSGA-II based Peak Load Shifting Optimization Method for Customers with Distributed Generators Considering Time-of-use Price

A NSGA-II based Peak Load Shifting Optimization Method for C...

引用

Chinese control Conference

作者： Hao Zhou Min Ding Bo Hu Qingyi Wang Zhili Tan Danyun Li Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex System Wuhan P. R. China Global Energy Interconnection Development and Cooperation Organization Beijing P. R. China

With the extensive use of distributed generation, the traditional demand response analysis cannot meet the current requirements. This paper proposes a NSGA-II based peak load shifting optimization method for customers with distributed generators considering time-of-use price. Firstly, a fuzzy classification method divides the daily power into three time segments, peak hours, flat hours and valley hours. Secondly, on the basis of the time-of-use price, a peak load shifting optimization model is built with constraints and the objectives of minimizing the peak load, maximizing the valley load, and minimizing the peak-valley difference. Then, a NSGA-II based optimization method solves the optimal model and obtains the optimal electricity prices of different time segments to shift the peak load and the valley load. Finally, the simulation results shows the effectiveness of the proposed method.

关键词： Load management Load modeling Real-time systems Mathematical model Distributed power generation Optimization Heuristic algorithms

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：