检索结果-内蒙古大学图书馆

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

Coalition formation based on a task-oriented collab.rative 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 collab.rative abilities for agents is the basic and key precondition in handling this problem. In this paper, a model of task-oriented collab.rative abilities is established, where five task-oriented abilities are extracted to form a collab.rative 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： Collab.rative 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

Power system state estimation via feasible point pursuit: Algorithms and Cramér-rao bound

Power system state estimation via feasible point pursuit: Al...

引用

作者： Wang, Gang Zamzam, Ahmed S. Giannakis, Georgios B. Sidiropoulos, Nicholas D. State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China Digital Technology Center Department of Electrical and Computer Engineering University of Minnesota MinneapolisMN55455 United States Department of Electrical and Computer Engineering University of Virginia CharlottesvilleVA22904 United States

Accurately monitoring the system's operating point is central to the reliable and economic operation of an autonomous energy grid. Power system state estimation (PSSE) aims to obtain complete voltage magnitude and angle information at each bus given a number of system variables at selected buses and lines. Power flow analysis amounts to solving a set of noise-free power flow equations, and is cast as a special case of PSSE. Physical laws dictate quadratic relationships between availab.e quantities and unknown voltages, rendering general instances of power flow and PSSE nonconvex and NP-hard. Past approaches are largely based on gradient-type iterative procedures or semidefinite relaxation (SDR). Due to nonconvexity, the solution obtained via gradient-type schemes depends on initialization, while SDR methods do not perform as desired in challenging scenarios. This paper puts forth novel feasible point pursuit (FPP)-based solvers for power flow analysis and PSSE, which iteratively seek feasible solutions for a nonconvex quadratically constrained quadratic programming reformulation of the weighted least-squares (WLS). Relative to the prior art, the developed solvers offer superior numerical performance at the cost of higher computational complexity. Furthermore, they converge to a stationary point of the WLS problem. As a baseline for comparing different estimators, the Cramér-Rao lower bound is derived for the fundamental PSSE problem in this paper. Judicious numerical tests on several IEEE benchmark systems showcase markedly improved performance of our FPP-based solvers for both power flow and PSSE tasks over popular WLS-based Gauss-Newton iterations and SDR approaches. © 1991-2012 IEEE.

关键词： state estimation

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Features Comparison Between Back-Propagation and Extreme Learning Machine

Convolutional Neural Network Features Comparison Between Bac...

引用

Chinese control Conference

Recently deep learning based architectures have been widely deployed in many problems of artificial intelligence. Among deep learning models, Convolutional Neural Networks (CNN) have been reported in numerous successful applications such as object recognition, and natural language processing. The convolutional neural networks are trained by back-propagating the classification error using the Back-Propagation (BP) algorithm, which requires a large amount of data and slows the training process. To overcome these difficulties, a new fast and accurate approach based on Extreme Learning Machine (ELM) to train any convolutional neural network has been proposed. The developed framework (ELM-CNN) is based on the concept of auto-encoding to learn the convolutional filters with biases, by reconstructing the normalized input and the intercept term. In this paper, systematic comparison with traditional back-propagation based training method (BP-CNN) has been made with respect to two aspects qualitative and quantitative. The experimental results on the popular MNIST dataset show that the ELM-CNN algorithm achieves competitive results in terms of generalization performance and up to 16 times faster than the back-propagation based training of CNN.

关键词： Training Convolutional neural networks Feature extraction Computer architecture Convolution Machine learning Encoding

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking based on Time-Varying Sliding Mode controller for Hypersonic Vehicle with Aileron Stuck 36

Trajectory Tracking based on Time-Varying Sliding Mode Contr...

引用

第36届中国控制会议

作者： Haibo Ji Lei Wang Zhuoyue Song Xiangdong Liu Zhirong Lei State Key Laboratory of Intelligent Control and Decision of Complex Systems and School of Automation Beijing Institute of Technology School of Automation Northwestern Polytechnical University

ISBN: (纸本)9781538629185

This paper presents nonlinear robust trajectory tracking strategies for the hypersonic vehicle whose ailerons are stuck at an unknown angular position. Firstly, a time-varying sliding mode control strategy for general second-order systems is introduced, and the chattering of sliding mode controller is alleviated. Secondly, the dynamics of hypersonic vehicle are transformed into two second-order systems. Then, the corresponding guidance law and attitude controller are designed using time-varying sliding mode controller. By the proposed strategies, the hypersonic vehicle can fly along the reference ***, the proposed strategies are applied to a hypersonic platform to verify its validity.

关键词： Trajectory Tracking Stuck Aileron Time-Varying Sliding Mode

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric Analysis of Blockchain Research

A Bibliometric Analysis of Blockchain Research

引用

2018 IEEE intelligent Vehicles Symposium, IV 2018

作者： Zeng, Shuai Ni, Xiaochun Yuan, Yong Wang, Fei-Yue State Key Lab for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Qingdao Academy of Intelligent Industries Shandong266000 China Research Center of Military Computational Experiments and Parallel System National University of Defense China

ISBN: (纸本)9781538644522

Taking Ei Compendex (EI) and China National Knowledge Infrastructure (CNKI) databases as the literature sources, this paper presented a bibliographic analysis of the blockchain-related literature between January 2011 and September 2017. For each literature source, we built a separate dataset. Authors' productivity and collab.ration, affiliation of authors and collab.ration amongst institutions were analyzed using techniques of social networks analysis on both datasets. According to the results, the CNKI authors/institutes raised their productivity and outperformed the EI authors/institutes since 2016. However, the EI authors/institutes show a higher level than the CNKI authors/institutes in collab.ration. We also summarized the hot topics on the EI dataset using textual analysis and discovered researchers have shifted their attention from Bitcoin itself to the blockchain technology underlying it. © 2018 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Measurement System of Ferromagnetic Film Magnetic Properties Based on Mazneto-optical Kerr Effect

Measurement System of Ferromagnetic Film Magnetic Properties...

引用

Chinese control Conference (CCC)

作者： Xueying Fu Wenqin Mo Shun Yuan Liming Xu Junlei Song Kaifeng Dong Fang Jin Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan China Hubei key Lab. of Adv. Control & Intell. Autom. for Complex Syst. Wuhan China

A new measuring system for magnetic properties of the ferromagnetic thin film has developed based on magneto-optical Kerr effect (MOKE). This system can realize both polar MOKE and longitudinal MOKE measurements through the optimization of optical path and electromagnet's poles. The signal processing software on lab.View has been also designed to acquire the Kerr signal and plot the hysteresis loop. The MOKE measurements have been performed to investigate the magnetic properties of ferromagnetic films such as CoFeSiB, permalloy and NiFe/Ag/NiFe multilayer. The experimental results proved that the system has a high angular accuracy of 0.0008°.

关键词： Magnetic field measurement Magnetic fields Kerr effect Magnetic hysteresis Optical variables measurement Optical films Biomedical measurement

来源：评论

学校读者我要写书评

暂无评论

A Vision and Neural Network Based Air-Ground Coordinated control System

A Vision and Neural Network Based Air-Ground Coordinated Con...

引用

2017 IEEE International Conference on Unmanned systems (ICUS)

作者： Muyun Jiang Jiahui Shi Hongbin Ma You Li School of Automation Beijing Institute of Technology State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology

ISBN: (纸本)9781538631089;9781538631072

This paper presents an air-ground coordinated system made up of an Unmanned Aerial Vehicle(UAV) and an Unmanned Ground Vehicle(UGV).The movement of UGV is totally controlled by UAV and multiple sensors are adopted in the system to ensure the stability.A novel neutral network algorithm is introduced to identify the location and orientation of *** component is introduced and tested in detail and the coordinated system performs a satisfying result.

关键词： Air-ground system Neutral Network

来源：评论

学校读者我要写书评

暂无评论

Trajectory tracking of under-actuated reentry vehicle based on time-varying SMC with RBF disturbance observer 5

Trajectory tracking of under-actuated reentry vehicle based ...

引用

5th International Workshop on Advanced Computational Intelligence and intelligent Informatics, IWACIII 2017

作者： Ji, Haibo Guo, Fuhui Liu, Xiangdong School of Automation State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing100081 China

In this paper, an effective guidance scheme and a control scheme are proposed to realize trajectory tracking of hypersonic reentry vehicle(HRV) subject to aileron stuck in some position. The overload is adopted as virtual control instead of lift and lateral force, then guidance order can be obtained by torque coefficient function. In attitude subsystem, attack of angle and sideslip angle are controlled to track guidance order. Time-varying sliding mode control method is adopted to design guidance law and attitude controller. Besides, a RBF observer is designed to estimate the unknown external disturbance to soften the chattering caused by TVSMC. Simulations verify the proposed schemes.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Exponential input-to-state stability of stochastic fuzzy delayed Cohen-Grossberg neural networks under impulsive perturbations

Exponential input-to-state stability of stochastic fuzzy del...

引用

第37届中国控制会议

作者： Weisong Zhou Hao Zeng Donghai Wu Key Lab of Intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications Key Laboratory of Industrial Internet of Things and Networked Control Ministry of EducationChongqing University of Posts and Telecommunications

In this paper,we study a class of stochastic fuzzy delayed Cohen-Grossberg neural networks under impulsive *** Razumikhin method and iteration technique,some sufficient conditions ensuring the mean-square exponential input-to-state stability of the designed delayed neural networks are *** results can generalize and improve some earlier publications.A numerical example is demonstrated to verify the theoretical results.

关键词： Impulsive Stochastic Cohen-Grossberg neural networks Exponential input-to-state stability

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：