检索结果-内蒙古大学图书馆

Chinese control Conference (CCC)

作者： Changhui Hu Xiaobo Lu Yijun Du Key Laboratory of Measurement and Control of Complex System of Engineering Southeast University Nanjing China

In this paper, an adaptive approximation image reconstruction method based on orthogonal triangular with column pivoting (QRCP) decomposition algorithm is proposed for single sample problem in face recognition. By using QRCP the single sample and its transpose are decomposed to two sets of basis images. Then an adaptive approximation image reconstruction method is proposed to reconstruct two approximation images from the two basis image sets respectively. The single training sample and its two approximation images of each object form a new training set, which can make the fisher linear discriminant analysis (FLDA) be applied to single sample problem in face recognition. The performance of the proposed method is verified on Yale, FERET, and ORL face databases. The experimental results indicate that the proposed method is efficient and outperforms some existing methods which are proposed to overcome the single sample problem.

关键词： Face recognition Databases Face Training Approximation methods Image reconstruction Image recognition

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of the Knowledge Base for Battlefield Task Management system 33

Design and Implementation of the Knowledge Base for Battlefi...

引用

第三十三届中国控制会议

作者： Zhang Jia Wang Xiang School of Automation Beijing Institute of Technology Key Laboratory of Complex System Intelligent Control and Decision (Beijing Institute of Technology) Ministry of Education

ISBN: (纸本)9781479947249

In order to reduce the operators on the battlefield, and obtain adequate knowledge and improve reaction speed to enhance combat efficiency, the paper builds a knowledge base of battlefield mission management system to manage a variety of required knowledge on the battlefield and supervise each mission profile. Knowledge is presented by production method and is reasoned by forward reasoning method. According to different levels of battlefield tasks, task links are used to organize knowledge. Take combat preparation mission profile as an example, we design every data sheet of the knowledge base. The knowledge base of the battlefield management system could enhance the reusability, sharing and timeliness of knowledge on the battlefield.

关键词： Battlefield Task Management Knowledge Base Task Links Mission Profile

来源：评论

学校读者我要写书评

暂无评论

A Positioning Algorithm of Autonomous Car Based on Map-matching and Environmental Perception 33

A Positioning Algorithm of Autonomous Car Based on Map-match...

引用

第三十三届中国控制会议

作者： XU Qian WANG Meiling DU Zhifang ZHANG Yi School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex System Chongqing Jialing Huaguang Photoelectric Technology Co.Ltd.

ISBN: (纸本)9789881563842

Autonomous car is an important tool for transportation and military in the future,and its precise positioning is the basis of autonomous *** positioning algorithms based on map-matching for autonomous car make little use of environmental perception *** solve this problem,a positioning algorithm is proposed in this paper,which is based on map-matching and environmental perception for autonomous *** algorithm includes macroscopic road matching and microscopic precise *** for macroscopic road matching,the algorithm makes use of computational geometry to match the position of autonomous car to the corresponding road,based on GPS point and map information of the road *** for microscopic precise positioning,the algorithm makes use of the environmental perception,which is detected by the autonomous car to make precise *** road matching provides matching road to microscopic precise positioning,and microscopic precise positioning eliminates gross error produced in macroscopic road *** real car tests,the algorithm can match map quickly,improving the positioning precision with strong real-time.

关键词： Autonomous car,Map-matching,Environmental perception,Computational geometry

来源：评论

学校读者我要写书评

暂无评论

Decentralized control for power systems components based-on nonlinear differential-algebraic equations subsystem model

Communications in Computer and Information Science

引用

Communications in Computer and Information Science 2014年 462卷 397-406页

作者： Zang, Qiang Zhou, Ying Mei, Ping Zheng, Baichao Zhang, Kaifeng School of Information and Control Engineering Nanjing University of Information Science & Technology Nanjing210044 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China College of Automation Nanjing University of Posts and Telecommunications Nanjing210003 China

ISBN: (纸本)9783662452608

Components of power systems essentially belong to a special class of nonlinear differential-algebraic equations subsystem, whose index is one and interconnection is locally measurable. In this paper, the decentralized control problem is discussed using inverse systems method for such class of power systems components. Firstly, the definition of α -order integral right inverse system is presented. Secondly, a recursive algorithm is proposed to judge whether the controlled component is invertible. Then a physically feasible α -order integral right inverse system is constructed with which the controlled component is made linearization and decoupled, so that linear control theory and methods can be applied. Finally, a decentralized excitation controller is designed for one synchronous generator within multi-machine power systems based on the proposed method in this *** simulation results demonstrate the effectiveness of the proposed control scheme. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Decentralized control

来源：评论

学校读者我要写书评

暂无评论

High-level spatial modeling in convolutional neural network with application to pedestrian detection

High-level spatial modeling in convolutional neural network ...

引用

Canadian Conference on Electrical and Computer Engineering (CCECE)

作者： Feng Liu Yongzhen Huang Wankou Yang Changyin Sun School of Automation. Southeast University Nanjing China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China Key Lab of Child Development and Learning Science of Ministry of Education. Southeast University Nanjing China

ISBN: (纸本)9781479958306

Convolutional neural network (CNN) has achieved great success in many vision tasks. A key to this success is its ability to powerful automatically learns both high-level and low-level features. In general, low-level features have a small size of receptive fields and appear multiple times in different locations of objects, while high-level semantic features have a relatively large size of receptive fields and only appear once in a specific location of objects. However, traditional CNN treats these two kinds of features in the same manner, i.e., learning them by the convolution operation, which can be approximately considered as cumulating the probabilities that a feature appears in different locations. This strategy is reasonable for low-level features but not for high-level semantic ones, especially in the case of pedestrian detection, where a local feature can be shared by different locations but a semantic part, e.g., a head, only appears once for a human. To jointly model the spatial structure and appearance of high-level semantic features, we propose a new module to learn spatially weighted max pooling in CNN. The proposed method is evaluated on several pedestrian detection databases and the experimental results show that it achieves much better performance than traditional CNN.

关键词： Convolution Semantics Kernel Deformable models Computational modeling Feature extraction Training

来源：评论

学校读者我要写书评

暂无评论

Linguistic dynamic analysis for single lane's traffic status based on FCM

Linguistic dynamic analysis for single lane's traffic status...

引用

2014 International Conference on Informative and Cybernetics for Computational Social systems, ICCSS 2014

作者： Jie, Wang Hong, Mo Fenghua, Zhu College of Electrical AndInformation Engineering Changsha University of Science and Technology Changsha China State Key Laboratory of Management and Control for Complex System Beijing China

ISBN: (纸本)9781479947522

The results of traditional traffic status analysis are mostly single values, whose accuracy can't be determined;fuzzy c-means clustering (FCM) algorithm based on fuzzy theory can calculate the clustering center of plenty data quickly and easily;linguistic dynamic systems could describe the dynamic rules of complex systems in the language level. In this paper, membership functions are decided by FCM;result of a specific time period taken as one example is obtained;it's discussed that linguistic dynamic analysis of traffic status in different period within a day by the same method. © 2014 IEEE.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

Global decentralized stabilization for a class of large-scale feedforward nonlinear systems

Global decentralized stabilization for a class of large-scal...

引用

American control Conference

作者： Qixun Lan Chuanlin Zhang Shihua Li Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing 210096 P. R. China College of Automation Engineering Shanghai University of Electric Power Shanghai 200090 P.R. China School of Automation Southeast University Nanjing 210096 P. R. China

ISBN: (纸本)9781479917730

This paper considers the problem of global decentralized stabilization for a class of large-scale feedforward nonlinear systems. First, by using generalized homogeneous systems theory, a local linear decentralized control law is recursively constructed. Second, a series of nested saturation functions are integrated with the proposed local linear control law to render the whole closed-loop large-scale system global asymptotical stability. Due to the flexibility of the generalized homogeneous systems theory, the proposed approach not only weakens the existing restrictions imposed on the interconnected nonlinearities, but also can be applied to more general classes of large-scale feedforward nonlinear systems. Numerical example shows that the effectiveness of the proposed control scheme.

关键词： Decentralized control Feedforward neural networks Nonlinear systems Closed loop systems Lyapunov methods Asymptotic stability Feedforward systems

来源：评论

学校读者我要写书评

暂无评论

Novel Embedded system Design and Implementation for Automatic Platelet Aggregometer 33

Novel Embedded System Design and Implementation for Automati...

引用

第三十三届中国控制会议

作者： JU Ben MA Xudong FANG Fang XU Xin DONG Ziquan SINNOWA Medical Science & Technology Co. LTD School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University

ISBN: (纸本)9781479947249

The platelet aggregation function analysis is applied in clinical research and application more and more *** this paper,an automatic double-channel platelet analysis system PL12 is designed and *** system framework is based on embedded processor ARM and DSP architecture,in which a signal modulation circuit is *** an analog to digital conversion scheme is proposed and realized for measuring weak pulse signals of blood *** principle of control system and management software is also *** validate the high efficiency,precision and stability of the system.

关键词： double-channel,platelet aggregation,signal acquisition,embedded systems

来源：评论

学校读者我要写书评

暂无评论

In vitro corrosion of Mg–1.21Li–1.12Ca–1Y alloy

引用

Progress in Natural Science:Materials International 2014年第5期24卷 492-499页

作者： Rongchang Zeng Weichen Qi Fen Zhang Hongzhi Cui Yufeng Zheng College of Materials Science and Engineering Shandong University of Science and Technology State Key Laboratory of Mining Disaster Prevention and Control Co-founded by Shandong Province and the Ministry of Science and Technology Shandong University of Science and Technology State Key Laboratory for Turbulence and Complex System Department of Materials Science and Engineering College of EngineeringPeking University

The influence of the microstructure on mechanical properties and corrosion behavior of the Mg–1.21Li–1.12Ca–1Y alloy was investigated using OM, SEM, XRD, EPMA, EDS, tensile tests and corrosion measurements. The results demonstrated that the microstructure of the Mg–1.21Li–1.12Ca–1Y alloy was characterized by α-Mg substrate and intermetallic compounds Mg2 Ca and Mg24Y5. Most of the fine Mg2 Ca particles for the as-cast alloy were distributed along the grain boundaries, while for the as-extruded along the extrusion direction. The Mg24Y5 particles with a larger size than the Mg2 Ca particles were positioned inside the grains. The mechanical properties of Mg–1.21Li–1.12Ca–1Y alloy were improved by the grain refinement and dispersion strengthening. Corrosion pits initiated at the α-Mg matrix neighboring the Mg2 Ca particles and subsequently the alloy exhibited general corrosion and filiform corrosion as the corrosion product layer of Mg(OH)2and Mg CO3 became compact and thick.

关键词： Magnesium–lithium alloys Microstructure Mechanical property Corrosion Biomaterial

来源：评论

学校读者我要写书评

暂无评论

Mars Entry Trajectory Tracking Via Constrained Multi-Model Predictive control 33

Mars Entry Trajectory Tracking Via Constrained Multi-Model P...

引用

第三十三届中国控制会议

作者： WU Chao LI Shihua YANG Jun GUO Lei School of Automation Southeast University & Key Laboratory of Measurement and Control of Complex Systems of EngineeringMinistry of Education School of Automation Science and Electrical Engineering Beihang University & Institute of Instrument Science and Opto-Electronics Engineering

ISBN: (纸本)9781479947249

Tracking law designed for future Mars entry missions is investigated in this article. For precision landing, the nonlinear entry dynamics, complex uncertainties and input saturation constraints are unavoidable problems. Facing these challenges, the Mars entry trajectory tracking scheme via constrained multi-model predictive control(CMPC) is employed. The CMPC is made up of some constrained predictive control(CPC) in different time domain during the Mars entry mission. Each constrained predictive controller consists of a linearized prediction model(obtained by linearizing at different operating point), feedback correction for active model mismatch rejection caused by the complex uncertainties, and constrained rolling optimization for a smooth control input under a saturation constraint. Monte Carlo simulations demonstrate the effectiveness and excellence of the proposed method under the saturation constraint of input and uncertainties of initial state and aerodynamic parameters such as atmospheric density, ballistic coefficient and lift-to-drag ratio.

关键词： Mars Entry,Trajectory Tracking,Constrained Multi-Model Predictive control,Monte Carlo Simulation

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：