检索结果-内蒙古大学图书馆

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Jin Hu Zeng-Guang Hou Yi-Xiong Chen Nikola Kasabov Nathan Scott State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Knowledge Engineering and Discovery Research Institute Auckland University of Technology Auckland New Zealand

Repetitive activities of daily living (ADL) and robotic active training are commonly practised in the rehabilitation of paralyzed patients, both of which have been proven rather effective to recover the locomotor function of impaired limbs. ADL classification based on electroencephalogram (EEG) is of great significance to perform active robotic rehabilitation for patients with complete spinal cord injury (SCI) who lose locomotion of affected limbs absolutely, where surface electromyography (sEMG) or active force signal can hardly be detected. It is a challenge to achieve a satisfying result in neuro-rehabilitation robotics using EEG signals due to the high randomness of the EEG data. A classification method is proposed based on spiking neural networks (SNN) to identify the upper-limb ADL of three classes with 14-channel EEG data. The continuous real-number signals are firstly encoded into spike trains through Ben's Spike Algorithm (BSA). The generated spikes are then submitted into a 3-D brain-mapped SNN reservoir called NeuCube trained by Spike Timing Dependant Plasticity (STDP). Spike trains from all neurons of the trained reservoir are finally classified using one version of dynamic evolving spiking neuron networks (deSNN) - deSNNs. Classifications are presented with and without NeuCube respectively on the same EEG data set. Results indicate that using the reservoir improves identification accuracy which turns out pretty promising despite that EEG data is highly noisy, low frequently sampled, and only from 14 channels. The classification technique reveals a great potential for the further implementation of active robotic rehabilitation to the sufferers of complete SCI.

关键词： Neurons Electroencephalography Training Robot kinematics Encoding Reservoirs

来源：评论

学校读者我要写书评

暂无评论

Approximation-error-ADP-based optimal tracking control for chaotic systems with convergence proof

引用

Chinese Physics B 2013年第9期22卷 305-311页

作者：宋睿卓肖文栋孙长银魏庆来 School of Automation and Electrical Engineering University of Science and Technology Beijing The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

In this paper, an optimal tracking control scheme is proposed for a class of discrete-time chaotic systems using the approximation-error-based adaptive dynamic programming （ADP） algorithm. Via the system transformation, the optimal tracking problem is transformed into an optimal regulation problem, and then the novel optimal tracking control method is proposed. It is shown that for the iterative ADP algorithm with finite approximation error, the iterative performance index functions can converge to a finite neighborhood of the greatest lower bound of all performance index functions under some convergence conditions. Two examples are given to demonstrate the validity of the proposed optimal tracking control scheme for chaotic systems.

关键词： chaotic systems approximation error adaptive dynamic programming optimal tracking control

来源：评论

学校读者我要写书评

暂无评论

A user-friendly building energy consumption program

A user-friendly building energy consumption program

引用

2013 International Conference on Precision Mechanical Instruments and Measurement technology, ICPMIMT 2013

作者： Jia, Yi Long Jin, Jian Xiang Zhou, Xuan Hao State Key Laboratory of Industrial Control Technology Institue of Cyber-Systems and Control Zhejiang University Hangzhou China Research Company SUPCON Group Hangzhou China

Building energy simulation program plays an important role in reducing energy consumption for heating in North China. For the past 60 years, a wide range of building energy simulation programs have been developed. However, in China, building energy simulation programs are not popularized smoothly because of the problems such as unfriendly interface, complex usage and excessively specialized. This paper presents a new building energy simulation program with B/S structure. As a collection of building energy simulation and economic analysis, this program can be accepted by the professionals and non-professionals due to its accuracy and easy operation. © 2013 Trans Tech Publications Ltd, Switzerland.

关键词： state space methods

来源：评论

学校读者我要写书评

暂无评论

Analyzing the characteristics of "East Turkistan" activities using text mining and network analysis

引用

Zidonghua Xuebao/Acta Automatica Sinica 2014年第11期40卷 2456-2468页

作者： Fu, Ju-Lei Liu, Wen-Li Zheng, Xiao-Long Fan, Ying Wang, Shou-Yang College of Information System and Management National University of Defense Technology Changsha410073 China Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Management and Control Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China Cloud Computing Industrial Technology Innovation and Incubation Center Chinese Academy of Sciences Dongguan523808 China School of Systems Science Beijing Normal University Beijing100875 China

Open source intelligence, with rich content and sophisticated collection and analytical techniques, is an alternative data source in many anti-terrorism studies and has manifested significant applicable prospects. In this paper, we take the "East Turkistan" separatist activities as the research objects and collect the data from the world wide web by utilizing web crawlers. We adopt text analysis techniques to extract the information of four fundamental elements of "East Turkistan" separatist activities, including person, organization, time and place, and then construct multi-mode networks according to the relations between concepts. To analyze the characteristics of these networks, we first apply the approach of dimensional decomposition to separate the multimode networks into single vertex sub-networks and bipartite sub-networks, distinguish the importances of different types of nodes by measuring the centrality of each sub-network, and synthesize the centrality index of each sub-network to form an importance composite index (ICI). To further identify the core nodes of the four types of nodes in the network, we adopt the k-shell decomposition method to directly decompose the multi-mode network. We find that the results produced by these approaches presented above can be in accord with the actual ones. ©, 2014, Acta Automatica Sinica. All rights reserved.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Influence of the Cylindrical Source Size on Impact Probability Caused by Fragments

引用

Procedia Engineering 2014年 84卷 786-795页

作者： Sun Dongliang Jiang Juncheng Zhang Mingguang Wang Zhirong State Environmental Protection Key Laboratory of Environmental Risk Assessment and Control on Chemical Process School of Resources and Environmental Engineering East China University of Science and Technology Shanghai 200237 China Jiangsu Key Laboratory of Urban and Industrial Safety Institute of Safety Engineering School of Urban Construction and Safety Engineering Nanjing University of Technology Nanjing 210009 China

The movement equations of fragment with the size of the bursting vessel were developed. The ground distributions of fragments, and the probability of impact between the fragments and the target were investigated in consideration of cylindrical source size using Monte-Carlo simulations. The results showed that the distributions of the fragments from the lower half of the source vessels on the ground were larger than 0, it was simply probable that the fragments would hit the target around the source. The relative deviation of impact probability would be larger than 10% when the target vessel was located in the distance less than 8 times of the cylindrical source diameter. The proportion of impact probability of lower part of the source to the total impact probability decreased with the distance, but that of upper part increased. The proportion of upper and lower parts would be equal if the distance was about 5 times of the source diameter. The source size should be considered with the distance from the source to the target less than 14 times of the source diameter, and its effect on the impact probability was significant.

关键词： fragments impact probability Monte-Carlo simulations source size

来源：评论

学校读者我要写书评

暂无评论

Dual adaptive control of bimanual manipulation with online fuzzy parameter tuning

Dual adaptive control of bimanual manipulation with online f...

引用

IEEE International Symposium on Intelligent control (ISIC)

作者： Alex Smith Chenguang Yang Hongbin Ma Phil Culverhouse Angelo Cangelosi Etienne Burdet Center for Robotics and Neural Systems Plymouth University Devon UK Key Laboratory of Autonomous System and Network Control South China University of Technology Guangzhou P. R. China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing P. R. China Department of Bioengineering Imperial College London UK

A biomimetic controller with online adaptation of impedance and force is applied to a full kinematic and dynamic model of the Baxter bimanual robot. A set of fuzzy logic engines are proposed to infer the values of tuning gains which affect the control performance and control effort of the controller, which would conventionally be set to a static value based on expert knowledge of the controller; the aim of this being to avoid the use of arbitary values to set these values. A simulated experiment is carried out, where the Baxter robot is required to move an object through a trajectory while subjected to two different disturbance forces in four phases. The controller with fuzzy inferred control gains is compared against the same controller with fixed gains to gauge the effectiveness of the new method. Results show that fuzzy inference of control gains impart an improvement in both tracking error and control effort.

关键词： Trajectory Fuzzy logic Force Dynamics Mathematical model Manipulators

来源：评论

学校读者我要写书评

暂无评论

Computing Open-Loop Optimal control of the q-Profile in Ramp-Up Tokamak Plasmas Using the Minimal-Surface Theory

引用

Plasma Science and technology 2013年第5期15卷 403-410页

作者：许超欧勇盛 Eugenio SCHUSTER 于欣 The State Key Laboratory of Industrial Control Technology Zhejiang University Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Department of Mechanical Engineering & Mechanics Lehigh University Ningbo Institute of Technology Zhejiang University

The q-profile control problem in the ramp-up phase of plasma discharges is consid- ered in this work. The magnetic diffusion partial differential equation （PDE） models the dynamics of the poloidal magnetic flux profile, which is used in this work to formulate a PDE-constrained op-timization problem under a quasi-static assumption. The minimum surface theory and constrained numeric optimization are then applied to achieve suboptimal solutions. Since the transient dy- namics is pre-given by the minimum surface theory, then this method can dramatically accelerate the solution process. In order to be robust under external uncertainties in real implementations, PID （proportional-integral-derivative） controllers are used to force the actuators to follow the computational input trajectories. It has the potential to implement in real-time for long time discharges by combining this method with the magnetic equilibrium update.

关键词： advanced plasma operations current profile dynamics optimal control theory,minimal surface equation differential geometry

来源：评论

学校读者我要写书评

暂无评论

Multirate output feedback control for complex industrial processes in double-layer network environment with RBF performance index

Multirate output feedback control for complex industrial pro...

引用

World Congress on Intelligent control and Automation (WCICA)

作者： Tong Wang Jianbin Qiu Huijun Gao Jialu Fan Tianyou Chai Research Institute of Intelligent Control and Systems Harbin Institute of Technology Harbin China School of Information Bohai University Jinzhou China State Key Laboratory of Synthetical Automation of Process Industries Northeastern University Shenyang China

This paper investigates the output feedback control problem for a class of complex industrial processes in double-layer (upper operation layer and local device layer) network environment with radial basis function (RBF) performance index. First, sampled-data local plants at the device layer with sampling period T d are controlled by local output feedback proportional integral (PI) controllers. Then, the outputs and inputs of local plants are sampled at operation layer with sampling period T u to form the index prediction by using RBF neural networks. In addition, consider the effect of Ethernet between operation and device layer, a Bernoulli random binary distribution is employed to model the packet dropout phenomenon during data transmission. Furthermore, considering the nonlinearity of RBF neural networks, the Lagrange multipliers approach is utilized to solve the real time optimization (RTO) problem at operation layer and an output feedback compensator is designed to regulate the dynamic setpoints. Finally, a rougher flotation process model is employed to demonstrate the effectiveness of the proposed method.

关键词： Indexes Process control Optimization Output feedback Symmetric matrices Neurons Automation

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking control for a Class of Continuous Time Complex-valued systems Based on Adaptive Dynamic Programming Algorithm

Optimal Tracking Control for a Class of Continuous Time Comp...

引用

第三十三届中国控制会议

作者： Ruizhuo Song Frank L.Lewis Qinglai Wei Wendong Xiao School of Automation and Electrical Engineering University of Science and Technology Beijing University of Texas at Arlington Research Institute University of Texas at Arlington State Key Laboratory of Synthetical Process Automation Northeastern University The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

ISBN: (纸本)9781479947249

Based on the adaptive dynamic programming(ADP) algorithm,a new optimal tracking control method is proposed for a class of complex-valued nonlinear systems in this *** tracking error is rst de ned,and then the performance index function which is about the tracking error is *** transformation,the complex-valued tracking error system is mapped into *** optimal control method for the tracking error system is *** two neural networks are used to be as the critic network and action network,*** is proven that the closed-loop system is uniformly ultimately bounded based on Lyapunov ***,the simulation study is given to show the effectiveness of the proposed optimal tracking control method for complex-valued nonlinear system.

关键词： Adaptive dynamic programming,optimal control,neural network,complex-valued

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-Dimensional Data Visualization Analysis of Large Enterprise's Purchasing Fund

Research on Multi-Dimensional Data Visualization Analysis of...

引用

2014 IEEE International Conference on Service Operations and Logistics,and Informatics

作者： Minhui Lv Hongxia Zhao School of Management Huazhong University of Science and Technology Department of Equipment Economics and Management Naval University of Engineering The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

With the continuous development of data storage technology,the complexity,category and size of data increase sharply;on the other hand,the wide expansion of its application domain brings great challenges on the traditional data processing and analysis *** this paper,the data analysis and processing technology and its development status are introduced and by multi-dimensional data visualization analysis method and combining the knowledge of domain experts,the equipment purchasing fund data of a large enterprise is analyzed to provide reliable management decision to the investment and investment volume of business fund.

关键词： data analysis data mining visualization corporate purchasing fund

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：