检索结果-内蒙古大学图书馆

10th International Symposium on Neural Networks, ISNN 2013

作者： Zhao, Zeng-Shun Feng, Xiang Wei, Fang Wang, Shi-Ku Cao, Mao-Yong Hou, Zeng-Guang College of Information and Electrical Engineering Shandong University of Science and Technology Qingdao 266590 China School of Control Science and Engineering Shandong University Jinan 250061 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

ISBN: (纸本)9783642390647

The Neural-Network Ensemble (NNE) is a very effective method where the outputs of separately trained neural networks are combined to perform the prediction. In this paper, we introduce the improved Neural Network Ensemble (INNE) in which each component forward neural network (FNN) is optimized by particle swarm optimization (PSO) and back-propagation (BP) algorithm. At the same time, the ensemble weights are trained by Particle Swarm Optimization and Differential Evolution cooperative algorithm(PSO-DE). We take two obviously different populations to construct our algorithm, in which one population is trained by PSO and the other is trained by DE. In addition, we incorporate the fitness value from last iteration into the velocity updating to enhance the global searching ability. Our experiments demonstrate that the improved NNE is superior to existing popular NNE. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Map Building in Eigenspace - A PCA-based Approach

Mobile Robot Map Building in Eigenspace - A PCA-based Approa...

引用

第25届中国控制与决策会议

作者： Ke Wang Lijun Zhao Ruifeng Li State Key Laboratory of Robotics and Systems Harbin Institute of Technology Key Laboratory of Measurement and Control of CSE Ministry of Education

ISBN: (纸本)9781467355339

Detection and compression of the environmental information incrementally is useful when the mobile robot needs to continuously update its perception database online. In this paper, we propose an incremental subspace fusion method for abstract map building of mobile robot. We firstly adopt PCA to preprocess the panoramic images taken from omnidirectional camera at corresponding location, which can optimally extracts the local map features formed in the subspace and reduces the uncorrelated features. This enables robot to memorize the environmental features incrementally when it travels in an unknown environment. Experimental results are shown finally.

关键词： Map Building, Mobile robot, Principle Component Analysis, Incremental Map Fusion, Appearance-based modeling

来源：评论

学校读者我要写书评

暂无评论

Optimal node placement strategies of linear wireless sensor networks with sensor node uniformly distributed

Optimal node placement strategies of linear wireless sensor ...

引用

Chinese control Conference (CCC)

作者： Jian Bo Yang Xue An Ke Han Shen-Tu Zhejiang University Hangzhou Zhejiang CN Institution of Information and Control Hangzhou Dianzi University Hangzhou China State Key Laboratory of Industrial Control Technology Institute of Cyber-System and Control Zhejiang University Hang Zhou 310027 China

The linear and multi-hop transmission feature of wireless sensor networks on city drainage pipelines, roads, power lines and other monitoring occasions, is easy to lead to energy imbalance consumption of the network node and premature failure of the monitoring network. In this paper, the linear wireless sensor networks with sensor nodes uniformly distributed and emission capacity restricted is taken as the research object, the network energy consumption characteristic is analyzed. Network efficiency taked as optimization objective, then an efficient node deployment algorithm is proposed. Combining with network performance requirements, the optimal relay node deployment scheme and node forwards the data flow is solved to balance energy consumption and prolong the network life. Results of theoretical analysis and simulation show that the method of nodes placement and topology control can delay the “energy hole” problem and improve network efficiency. The researches for guiding nodes placement of linear wireless sensor networks is of great significance.

关键词： Wireless sensor networks Electronic mail Energy consumption Educational institutions Monitoring Laboratories industrial control

来源：评论

学校读者我要写书评

暂无评论

Vehicle detection method based on active basis model and symmetry in ITS

Vehicle detection method based on active basis model and sym...

引用

2013 16th International IEEE Conference on Intelligent Transportation systems: Intelligent Transportation systems for All Modes, ITSC 2013

作者： Yao, Yanjie Gang, Xiong Wang, Kunfeng Zhu, Fenghua Wang, Fei-Yue State Key Laboratory of Management and Control for Complex Systems Beijing Engineering Research Center of Intelligent Systems and Technology Chinese Academy of Sciences Beijing 100190 China Dongguan Research Institute of CASIA Cloud Computing Center Chinese Academy of Sciences Dongguan China

ISBN: (纸本)9781479929146

Vehicle detection is a foundational and significant task in video surveillance systems. In this paper, a vehicle detection method using a deformable model and symmetry is proposed. First, we learn the active basis model (ABM) from the target training sample set by using the shared sketch algorithm. Then, we utilize the edge information obtained by ABM and HSV color information to do symmetry analysis for vehicle objects. The ABM can detect vehicles in various poses, shapes, and sizes for its deformability. By doing edge and color symmetry analysis, subtle difference between two images and environment noises can be adapted. The results of experiments indicate that our approach is capable of detection different vehicles and localization vehicle in bad environment. What's important, the detection results support the capability of the proposed method to enable the introduction of novel intelligent transportation systems applications. © 2013 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

The algorithm of MIMU/odometer integrated navigation system aided by nonholonomic constraints

The algorithm of MIMU/odometer integrated navigation system ...

引用

International Conference on Mechatronic Science, Electric Engineering and Computer

作者： Shi Peng Xiao Xuan State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Beijing China

ISBN: (纸本)9781479925667

The navigation precision drops rapidly when MIMU (Micro Inertial Measurement Unit) works alone. Odometer data are easy to get on land vehicle, but the performance of integration system of MIMU/odometer is not enhanced obviously. In this work, a novel method is designed using nonholonomic constraints. When vehicle travels without slide and jump, the velocity in the plane perpendicular to forward direction is zero, as well as acceleration. Taking velocity constraint and acceleration constraint as measurement value, new measurement models are established. Integrated navigation algorithm is designed with the help of Kalman filter. With this method, the position error is 150m after 600s, and heading attitude error is 0.1°, comparing the result that the position error expands to 300m after 150s only aided by odometer.

关键词： Vehicles Acceleration Global Positioning System Velocity measurement Noise Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Detection of Penicillin via Surface Plasmon Resonance Biosensor

引用

Chemical Research in Chinese Universities 2012年第5期28卷 792-796页

作者： ZHANG Ying JIN Wei YANG Meng-chao ZHANG Ti-qiang ZHOU Chao XIE Fei SONG Qi REN Hao JIN Qin-han MU Ying Research Center for Analytical Instrumentation Institute of Cyber-systems and ControlState Key Laboratory of Industrial Control TechnologyDepartment of Control Science and TechnologyZhejiang UniversityHangzhou 310058PR.China

A method of using Au colloid to capture the decomposed product of penicillin, penicillamine, on a surface plasmon resonance（SPR） biosensor for the quantitative determination of penicillin was developed. Based on the de-composition of penicillin to generate penicillamine and penilloaldehyde, a high sensitive biosensor for detecting penicillin was also developed. In our experiment, it was penicillamine rather than penicillin that has been measured. This is because penicillamine contains a functional group that makes it self-assembling on Au colloid to increase the molecular weight so as to improve the surface plasmon resonance signal. On a UV-Vis spectrophotometer, a high concentration of penicilliamine-Au complex was determined, indicating that penicillamine was already well combined with Au colloid. The method, using the combination of Au colloid with penicillamine, proved to detect penicillin.

关键词： Surface plasmon resonance（SPR） Biosensor Penicillamine Au colloid

来源：评论

学校读者我要写书评

暂无评论

sEMG based joint angle estimation of lower limbs using LS-SVM

sEMG based joint angle estimation of lower limbs using LS-SV...

引用

20th International Conference on Neural Information Processing, ICONIP 2013

作者： Li, Qingling Song, Yu Hou, Zengguang Zhu, Bin Department of Mechanical Engineering China University of Mining and Technology Beijing China School of Electronic and Information Engineering Beijing Jiaotong University Beijing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Science Beijing China

ISBN: (纸本)9783642420535

In this paper, a new estimation model based on least squares support vector machine (LS-SVM) is proposed to build up the relationship between Surface electromyogram (sEMG) signal and joint angle of the lower limb. The input of the model is 2 channels of preprocessed sEMG signal. The outputs of the model are joint angles of the hip and the knee. sEMG signal is acquired from 7 motion muscles in treadmill exercise. And two channels of them are selected for dynamic angle estimation for their strong correlation with angle data. Angle estimation model is constructed by 2 independent LS-SVM based regression model with radial basis function (RBF). It is trained using part of the sample sets acquired in 10s exercise duration and test by all data. Experimental result shows proposed method has good performance on joint angles estimation based sEMG. Root mean square error (RMSE) of prediction knee and hip joint angles is 3.02° and 2.09° respectively. It provide new human-machine interface for active rehabilitation training of SCI, stroke or neurological injury patients. © Springer-Verlag 2013.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Application of vector ordinal optimization to the transportation systems with agent based modelling

Application of vector ordinal optimization to the transporta...

引用

2013 IEEE International Conference on Automation Science and Engineering, CASE 2013

作者： Shen, Z. Wang, K. Wang, F.-Y. State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences No. 95 Zhongguancun E. Road Beijing 100190 China Centre for Military Computational Experiments and Parallel Systems Technology College of Mechatronics Engineering and Automation National University of Defense Technology Changsha 410073 Hunan Province China

ISBN: (纸本)9781479915156

As the computing technology develops, micro-simulation becomes more and more important in the Intelligent Transportation systems (ITS) research, because it can provide detailed descriptions of the system. However, for a multi-agent systems (MAS) modelling of an ITS, the computation burden is large, as it involves the computation of the state changing of all the agents. Further, if we consider simulation based optimization, which can be simply understood as an intelligent way of running a number of micro-simulations, the computation burden is huge. Moreover, there are multiple objective optimization problems in the ITS. The Vector Ordinal Optimization (VOO) method is a powerful tool for multi-objective optimization. In this paper, we apply VOO to the problem of optimizing the stop times and delay time of an ITS. We test the method on a 4 intersection lattice road network, and on the 18 intersection road network of the Zhongguancun area of Beijing. Compared with the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) method, the VOO method can achieve a speedup of factor of more than 150, with only a little sacrifice of performance. © 2013 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

MODULAR HIERARCHICAL FEATURE LEARNING WITH DEEP NEURAL NETWORKS FOR FACE VERIFICATION

MODULAR HIERARCHICAL FEATURE LEARNING WITH DEEP NEURAL NETWO...

引用

IEEE International Conference on Image Processing

作者： Xue Chen Baihua Xiao Chunheng Wang Xinyuan Cai Zhijian Lv Yanqin Shi State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing Institute of Science and Technology Information

ISBN: (纸本)9781479923427

Feature representations play a crucial role in modern face recognition systems. Most hand-crafted image descriptors usually provide low-level information. In this paper, we propose a novel feature learning method based on deep neural networks to obtain high-level, hierarchical representations for face verification. Learning proceeds in two phases. In the pre-training phase, we train Restricted Boltzmann Ma-chine(RBM) networks for each modular region in the image separately. In the fine-tuning phase, in order to develop good discriminative ability, we stack the RBM networks of each region in deep architecture and combine deep learning with side information constraints in the whole image scale. Finally, we formulate the proposed method as an appropriate optimization problem and adopt gradient descent algorithm to get the optimal solution. We evaluate our method on the LFW dataset. Representations learned from the networks achieve comparable performance (93.11%) to the state-of-art method.

关键词： deep neural networks feature learning face verification face verification Modularity Neural network image scale face recognition system Face Verification

来源：评论

学校读者我要写书评

暂无评论

Parameter-dependent vibration-attenuation controller design for electro-hydraulic actuated linear structural systems

引用

Earthquake Engineering and Engineering Vibration 2012年第1期11卷 73-82页

作者： Weng Falu Mao Weijie State Key Lab of Industrial Control Technology Institute of Cyber-Systems and Control Zhejiang University Hangzhou 310027 China School of Mechanical and Electrical Engineering Jiangxi University of Science and Technology Ganzhou 341000 China

The problem of robust active vibration control for a class of electro-hydraulic actuated structural systems with time-delay in the control input channel and parameter uncertainties appearing in all the mass, damping and stiffness matrices is investigated in this paper. First, by introducing a linear varying parameter, the nonlinear system is described as a linear parameter varying （LPV） model. Second, based on this LPV model, an LMI-based condition for the system to be asymptotically stabilized is deduced. By solving these LMIs, a parameter-dependent controller is established for the closed- loop system to be stable with a prescribed level of disturbance attenuation. The condition is also extended to the uncertain case. Finally, some numerical simulations demonstrate the satisfying performance of the proposed controller.

关键词： structural system electro-hydraulic servo system robust stabilization vibration attenuation parameter-dependent controller

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：