检索结果-内蒙古大学图书馆

第三十二届中国控制会议

作者： XIE Qingqing LUO Bin TAN Fuxiao School of Computer Science and Technology Anhui University Key Laboratory of Intelligent Computing ＆ Signal Processing Ministry of EducationAnhui University School of Computer and Information Fuyang Teachers college

ISBN: (纸本)9781479900305

Dynamic programming(DP) is not a useful tool for solving many control problems because of its complexity in computation. In this paper,we propose Approximate Dynamic Programming(ADP) optimal control strategy for ship course trajectory tracking control *** system transformation,we convert the optimal tracking problem into designing a infinite-horizon optimal regulator for the tracking error ***-dependent Heuristic Dynamic programming(ADHDP) technique,as one form of ADR is presented to obtain the infinite-horizon optimal tracking *** the ship course optimal tracking control simulation results,we can see that the ADHDP controller makes the performance index and the control sequence for the error dynamics converge to the optimal *** BP neural networks are used as parametric structures to implement ADHDP *** two neural networks aim at approximating the cost function and the control law,respectively.

关键词： Optimal Tracking Control Approximate Dynamic Programming ADHDP Ship Course

来源：评论

学校读者我要写书评

暂无评论

Novel non-convex online algorithms for robust ranking

引用

Journal of Information and Computational Science 2013年第17期10卷 5743-5759页

作者： Cheng, Fan Wang, Xufa Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei 230039 China School of Computer Anhui University Hefei 230039 China School of Computer University of Science and Technology of China Hefei 230027 China

Recently increasing attention has been focused on learning to rank, which aims to learn a ranking function from a set of training data with relevance labels. Many of the ranking algorithms are based on the pairwise preference framework. However, one disadvantage of pairwise ranking is that it is sensitive to the outliers. To tackle the problem, in this paper, we propose two novel online algorithms based on non-convex Ramp Loss which can suppress the influence of outliers. The first one directly defines a new objective function based on Ramp Loss. Considering that the objective function is non-convex, we use the Concave-convex Procedure (CCCP) for convex approximation, then design an online algorithm based on Dual Coordinate Descend Method to learn the final ranking model. The second algorithm applies selective sampling technology in the training phase. It ignores the instances that lie in the flat region of the Ramp Loss in advance, before they are processed by the learner. Experimental results show that the algorithms we proposed have significant robustness to outliers and yield better generalization performance than the baseline rankers, and the results also prove that our algorithms have less computational running time for their less support vectors. © 2013 Binary Information Press.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Image bag generator based on bag of visual words

引用

Journal of Information and Computational Science 2013年第5期10卷 1453-1462页

作者： Zhao, Shu Xu, Chao Xu, Xiansheng Xu, Chenchu Zhang, Yanping Ye, Hong School of Computer Science and Technology Anhui University Hefei 230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China Insurance Office Anhui Provincial Hospital Hefei 230001 China

Multi-instance learning is a good tool to deal with the ambiguity of image in Content-based Image Retrieval (CBIR). According to some researchers' work, image bag generator which transforms an image into an instance bag plays an important role in applying multi-instance learning for CBIR. In this paper, the bag generator based on bag of visual words, named Vdbag, is proposed. First, it extracts local features of image from all images, and then it obtains a set of visual words called visual vocabulary by clustering local features where each local cluster's center is a visual word. Our work mainly includes (1) We introduce bag of visual words into image bag generator. (2) We give a reasonable description to express the instance in an image bag. We add the frequency of each visual word as the last dimension of this visual word to construct the corresponding instance. Experimental results with Corel image database show that the proposed method could achieve better precision than that of some existing bag generators. © 2013 Binary Information Press.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Spectral power estimation for unevenly spaced motor imagery data

Spectral power estimation for unevenly spaced motor imagery ...

引用

20th International Conference on Neural Information processing, ICONIP 2013

作者： Li, Junhua Struzik, Zbigniew Zhang, Liqing Cichocki, Andrzej MOE-Microsoft Key Laboratory for Intelligent Information and Intelligent Systems Shanghai Jiao Tong University Shanghai 200240 China Laboratory for Advanced Brain Signal Processing Brain Science Institute RIKEN Saitama 351-0198 Japan

ISBN: (纸本)9783642420535

The human brain can send a command to external devices or communicate with the outside environment by the means of a brain computer interface (BCI) system. The effectiveness depends on how precisely specific brain activities can be identified from EEG. Noise is usually mixed into the EEG signal, and cannot be separated or filtered out in some cases. In a practical BCI system, the whole segment of EEG is discarded when a portion of that segment is contaminated by extreme noise or artifacts. This leads to the weakness that the BCI system cannot output decoding results during the period of that discarded segment. In order to solve this problem, we employed a Lomb-Scargle periodogram to estimate the spectral power based on an unevenly spaced segment, a portion of which has been removed due to noise contamination. According to the classification results of motor imagery data, the accuracy is not dramatically decreased along with increased proportion of data removal. © Springer-Verlag 2013.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Method for convergent projective non-negative matrix factorization

引用

Journal of Information and Computational Science 2013年第6期10卷 1847-1854页

作者： Hu, Lirui Wu, Jianguo Wang, Lei Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Computer Science and Technology Nantong University Nantong 226019 China School of Computer Science and Technology Anhui University Hefei 230039 China

In order to solve the problem of algorithm convergence in Projective Non-negative Matrix Factorization (P-NMF), a method, called Convergent Projective Non-negative Matrix Factorization (CP-NMF), is proposed. In CP-NMF, an objective function of Frobenius norm is defined. The Taylor series expansion and the Newton iteration formula of solving root are used. An iterative algorithm for basis matrix is derived, and a proof of algorithm convergence is provided. Experimental results show that the convergence speed of the algorithm is higher, however it is affected by the initial value of the basis matrix;relative to Non-negative Matrix Factorization (NMF), the orthogonality and the sparseness of the basis matrix are better, however the reconstructed results of data show that the basis matrix is still approximately orthogonal;in face recognition, there is higher recognition accuracy. The method for CP-NMF is effective. Copyright © 2013 Binary Information Press.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Application and method of feature extraction for approximate orthogonal non-negative matrix factorization

引用

Journal of Computational Information Systems 2013年第2期9卷 805-812页

作者： Hu, Lirui Wu, Jianguo Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China School of Computer Science and Technology Nantong University Nantong 226019 China School of Computer Science and Technology Anhui University Hefei 230039 China

In order to get effectively feature vectors of samples, a method of feature extraction is proposed based on non-negative matrix factorization (NMF) with approximate orthogonal constraint. An objective function is defined to impose approximate orthogonal constraint, in addition to the non-negative constraint in the standard NMF. An algorithm of iterative update for basis matrix and weight matrix in non-negative matrix factorization is derived, and then computational method of feature vectors is gotten. A proof of the convergence of the algorithm is provided. Empirical results of handwritten character recognition show that there is high recognition accuracy if only the rank of the basis matrix is set correctly. The method of feature extraction is useful to get essential feature of sample, and is effective to recognition when the structures of the handwritten characters are obviously different. Copyright © 2013 Binary Information Press.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-granular model to solve netted problem

引用

Journal of Computational Information Systems 2013年第19期9卷 7919-7927页

作者： Chen, Jie Zhang, Yanping Zhao, Shu Liu, Lulu School of Computer Science and Technology Anhui University Hefei 230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei 230039 China Department of Computer Science and Technology Hefei Normal University Hefei 230061 China

The complex problems usually have netted structure, namely netted problems. The generally solving methods are based on sequence-searching or tree-searching of this kind of problems. But the structure of netted problems isn't merely sequence or tree. The Multi-granular Model was proposed in this paper which is put forward based on granular transaction of Quotient Space Theory. The whole problem is represented as a directed graph. Firstly, this graph was projected by constraints of original problem into coarse-grained spaces. Then granular decomposition is used to clear up the circle paths in new graph. In optimal quotient space, we search the answers according to the ordered sequence which is got by traversing the result of granular decomposition. In this paper, an applicable example is given and experiment contrasted with traditional tree searching method shows that this algorithm spends less time complexity and smaller space complexity. © 2013 Binary Information Press.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

A quasi-static clustering algorithm in mobile heterogeneous sensor network

引用

Journal of Computational Information Systems 2013年第9期9卷 3741-3749页

作者： Wang, Bingting Lin, Qibin Hu, Yanjun Liang, Hui Wang, Xianbing Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei 230039 China School of Mechanical and Electronic Engineering Chuzhou University Chuzhou 239000 China School of Information Science and Technology Southwest Jiaotong University Chengdu 610031 China

In this paper, we constructed the architecture of mobile heterogeneous sensor network by introducing user equipments (UEs) in static wireless sensor network. We analyzed the failure of traditional static clustering algorithm, gave a set of parameters that affected the performance of cluster heads in the mobile environment and proposed a Quasi-Static Clustering Algorithm (QSCA). Through theoretical analysis and simulation, this algorithm can reduce average delay and prolong network lifetime. We verified the adaptability of QSCA algorithm to energy consumption and dynamic topology by comparing with the LEACH algorithm. © 2013 by Binary Information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

The Restoring Casimir Force between Doped Silicon Slab and Metamaterials

The Restoring Casimir Force between Doped Silicon Slab and M...

引用

2013 International Symposium on Antennas and Propagation(2013天线与传播国际会议)

作者： Zhi-Xiang Huang Xue-Wei Li Xian-Liang Wu Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei 230039China Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei 230039China

ISBN: (纸本)9781479909216

Casimir effect is an observable macroscopic quantum *** has significant influence on micro-machine and *** on a generalization of the Lifshitz theory, we calculate Casimir force between the doped silicon slab and *** simulating, we can see that the magnitude and the direction of the Casimir force can be changed by varying doping level, the thickness of doped silicon slab, and filling factor of *** the force can be controlled by tuning these *** can be restoring force in a certain range of distance, which can provide a method to deal with the stability problem, and bring much meaningful results from the practical views.

关键词： Repulsive and Restoring Casimir Force Doped Silicon Metamaterials

来源：评论

学校读者我要写书评

暂无评论

Study on the Optical Properties of Nanowires Using FDTD Method

Study on the Optical Properties of Nanowires Using FDTD Meth...

引用

2013 International Symposium on Antennas and Propagation(2013天线与传播国际会议)

作者： Zhi-Xiang Huang Jin-Yang Chu Liang Yu Xiang Huang Xian-Liang Wu Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei 230039China Key Laboratory of Intelligent Computing and Signal Processing Anhui University Hefei 230039China

Finite-difference tine-domain studies of a variety of cylinder arrays with nanometer-scale diameters (nanowires)interacting with light are *** and absorption cross sections for metallic nanoscale objects can be obtained from such *** method is verified by comparing the analytical results for cylindrical *** the optical properties of Ag nanowires and study the explicit time-domain behavior of more cylinders.

关键词： Finite-Difference Time-Domain Method Absorption Cross Section Scattering Cross Section Extinction Cross Section

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：