检索结果-内蒙古大学图书馆

2013 International Conference on Artificial Intelligence, ICAI 2013

作者： Zang, Liangjun Cao, Cungen Sui, Yuefei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences No.6 Kexueyuan South Road Hai Dian Distinct Beijing 100190 China University of Chinese Academy of Sciences No.19 Yu Quan Road Shi Jing Shan Distinct Beijing 100049 China

ISBN: (纸本)1601322488

Default Logic employs assumption-based default rules to draw plausible consequences in face of incomplete information. In ontology representation, there are two kinds of relations between concepts: subsumption relation and default subsumption relation. Subsumption relation is transitive, whereas default subsumption relation is transitive by default. Both default transitivity of default subsumption and default inheritance of default property should be represented as defaults about defaults, i.e. two-level defaults. None of existing default logics can represent two-level defaults. In this paper, we propose two-level default theories which augment default theories with two-level defaults. A two-level default theory can be divided into two levels and its extensions can be generated by two steps. We prove that normal two-level default theories cannot reduce to normal default theories. Specifically, there is a normal two-level default theory such that there exists no normal default theory such that they share the same set of extensions.

关键词： Formal logic

来源：评论

学校读者我要写书评

暂无评论

Preface: WCSE 2013

Proceedings - 2013 4th World Congress on Software Engineerin...

引用

Proceedings - 2013 4th World Congress on Software Engineering, WCSE 2013 2013年 xi-xii页

作者： Xu, Li Da Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology China University of Mining and Technology China

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised learning with local and global consistency by geodesic distance and sparse representation 1

引用

3rd Sino-Foreign-Interchange Workshop on intelligent Science and intelligent Data Engineering, IScIDE 2012

作者： Gui, Jie Zhao, Zhongqiu Hu, Rongxiang Jia, Wei Intelligent Computing Lab. Hefei Institute of Intelligent Machines Chinese Academy of Sciences Hefei Anhui 230031 China State Key Laboratory for Novel Software Technology Nanjing University China College of Computer Science and Information Engineering Hefei University of Technology China Institue of Energy Safety Chinese Academy of Sciences Hefei Anhui 230031 China

ISBN: (数字)9783642366697

ISBN: (纸本)9783642366680

In many practical data mining applications, such as web categorization, key gene selection, etc., generally, unlabeled training examples are readily available, but labeled ones are fairly expensive to obtain. Therefore, in recent years, semi-supervised learning algorithms such as graph-based methods have attracted much attention. However, most of these traditional methods adopted a Gaussian function to calculate the edge weights of the graph. In this paper, a novel weight for semi-supervised graph-based methods is proposed. The new method adds the label information from problem into the target function, and adopts the geodesic distance rather than Euclidean distance as the measure of the difference between two data points when conducting the calculation. In addition, we also add class prior knowledge from problem into semi-supervised learning algorithm. Here we address the problem of learning with local and global consistency (LGC). It was found that the effect of class prior knowledge was probably different between under high label rate and low label rate. Furthermore, we integrate sparse representation (SR) in LGC algorithm. Experiments on a UCI data set show that our proposed method outperforms the original algorithms. © Springer-Verlag 2013.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Forward non-rigid motion tracking for facial MoCap

引用

The Visual Computer 2013年第2期30卷 139-157页

作者： Xiaoyong Fang Xiaopeng Wei Qiang Zhang Dongsheng Zhou Key Laboratory of Advanced Design and Intelligent Computing (Dalian University) Ministry of Education Dalian China School of Computer and Information Science Hunan Institute of Technology Hengyang China

For the existing motion capture (MoCap) data processing methods, manual interventions are always inevitable, most of which are derived from the data tracking process. This paper addresses the problem of tracking non-rigid 3D facial motions from sequences of raw MoCap data in the presence of noise, outliers and long time missing. We present a novel dynamic spatiotemporal framework to automatically solve the problem. First, based on a 3D facial topological structure, a sophisticated non-rigid motion interpreter (SNRMI) is put forward; together with a dynamic searching scheme, it cannot only track the non-missing data to the maximum extent but recover missing data (it can accurately recover more than five adjacent markers under long time (about 5 seconds) missing) accurately. To rule out wrong tracks of the markers labeled in open structures (such as mouth, eyes), a semantic-based heuristic checking method was raised. Second, since the existing methods have not taken the noise propagation problem into account, a forward processing framework is presented to solve the problem. Another contribution is the proposed method could track facial non-rigid motions automatically and forward, and is believed to greatly reduce even eliminate the requirements of human interventions during the facial MoCap data processing. Experimental results proved the effectiveness, robustness and accuracy of our system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A graph-based multi-hop cooperative MIMO scheme for heterogeneous WSN

A graph-based multi-hop cooperative MIMO scheme for heteroge...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Li, Zhetao Xie, Da Pei, Tingrui Choi, Youngjune Li, Renfa College of Information Engineering Xiangtan University Xiangtan 411105 China School of Computer National University of Defense Technology Changsha 410073 China Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan 411105 China Department of Information and Computer Engineering Ajou University Suwon 443749 Korea Republic of School of Computers and Communications Hunan University Changsha 410082 China

ISBN: (纸本)9783642362514

A Graph-based multi-hop cooperative MIMO transmission scheme (GM-MIMO) aimed at optimizing the network lifetime and saving energy for heterogeneous wireless sensor networks (WSN) is proposed. In GM-MIMO, clusters are established based on geographical position. Graph theory is applied to find an optimal forwarding path. For taking the presence of node heterogeneity into consideration, GM-MIMO obtains maximum network lifetime. Simulation results show that GM-MIMO makes a significant performance improvement in terms of network lifetime and survival rate of nodes. © 2013 Springer-Verlag.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Synchronic Analysis in a Neural Network Based on FitzHugh-Nagumo Equations with Time Delay

Synchronic Analysis in a Neural Network Based on FitzHugh-Na...

引用

2013 ICME International Conference on Complex Medical Engineering(2013 ICME复合医学工程国际会议)

作者： Shurui Qin Yuanhua Qiao Jun Miao Lijuan Duan College of Applied Science Beijing University of Technology Beijing 100124 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Acad College of Computer Science Beijing University of Technology Beijing 100124 China

The dynamics of a neuronal network often involves time delay due to the finite signal propagation speed in biological *** this paper,we make some analysis on the FitzHugh-Nagumo model with coupling delay and then inve... 详细信息

ISBN: (纸本)9781467329705

关键词： FitzHugh-Nagumo model neural network synchronization time delay

来源：评论

学校读者我要写书评

暂无评论

Adaptive visual servoing using common image features with unknown geometric parameters

Adaptive visual servoing using common image features with un...

引用

作者： Liu, Yun-Hui Wang, Hesheng Chen, Weidong Zhou, Dongxiang Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong Hong Kong Department of Automation Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai 200240 China State Key Laboratory of Robotics Technology and System Harbin Institute of Technology Harbin 150001 China Joint Center for Intelligent Sensing and Systems National University of Defense Technology China

This paper generalizes the concept of the depth-independent interaction matrix, developed for point and line features in our early work, to generalized image features. We derive the conditions under which the depth-independent interaction matrix can be linearly parameterized by the geometric parameters of the generalized image features, and propose an adaptive visual servo controller for robot manipulators using the generalized image features whose geometric parameters are unknown. To estimate the unknown parameters on-line, we propose new error functions that are linear to estimation errors of the parameters and an algorithm that minimizes the error functions using multiple images. The Lyapunov theory is used to prove asymptotic stability of the proposed controller based on the nonlinear dynamics of the manipulator. It is also shown that in addition to points and lines, other common image features like distances, angles, areas, and centroids all satisfy the conditions for the linear parameterization. Experiments have been conducted to validate the proposed control method. © 2013 Elsevier Ltd. All rights reserved.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Spectral Distance Distributions for Non-rigid Objects

引用

Computer Aided Drafting,Design and Manufacturing 2013年第2期23卷 17-24页

作者： CAO Wei-guo Li Hai-yang LI Shi-rui LIU Yu-jie LI Hua Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China School of Computer Science and Communication Engineering China University of Petroleum Qingdao 266555 China.

Non-rigid shape deformation without tearing or stretching is called isometry. There are many difficulties to research non-rigid shape in Euclidean space. Therefore, non-rigid shapes are firstly embedded into a none-Euclidean space. Spectral space is chosen in this paper. Then three descriptors are proposed based on three spectral distances. The existence of zero-eigenvalue has negative effects on computation of spectral distance, Therefore the spectral distance should be computed from the first non-zcro-eigenvalue. Experiments show that spectral distance distributions are very effective to describe the non-rigid shapes.

关键词： non-rigid shape analysis pattern recognization isometry Laplace-Beltrami operator spectrum

来源：评论

学校读者我要写书评

暂无评论

Converting continuous-space language models into N-gram language models for statistical machine translation

Converting continuous-space language models into N-gram lang...

引用

2013 Conference on Empirical Methods in Natural Language processing, EMNLP 2013

作者： Wang, Rui Utiyama, Masao Goto, Isao Sumita, Eiichro Zhao, Hai Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering Shanghai Jiao Tong Unviersity Shanghai200240 China Multilingual Translation Laboratory MASTAR Project National Institute of Information and Communications Technology 3-5 Hikaridai Keihanna Science City Kyoto619-0289 Japan MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong Unviersity Shanghai200240 China

ISBN: (纸本)9781937284978

Neural network language models, or continuous-space language models (CSLMs), have been shown to improve the performance of statistical machine translation (SMT) when they are used for reranking n-best translations. However, CSLMs have not been used in the first pass decoding of SMT, because using CSLMs in decoding takes a lot of time. In contrast, we propose a method for converting CSLMs into back-off n-gram language models (BNLMs) so that we can use converted CSLMs in decoding. We show that they outperform the original BNLMs and are comparable with the traditional use of CSLMs in reranking. © 2013 Association for Computational Linguistics.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Using Chou’s Pseudo Amino Acid Composition for Protein Remote Homology Detection

引用

Engineering（科研） 2013年第10期5卷 149-153页

作者： Bin Liu Xiaolong Wang School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Key Laboratory of Network Oriented Intelligent Computation Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Shanghai Key Laboratory of Intelligent Information Processing Shanghai China School of Computer Science and Technology Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China Key Laboratory of Network Oriented Intelligent Computation Harbin Institute of Technology Shenzhen Graduate School Shenzhen Guangdong China

Protein remote homology detection is a key problem in bioinformatics. Currently, the discriminative methods, such as Support Vector Machine (SVM), can achieve the best performance. The most efficient approach to improve the performance of the SVM-based methods is to find a general protein representation method that is able to convert proteins with different lengths into fixed length vectors and captures the different properties of the proteins for the discrimination. The bottleneck of designing the protein representation method is that native proteins have different lengths. Motivated by the success of the pseudo amino acid composition (PseAAC) proposed by Chou, we applied this approach for protein remote homology detection. Some new indices derived from the amino acid index (AAIndex) database are incorporated into the PseAAC to improve the generalization ability of this method. Our experiments on a well-known benchmark show this method achieves superior or comparable performance with current state-of-the-art methods.

关键词： Protein Remote Homology Support Vector Machine Pseudo Amino Acid Composition Protein Representation

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：