检索结果-内蒙古大学图书馆

A granularity attribute reduction method based on binary discernibility matrix

International Journal of Advancements in computing technology 2012年第12期4卷 213-221页

作者： Chang, Tong Shifei, Ding Hong, Zhu Hongjie, Jia Jian, Wang School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Geomatics College Shandong University of Science and Technology Qingdao 266510 China

At present, most of the attribute reduction algorithms based on granularity are simply computing the granularity of knowledge. Repeated calculation will increase the time complexity. Binary discernibility matrix is used to express binary form, which has a clear ascension whether in space or in time than the traditional discernibility matrix efficiency. On the basis of granularity-based attribute reduction, a method is proposed to preprocess the dataset by using binary discernibility matrix. Firstly, find the core attribute and a minimal reduction. Then use the granularity thought to calculate each particle of the importance of attributes. Most important is joined to the reduction set, thereby achieving the attributes reduction. The example analysis shows that the method can improve the performance of the traditional attribute reduction algorithms effectively. It is a feasible approach to reduce attributes.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

A support vector extraction method based on clustering membership

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第13期6卷 1-10页

作者： Qi, Bingjuan Ding, Shifei Huang, Huajuan Yu, Junzhao Wang, Jian School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China Geomatics College Shandong University of Science and Technology Qingdao 266510 China

Traditional support vector machine has disadvantages of slow training speed and great time consumption when dealing with large-scale datasets. This paper proposes a support vector extraction method based on clustering membership, which preprocesses the training datasets and extracts all possible support vectors for SVM training according to the memberships. Considering the training datasets may be linear or nonlinear, this paper severally uses FCM and KFCM to extract support vectors. Experiment results show that the method proposed in this paper can improve the training speed greatly in the condition of maintaining the classification accuracy.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Left-to-Right Tree-to-String Decoding with Prediction 12

Left-to-Right Tree-to-String Decoding with Prediction

引用

Conference on Empirical Methods in Natural Language processing

作者： Yang Feng Yang Liu Qun Liu Trevor Cohn Department of Computer Science The University of Sheffield Sheffield UK State Key Laboratory on Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Sci. and Tech. Tsinghua University Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781622765034

Decoding algorithms for syntax based machine translation suffer from high computational complexity, a consequence of intersecting a language model with a context free grammar. Left-to-right decoding, which generates the target string in order, can improve decoding efficiency by simplifying the language model evaluation. This paper presents a novel left to right decoding algorithm for tree-to-string translation, using a bottom-up parsing strategy and dynamic future cost estimation for each partial translation. Our method outperforms previously published tree-to-string decoders, including a competing left-to-right method.

关键词： modelling languages DECODING decoding algorithm machine translation syntax context-free grammars

来源：评论

学校读者我要写书评

暂无评论

STRUCTURED SPARSE LINEAR DISCRIMINANT ANALYSIS

STRUCTURED SPARSE LINEAR DISCRIMINANT ANALYSIS

引用

IEEE International Conference on Image processing

作者： Zhen Cui Shiguang Shan Haihong Zhang Shihong Lao Xilin Chen School of Computer Science and Technology Huaqiao University Xiamen China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China Omron Social Solutions Company Limited Kyoto Japan

Linear Discriminant Analysis (LDA) is an efficient image feature extraction technique by supervised dimensionality reduction. In this paper, we extend LDA to Structured Sparse LDA (SSLDA), where the projecting vectors are not only constrained to sparsity but also structured with a pre-specified set of shapes. While the sparse priors deal with small sample size problem, the proposed structure regularization can also encode higher-order information with better interpretability. We also propose a simple and efficient optimization algorithm to solve the proposed optimization problem. Experiments on face images show the benefits of the proposed structured sparse LDA on both classification accuracy and interpretability.

关键词： Face Face recognition Databases Linear discriminant analysis Optimization Training Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

Rough fuzzy subspaces based on subspaces in the vector space

Rough fuzzy subspaces based on subspaces in the vector space

引用

IEEE International Conference on Granular computing (GRC)

作者： Mingfen Wu Tao Chen School of Computer Science Wuyi University Guangdong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science Wuyi University China

Rough set theory and fuzzy set theory are complementary generalizations of classical set *** paper concerns with rough sets,fuzzy sets and vector *** construct a rough fuzzy sets model based on a congruence of a vector space and it is assumed that the knowledge about a vector space should be restricted by a ***, we research fuzzy subs paces of the vector space over a field, and get a series of properties. Specifically,we construct the minimum fuzzy subspace containing two fuzzy subspaces in a vector space. Secondly, we define concepts of the lower(upper) approximations of fuzzy subsets with respect to a subspace, and give some properties of the lower and the upper approximations of fuzzy subsets. Finally, we focus on fuzzy subspaces of the vector space, and define the lower(upper) rough fuzzy subspaces and the rough fuzzy subspaces of the vector space. We obtain that a fuzzy subspace is certainly a rough fuzzy subspace, the intersection and sum of two fuzzy subspaces are also rough fuzzy subs paces and other valuable results.

关键词： Educational institutions Vectors Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Practical privacy for value-added applications in vehicular ad hoc networks 5th

引用

5th International Conference on Internet and Distributed computing Systems, IDCS 2012

作者： Zhang, Lei Wu, Qianhong Qin, Bo Domingo-Ferrer, Josep Shanghai Key Laboratory of Trustworthy Computing Software Engineering Institute East China Normal University Shanghai China UNESCO Chair in Data Privacy Dept. of Comp. Eng. and Maths Universitat Rovira i Virgili TarragonaCatalonia Spain Key Lab. of Aerospace Information Security and Trusted Computing Ministry of Education Wuhan University School of Computer China Department of Maths School of Science Xi’an University of Technology China

ISBN: (纸本)9783642348822

Advances in mobile networking and information processing technologies have triggered vehicular ad hoc networks (VANETs) for traffic safety and value-added applications. Most efforts have been made to address the security concerns while little work has been done to investigate security and privacy for value-added applications in VANETs. To fill this gap, we propose a value-added application, specifically, a security and privacy preserving location-based service (LBS) scheme for VANETs. For each LBS transaction, the scheme provides authentication, integrity and non-repudiation for both the service provider and the user. A user can obtain the service in an anonymous way and hence user privacy is well protected. However, a tracing procedure can be invoked to find malicious users, thereby efficiently preventing users from abusing the anonymity provided by the system. © Springer-Verlag Berlin Heidelberg 2012.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Twin support vector machines based on rough sets

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第20期6卷 493-500页

作者： Yu, Junzhao Ding, Shifei Jin, Fengxiang Huang, Huajuan Han, Youzhen School of Computer Science and Technology China University of Mining and Technology Xuzhou 221116 China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing 100190 China Beijing Key Laboratory of Intelligent Telecommunications Software and Multimedia Beijing University of Posts and Telecommunications Beijing 100876 China Geomatics College Shandong University of Science and Technology Qingdao 266510 China

TWSVM(Twin Support Vector Machines) is based on the idea of GEPSVM (Proximal SVM based on Generalized Eigenvalues), which determines two nonparallel planes by solving two related SVM-type problems, so that its computing cost in the training phase is 1/4 of standard SVM. In addition to keeping the superior characteristics of GEPSVM, the classification performance of TWSVM significantly outperforms that of GEPSVM. In order to further improve the speed and accuracy of TWSVM, this paper proposes the twin support vector machines based on rough sets. Firstly, using the rough sets theory to reduce the attributes, and then using TWSVM to train and predict the new datasets. The final experimental results and data analysis show that the proposed algorithm has higher accuracy and better efficiency compared with the traditional twin support vector machines.

关键词： Rough set theory

来源：评论

学校读者我要写书评

暂无评论

Image sets alignment for Video-Based Face Recognition

Image sets alignment for Video-Based Face Recognition

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Zhen Cui Shiguang Shan Haihong Zhang Shihong Lao Xilin Chen School of Computer Science and Technology Huaqiao University Xiamen China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China Omron Social Solutions Company Limited Kyoto Japan

Video-based Face Recognition (VFR) can be converted to the matching of two image sets containing face images captured from each video. For this purpose, we propose to bridge the two sets with a reference image set that is well-defined and pre-structured to a number of local models offline. In other words, given two image sets, as long as each of them is aligned to the reference set, they are mutually aligned and well structured. Therefore, the similarity between them can be computed by comparing only the corresponded local models rather than considering all the pairs. To align an image set with the reference set, we further formulate the problem as a quadratic programming. It integrates three constrains to guarantee robust alignment, including appearance matching cost term exploiting principal angles, geometric structure consistency using affine invariant reconstruction weights, smoothness constraint preserving local neighborhood relationship. Extensive experimental evaluations are performed on three databases: Honda, MoBo and YouTube. Compared with competing methods, our approach can consistently achieve better results.

关键词： Manifolds Face Image matching Face recognition Image reconstruction Video sequences Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Activity recognition based on semantic spatial relation

Activity recognition based on semantic spatial relation

引用

International Conference on Pattern Recognition

作者： Lingxun Meng Laiyun Qing Peng Yang Jun Miao Xilin Chen Dimitris N. Metaxas University of the Chinese Academy of Sciences Beijing Beijing CN Computer Science Department Rutgers University Piscataway NJ USA Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

We propose an approach to recognize group activities which involve several persons based on modeling the interactions between human bodies. Benefitted from the recent progress in pose estimation [1], we model the activities as the interactions between the parts belong to the same person (intra-person) and those between the parts of different persons (inter-person). Then a unified, discriminative model which integrates both types of interactions is developed. The experiments on the UT-Interaction Dataset [2] show the promising results and demonstrate the power of the interacting models.

关键词： Joints Humans Semantics Testing Estimation Biological system modeling Image recognition

来源：评论

学校读者我要写书评

暂无评论

引用

Annual meeting of the Association for Computational Linguistics

作者： Xinyan Xiao Deyi Xiong Min Zhang Qun Liu Shouxun Lin Key Lab. of Intelligent Info. Processing Institute of Computing Technology Chinese Academy of Sciences Human Language Technology Institute for Infocomm Research

ISBN: (纸本)9781622761715

Previous work using topic model for statistical machine translation (SMT) explore topic information at the word level. However, SMT has been advanced from word-based paradigm to phrase/rule-based paradigm. We therefore propose a topic similarity model to exploit topic information at the synchronous rule level for hierarchical phrase-based translation. We associate each synchronous rule with a topic distribution, and select desirable rules according to the similarity of their topic distributions with given documents. We show that our model significantly improves the translation performance over the baseline on NIST Chinese-to-English translation experiments. Our model also achieves a better performance and a faster speed than previous approaches that work at the word level.

关键词：

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：