检索结果-内蒙古大学图书馆

2012 IEEE 8th World Congress on Services, SERVICES 2012

作者： Li, Zheng State Key Lab. of Software Engineering Computer School Wuhan University Wuhan China

ISBN: (纸本)9780769547565

With the increasing availab.lity of Web services, how to effictively and accurately discover services according to users' requirements becomes a key issue. In this paper, we propose an on-demand service discovery approach based on "requirement-domain-topic cluster" matching. The proposed approach is achieved by the following steps: domain-oriented service classification based on an ontology-empowered Support Vector Machine (SVM), topic-oriented service clustering based on Latent Dirichlet Allocation (LDA), and on-demand service discovery based on the mined domain knowledge. The proposed approach will contribute to the management of domain services, which can greatly facilitate on-demand service discovery. © 2012 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection for Multi-Cluster data

Unsupervised feature selection for Multi-Cluster data

引用

16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD-2010

作者： Cai, Deng Zhang, Chiyuan He, Xiaofei State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781450300551

In many data analysis tasks, one is often confronted with very high dimensional data. Feature selection techniques are designed to find the relevant feature subset of the original features which can facilitate clustering, classification and retrieval. In this paper, we consider the feature selection problem in unsupervised learning scenario, which is particularly difficult due to the absence of class lab.ls that would guide the search for relevant information. The feature selection problem is essentially a combinatorial optimization problem which is computationally expensive. Traditional unsuper-vised feature selection methods address this issue by selecting the top ranked features based on certain scores computed independently for each feature. These approaches neglect the possible correlation between different features and thus can not produce an optimal feature subset. Inspired from the recent developments on manifold learning and L1-regularized models for subset selection, we propose in this paper a new approach, called Multi-Cluster Feature Selection (MCFS), for unsupervised feature selection. Specifically, we select those features such that the multi-cluster structure of the data can be best preserved. The corresponding optimization problem can be efficiently solved since it only involves a sparse eigen-problem and a L1-regularized least squares problem. Extensive experimental results over various real-life data sets have demonstrated the superiority of the proposed algorithm. © 2010 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Error-Correcting Output Hashing in fast similarity search 10

Error-Correcting Output Hashing in fast similarity search

引用

Proceedings of the Second International Conference on Internet Multimedia Computing and Service

作者： Yu, Zhou Cai, Deng He, Xiaofei State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781450304603

Fast similarity search is one of the key techniques in many large scale learning and data mining applications. Recently, hashing-based methods, which create compact and efficient codes that preserve data distribution, have received considerable attention due to their promising theoretical and empirical results. An ideal hashing method 1) can naturally have out-of-sample extension;2) has very low computational complexity;and 3) has significant improvement over linear search in the original space in terms of accuracy. However, most existing hashing methods failed to satisfy all the above three requirements. In this paper, we propose a new method called Error-correcting Output Hashing (ECOH) which meets all the above three requirements. ECOH first groups all the samples into clusters using a conventional clustering algorithm. Each cluster is assigned an Error-Correcting Output Code (ECOC) and the linear mappings from the sample vectors to the ECOC are then learned using linear regression models. In this way, ECOH learns both the binary code for each sample and the function which links the input vector and the output code. Experimental results on real world data sets demonstrate the effectiveness and efficiency of the proposed approach. Copyright 2010 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Detecting implicit exceptions of service-oriented application based on context

Detecting implicit exceptions of service-oriented applicatio...

引用

2010 International Conference on computer and Information Application, ICCIA 2010

作者： Jia, Xiangyang Ying, Shi Zhao, Kai Wu, Qing State Key Lab. of Software Engineering Computer School Wuhan University Wuhan China

ISBN: (纸本)9781424485963

Implicit exceptions in service-oriented applications will result in uncertainty of system, incorrect business data, unexpected error pages, or even uncovered disaster situations. This paper proposes a context-based approach to detect implicit exceptions. An implicit exception feature model named ECC is presented, and a detecting approach based on ECC model is given. Also the implementation of a prototype system is provided to demonstrate the practicability of our approach. © 2010 IEEE.

关键词： context-based checking exception detecting implicit exception service oriented system

来源：评论

学校读者我要写书评

暂无评论

Large scale spectral clustering with landmark-based representation 25

Large scale spectral clustering with landmark-based represen...

引用

25th AAAI Conference on Artificial Intelligence and the 23rd Innovative Applications of Artificial Intelligence Conference, AAAI-11 / IAAI-11

作者： Chen, Xinlei Cai, Deng State Key Lab. of CAD and CG College of Computer Science Zhejiang University China

ISBN: (纸本)9781577355083

Spectral clustering is one of the most popular clustering approaches. Despite its good performance, it is limited in its applicability to large-scale problems due to its high computational complexity. Recently, many approaches have been proposed to accelerate the spectral clustering. Unfortunately, these methods usually sacrifice quite a lot information of the original data, thus result in a degradation of performance. In this paper, we propose a novel approach, called Landmark-based Spectral Clustering (LSC), for large scale clustering problems. Specifically, we select p( n) representative data points as the landmarks and represent the original data points as the linear combinations of these landmarks. The spectral embedding of the data can then be efficiently computed with the landmark-based representation. The proposed algorithm scales linearly with the problem size. Extensive experiments show the effectiveness and efficiency of our approach comparing to the state-of-the-art methods. Copyright © 2011, Association for the Advancement of Artificial Intelligence. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A strong and efficient user authentication protocol for wireless sensor networks using smart card

引用

Journal of Convergence Information Technology 2012年第7期7卷 35-42页

作者： Su, Bo Pei, Changxing Yang, Junhan Tang, Jun Wang, Bin The State Key Lab. of ISN Xidian University Xi'an Shaanxi 710071 China School of Computer China University of Mining and Technology Xuzhou Jiangsu 221116 China

Cryptanalysis of Zhou et al.'s user authentication protocol, we found that it was easily vulnerable to password guessing attack, user impersonation attack, privileged administrator attack and Dos attack if the attacker stole the legitimate user's smart card. Moreover, a key problem to design user authentication protocol for wireless sensor networks is to prolong the lifetime of the WSNs while guaranteeing the security. In this paper, we proposed a strong and efficient user authentication protocol for WSNs using smart card. Performance analysis shows that our proposed protocol is more secure against many popular attacks and achieves high efficiency.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

A reconfigurable routing method for fault-tolerant mesh-based network on chip

引用

Journal of Information and Computational Science 2013年第1期10卷 157-165页

作者： Liu, Yanhua Ruan, Ying Lai, Zongsheng Sun, Ling Institute of Microelectronics Circuit and System East China Normal University Shanghai 200241 China Jiangsu Provincial Key Lab. of ASIC Design Nantong University Nantong 226019 China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

As the semiconductor industry advances to nano-technology points, Network on Chip (NoC) components are becoming vulnerable to errors during the system operation. Consequently, fault-tolerant techniques for NoC are needed to achieve high reliability. In this paper, we present a fault-tolerant routing method to tolerate faulty routers in a two-dimension (2D) mesh-based NoC. With this method, the system can have a multi-router fault-tolerant capability and the routing path can be dynamically reconfigured to support different situations caused by faulty routers in NoC. Fault-tolerance capability and system performance of the proposed method are evaluated through analysis and simulations. Theoretical analysis and simulation results show that the proposed method can enhance the reliability of system and offer considerable fault-tolerance capability. © 2013 by Binary Information Press.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

Sparse structured probabilistic projections for factorized latent spaces 11

Sparse structured probabilistic projections for factorized l...

引用

20th ACM Conference on Information and Knowledge Management, CIKM'11

作者： Qu, Xinquan Chen, Xinlei State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450307178

Building a common representation for several related data sets is an important problem in multi-view learning. CCA and its extensions have shown that they are effective in finding the shared variation among all data sets. However, these models generally fail to exploit the common structure of the data when the views are with private information. Recently, methods explicitly modeling the information into shared part and private parts have been proposed, but they presume to know the prior knowledge about the latent space, which is usually impossible to obtain. In this paper, we propose a probabilistic model, which could simultaneously learn the structure of the latent space whilst factorize the information correctly, therefore the prior knowledge of the latent space is unnecessary. Furthermore, as a probabilistic model, our method is able to deal with missing data problem in a natural way. We show that our approach attains the performance of state-of-art methods on the task of human pose estimation when the motion capture view is completely missing, and significantly improves the inference accuracy with only a few observed data. © 2011 ACM.

关键词： factorized latent space multi-view learning sparse structured projections

来源：评论

学校读者我要写书评

暂无评论

A high-performance algorithm for frequent itemset mining

A high-performance algorithm for frequent itemset mining

引用

13th International Conference on Web-Age Information Management, WAIM 2012

作者： Qu, Jun-Feng Liu, Mengchi State Key Lab. of Software Engineering School of Computer Wuhan University Wuhan 430072 China

ISBN: (纸本)9783642322808

Frequent itemsets, also called frequent patterns, are important information about databases, and mining efficiently frequent itemsets is a core problem in data mining area. Pattern growth approaches, such as the classic FP-Growth algorithm and the efficient FPgrowth*algorithm, can solve the problem. The approaches mine frequent itemsets by constructing recursively conditional databases that are usually represented by prefix-trees. The three major costs of such approaches are prefix-tree traversal, support counting, and prefix-tree construction. This paper presents a novel pattern growth algorithm called BFP-growth in which the three costs are greatly reduced. We compare the costs among BFP-growth, FP-Growth, and FPgrowth*, and illuminate that the costs of BFP-growth are the least. Experimental data show that BFP-growth outperforms not only FP-Growth and FPgrowth*but also several famous algorithms including dEclat and LCM, ones of the fastest algorithms, for various databases. © 2012 Springer-Verlag.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Search web images using objects, backgrounds and conditions

Search web images using objects, backgrounds and conditions

引用

20th ACM International Conference on Multimedia, MM 2012

作者： Zhang, Jiemi Wu, Chenxia Cai, Deng State Key Lab. of CAD and CG College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9781450310895

As the volumes of web images have grown rapidly in the last decade, Content-Based Image Retrieval (CBIR) has attracted substantial interests as an effective tool to manage the images. Most existing CBIR systems focus on the object in the image, while ignoring the conditions (day/night, sunny/rain, etc) and the backgrounds, both of which are very helpful to meet the user's information need. To overcome this shortcoming, in this paper, we present a novel CBIR system depending on a novel query formulation considering three aspects: Object, Background and Condition. Specifically, we design a user-friendly interface to help the user formulate a query. The interface can allow the user to give the percentage, relative position and size of each object in the background. Moreover, a corresponding effective ranking method is proposed to return the desirable search results. Experimental results demonstrate that our proposed system improves the searching performance and the user experience compared with the existing searching systems. © 2012 ACM.

关键词： Content based retrieval

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：