检索结果-内蒙古大学图书馆

International Conference on Digital Information Management

作者： Wang, Xiao-Lin Lu, Bao-Liang Center for Brain-Like Computing and Machine Intelligence Department of Computer Science and Engineering China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University China

ISBN: (纸本)9781424475728

Hierarchies are very popular in organizing documents and web pages, hence automated hierarchical classification techniques are desired. However, the current dominant hierarchical approach of top-down method suffers accuracy decrease compared with flat classification approaches, because of error propagation and bottom nodes' data sparsity. In this paper we flatten hierarchies to relieve such accuracy decrease in top-down method, which aims to make hierarchies both effective enough to make large-scale classification tasks feasible, and simple enough to ensure high classification accuracy. We propose two flattening strategies based on these two causes of the accuracy decrease, and experimental results show that the flattening strategy designed for error propagation is more effective, which suggests that hierarchies with lots of branches at top layers can provide high classification accuracy. Besides, we analyze the computational complexity before and after flattening, which approximately agree with the experimental results. ©2010 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Constructing prioritized interaction test suite with interaction relationship

Constructing prioritized interaction test suite with interac...

引用

2nd International Workshop on Education Technology and computer science, ETCS 2010

作者： Yuan, Jianjun Jiang, Zuowen Key Laboratory of Embedded System and Service Computing Ministry of Education of China Tongji University Shanghai China Department of Computer Science and Technology Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

ISBN: (纸本)9780769539874

Interaction testing has addressed some issues on how to select a small subset of test cases. In many systems where interaction testing is needed, the entire test suite is not executed because of time or budget constraints. It is important to prioritize the test cases in these situations. On the other hand, there are not always interactions among any factors in real systems. Moreover, some factors may need N-way (N>2) testing since there is a closer relationship among them. We present a model for prioritized interaction testing with interaction relationship and propose a greedy algorithm for generating variable strength covering arrays with bias. © 2010 IEEE.

关键词： Testing

来源：评论

学校读者我要写书评

暂无评论

On robustness of forward-looking in sponsored search auction

On robustness of forward-looking in sponsored search auction

引用

作者： Bu, Tian-Ming Liang, Li Qi, Qi Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Department of Computer Science City University of Hong Kong Kowloon Hong Kong

We analyze the robustness of pure Nash Equilibria of sponsored search auctions, based on the forward-looking response function. To consider the robustness of such refined solution concept, we first study the convergence property of several adjustment schemes. Especially, we prove that under the randomized scheme, the auction always converges to a unique fixed point with probability one, whose revenue is equal to the celebrated VCG mechanism. Additionally, we study the robustness of such forward-looking strategic heuristic against aggressive selfish strategic heuristic called vindictive bidding. We investigate three types of such bidding strategies and substantiate that the pure Nash equilibrium still exists under two types even if there is an arbitrary portion of vindictive bidders. © Springer science+Business Media, LLC 2009.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Spectral and semidefinite relaxations of the CLUHSIC algorithm

Spectral and semidefinite relaxations of the CLUHSIC algorit...

引用

10th SIAM International Conference on Data Mining, SDM 2010

作者： Yang, Wen-Yun Kwok, James T. Lu, Bao-Liang University of California Los Angeles CA United States Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong Hong Kong Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University Shanghai China

CLUHSIC is a recent clustering framework that unifies the geometric, spectral and statistical views of clustering. In this paper, we show that the recently proposed discriminative view of clustering, which includes the DIFFRAC and DisKmeans algorithms, can also be unified under the CLUH-SIC framework. Moreover, CLUHSIC involves integer programming and one has to resort to heuristics such as iterative local optimization. In this paper, we propose two relaxations that are much more disciplined. The first one uses spectral techniques while the second one is based on semidefinite programming (SDP). Experimental results on a number of structured clustering tasks show that the proposed method significantly outperforms existing optimization methods for CLUHSIC. Moreover, it can also be used in semi-supervised classification. Experiments on real-world protein subcellu-lar localization data sets clearly demonstrate the ability of CLUHSIC in incorporating structural and evolutionary information. Copyright © by SIAM.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Gene selection and cancer classification: A rough sets based approach

Gene selection and cancer classification: A rough sets based...

引用

Rough Set and Knowledge Technology Conference, RSKT 2008

作者： Sun, Lijun Miao, Duoqian Zhang, Hongyun Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 China Department of Computer Science and Technology Tongji University Shanghai 201804 China

ISBN: (纸本)3642144667

Indentification of informative gene subsets responsible for discerning between available samples of gene expression data is an important task in bioinformatics. Reducts, from rough sets theory, corresponding to a minimal set of essential genes for discerning samples, is an efficient tool for gene selection. Due to the compuational complexty of the existing reduct algoritms, feature ranking is usually used to narrow down gene space as the first step and top ranked genes are selected . In this paper,we define a novel certierion based on the expression level difference btween classes and contribution to classification of the gene for scoring genes and present a algorithm for generating all possible reduct from informative *** algorithm takes the whole attribute sets into account and find short reduct with a significant reduction in computational complexity. An exploration of this approach on benchmark gene expression data sets demonstrates that this approach is successful for selecting high discriminative genes and the classification accuracy is impressive. © 2010 Springer-Verlag.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

A comparative study on two large-scale hierarchical text classification tasks' solutions

A comparative study on two large-scale hierarchical text cla...

引用

International Conference on Machine Learning and Cybernetics

作者： Zhang, Jian Zhao, Hai Lu, Bao-Liang Department of Computer Science and Engineering Center for Brain-Like Computing and Machine Intelligence Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai 200240 China MOE-Microsoft Key Laboratory for Intelligent Computing and Intelligent Systems Shanghai Jiao Tong University 800 Dong Chuan Road Shanghai 200240 China

ISBN: (纸本)9781424465262

Patent classification is a large scale hierarchical text classification (LSHTC) task. Though comprehensive comparisons, either learning algorithms or feature selection strategies, have been fully made in the text categorization field, few work was done for a LSHTC task due to high computational cost and complicated structural label characteristics. For the first time, this paper compares two popular learning frameworks, namely hierarchical support vector machine (SVM) and k nearest neighbor (k-NN) that are applied to a LSHTC task. Experiment results show that the latter outperforms the former in this LSHTC task, which is quite different from the usual results for normal text categorization tasks. Then this paper does a comparative study on different similarity measures and ranking approaches in k-NN framework for LSHTC task. Conclusions can be drawn that k-NN is more appropriate for the LSHTC task than hierarchical SVM and for a specific LSHTC task. BM25 outperforms other similarity measures and List Weak gains a better performance than other ranking approaches. We also find an interesting phenomenon that using all the labels of the retrieved neighbors can remarkably improve classification performance over only using the first label of the retrieved neighbors. © 2010 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

DCMTs: Supporting dynamically created migratory threads

DCMTs: Supporting dynamically created migratory threads

引用

International Conference on Computational science and Engineering

作者： Zhu, Yueting Zhang, Wu Jiang, Hai Lei, Yu Peng, Junjie Department of Computer Science and Engineering Shanghai University Shanghai China Department of Computer Science Arkansas State University Jonesboro AR United States Department of Computer Science and Engineering University of Texas Arlington TX United States Key Laboratory of Computer System and Architecture Institute of Computing Technology Chinese Academy of Sciences China

ISBN: (纸本)9780769543239

Thread migration is an effective technique for fault resilience and load balancing in high performance computing. However, flexible thread migration is not easy to achieve. In this paper, we present an approach to creating migratory threads dynamically at application level. The targets must be executable source files. Compared to the static ones, the number of threads created during migration with the new scheme is independent from the context. Various thread cases are considered for migration. Thread state is handled at application level. Variables are saved in structures in C language for speedy state construction. In order to solve the inability of traditional methods in tracking the created threads, a tree of active function calls is used to record the callback. The preprocessor of the proposed one is written in YACC for accuracy and programmability. The migration enabling process is transparent to programmers with the help of the preprocess. The experimental results have demonstrated the effectiveness of this approach. © 2010 IEEE.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

KNOB particle swarm optimizer 1

引用

1st International Conference on Advances in Swarm Intelligence, ICSI 2010

作者： Zhang, Junqi Liu, Kun Tan, Ying Key Laboratory of Embedded System and Service Computing Department of Computer Science and Technology Tongji University Shanghai 200092 China Department of Machine Intelligence School of Electronics Engineering and Computer Science Peking University Beijing 100871 China

ISBN: (数字)9783642134951

ISBN: (纸本)3642134947

It is not trivial to tune the swarm behavior just by parameter setting because of the randomness, complexity and dynamic involved in particle swarm optimizer (PSO). Hundreds of variants in the literature of last decade, brought various mechanism or ideas, sometimes also from outside of the traditional metaheuristics field, to tune the swarm behavior. While, in the same time, additional parameters have to be afforded. This paper proposes a new mechanism, named KNOB, to directly tune the swarm behavior through parameter setting of PSO. KNOB is defined as the first principal component of the statistical probability sequence of exploration and exploitation allocation along the search process. The using of the KNOB to tune PSO by parameter setting is realized through a statistical mapping, between the parameter set and the KNOB, learned by a radial basis function neural network (RBFNN) simulation model. In this way, KNOB provides an easy way to tune PSO directly by its parameter setting. A simple application of KNOB to promote is presented to verify the mechanism of KNOB. © 2010 Springer-Verlag.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Multicast capacity scaling for cognitive networks: General extended primary network

Multicast capacity scaling for cognitive networks: General e...

引用

2010 IEEE 7th International Conference on Mobile Adhoc and Sensor systems, MASS 2010

作者： Wang, Cheng Li, Xiang-Yang Tang, Shaojie Jiang, Changjun Department of Computer Science Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China Tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing China Department of Computer Science Illinois Institute of Technology Chicago IL 60616 United States

ISBN: (纸本)9781424474882

We study the capacity scaling laws for the cognitive network that consists of the primary hybrid network (PhN) and secondary ad hoc network (SaN). PhN is further comprised of an ad hoc network and a base station based (BS-based) network. SaN and PhN are overlapping in the same deployment region, operate on the same spectrum, but are independent with each other in terms of communication requirements. The primary users (PUs), i.e., the ad hoc nodes in PhN, have the priority to access the spectrum. The secondary users (SUs), i.e., the ad hoc nodes in SaN, are equipped with cognitive radios, and have the functionalities to sense the idle spectrum and obtain the necessary information of primary nodes in PhN. We assume that PhN adopts one out of three classical types of strategies, i.e., pure ad hoc strategy, BS-based strategy, and hybrid strategy. We aim to directly derive multicast capacity for SaN to unify the unicast and broadcast capacity under two basic principles: (1) The throughput for PhN cannot be undermined in order sense due to the presence of SaN. (2) The protocol adopted by PhN does not alter in the interest of SaN, anyway. Depending on which type of strategy is adopted in PhN, we design the optimal-throughput strategy for SaN. We show that there exists a threshold of the density of SUs according to the density of PUs beyond which it can be proven that: (1) when PhN adopts the pure ad hoc strategy or hybrid strategy, SaN can achieve the multicast capacity of the same order as it is stand-alone;(2) when PhN adopts the BS-based strategy, SaN can asymptotically achieve the multicast capacity of the same order as if PhN were absent, if some conditions of the relations among the number of SUs, PUs, the destinations of each multicast sessions in SaN, and the base stations in PhN hold. ©2010 IEEE.

关键词： Base stations

来源：评论

学校读者我要写书评

暂无评论

Enhance Information Flow Tracking with Function Recognition

引用

China Communications 2010年第6期7卷 24-29页

作者： Zhou Kan Huang Shiqiu Huang Shan Qi Zhengwei Gu Jian Guan Haibing School of software Shanghai Jliao Tong University Shanghai 200240 P. R. China Key Lab of Information Network Security Ministry of Public Security Department of Computer Science ＆ Engineering Shanghai Jiao Tong University Shanghai 200240 P. R China Shanghai Key Laboratory of Scalable Computing ＆ System Shanghai P. R. China

With the spread use of the computers, a new crime space and method are presented for criminals. Thus computer evidence plays a key part in criminal cases. Traditional computer evidence searches require that the computer specialists know what is stored in the given computer. Binary-based information flow tracking which concerns the changes of control flow is an effective way to analyze the behavior of a program. The existing systems ignore the modifications of the data flow, which may be also a malicious behavior. Thus the function recognition is introduced to improve the information flow tracking. Function recognition is a helpful technique recognizing the function body from the software binary to analyze the binary code. And that no false positive and no false negative in our experiments strongly proves that our approach is effective.

关键词： function recognition information flow tracking program behavior e-evidence.

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：