检索结果-内蒙古大学图书馆

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

作者： Liu, Tao Li, Minghui Zhou, Shusen Du, Xiaoyong Key Laboratory of Data Engineering and Knowledge Engineering MOE 100872 Beijing China School of Information Renmin University of China 100872 Beijing China Microsoft Asian Research and Development Group 100080 Beijing China Shenzhen Graduate School Harbin Institute of Technology 518055 Shenzhen China

ISBN: (纸本)9781450307178

Automatic analysis of sentiments expressed in large scale online reviews is very important for intelligent business applications. Sentiment classification is the most popular task of sentiment analysis, which is more challenging than traditional topic-based text classification. Basic features, such as vocabulary words, are not enough to classify sentiments well. Deep Belief Network (DBN) is introduced to discover more abstract features of sentiments. To capture full information of the features, large-size network can be constructed, but at the same time, large-size network tends to over fit the training data and even noise, which will reduce the generalization ability of the network. In this paper, L2-norm Deep Belief Network (L2DBN) is proposed, which uses L2-norm regularization to optimize the network parameters of DBN. L2DBN is first initialized by an unsupervised layer-wise training algorithm, and then fine-tuned by a supervised procedure. Network parameters are optimized using both classification loss and network complexity. Experimental results show that the proposed L2DBN outperforms the state-of-the-art method and the basic DBN on golden, noisy and heterogeneous datasets. © 2011 ACM.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A practice probability frequent pattern mining method over transactional uncertain data streams

A practice probability frequent pattern mining method over t...

引用

Lecture Notes in Computer Science

作者： Liao, Guoqiong Wu, Linqing Wan, Changxuan Xiong, Naixue School of Information Technology Jiangxi University of Finance and Economics Nanchang 330013 China Jiangxi Key Laboratory of Data and Knowledge Engineering Nanchang 330013 China Department of Computer Science Georgia State University United States

ISBN: (纸本)9783642236402

In recent years, large amounts of uncertain data are emerged with the widespread employment of the new technologies, such as wireless sensor networks, RFID and privacy protection. According to the features of the uncertain data streams such as incomplete, full of noisy, non-uniform and mutable, this paper presents a probability frequent pattern tree called PFP-tree and a method called PFP-growth, to mine probability frequent patterns based on probability damped windows. The main characteristics of the suggested method include: (1) adopting time-based probability damped window model to enhance the accuracy of mined frequent patterns;(2) setting an item index table and a transaction index table to speed up retrieval on the PFP-tree;and (3) pruning the tree to remove the items that cannot become frequent patterns;. The experimental results demonstrate that PFP-growth method has better performance than the main existing schemes in terms of accuracy, processing time and storage space. © 2011 Springer-Verlag.

关键词： Probability

来源：评论

学校读者我要写书评

暂无评论

K-nearest neighbors in uncertain graph

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2011年第10期48卷 1850-1858页

作者： Zhang, Yinglong Li, Cuiping Chen, Hong Du, Lingxia Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Ministry of Education Beijing 100872 China School of Computer and Information Engineer Jiangxi Agriculture University Nanchang 330045 China

In many areas, a lot of data have been modeled by graphs which are subject to uncertainties, such as molecular compounds and protein interaction networks. While many real applications, for example, collaborative filtering, fraud detection, and link prediction in social networks etc, rely on efficiently answering k-nearest neighbor queries (kNN), which is the problem of computing the most "similar" k nodes to a given query node. To solve the problem, in this paper a novel method based on measurement of SimRank is proposed. However, because graphs evolve over time and are uncertainly, the computing cost can be very high in practice to solve the problem using the existing algorithms of SimRank. So the paper presents an optimization algorithm. Introducing path threshold, which is suitable in both determined graph and uncertain graph, the algorithm merely considers the local neighborhood of a given query node instead of whole graph to prune the search space. To further improving efficiency, the algorithm adopts sample technology in uncertain graph. At the same time, theory and experiments interpret and verify that the optimization algorithm is efficient and effective.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

On Mutual Support of Modern and Traditional Access Control Models with UCON and BLP as Case Study

On Mutual Support of Modern and Traditional Access Control M...

引用

WRI International Conference on Communications and Mobile Computing, CMC

作者： Hui Feng Wenchang Shi Zhaohui Liang Bin Liang School of Information Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Renmin University of China Beijing China

Access control is essential to computer security, especially in an open, distributed, networked communication environment. Modern access control model such as UCON aims at accommodating general requirements. Traditional one such as BLP focuses on specific properties, e.g. confidentiality. Both of these two realms have their limitations. Taking UCON and BLP as case study, this paper explores mutual support of modern and traditional access control models. It investigates BLP's adaptable characteristic in the UCON perspective. First, it constructs properties in the UCON language to manifest the BLP adaptability, which shows that the BLP adaptability can be ensured to function correctly by the UCON framework. Further, it proposes a formal specification for the BLP adaptability under the UCON framework with the Temporal Logic of Actions, which demonstrates that the BLP adaptability is in good consistency with the UCON model. The significance of the paper is twofold. On the one hand, it exhibits that adaptable quality of the traditional BLP model may be ensured theoretically by the philosophy of modern access control. On the other hand, it enriches the real sense of modern access control models by strengthening the power of traditional access control models.

关键词： Adaptation model Sensitivity Authorization Permission Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Analysis of bandwagon and average hybrid attack model against trust-based recommender systems

Analysis of bandwagon and average hybrid attack model agains...

引用

2011 International Conference on Management of e-Commerce and e-Government, ICMeCG 2011

作者： Zhang, Fuguo School of Information and Technology Jiangxi University of Finance and Economics Nanchang China Institute of Information Resource Management Jiangxi University of Finance and Economics Nanchang China Jiangxi Key Laboratory of Data and Knowledge Engineering Jiangxi University of Finance and Economics Nanchang China

ISBN: (纸本)9780769545448

Recommender systems have been accepted as a vital application on the web by offering product advice or information that users might be interested in. Despite its success, similarity-based collaborative filtering suffers from some significant limitations, such as scalability, sparsity and recommendation attack. Prior work has shown incorporating trust mechanism into traditional collaborative filtering recommender systems can improve these limitations. However, trust-based recommender systems are also known to be vulnerable to profile infection attacks. Malicious users can inject a large number of biased profiles into such a system in order to make recommendations that favor or disfavor given items. In this paper, we propose a bandwagon and average hybrid attack model and analysis the effectiveness of the attack model against topic-level trust-based recommender algorithm. The results of our experiments conducted on well-known dataset show that the hybrid attack model is more effective than other attack models. © 2011 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Lawyer information integration and recommendation by multi-source information validation

Lawyer information integration and recommendation by multi-s...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Tao Liu Biao Fan He Hu Xiao-Yong Du Key Laboratory of Data Engineering and Knowledge Engineering MOE Renmin University of China China School of Information Renmin University of China Beijing China

On the internet, all-round lawyer information is located at separated information sources, which prevent web users from effective information acquisition. In order to build a unified view of separated, heterogeneous, and often redundant lawyer information, we propose a new information integration method using multi-source information cross-validation. Based on the unified integrated data, a lawyer recommendation system is built. Several key technologies are presented and evaluated, including the multi-source information acquisition and validation. Experimental results indicate the key techniques used in the system are effective for lawyer information integration and recommendation.

关键词： Organizations Crawlers Search engines data mining Web pages databases Reliability

来源：评论

学校读者我要写书评

暂无评论

Parallel Aggregation Queries over Star Schema: A Hierarchical Encoding Scheme and Efficient Percentile Computing as a Case

Parallel Aggregation Queries over Star Schema: A Hierarchica...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Xiongpai Qin Huiju Wang Xiaoyong Du Shan Wang Ministry of Education Key Laboratory of Data Engineering and Knowledge Engineering RUC Beijing China School of Information Renmin University of China Beijing China

Big data analysis is a main challenge we meet recently. Cloud computing is attracting more and more big data analysis applications, due to its well scalability and fault-tolerance. Some aggregation functions, like SUM, can be computed in parallel, because they satisfy distributive law of addition. Unfortunately, some of statistical functions are not naturally parallelizable. That means they do not satisfy distributive law of addition. In this paper, we focus on percentile computing problem. We proposed an iterative-style prediction-based parallel algorithm in a distributed system. Prediction is done through a sampling technique. Experiment results verify the efficiency of our algorithm.

关键词： Prediction algorithms Convergence Algorithm design and analysis Histograms Encoding Query processing Indexes

来源：评论

学校读者我要写书评

暂无评论

Managing Electronic Records in E-government:Current Trends and Future Directions Internationally

Managing Electronic Records in E-government:Current Trends a...

引用

International Conference on Management and Service Science(2011年第五届管理与服务科学国际会议 MASS 2011)

作者： Xiaomi An Wei Zhang Shuyang Sun Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of China Ministry of School of Information Resources Management Renmin University of China Beijing China

More and more literature has been written on electronic records management (ERM) in e-government in recent three years, however, much is limited to experiences of one country with more focus on electronic records management systems (ERMS). This paper aims to investigate current trends and future directions of ERM including ERMS in e-government with more focus on comprehensive approaches internationally. Representative shows current ERMS have limitations either from IT perspectives or records and archives management perspectives managing records as data. Future research is called for more concerns of e-government and more involvement in efficient civil service. Case studies of representative policies, regulations, best practices guidelines from Australia, Canada, New Zealand, UK and U.S show challenges of ERM in e-government are getting more and more recognized in information risk, data governance and efficient civil service. Current trends of ERM in e-government are toward multidisciplinary and collaborative approaches to ERM managing records as information resources and business asset. Findings indicate that future directions of ERM in e-government would be toward meta-synthesis management at both organizational and national level, with integration concerns of collaboration, optimization and innovation of both ERM and e-government for civil service. The findings may have implications to be of use to both ERM and e-government professions internationally.

关键词： Electronic government Law Information services Collaboration

来源：评论

学校读者我要写书评

暂无评论

A decomposition method to solve the large-scale scheduling problems based on cellular manufacturing technology

A decomposition method to solve the large-scale scheduling p...

引用

International Conference on Artificial Intelligence, Management Science and Electronic Commerce (AIMSEC)

作者： Li Niu Xiaoting Han Data Engineering and Knowledge Engineering Key Laboratory School of Information Resource Management Renmin University of China Beijing China School of Economics and Management Beihang University Beijing China

A decomposition method to solve the large-scale scheduling problems is proposed in this paper. Focused on large-scale scheduling problems, introducing cellular manufacturing technology to decompose scheduling problems, a collaborative scheduling process based on manufacturing cells is designed. Moreover, focused on the coupling problem in scheduling process in the context of cellular manufacturing, a decomposition method is suggested to achieve the decomposition of cross-cell jobs. Finally, the whole scheduling process is simplified through redefining the environment of cellular manufacturing.

关键词： Job shop scheduling Cellular manufacturing Processor scheduling Computers Educational institutions Economics

来源：评论

学校读者我要写书评

暂无评论

A decomposition method to solve the large-scale scheduling problems based on cellular manufacturing technology

A decomposition method to solve the large-scale scheduling p...

引用

2011 2nd International Conference on Artificial Intelligence, Management Science and Electronic Commerce, AIMSEC 2011

作者： Niu, Li Han, Xiaoting Data Engineering and Knowledge Engineering Key Laboratory School of Information Resource Management Renmin University of China Beijing China School of Economics and Management Beihang University Beijing China

ISBN: (纸本)9781457705366

A decomposition method to solve the large-scale scheduling problems is proposed in this paper. Focused on largescale scheduling problems, introducing cellular manufacturing technology to decompose scheduling problems, a collaborative scheduling process based on manufacturing cells is designed. Moreover, focused on the coupling problem in scheduling process in the context of cellular manufacturing, a decomposition method is suggested to achieve the decomposition of cross-cell jobs. Finally, the whole scheduling process is simplified through redefining the environment of cellular manufacturing. © 2011 IEEE.

关键词： Cellular manufacturing

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：