检索结果-内蒙古大学图书馆

2017 2nd International Conference on Control, Automation and Artificial Intelligence(CAAI2017)

作者： Jia Chen Tongge Xu Zhang Xiong The State Key Laboratory of Software Development Environment Beihang University Research Institute of Beihang University in Shenzhen Lab 673 School of Computer Science and Engineering Beihang University

ISBN: (纸本)9781510845541

Find out the potential favorite data is the essence of recommendation techniques, which facilitates the recommendation techniques become a vital issue in the big data researches and applications. The traditional recommendation research and application centers on the commercial items and resources. We apply the recommendation to social relationships in social networks. We design a framework which can analyze and recommend various types of relationships. The framework has four modules and three work modes. Furthermore, we design a hybrid recommendation approach in the framework for the balancing between accuracy and efficiency. The framework can recommend the social relationships with high accuracy and low cost.

关键词： big data framework recommendation social relationships

来源：评论

学校读者我要写书评

暂无评论

Hierarchical recurrent attention network for response generation

arXiv

引用

arXiv 2017年

作者： Xing, Chen Wu, Wei Wu, Yu Zhou, Ming Huang, Yalou Ma, Wei-Ying College of Computer and Control Engineering Nankai University Tianjin China College of Software Nankai University Tianjin China Microsoft Research Beijing China State Key Lab of Software Development Environment Beihang University Beijing China

We study multi-turn response generation in chatbots where a response is generated according to a conversation context. Existing work has modeled the hierarchy of the context, but does not pay enough attention to the fact that words and utterances in the context are differentially important. As a result, they may lose important information in context and generate irrelevant responses. We propose a hierarchical recurrent attention network (HRAN) to model both aspects in a unified framework. In HRAN, a hierarchical attention mechanism attends to important parts within and among utterances with word level attention and utterance level attention respectively. With the word level attention, hidden vectors of a word level encoder are synthesized as utterance vectors and fed to an utterance level encoder to construct hidden representations of the context. The hidden vectors of the context are then processed by the utterance level attention and formed as context vectors for decoding the response. Empirical studies on both automatic evaluation and human judgment show that HRAN can significantly outperform state-of-the-art models for multi-turn response generation. Copyright © 2017, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

research on Web service composition based on relational database

引用

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) 2013年第SUPPL.2期41卷 6-9页

作者： Liu, Jianxiao Deng, Yong Liu, Sicong Zhang, Xiuwei Liu, Feng College of Science Huazhong Agricultural University Wuhan 430070 China NO.722 Research and Development Institute China Shipbuilding Industry Corporation Wuhan 430074 China State Key Lab of Software Engineering Wuhan University Wuhan 430072 China

In order to solve the problem of low efficiency and accuracy of existing Web service composition methods, the join operation in relational database was used and a Web service composition method based on relational database(RDB) was proposed. The information of Web services and ontology were stored into relational database firstly. Then the tables of Output and Input were joined looply using the join operation in RDB from the semantic reasoning aspect between ontology concepts. The service execution path can be constructed and the services can be composited dynamically and flexibly. Finally, it used the experiments to compare the composite service finding efficiency and recall rate between the proposed method and other approaches. The experiment shows this method can enhance the composite service finding recall rate apparently in the condition of not affecting composite services finding efficiency.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Unifying software and product configuration: A research roadmap

Unifying software and product configuration: A research road...

引用

Workshop on Configuration at ECAI, ConfWS 2012

作者： Hubaux, Arnaud Jannach, Dietmar Drescher, Conrad Murta, Leonardo Männistö, Tomi Czarnecki, Krzysztof Heymans, Patrick Nguyen, Tien Zanker, Markus PReCISE Research Center University of Namur Belgium Department of Computer Science TU Dortmund Germany Computing Laboratory University of Oxford United Kingdom Fluminense Federal University Niterói Brazil Aalto University School of Science Finland Generative Software Development Lab University of Waterloo Canada Electrical and Computer Engineering Department Iowa State University United States Alpen-Adria-Universität Klagenfurt Austria

For more than 30 years, knowledge-based product configuration systems have been successfully applied in many industrial domains. Correspondingly, a large number of advanced techniques and algorithms have been developed in academia and industry to support different aspects of configuration reasoning. While traditional research in the field focused on the configuration of physical artefacts, recognition of the business value of customizable software products led to the emergence of software product line engineering. Despite the significant overlap in research interests, the two fields mainly evolved in isolation. Only limited attempts were made at combining the approaches developed in the different fields. In this paper, we first aim to give an overview of commonalities and differences between software product line engineering and product configuration. We then identify opportunities for cross-fertilization between these fields and finally develop a research agenda to combine their respective techniques. Ultimately, this should lead to a unified configuration approach.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

An Improved Hidden Markov Model for Anomaly Detection Using Frequent Common Patterns

An Improved Hidden Markov Model for Anomaly Detection Using ...

引用

IEEE International Conference on Communications

作者： Afroza Sultana Abdelwahab Hamou-Lhadj Mario Couture Software Behavioural Analysis Research Lab Department of Electrical and Computer Engineering Concordia University Software Analysis and Robustness Group Defense Research and Development Canada

ISBN: (纸本)9781457720529

Host-based intrusion detection techniques are needed to ensure the safety and security of software systems, especially, if these systems handle sensitive data. Most host-based intrusion detection systems involve building some sort of reference models offline, usually from execution traces (in the absence of the source code), to characterize the system healthy behavior. The models can later be used as a baseline for online detection of abnormal behavior. Perhaps the most popular techniques are the ones based on the use of Hidden Markov Models (HMM). These techniques, however, require long training time of the models, which makes them computationally infeasible, the main reason being the large size of typical traces. In this paper, we propose an improved HMM using the concept of frequent common patterns. In other words, we build models based on extracting the largest n-grams (patterns) in the traces instead of taking each trace event on its own. We show through a case study that our approach can reduce the training time by 31.96%-48.44% compared to the original HMM algorithms while keeping almost the same accuracy rate.

关键词： Host-based Anomanly Detection Systems HMM N-gram extraction algorithm Behavioral modeling

来源：评论

学校读者我要写书评

暂无评论

Model based approach to assist test case creation, execution, and maintenance for test automation

Model based approach to assist test case creation, execution...

引用

1st International Workshop on End-to-End Test Script engineering, ETSE 2011, Co-located with the 2011 International Symposium on software Testing and Analysis

作者： Gupta, Priya Surve, Prafullakumar Tata Research Development and Design Center Software Engineering Lab 54 B Industrial Estate Pune 411013 India

ISBN: (纸本)9781450308083

Applications, once developed, need to be maintained and tested as they undergo frequent changes. Test automation plays a significant role in testing activity, as it saves time and provides better utilization of resources. Test automation itself comes with many challenges such as mapping of user specifications to test-cases, test-case generation, maintenance of test-cases and test-scripts. In this paper, we propose a model-driven approach for test automation to provide end-to-end assistance in test case generation and automation, with focus on re-usability and maintainability. Functional specifications of system are mapped to test-cases for traceability which ensures better test automation process. Functional specifications of system are used as an input to design process models, which are used for automatic generation of test-cases. Process models consist of flows of different tasks in specified sequence. By recording the individual tasks, test-scripts for all the test-cases are generated. The test-cases and test-scripts can be modified and maintained using user friendly user-interface (UI) to provide better control to test designer and ease the load of tester. In this paper, we also present a case study performed on JBilling application [18] to evaluate our approach. Copyright 2011 ACM.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Microgroup Mining on TSina via Network Structure and User Attribute

Microgroup Mining on TSina via Network Structure and User At...

引用

7th International Conference on Advanced Data Mining and Applications

作者： Xiong, Xiaobing Niu, Xiang Zhou, Gang Xu, Ke Huang, Yongzhong National Digital Switching System Engineering Technological Research Center China State Key Lab. of Software Development Environment Beihang University China

ISBN: (纸本)9783642258558

In this paper, we focus on the problem of community detection on TSina: the most popular microblogging network in China. By characterizing the structure and content of microgroup (community) on TSina in detail, we reveal that different from ordinary social networks, the degree assortativity coefficients are negative on most microgroups. In addition, we find that users from the same rnicrogroup likely exhibit some similar attributes (e.g., sharing many followers, tags and topics). Inspired by these new findings, we propose a united method for microgroup detection without losing the information of link structure and user attribute. First, the link direction is converted to the weight by giving higher value to the more surprising link, while attribute similarity between two users is measured by the Jaccard coefficient of common features like followers, tags, and topics. Then, above two factors are uniformly converted to the edge weight of a newly generated network. Finally, many frequently used community detection algorithms that support weighted network would be employed. Extensive experiments on real social networks show that the factors of link structure and user attribute play almost equally important roles in microgroup detection on TSina.. Our newly proposed method significantly outperforms the traditional methods with average accuracy being improved by 25%, and the number of unrecognized users decreasing by about 75%.

关键词： Microblogging Microgroup Mining Community Detection United Method

来源：评论

学校读者我要写书评

暂无评论

Performances and characteristics of DIGRank, ranking in the incomplete networks

Performances and characteristics of DIGRank, ranking in the ...

引用

11th IEEE International Conference on Data Mining, ICDM 2011

作者： Niu, Xiang Li, Lusong Tkach, Daniel Xiong, Xiaobing Li, He Xu, Ke State Key Lab. of Software Development Environment Beihang University Beijing China University of Science and Technology Beijing Beijing China National Digital Switching System Engineering and Technological Research Center Beijing China

ISBN: (纸本)9780769544083

PageRank has been widely used in ranking retrieval results on the web, finding the top influential papers in citation networks or detecting valuable users in online social networks. However, in practice, it is usually hard to obtain a complete structure of any above networks to rank nodes. Thus, some researchers have begun to explore how to get estimated ranks efficiently without acquiring the whole network. They have proposed some approximating methods, however, it is difficult to determine which method is the best one or which is suitable to a certain application. In this case, we set experiments in small-world and scale-free generated networks to certify the feasibility and characteristics of four approximating methods. We also use eleven real networks to mention different optimal conditions for these methods. We find the DIGRank method performs better than other local estimation methods in almost every given subgraph. Besides, Mean field approach method tends to perform well in networks that have low average shortest path length, small amount of nodes with the same low indegree, or weak community structure. Finally, we apply the most versatile method DIGRank to Sina micro-blog website to precisely classify users in a group as elites, grassroots or mummy users. © 2011 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Adaptive virtual machine provisioning in elastic multi-tier cloud platforms

Adaptive virtual machine provisioning in elastic multi-tier ...

引用

IEEE International Conference on Networking, Architecture and Storage

作者： Zhang, Fan Cao, Junwei Cai, Hong Mulcahy, James J. Wu, Cheng National CIMS Engineering and Research Center Department of Automation Tsinghua University Beijing 100084 China Research Institute of Information Technology Tsinghua University Beijing 100084 China Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China IBM China Software Development Lab. China Florida Atlantic University Boca Raton FL United States

ISBN: (纸本)9780769545097

Virtual machines are allocated on demand in virtualized cloud platforms to provide flexible and reliable services. The major difficulty lies in satisfying the conflicting objectives of reducing response time while lowering resource costs. In this paper, a mathematical multi-tier framework for virtual machine allocation is proposed, which can be used to capture the performance of the cloud platform. We first use simulations to derive virtual resource allocation policies, and later use real benchmarking applications to verify the effectiveness of this framework. Experimental results show that the model can be simply and effectively used to satisfy the response time requirement as well as lowering the cost of using the virtual machine resources. © 2011 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

Minimum error bounded efficient 1 tracker with occlusion detection

Minimum error bounded efficient 1 tracker with occlusion det...

引用

作者： Mei, Xue Ling, Haibin Wu, Yi Blasch, Erik Bai, Li Assembly Test Technology Development Intel Corporation Chandler AZ United States Center for Information Science and Technology Computer and Information Science Department Temple University Philadelphia PA United States College of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China Air Force Research Lab SNAA OH United States Electrical and Computer Engineering Department Temple University Philadelphia PA United States

ISBN: (纸本)9781457703942

Recently, sparse representation has been applied to visual tracking to find the target with the minimum reconstruction error from the target template subspace. Though effective, these L1 trackers require high computational costs due to numerous calculations for 1 minimization. In addition, the inherent occlusion insensitivity of the 1 minimization has not been fully utilized. In this paper, we propose an efficient L1 tracker with minimum error bound and occlusion detection which we call Bounded Particle Resampling (BPR)-L1 tracker. First, the minimum error bound is quickly calculated from a linear least squares equation, and serves as a guide for particle resampling in a particle filter framework. Without loss of precision during resampling, most insignificant samples are removed before solving the computationally expensive 1 minimization function. The BPR technique enables us to speed up the L1 tracker without sacrificing accuracy. Second, we perform occlusion detection by investigating the trivial coefficients in the 1 minimization. These coefficients, by design, contain rich information about image corruptions including occlusion. Detected occlusions enhance the template updates to effectively reduce the drifting problem. The proposed method shows good performance as compared with several state-of-the-art trackers on challenging benchmark sequences. © 2011 IEEE.

关键词： Error detection

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：