检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Lei, Kai Zhang, Bing Deng, Yang Zhang, Dongyu Shen, Ying Institute of Big Data Technologies Shenzhen Key Lab for Cloud Computing Technology & Applications Peking University SHENZHENP.R518055 China C.S. Depart. Harbin Institute of Technology

Named entity discovery and linking is the fundamental and core component of question answering. In Question Entity Discovery and Linking (QEDL) problem, traditional methods are challenged because multiple entities in one short question are difficult to be discovered entirely and the incomplete information in short text makes entity linking hard to implement. To overcome these difficulties, we proposed a knowledge graph based solution for QEDL and developed a system consists of Question Entity Discovery (QED) module and Entity Linking (EL) module. The method of QED module is a tradeoff and ensemble of two methods. One is the method based on knowledge graph retrieval, which could extract more entities in questions and guarantee the recall rate, the other is the method based on Conditional Random Field (CRF), which improves the precision rate. The EL module is treated as a ranking problem and Learning to Rank (LTR) method with features such as semantic similarity, text similarity and entity popularity is utilized to extract and make full use of the information in short texts. On the official dataset of a shared QEDL evaluation task, our approach could obtain 64.44% F1 score of QED and 64.86% accuracy of EL, which ranks the 2nd place and indicates its practical use for QEDL problem. Copyright © 2018, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Internet Traffic Analysis Using Community Detection and Apache Spark

Internet Traffic Analysis Using Community Detection and Apac...

引用

第九届网络分布式计算与知识发现国际会议( 2017 International Conference on Cyber-enabled distributed computing and knowledge discovery)

作者： Jiake Ni Weitao Weng Jiayu Chen Kai Lei Institute of Big Data Technologies Shenzhen Key Lab for Cloud Computing Technology & Applications School of Electronic and Computer Engineering(SECE)Peking University SHENZHEN 518055P.R.CHINA

With the rapid development of Internet,Internet traffic and end hosts continue to grow in *** behavior analysis for a large-scale network is becoming more and more *** address these challenges,this paper proposes an Internet traffic analysis approach based on community detection to discover community consisted of end hosts with similar traffic behavior in a large campus ***,we use only the IP-to-IP information without packet payloads to model the similarity of end hosts in campus *** the similarity graph which represent the social behavior similarity of all end hosts is ***,we leverage label Propagation algorithm to discover end hosts community on the similarity *** satisfy demands for the scalable analysis of evergrowing Internet traffic data,a Spark-based Internet traffic analysis system is developed,including implementing the above *** experimental results based on real campus network traffic show the benefits of the proposed approach in analyzing traffic behavior of a large-scale network on host community level and detecting potential anomalous traffic *** proposed approach reduces the complexity of analyzing the traffic behavior of a large network compare with analyzing individual *** addition,the experimental results also demonstrate the Spark-based Internet traffic analysis system can analyze Internet traffic efficiently.

关键词： Internet traffic analysis community detection Apache Spark data mining

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison and Evaluation of Web Development Technologies in PHP, Python, and ***

Performance Comparison and Evaluation of Web Development Tec...

引用

IEEE International Conference on Computational Science and Engineering, CSE

作者： Kai Lei Yining Ma Zhi Tan Shenzhen Key Lab for Cloud Computing Technology & Applications (SPCCTA) Peking University SHENZHEN P.R. CHINA GuangDong Poya Information & Technology Co. LTD GUANGZHOU P.R. CHINA

ISBN: (纸本)9781479979820

Large scale, high concurrency, and vast amount of data are important trends for the new generation of website. *** becomes popular and successful to build data-intensive web applications. To study and compare the performance of ***, Python-Web and PHP, we used benchmark tests and scenario tests. The experimental results yield some valuable performance data, showing that PHP and Python-Web handle much less requests than that of *** in a certain time. In conclusion, our results clearly demonstrate that *** is quite lightweight and efficient, which is an idea fit for I/O intensive websites among the three, while PHP is only suitable for small and middle scale applications, and Python-Web is developer friendly and good for large web architectures. To the best of our knowledge, this is the first paper to evaluate these Web programming technologies with both objective systematic tests (benchmark) and realistic user behavior tests (scenario), especially taking *** as the main topic to discuss.

关键词： Benchmark testing Web servers Concurrent computing Java Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Sledge: Towards Efficient Live Migration of Docker Containers

Sledge: Towards Efficient Live Migration of Docker Container...

引用

IEEE International Conference on cloud computing, cloud

作者： Bo Xu Song Wu Jiang Xiao Hai Jin Yingxi Zhang Guoqiang Shi Tingyu Lin Jia Rao Li Yi Jizhong Jiang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China State Key Laboratory of Intelligent Manufacturing System Technology Beijing China The University of Texas at Arlington Arlington TX USA Alibaba Cloud Computing Co. Ltd. Hangzhou China

ISBN: (数字)9781728187808

ISBN: (纸本)9781728187815

Modern large-scale cloud platforms require live migration technique on Docker containers with stateful workload to support load balancing, host maintenance, and Quality of Service (QoS) improvement. Efficient and scalable Docker live migration is expected to guarantee the component-integrity (image, runtime, and management context) with negligible downtime. In this paper, we present a highly efficient live migration system called Sledge, which ensures the component-integrity by integrating both images and management context during runtime migration. The key insight is that the layered image can be leveraged to reduce the migration overhead, and appropriately selective migration of management context will effectively improve QoS with negligible downtime. To achieve good scalability, a lightweight container registry mechanism for end-to-end image migration is designed to avoid the redundant layers transmission. In addition, a dynamic context loading scheme is proposed to precisely load the management context into the running daemon, which can significantly reduce downtime. Experiments show that, compared with the state-of-the-art, Sledge reduces 57% of total migration time, 55% of image migration time, and 70% downtime.

关键词： cloud computing Runtime Scalability Loading Quality of service Containers Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Extracting Unknown Words from Sina Weibo via Data Clustering

Extracting Unknown Words from Sina Weibo via Data Clustering

引用

IEEE International Conference on Communications

作者： Kai Lei WeiYang Zhang Kai Zhang Kuai Xu Institute of Big Data Technologies Shenzhen Key Lab for Cloud Computing Technology & Applications School of Electronics and Computer Engineering (SECE) Peking University School of Mathematical and Natural Sciences Arizona State University

ISBN: (纸本)9781467364300

Sina Weibo, a Twitter-like microblogging site attracting over 240 million monthly active users to tweet, retweet, and comment, has rapidly become one of the most popular social media sites in China. As many users create new and innovative words on their tweets and comments, it is necessary to extract these emerging words, which do not exist in today's Chinese vocabulary or dictionary. Towards this end, this paper proposes a novel method based on data clustering of Weibo users and tweets for extracting unknown words from Weibo tweets and comments. Specifically, relying on the similarity of the users who post the tweets, we apply a hierarchical clustering to divide Weibo data into distinct groups, e.g., sports, news stories, movies, before extraction. Comparing with the method of unclustered Weibo data, our experimental results have successfully demonstrated the benefits of the proposed data clustering scheme for improving the recall and accuracy of extracting unknown Chinese words from tweets and comments.

关键词： Entropy Context Data mining Clustering algorithms Social network services Clustering methods Couplings

来源：评论

学校读者我要写书评

暂无评论

Profiling the Followers of the Most Influential and Verified Users on Sina Weibo

Profiling the Followers of the Most Influential and Verified...

引用

IEEE International Conference on Communications

作者： Huiyu Wang Kai Lei Kuai Xu Institute of Big Data Technologies Shenzhen Key Lab for Cloud Computing Technology & Applications School of Electronics and Computer Engineering (SECE) Peking University School of Mathematical and Natural Sciences Arizona State University

ISBN: (纸本)9781467364300

The new social media such as Twitter and Sina Weibo has become an increasingly popular channel for spreading influence, challenging traditional media such as TVs and news-papers. The most influential and verified users, also called big-V accounts on Sina Weibo often attract million of followers and fans, creating massive "celebrity-centric" social networks on the social media, which play a key role in disseminating breaking news, latest events, and controversial opinions on social issues. Given the importance of these accounts, it is very crucial to understand social networks and user influence of these accounts and profile their followers' behaviors. Towards this end, this paper monitors a selected group of influential users on Sina Weibo and collects their tweet streams as well as retweeting and commenting activities on these tweets from their followers. Our analysis on tweet data streams from Sina Weibo reveals when and what the followers comment on the tweets of these influential users, and discovers different temporal patterns and word diversity in the comments. Based on the insight gained from follower characteristics, we further develop simple and intuitive algorithms for classifying the followers into spammers and normal fans. Our experimental results demonstrate that the proposed algorithms are able to achieve an average accuracy of 95.20% in detecting spammers from the followers who have commented on the tweets of these influential accounts.

关键词： Classification algorithms Fans Social network services Media Feature extraction Standards Entropy

来源：评论

学校读者我要写书评

暂无评论

Robust unsupervised feature selection by nonnegative sparse subspace learning

引用

Neurocomputing 2019年 334卷 156-171页

作者： Wei Zheng Hui Yan Jian Yang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China School of Computer Engineering Jinling Institute of Technology Nanjing PR China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Key Laboratory of Trusted Cloud Computing and Big Data Analysis Nanjing Xiaozhuang University Nanjing PR China

Sparse subspace learning has been demonstrated to be effective in data mining and machine learning. In this paper, we cast the unsupervised feature selection scenario as a matrix factorization problem from the viewpoint of sparse subspace learning. By minimizing the reconstruction residual, the learned feature weight matrix with the l 2,1 -norm and the non-negative constraints not only removes the irrelevant features, but also captures the underlying low dimensional structure of the data points. Meanwhile in order to enhance the model's robustness, l 1 -norm error function is used to resistant to outliers and sparse noise. An efficient iterative algorithm is introduced to optimize this non-convex and non-smooth objective function and the proof of its convergence is given. Although, there is a subtraction item in our multiplicative update rule, we validate its non-negativity. The superiority of our model is demonstrated by comparative experiments on various original datasets with and without malicious pollution.

关键词： Subspace learning Non-negative matrix factorization Unsupervised feature selection

来源：评论

学校读者我要写书评

暂无评论

The real implementation of NDN forwarding strategy on Android smartphone

The real implementation of NDN forwarding strategy on Androi...

引用

IEEE Annual Ubiquitous computing, Electronics & Mobile Communication Conference (UEMCON)

作者： Xuewei Piao Lei Huang Kaiqi Yuan Jie Yuan Kai Lei School of Electronic and Computer Engineering (SECE) Peking University Shenzhen P.R. China Shenzhen Key Lab for Cloud Computing Technology & Applications (SPCCTA) Peking University Shenzhen P.R. China

ISBN: (纸本)9781509014972

A prototype system of Named Data Networking (NDN) wireless communication for Android is established based on NDN Forwarding Daemon (NFD). By porting NDN to Raspberry Pi and Android smartphone, the NDN-based Android application can connect to an NDN-supported access point built on Raspberry Pi, and communicate with remote NDN Testbed. As a contribution, this paper make a preliminary exploration on deploying NDN on Android terminals and interfacing Android smartphones with multiple NDN networks, on which various NDN forwarding strategies can be tested.

关键词： Androids Humanoid robots Wireless communication Java Libraries Routing Protocols

来源：评论

学校读者我要写书评

暂无评论

On-edge multi-task transfer learning: Model and practice with data-driven task allocation

arXiv

引用

arXiv 2021年

作者： Zheng, Zimu Chen, Qiong Hu, Chuang Wang, Dan Liu, Fangming The National Engineering Research Center for Big Data Technology and System Key Laboratory of Services Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China The Edge Cloud Innovation Lab. Technical Innovation Department Cloud BU Huawei Technologies Co. Ltd. Shenzhen China The Department of Computing Hong Kong Polytechnic University Kowloon Hong Kong Hong Kong

On edge devices, data scarcity occurs as a common problem where transfer learning serves as a widely-suggested remedy. Nevertheless, transfer learning imposes heavy computation burden to the resource-constrained edge devices. Existing task allocation works usually assume all submitted tasks are equally important, leading to inefficient resource allocation at a task level when directly applied in Multi-task Transfer Learning (MTL). To address these issues, we first reveal that it is crucial to measure the impact of tasks on overall decision performance improvement and quantify task importance. We then show that task allocation with task importance for MTL (TATIM) is a variant of NP-complete Knapsack problem, where the complicated computation to solve this problem needs to be conducted repeatedly under varying contexts. To solve TATIM with high computational efficiency, we propose a Data-driven Cooperative Task Allocation (DCTA) approach. Finally, we evaluate the performance of DCTA by not only a trace-driven simulation, but also a new comprehensive real-world AIOps case study which bridges model and practice via a new architecture and main components design within AIOps system. Extensive experiments show that our DCTA reduces 3.24 times of processing time, and saves 48.4% energy consumption compared with the state-of-the-art when solving TATIM. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Relation-Guided Representation Learning

arXiv

引用

arXiv 2020年

作者： Kang, Zhao Lu, Xiao Liang, Jian Bai, Kun Xu, Zenglin School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Cloud and Smart Industries Group Tencent Beijing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Center for Artificial Intelligence Peng Cheng Lab Shenzhen China

Deep auto-encoders (DAEs) have achieved great success in learning data representations via the powerful representability of neural networks. But most DAEs only focus on the most dominant structures which are able to reconstruct the data from a latent space and neglect rich latent structural information. In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning. Different from previous work, our framework well preserves the relations between samples. Since the prediction of pairwise relations themselves is a fundamental problem, our model adaptively learns them from data. This provides much flexibility to encode real data manifold. The important role of relation and representation learning is evaluated on the clustering task. Extensive experiments on benchmark data sets demonstrate the superiority of our approach. By seeking to embed samples into subspace, we further show that our method can address the large-scale and out-of-sample problem. Our source code is publicly available at: https://***/nbShawnLu/RGRL. Copyright © 2020, The Authors. 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

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：