检索结果-内蒙古大学图书馆

Ranking and tagging bursty features in text streams with context language models

Frontiers of Computer Science 2017年第5期11卷 852-862页

作者： Wayne Xin ZHAO Chen LIU Ji-Rong WEN Xiaoming LI School of Information Renmin University of China Beijing 100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Renmin University of China Beijing 100872 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing 100144 China School of Electronics Engineering and Computer Science Peking University Beijing 100871 China

Detecting and using bursty pattems to analyze text streams has been one of the fundamental approaches in many temporal text mining applications. So far, most existing studies have focused on developing methods to detect bursty features based purely on term frequency changes. Few have taken the semantic contexts of bursty features into consideration, and as a result the detected bursty features may not always be interesting and can be hard to interpret. In this article, we propose to model the contexts of bursty features using a language modeling approach. We propose two methods to estimate the context language models based on sentence-level context and document-level context. We then propose a novel topic diversity-based metric using the context models to find newsworthy bursty features. We also propose to use the context models to automatically assign meaningful tags to bursty features. Using a large corpus of news articles, we quantitatively show that the proposed context language models for bursty features can effectively help rank bursty features based on their newsworthiness and to assign meaningful tags to annotate bursty features. We also use two example text mining applications to qualitatively demonstrate the usefulness of bursty feature ranking and tagging.

关键词： bursty features bursty features ranking bursty feature tagging context modeling

来源：评论

学校读者我要写书评

暂无评论

(WIP) Correlation-Driven Service Event Routing for Predictive Industrial Maintenance

(WIP) Correlation-Driven Service Event Routing for Predictiv...

引用

IEEE International Conference on Web Services (ICWS)

作者： Meiling Zhu Chen Liu Shouli Zhang Yanbo Han School of Computer Science and Technology Tianjin University Tianjin China Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of Technology Beijing China

Predictive industrial maintenance promotes proactive scheduling of maintenance to minimize unexpected device faults. A fault is not always isolated and may be formed by a propagation of trivial anomalies, which are regarded as service events herein. In this paper, we firstly propose an algorithm for generating service event correlation. Such correlations can show us lots of clues to the anomaly/fault propagation. The correlations are encapsulated into service hyperlinks as our previous works did, and thus we depict the anomaly/fault propagation as service event routing among services via the refined service hyperlinks. Our scenario illustrates that a trivial anomaly may propagate into different faults under different service event correlations. It indicates that the destination of a service event is often uncertain. Therefore, this paper further proposes a heuristic approach to handle the uncertainty problem. Extensive experiments have been made to verify the effectiveness of the approach.

关键词： Sensors Correlation Hypertext systems Maintenance engineering Routing Coal Computer science

来源：评论

学校读者我要写书评

暂无评论

Face recognition based on enhanced CSLBP 12th

Face recognition based on enhanced CSLBP

引用

12th International Conference on Future Information Technology, FutureTech 2017

作者： Li, Chen Zhao, Shuai Xiao, Ke Wang, Yanjie College of Computer Science North China University of Technology Beijing China Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data Beijing China

ISBN: (纸本)9789811050404

Face image with illumination variation usually contains redundant data that will seriously reduce the recognition rate. To combat the influence of illumination variation and extracting illumination-robust feature, a novel feature extraction method is proposed. The novel method is based on the combination of Center-Symmetric Local Binary Pattern (CS-LBP) and the fusion of the vertical and horizontal component images derived from wavelet decomposition. Numerous experiments have been done on the Extended Yale B to verify its effectiveness. The experimental results show that by applying the proposed method, redundant data caused by severe illumination variation can be filtered, while useful texture information can be reserved and enhanced. Compared with CSLBP, it significantly improves the face recognition performance under severe illumination variation. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Text extraction method for historical Tibetan document images based on block projections

引用

Optoelectronics Letters 2017年第6期13卷 457-461页

作者：段立娟张西群马龙龙吴健 Faculty of Information Technology. Beijing University of Technology Beijing 100124 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing University of Technology Beijing 100124 China Beijing Key Laboratory of Trusted Computing Beijing University of Technology Beijing 100124 China Chinese Information Processing Laboratory Institute of Software Chinese Academy of Sciences Beijing 100190 China

Text extraction is an important initial step in digitizing the historical documents. In this paper, we present a text extraction method for historical Tibetan document images based on block projections. The task of text extraction is considered as text area detection and location problem. The images are divided equally into blocks and the blocks are filtered by the information of the categories of connected components and corner point density. By analyzing the filtered blocks' projections, the approximate text areas can be located, and the text regions are extracted. Experiments on the dataset of historical Tibetan documents demonstrate the effectiveness of the proposed method.

关键词： historical Tibetan document filtered blocks bounding corner approximate projection coordinate

来源：评论

学校读者我要写书评

暂无评论

Audiences counting in cinema by detecting occupied chairs 12th

Audiences counting in cinema by detecting occupied chairs

引用

12th International Conference on Future Information Technology, FutureTech 2017

作者： Su, Zhitong Lan, Jun Song, Wei Fong, Simon Tian, Yifei Department of Digital Media Technology North China University of Technology Beijing China Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of Technology Beijing China Department of Computer and Information Science University of Macau Macau China

ISBN: (纸本)9789811050404

Human counting in cinema is easily influenced by varied illumination, so as to become a complicated problem. This paper develops an audience counting system in cinema by detecting occupied chairs in captured images. Firstly, we initialize chair regions in a background image manually. Then, the differences between the background and current images are detected as foreground regions. Such rough segmentation results always contain noise because of environmental illumination changing. Thus, a contour difference detection algorithm is applied to refine the audience detection results. Next, if both foreground and contour differences in a chair region are larger than a threshold, this chair is recognized to be occupied by an audience. Finally, the audience number is estimated by counting the occupied chairs. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Audiences counting Contour detection Foreground segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards merging collaborating processes for artifact lifecycle synthesis 17

Towards merging collaborating processes for artifact lifecyc...

引用

2017 Australasian Computer Science Week Multiconference, ACSW 2017

作者： Kunchala, Jyothi Yu, Jian Yongchareon, Sira Han, Yanbo School of Engineering Computer and Mathematical Sciences Auckland University of Technology Auckland1142 New Zealand Research Centre for Cloud Computing Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing100144 China

ISBN: (纸本)9781450347686

Research on transforming traditional activity-centric processes into the newly emerged artifact-centric processes has gained an increasing interest in recent years. This transformation lead to the emergence of several approaches to transforming standalone activity-centric business processes, while neglecting the inter-organizational processes consisting of multiple collaborating processes having message flows among them. In this paper, we propose an approach for transforming activity-centric collaborating processes into the artifact-centric processes. The proposed approach consists of two phases: the first phase is to merge the collaborating processes into an integrated process and the second phase is to synthesize the artifact lifecycles from the resulting integrated process. The feasibility of this approach has been studied with an inter-organizational e-business process scenario. © 2017 ACM.

关键词： Merging

来源：评论

学校读者我要写书评

暂无评论

The Design and Implementation of a Cleaning System Prototype

引用

IOP Conference Series: Earth and Environmental Science 2019年第3期252卷

作者： He Yang Weiwei Liu Xiaohui Wang He Liu Bin Yu Hongwei Zhou Artificial Intelligence on Electric Power System State Grid Corporation Joint Laboratory Global Energy Interconnection Research Institute co.Ltd Beijing 102209 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data College of Computer Science North China University of Technology Beijing 100144 China State Grid Jiangsu Economic Research Institute Jiangsu 210000 China

As we all know, data is one of the most valuable assets, however, raw data is often problematic, not conducive to the training of algorithm models. To cope with this, we can process the dirty data with cleaning systems [1] to obtain standard clean data for data statistics, data mininig and other use. Instead of manually modifying data, writing SQLs or other cumbersome methods which are popular present ways to clean data, the article proposes an approach by making use of the Hadoop big data platform to support massive data and support the cleaning of multiple heterogeneous data sources. Moreover, our system prototype supports custom rules and algorithms, can export results to a specified database, greatly simplifying the workload of data cleaning personnel. Based on the system design and theoretical verification presented in this paper, the author implemented a big data cleaning tool based on big data platform. The typical data cleaning process shows that the data cleaning can be achieved and user operations can be simplified on the basis of the theory proposed in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A collaborative calculation on real-time stream in smart cities

引用

Simulation Modelling Practice and Theory 2017年 72卷 23-33页

作者： Ding, Weilong Zhang, Shuai Zhao, Zhuofeng Data Engineering Institute North China University of Technology Beijing100144 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing100144 China Department of Storage Dawning Information Industry Beijing100194 China

In the smart cities, the travel-time is a typical business calculation to monitor and control the traffic congestions. But it still faces challenges on real-time stream due to the limitation of latency and accuracy. In this paper, we propose a collaborative approach for travel-time calculation on stream of recognized data of vehicles. Compared with other types of sensory data in urban roads, the recognized data of vehicles has wider coverage, finer interval and more exact locality. Our approach continuously achieves both factual and predictive values, and consists of two-step spatio-temporal parallelism on real-time data and Bayes prior rules mining on historical data. It can be analyzed theoretically for its low latency with high accuracy, and has been implemented on Apache Storm correlated with Hadoop MapReduce. Through exhaustive experiments on simulated and real data, our approach holds millisecond-level latencies steadily on high speed stream with nearly linear scalability, and keeps the accuracy above 80% for prediction. © 2016 Elsevier B.V.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Generating timeline summaries with social media attention

引用

Frontiers of Computer Science 2016年第4期10卷 702-716页

作者： Wayne Xin ZHAO Ji-Rong WEN Xiaoming LI School of Information Renmin University of China Beijing 100872 China Beijing Key Laboratory of Big Data Management and Analysis Methods Renmin University of China Beijing 100872 China School of Electronics Engineering and Computer Science Peking University Beijing 100871 China Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing 100144 China

Timeline generation is an important research task which can help users to have a quick understanding of the overall evolution of one given topic. Previous methods simply split the time span into fixed, equal time intervals without studying the role of the evolutionary patterns of the underlying topic in timeline generation. In addition, few of these methods take users＇ collective interests into considerations to generate timelines. We consider utilizing social media attention to address these two problems due to the facts： 1） social media is an important pool of real users＇ collective interests; 2） the information cascades generated in it might be good indicators for boundaries of topic phases. Employing Twitter as a basis, we propose to incorporate topic phases and user＇s collective interests which are learnt from social media into a unified timeline generation algorithm. We construct both one informativeness-oriented and three interestingness-oriented evaluation sets over five topics. We demonstrate that it is very effective to generate both informative and interesting timelines. In addition, our idea naturally leads to a novel presen- tation of timelines, i.e., phase based timelines, which can potentially improve user experience.

关键词： timeline social media attention phase users＇collective interests

来源：评论

学校读者我要写书评

暂无评论

SDaaS: A Method for Encapsulating Sensor stream data as Services

引用

Jisuanji Xuebao/Chinese Journal of Computers 2017年第2期40卷 445-463页

作者： Zhang, Zhong-Mei Liu, Chen Su, Shen Zhang, Shou-Li Han, Yan-Bo School of Computer Science and Technology Tianjin University Tianjin300072 China Beijing Key Laboratory on Integration and Analysis of Large -scale Stream Data North China University of Technology Beijing100144 China Cloud Computing Research Center North China University of Technology Beijing100144 China

The sharing and integration of multiple stream data derived from different Sensor Networks significant for the innovation of business and industry. The current Sensor Networks are generally domain-specific and task-oriented, tailored for particular applications with little possibility of sharing and reusing sensor data for different applications. The servitization of stream sensor data is an effective solution for sharing and reusing sensor data resources. Considering the limitations of existing methods on processing large-scale stream data and concurrent requests, this paper proposes to encapsulate stream data as a Service (SDaaS), which process sensor stream data with service modeling operations and distribute data on-demand based on Pub/Sub mechanism. Then this paper fulfills the encapsulation by utilizing event-driven mechanism for stream data service processing, using Spark streaming framework to process sensor events, and improving traditional matching-tree algorithm to distribute stream data efficiently. Finally, we evaluate our approach through experiments, and the stream data service can handle multiple requests and deliver data to corresponding applications in milliseconds level. © 2017, Science Press. All right reserved.

关键词： Sensor networks

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：