检索结果-内蒙古大学图书馆

IEEE International Congress on Big Data (BigData Congress)

作者： Yan, Danfeng Hua, Enzheng Hu, Bo Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing Peoples R China

ISBN: (纸本)9781509026227

Microblog is a very popular social platform, as the source of news and popular information dissemination. Detection and tracking of hot topics through Microblog research has arose the domestic and foreign scholar's attention. So, this paper mainly focuses on financial domain topic detection and tracking of Chinese Microblog. In this paper, we propose incremental TF-IWF-IDF of terms part-of-speech and position weight calculation method. This weight calculation method can solve the problem that IDF of TF-IDF is a constant value and can't change with the dataset dynamically. The traditional feature vector doesn't consider the semantic and context of terms. The paper proposes a new feature vector representation method to solve this problem by incorporating IWF into TF-IDF. This text representation method is called Word vector based on an incremental TF-IWF-IDF of terms part-of-speech and position. This paper proposes Two Steps of single-pass based on Multi Topic Centers (MC-TSP) to overcome the shortcomings of the traditional single-pass algorithm. By experimental comparison, the improved algorithm has better performance than the traditional single-pass algorithm. With improved algorithm, financial hot topic detection and tracking model is designed and implemented. The application of this model in financial domain improved the accuracy of topic detection and tracking.

关键词： Incremental TF-IWF-IDF Word2Vec single-pass algorithm topic detection and tracking financial domain

来源：评论

学校读者我要写书评

暂无评论

A single-pass Triclustering algorithm

引用

AUTOMATIC DOCUMENTATION AND MATHEMATICAL LINGUISTICS 2015年第1期49卷 27-41页

作者： Gnatyshak, D. V. Natl Res Univ Higher Sch Econ Sci & Educ Lab Intelligent Syst & Struct Anal Moscow Russia

As the popularity of the field of big data continues to rise, the problem of the development of efficient algorithms with low time complexity and that ability to be parallelized is more and more frequently posed. This work is aimed at the development of an efficient single-pass algorithm for the triclustering of binary data that is suitable for use in the field of big data. As a result, a single-pass serial online OAC triclustering algorithm (triclustering of object-attribute-condition) was obtained. This algorithm not only has a very low complexity in time and memory, but it also can be effectively parallelized.

关键词： formal concept analysis data analysis clustering triclustering big data linear algorithm single-pass algorithm

来源：评论

学校读者我要写书评

暂无评论

Online randomized interpolative decomposition with a posteriori error estimator for temporal PDE data reduction

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 434卷

作者： Li, Angran Becker, Stephen Doostan, Alireza Univ Colorado Boulder Smead Aerosp Engn Sci Boulder CO 80309 USA Univ Colorado Boulder Appl Math Boulder CO 80309 USA

Traditional low-rank approximation is a powerful tool for compressing large data matrices that arise in simulations of partial differential equations (PDEs), but suffers from high computational cost and requires several passes over the PDE data. The compressed data may also lack interpretability thus making it difficult to identify feature patterns from the original data. To address these issues, we present an online randomized algorithm to compute the interpolative decomposition (ID) of large-scale data matrices in situ. Compared to previous randomized IDs that used the QR decomposition to determine the column basis, we adopt a streaming ridge leverage score-based column subset selection algorithm that dynamically selects proper basis columns from the data and thus avoids an extra pass over the data to compute the coefficient matrix of the ID. In particular, we adopt a single-pass error estimator based on the non- adaptive Hutch++ algorithm to provide real-time error approximation for determining the best coefficients. As a result, our approach only needs a single pass over the original data and thus is suitable for large and high-dimensional matrices stored outside of core memory or generated in PDE simulations. A strategy to improve the accuracy of the reconstructed data gradient, when desired, within the ID framework is also presented. We provide numerical experiments on turbulent channel flow and ignition simulations, and on the NSTX Gas Puff Image dataset, comparing our algorithm with the offline ID algorithm to demonstrate its utility in real-world applications.

关键词： Low-rank approximation single-pass algorithm Interpolative decomposition Column subset selection Randomized algorithm

来源：评论

学校读者我要写书评

暂无评论

DSM-PLW: single-pass mining of path traversal patterns over streaming Web click-sequences

引用

COMPUTER NETWORKS 2006年第10期50卷 1474-1487页

作者： Li, Hua-Fu Lee, Suh-Yin Shan, Man-Kwan Natl Chiao Tung Univ Dept Comp Sci & Informat Engn Hsinchu 300 Taiwan Natl Chengchi Univ Dept Comp Sci Taipei 116 Taiwan

Mining Web click streams is an important data mining problem with broad applications. However, it is also a difficult problem since the streaming data possess some interesting characteristics, such as unknown or unbounded length, possibly a very fast arrival rate, inability to backtrack over previously arrived click-sequences, and a lack of system control over the order in which the data arrive. In this paper, we propose a projection-based, single-pass algorithm, called DSM-PLW (Data Stream Mining for Path traversal patterns in a Landmark Window), for online incremental mining of path traversal patterns over a continuous stream of maximal forward references generated at a rapid rate. According to the algorithm, each maximal forward reference of the stream is projected into a set of reference-suffix maximal forward references, and these reference-suffix maximal forward references are inserted into a new in-memory summary data structure, called SP-forest (Summary Path traversal pattern forest), which is an extended prefix tree-based data structure for storing essential information about frequent reference sequences of the stream so far. The set of all maximal reference sequences is determined from the SP-forest by a depth-first-search mechanism, called MRS-mining (Maximal Reference Sequence mining). Theoretical analysis and experimental studies show that the proposed algorithm has gently growing memory requirements and makes only one pass over the streaming data. (c) 2005 Elsevier B.V. All rights reserved.

关键词： web click-sequence streams path traversal patterns single-pass algorithm

来源：评论

学校读者我要写书评

暂无评论

DSM-FI: an efficient algorithm for mining frequent itemsets in data streams

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2008年第1期17卷 79-97页

作者： Li, Hua-Fu Shan, Man-Kwan Lee, Suh-Yin Kainan Univ Dept Comp Sci Tao Yuan Taiwan Natl Chengchi Univ Dept Comp Sci Taipei 11623 Taiwan Natl Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan

Online mining of data streams is an important data mining problem with broad applications. However, it is also a difficult problem since the streaming data possess some inherent characteristics. In this paper, we propose a new single-pass algorithm, called DSM-FI (data stream mining for frequent itemsets), for online incremental mining of frequent itemsets over a continuous stream of online transactions. According to the proposed algorithm, each transaction of the stream is projected into a set of sub-transactions, and these sub-transactions are inserted into a new in-memory summary data structure, called SFI-forest (summary frequent itemset forest) for maintaining the set of all frequent itemsets embedded in the transaction data stream generated so far. Finally, the set of all frequent itemsets is determined from the current SFI-forest. Theoretical analysis and experimental studies show that the proposed DSM-FI algorithm uses stable memory, makes only one pass over an online transactional data stream, and outperforms the existing algorithms of one-pass mining of frequent itemsets.

关键词： Data mining Data streams Frequent itemsets single-pass algorithm Landmark window

来源：评论

学校读者我要写书评

暂无评论

Real-Time Monitoring of Smart Campus and Construction of Weibo Public Opinion Platform

引用

IEEE ACCESS 2018年 6卷 76502-76515页

作者： Nan, Feng Suo, Yina Jia, Xueyong Wu, Yuying Shan, Shuaijie North China Univ Sci & Technol Coll Elect Engn Tangshan 063000 Peoples R China North China Univ Sci & Technol Informat Engn Inst Tangshan 063000 Peoples R China North China Univ Sci & Technol Key Lab Engn Calculat Tangshan City Tangshan 063000 Peoples R China

With the development and penetration of information technology, the "fourth media"-the network media is coming, and the "grievance crisis" is increasingly happening. The effective monitoring of online public opinion information becomes a problem. For each university, how to understand the sensation of teachers and students in real time in the era of informationization entering the intelligent campus has become an urgent problem for all colleges and universities. This paper first analyzes the characteristics of Weibo's communication and the process of microblogging's public opinion formation, the mechanism of communication, and so on. For the acquisition of this information, the reptile method was used to obtain the required data, which was beneficial to the real-time sensation in the smart campus. Then, based on the improved single-pass algorithm to analyze the new characteristics of microblog propagation information and the public opinion sent by college students, and compared the improved single-pass algorithm with the effect of single-pass algorithm, the improved algorithm had the recall rate was high, the false detection rate was low, and the running time was short. Finally, taking the lyrics of college teachers and students as the research object, unified modeling language modeling was used to analyze the public opinion monitoring platform of the smart campus, and the campus public opinion of several major events was monitored and analyzed. This provided a reference for the effective, intelligent, and real-time detection of Weibo public opinion in colleges and universities.

关键词： Public opinion monitoring single-pass algorithm UML smart campus Weibo

来源：评论

学校读者我要写书评

暂无评论

Improving Online Clustering of Chinese Technology Web News With Bag-of-Near-Synonyms

引用

IEEE ACCESS 2020年 8卷 94245-94257页

作者： Zhang, Zhe Chen, Le Yin, Fengjing Zhang, Xin Guo, Lixiang Natl Univ Def Technol Coll Syst Engn Sci & Technol Informat Syst Engn Lab Changsha 410073 Peoples R China Acad Mil Sci Inst Syst Engn Beijing 100091 Peoples R China

In the Internet era, online clustering of technology web news can help discover scientific breakthroughs and grasp technology trends. To do that automatically, the news documents to be clustered must be represented appropriately with numerical vectors. However, traditional representations such as Term Frequency-Inverse Document Frequency (TF-IDF) cannot distinguish near-synonyms and may cause "dimension disaster" To overcome these problems, this article proposes the Bag-of-Near-Synonyms (BoNS) model based on the idea to construct near-synonym sets using word embeddings and agglomerative clustering, and then to represent a document with a Set Frequency-Inverse Document Frequency (SF-IDF) vector in which each dimension corresponds to a near-synonym set rather than a single word. To speed up computation, we further propose the hashed version of SF-IDF and name it hSF-IDF, which employs a hash function to map each near-synonym set to a unique number as the key and hence reduces the computation of SF to linear time. In addition, we apply hSF-IDF to online clustering of Chinese technology web news and propose an improved batch-based method. Extensive experiments have been conducted on a real-world dataset. The results show that our model outperforms some strong baselines including TF-IDF, average pooling of word or character embeddings, Latent Dirichlet Allocation (LDA), and bag-of-concepts in terms of both accuracy and efficiency.

关键词： Computational modeling Semantics Vocabulary Clustering algorithms Facebook Licenses Artificial intelligence Information retrieval single-pass algorithm document representation word embeddings agglomerative clustering

来源：评论

学校读者我要写书评

暂无评论

Non-localised contact between beams with circular and elliptical cross-sections

引用

COMPUTATIONAL MECHANICS 2020年第5期65卷 1247-1266页

作者： Magliulo, Marco Lengiewicz, Jakub Zilian, Andreas Beex, Lars A. A. Univ Luxembourg Fac Sci Technol & Commun Inst Computat Engn Maison Nombre 6Ave Fonte L-4364 Esch Sur Alzette Luxembourg Polish Acad Sci IPPT PAN Inst Fundamental Technol Res Ul Pawinskiego 5B PL-02106 Warsaw Poland

The key novelty of this contribution is a dedicated technique to efficiently determine the distance (gap) function between parallel or almost parallel beams with circular and elliptical cross-sections. The technique consists of parametrizing the surfaces of the two beams in contact, fixing a point on the centroid line of one of the beams and searching for a constrained minimum distance between the surfaces (two variants are investigated). The resulting unilateral (frictionless) contact condition is then enforced with the Penalty method, which introduces compliance to the, otherwise rigid, beams' cross-sections. Two contact integration schemes are considered: the conventional slave-master approach (which is biased as the contact virtual work is only integrated over the slave surface) and the so-called two-half-pass approach (which is unbiased as the contact virtual work is integrated over the two contacting surfaces). Details of the finite element formulation, which is suitably implemented using Automatic Differentiation techniques, are presented. A set of numerical experiments shows the overall performance of the framework and allows a quantitative comparison of the investigated variants.

关键词： Beams Contact Circular and elliptical cross-sections Rigid cross-sections single-pass algorithm Two-half-pass algorithm

来源：评论

学校读者我要写书评

暂无评论

Mining top-k Hot Melody Structures over online music query streams

引用

PATTERN RECOGNITION LETTERS 2008年第16期29卷 2116-2121页

作者： Li, Hua-Fu Kainan Univ Dept Comp Sci Tao Yuan 338 Taiwan

Online mining of frequent patterns from music data is one of the most important research issues of multimedia data mining. Most previous studies require the specification of a min_support threshold and aim at mining a complete set of frequent patterns satisfying min_support. However. in practice, it is difficult for users to provide an appropriate value of min_support threshold. In this paper, we propose a new problem of multimedia data mining: online mining of top-k melody structures of length no less than min_1, where k is the desired number of hot melody structures to be mined and min_1 is the minimal length of each melody structure. An efficient single-pass algorithm, called top-k-HMS (top-k Hot Melody Structures) is developed for mining such melody structures Without min_support. In the framework of top-k-HMS algorithm, a new summary data structure, called TKM-list (top-k melody list) is developed to maintain the essential information about the top-k hot melody structures from the Current melody sequence streams. Experimental Studies show that the proposed top-k-HMS algorithm is an efficient one-pass method for mining the set of top-k Hot Melody Structures over a continuous stream of melody sequences. (C) 2008 Elsevier B.V. All rights reserved.

关键词： Data mining Multimedia data mining Music query streams Top-k Hot Melody Structures single-pass algorithm

来源：评论

学校读者我要写书评

暂无评论

PRACTICAL SKETCHING algorithmS FOR LOW-RANK MATRIX APPROXIMATION

引用

SIAM JOURNAL ON MATRIX ANALYSIS AND APPLICATIONS 2017年第4期38卷 1454-1485页

作者： Tropp, Joel A. Yurtsever, Alp Udell, Madeleine Cevher, Volkan CALTECH Comp & Math Sci Pasadena CA 91125 USA Ecole Polytech Fed Lausanne CH-1015 Lausanne Switzerland Cornell Univ Ithaca NY 14853 USA

This paper describes a suite of algorithms for constructing low-rank approximations of an input matrix from a random linear image, or sketch, of the matrix. These methods can preserve structural properties of the input matrix, such as positive-semidefiniteness, and they can produce approximations with a user-specified rank. The algorithms are simple, accurate, numerically stable, and provably correct. Moreover, each method is accompanied by an informative error bound that allows users to select parameters a priori to achieve a given approximation quality. These claims are supported by numerical experiments with real and synthetic data.

关键词： dimension reduction matrix approximation numerical linear algebra randomized algorithm single-pass algorithm sketching streaming algorithm subspace embedding

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：