检索结果-内蒙古大学图书馆

Top-k Self-Adaptive Contrast Sequential Pattern mining

IEEE TRANSACTIONS ON CYBERNETICS 2022年第11期52卷 11819-11833页

作者： Wu, Youxi Wang, Yuehua Li, Yan Zhu, Xingquan Wu, Xindong Hebei Univ Technol Sch Econ & Management Sch Artificial Intelligence Tianjin 300401 Peoples R China Hebei Univ Technol Hebei Prov Key Lab Big Data Calculat Tianjin 300401 Peoples R China Florida Atlantic Univ Dept Comp & Elect Engn & Comp Sci Boca Raton FL 33431 USA Hefei Univ Technol Minist Educ Key Lab Knowledge Engn Big Data Hefei 230009 Peoples R China Mininglamp Acad Sci Beijing 100102 Peoples R China

For sequence classification, an important issue is to find discriminative features, where sequential pattern mining (SPM) is often used to find frequent patterns from sequences as features. To improve classification accuracy and pattern interpretability, contrast pattern mining emerges to discover patterns with high-contrast rates between different categories. To date, existing contrast SPM methods face many challenges, including excessive parameter selection and inefficient occurrences counting. To tackle these issues, this article proposes a top-k self-adaptive contrast SPM, which adaptively adjusts the gap constraints to find top-k self-adaptive contrast patterns (SCPs) from positive and negative sequences. One of the key tasks of the mining problem is to calculate the support (the number of occurrences) of a pattern in each sequence. To support efficient counting, we store all occurrences of a pattern in a special array in a Nettree, an extended tree structure with multiple roots and multiple parents. We employ the array to calculate the occurrences of all its superpatterns with one-way scanning to avoid redundant calculation. Meanwhile, because the contrast SPM problem does not satisfy the Apriori property, we propose Zero and Less strategies to prune candidate patterns and a Contrast-first mining strategy to select patterns with the highest contrast rate as the prefix subpattern and calculate the contrast rate of all its superpatterns. Experiments validate the efficiency of the proposed algorithm and show that contrast patterns significantly outperform frequent patterns for sequence classification. The algorithms and datasets can be downloaded from https://***/wuc567/Pattern-mining/tree/master/SCP-Miner.

关键词： databases Task analysis Electronic mail Time complexity Cybernetics Classification algorithms big data Apriori property contrast pattern self-adaptive sequence classification sequential pattern mining (SPM)

来源：评论

学校读者我要写书评

暂无评论

Activity Auto-Completion: Predicting Human Activities from Partial Videos 15

Activity Auto-Completion: Predicting Human Activities from P...

引用

IEEE International Conference on Computer Vision

作者： Xu, Zhen Qing, Laiyun Miao, Jun Chinese Acad Sci Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China

ISBN: (纸本)9781467383905

In this paper, we propose an activity auto-completion (AAC) model for human activity prediction by formulating activity prediction as a query auto-completion (QAC) problem in information retrieval. First, we extract discriminative patches in frames of videos. A video is represented based on these patches and divided into a collection of segments, each of which is regarded as a character typed in the search box. Then a partially observed video is considered as an activity prefix, consisting of one or more characters. Finally, the missing observation of an activity is predicted as the activity candidates provided by the auto-completion model. The candidates are matched against the activity prefix on-the-fly and ranked by a learning-to-rank algorithm. We validate our method on UT-Interaction Set #1 and Set #2 [19]. The experimental results show that the proposed activity auto-completion model achieves promising performance.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Do Media Reports Matter to House Price Expectations?Evidence from Beijing

引用

Journal of Systems Science and Information 2022年第4期10卷 388-409页

作者： Jing HE Diandian MA Xiuting LI Jichang DONG Postdoctoral Research Center of Agricultural Bank of China Beijing 100005China School of Statistics Renmin University of ChinaBeijing 100872China School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China

House price expectations(HPE)is a key factor affecting housing market *** Beijing as an example,this study innovatively proposes an internet data-based measurement of HPE and text analysis-based quantification of media reports from media attention and media *** model is performed to empirically test the impact of media reports on the level and accuracy of *** empirical results show no significant relationship between media attention and the level of HPE,but a significant relationship to the accuracy of *** higher the media attention(i.e.,the more intensive the media reports),the smaller the deviation between HPE and actual housing *** attitude of media reports is significantly related to the level and accuracy of *** is easier to guide the formation of HPE through media reports with clear opinions,indicating that media could promote the sustainable development of the real estate market.

关键词： media reports real estate market housing prices public expectations

来源：评论

学校读者我要写书评

暂无评论

NetDPO: (delta, gamma)-approximate pattern matching with gap constraints under one-off condition

引用

APPLIED INTELLIGENCE 2022年第11期52卷 12155-12174页

作者： Li, Yan Yu, Lei Liu, Jing Guo, Lei Wu, Youxi Wu, Xindong Hebei Univ Technol Sch Econ & Management Tianjin 300401 Peoples R China Hebei Univ Technol Sch Artificial Intelligence Tianjin 300401 Peoples R China Hebei Univ Technol State Key Lab Reliabil & Intelligence Elect Equip Tianjin 300401 Peoples R China Hebei Key Lab Big Data Comp Tianjin 300401 Peoples R China Hefei Univ Technol Minist Educ Key Lab Knowledge Engn Big Data Hefei 230009 Peoples R China Mininglamp Technol Mininglamp Acad Sci Beijing 100084 Peoples R China

Approximate pattern matching not only is more general than exact pattern matching, but also allows some data noise. Most of them adopt the Hamming distance to measure similarity, which indicates the number of different characters in two sequences, but it cannot reflect the approximation between two characters. This paper addresses the approximate pattern matching with a local distance no larger than delta and a global distance no larger than gamma, which is named Delta and gamma Pattern matching with gap constraints under One-off condition (DPO). First, we show that the problem is an NP-Hard problem. Therefore, we construct a heuristic algorithm named approximate Nettree for DPO (NetDPO), which transforms the problem into an approximate Nettree based on delta distance which is a specially designed data structure. Then, NetDPO calculates the number of paths that reach the roots within gamma distance. To find the maximal occurrences, we employ the rightmost parent strategy and the optimal parent strategy to select the better occurrence which can minimize the influence after removing the occurrence. Iterate this process until there are no occurrences. Finally, we analyze the time and space complexities of NetDPO. Extensive experimental results verify the superiority of the proposed algorithm.

关键词： Pattern matching Pattern discovery Approximate pattern matching Gap constraint Nettree structure

来源：评论

学校读者我要写书评

暂无评论

A comparison of 17 article-level bibliometric indicators of institutional research productivity: Evidence from the information management literature of China

引用

INFORMATION PROCESSING & management 2017年第5期53卷 1156-1170页

作者： Li, Jing Wu, Dengsheng Li, Jianping Li, Minglu Anhui Univ Sch Management Hefei 230601 Anhui Peoples R China Chinese Acad Sci Inst Policy & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Natl Nat Sci Fdn China Bur Planning Beijing 100085 Peoples R China

Periodically ranking institutional research productivity is necessary not only to understand the status of the development of related fields but also to identify gaps and take appropriate corrective steps. Many bibliometric indicators contribute to the assessment of institutional research productivity, but the appropriateness of the indicator and the relationships between different indicators are topics that have not been addressed. For this reason, an indicator framework for the ranking of institutional research performance, which consists of a count of published articles and quality weighted dimensions, is developed. Based on the literature review, 17 indicators in the framework are chosen for study. Based on these indicators, experiments are conducted to rank Chinese institutions in the field of Information management. Kendall's tau rank correlation coefficient (tau) is calculated, and all pair wise correlations are between 0.34 and 0.98. There are three primary findings: (1) among the article count indicators, the Straight count indicator is significantly different than others;(2) the rankings based on the indicators which are weighted by quality are consistent with those based on the indicators using article count;and (3) the Paper citation weighted indicator is sensitive to the procedure used for institutional ranking. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Research productivity Research assessment Institutional assessment Bibliometric indicators Information management

来源：评论

学校读者我要写书评

暂无评论

Learning Binary Descriptors for Fingerprint Indexing

引用

IEEE ACCESS 2018年 6卷 1583-1594页

作者： Bai, Chaochao Li, Mingqiang Zhao, Tong Wang, Weiqiang Univ Chinese Acad Sci Sch Comp & Control Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Fingerprint indexing is studied widely with the real-valued features, but few works focus on the binary feature descriptors, which are more appropriate to retrieve fingerprints efficiently in the large-scale fingerprint database. In this paper, the binary fingerprint descriptor (BFID), which is an effective and discriminative binary feature representation for fingerprint indexing, is proposed based on minutia cylinder code (MCC). Specifically, we first analyze MCC to find that it has characteristics of the high dimensionality, redundancy, and quantization loss. Accordingly, we propose an optimization model to learn a feature-transformation matrix, resulting in dimensionality reduction and diminishing quantization loss. Meanwhile, we also incorporate the balance, independence, and similarity-preservation properties in this learning process. Eventually, a multi-index hashing-based fingerprint indexing scheme further accelerate the exact search in Hamming space. The experiments on numerous public databases show that the BED is discriminative and compact and that the proposed approach is outstanding for fingerprint indexing.

关键词： Binary fingerprint descriptor fingerprint indexing minutia cylinder code

来源：评论

学校读者我要写书评

暂无评论

Challenges to Engineering management in the big data Era

引用

Frontiers of Engineering management 2015年第3期2卷 293-303,322-323页

作者： Yong Shi Research Center of Fictitious Economy & Data Science University of the Chinese Academy of Sciences and Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences

This paper presents a review of the challenges to engineering management in the big data Era as well as the big data applications. First, it outlines the definitions of big data, data science and intelligent knowledge and the history of big data. Second, the paper reviews the academic activities about big data in China. Then, it elaborates a number of challenging big data problems, including transforming semi-structured and non-structured data into"structured format" and explores the relationship of data heterogeneity, knowledge heterogeneity and decision heterogeneity. Furthermore, the paper reports various real-life applications of big data, such as financial and petroleum engineering and internet business.

关键词： big data data science intelligent knowledge engineering management real-life applications

来源：评论

学校读者我要写书评

暂无评论

Hybrid Learning Network: A Novel Architecture for Fast Learning 5

Hybrid Learning Network: A Novel Architecture for Fast Learn...

引用

5th International Conference on Information Technology and Quantitative management (ITQM)

作者： Liu, Ying Xiang, Chao Univ Chinese Acad Sci Sch Comp & Engn Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

There're many effective architectures of the artificial neural network(ANN). For which the training is a hard work. The cost for training an ANN increases exponentially when the ANN gets deeper or wider. We therefore propose a novel architecture, the Hybrid Learning Network(HLN), to achieve a fast learning with good stablity. The HLN can learn from both labeled data and unlabeled data at the same time in a hybrid learning manner. It uses a Self Organizing Map unified by the specially designed nonlinear function as the sparsity mask for a hidden layer to improve the training speed. We experiment our architecture on a synthetic dataset to test its regression capability against the traditional architecture, the result is promising. (C) 2017 The Authors. Published by Elsevier B.V.

关键词： hybrid learning neural network sparsity mask self organizing map fast learning

来源：评论

学校读者我要写书评

暂无评论

Scale Expansion and Operations Inefficiency in Pure E-commerce Firms

Scale Expansion and Operations Inefficiency in Pure E-commer...

引用

IEEE/WIC/ACM International Conference on Web Intelligence (WI)

作者： Yang, Zhuofan Shi, Yong Chinese Acad Sci Management Sch Univ Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Key Res Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)9781509047710

This paper examine the importance of website quality indicator in e-commerce efficiency evaluation. It applies data Envelopment Analysis (DEA) models and traditional production theory to account for how scale affects efficiency in pure e-commerce firms. The results of DEA models identify website quality, user scale and user experience each contribute to improving operations efficiency, but scale expansion often leads to overall operations inefficiency. Due to excessive scale expansion, all inefficient Decision Making Units exhibit decreasing return to scale. These findings may help managers resize the scale of their operations. This research enriches scale economic theory and improves the indicator system in e-commerce efficiency evaluation.

关键词： data envelopment analysis e-commerce efficiency returns to scale

来源：评论

学校读者我要写书评

暂无评论

Divide and conquer: A granular concept-cognitive computing system for dynamic classification decision making

引用

EUROPEAN JOURNAL OF OPERATIONAL RESEARCH 2023年第1期308卷 255-273页

作者： Mi, Yunlong Wang, Zongrun Liu, Hui Qu, Yi Yu, Gaofeng Shi, Yong Cent South Univ Sch Business Changsha 410083 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Sanming Univ Sch Management & Econ Sanming 365004 Fujian Peoples R China

Dynamic classification decision making is a crucial issue in management decision making and data min-ing, which is widely applied in different areas such as human-machine collaborative decision making, network intrusion detection, and traffic data stream mining. However, the existing strategies of static classification decision making are always unable to achieve desired outcomes in ill-structured domains, as the standard machine learning approaches mainly focus on static learning, which is not suitable to mine evolving dynamic data to support decision making. In addition, the main factors regarding incor-rect classification predictions are also important for knowledge management and decision making, which is often ignored in many standard learning systems. Therefore, inspired by the idea of divide and con-quer, we in this article propose a novel dynamic concept learning framework, namely granular concept -cognitive computing system (gC3S), for dynamic classification decision making by transforming instances into concepts. More specifically, to better characterize the process of dynamic classification decision mak-ing, we give the objective function of gC3S via mathematical programming theory. For management deci-sion making, gC3S emphasizes tracing the corresponding approximate concepts via the incorrect classifi-cation predictions. Finally, we also apply gC3S to traffic data stream mining, and the experimental results on the different real-world situations further demonstrate that our approach is very effective for dynamic classification decision making.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Decision support systems Dynamic classification decision making Dynamic learning Granular computing Concept -cognitive computing

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：