检索结果-内蒙古大学图书馆

30th Benelux Conference on Artificial Intelligence, BNAIC 2018

作者： Mehrkanoon, Siamak Huang, Xiaolin Suykens, Johan A.K. Dept. of Data Science and Knowledge Engineering Maastricht University Netherlands Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China KU Leuven ESAT-STADIUS Kasteelpark Arenberg 10 LeuvenB-3001 Belgium

This paper introduces the indefinite learning in the framework of least squares support vector machines (LS-SVM). Here the analysis of the Multi-Class Semi-Supervised Kernel Spectral Clustering (MSS-KSC) model with indefinite kernels is provided. In indefinite MSS-KSC one finds the solution by solving a linear system of equations in the dual. In addition the use of the propped indefinite model for large scale data using Nyström approximation technique as well as unsupervised learning using Kernel Spectral Clustering are also discussed in the published full paper1. Experimental results on several real-life datasets are given to illustrate the efficiency of the proposed indefinite kernel spectral learning. © 2018 University of Groningen. 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

Partitioning vectors into quadruples: Worst-case analysis of a matching-based algorithm 29

Partitioning vectors into quadruples: Worst-case analysis of...

引用

29th International Symposium on Algorithms and Computation, ISAAC 2018

作者： Ficker, Annette M.C. Erlebach, Thomas Mihalák, Matúš Spieksma, Frits C.R. Faculty of Economics and Business KU Leuven Leuven Belgium Department of Informatics University of Leicester Leicester United Kingdom Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Department of Mathematics and Computer Science Eindhoven University of Technology Eindhoven Netherlands

ISBN: (纸本)9783959770941

Consider a problem where 4k given vectors need to be partitioned into k clusters of four vectors each. A cluster of four vectors is called a quad, and the cost of a quad is the sum of the component-wise maxima of the four vectors in the quad. The problem is to partition the given 4k vectors into k quads with minimum total cost. We analyze a straightforward matching-based algorithm and prove that this algorithm is a23 -approximation algorithm for this problem. We further analyze the performance of this algorithm on a hierarchy of special cases of the problem and prove that, in one particular case, the algorithm is a54 -approximation algorithm. Our analysis is tight in all cases except one. © Annette M. C. Ficker, Thomas Erlebach, Matúš Mihalák, and Frits C. R. Spieksma;licensed under Creative Commons License CC-BY

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-perspective ant colony optimization for mining and understanding the topology oriented big data

Multi-perspective ant colony optimization for mining and und...

引用

2017 World Congress on engineering, WCE 2017

作者： Hiba, Khalid Usman, Qamar Mazhar, Hameed Knowledge and Data Engineering Research Centre Department of Computer Engineering College of Electrical and Mechanical Engineering NUST Pakistan

ISBN: (纸本)9789881404749

Big data has the potential to transform how data can be used to manipulate, gather, collect, enforce and contribute towards data centric applications. data can have meaning and big data has meaning hidden inside it which can be used to empower multiple applications. Big data has its challenges;this massive amount of data can be used to extract a few lines or a few million lines that actually serve the purpose and meaning. For such outputs the algorithmic techniques needs to be devised that can efficiently extract meaning from a topological shape based on the nature of application and the information that is being looked for. The search for hidden meaning in topology of data is a challenge. Many techniques are employed to discover the hidden meaning and patterns in the data. This paper presents an algorithm for mining the clustered topological data using ant colony optimization.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Larger, Cheaper, but Faster: SSD-SMR hybrid storage boosted by a new SMR-oriented cache framework 33

Larger, Cheaper, but Faster: SSD-SMR hybrid storage boosted ...

引用

33rd International Conference on Massive Storage Systems and Technology, MSST 2017

作者： Wang, Chunling Wang, Dandan Chai, Yupeng Wang, Chuanwen Sun, Diansen Key Laboratory of Data Engineering and Knowledge Engineering School of Information Renmin University of China Beijing China

By utilizing the new Shingled Magnetic Recording (SMR) technique, the emerging SMR disks achieve higher storage density and lower costs. Together with Flash-based SSDs, SMR disks can be used to construct a new hybrid storage system that is larger, but cheaper than the widely used conventional diskbased storage systems. It is appropriate for the fast growing big data applications which have strict requirements on both capacity and cost, e.g., the scientific computing in the fields of meteorology and astronomy. However, the most serious challenge of the SSD-SMR hybrid storage lies in its weak fine-grained random write performance caused by the write amplification in SMR disks, especially when I/Os are spread randomly across the Logical Block Address (LBA) range of the entire disk. Traditional cache algorithms like LRU usually lead to tens of or even hundreds of times more data written into magnetic plates than the original requests, thus resulting in poor I/O performance, because they do not consider and limit the LBA distribution of the eviction victims at all. Therefore, the cache algorithms for SSD-SMR hybrid storage systems should take this new dimension into account except for the data popularity. In this paper, we propose a new SMR-oriented cache framework, i.e., Partially Open Region for Eviction (PORE), which restricts the LBA range of evicted data from SSD caches appropriately to promote the overall performance of the hybrid storage by making a better tradeoff between the cached data popularity and the SMR write amplification. The experiments based on real-world traces reveal that PORE can boost the SSD-SMR hybrid storage performance by a factor of 3.26∼10.2 with only a 2% SSD cache compared with a conventional disk-based storage on average, while the hybrid storage coupled with LRU is slower than the conventional storage sometimes. PORE makes the hybrid storage much faster than traditional storage besides the advantages on capacity and cost. © 33rd Internati

关键词： Hard disk storage

来源：评论

学校读者我要写书评

暂无评论

Few-shot deep adversarial learning for video-based person re-identification

arXiv

引用

arXiv 2019年

作者： Wu, Lin Wang, Yang Yin, Hongzhi Wang, Meng Shao, Ling Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China University of Queensland St Lucia4072 Australia School of Computer Science and Information Engineering Hefei University of Technology Hefei230000 China Abu Dhabi United Arab Emirates

Video-based person re-identification (re-ID) refers to matching people across camera views from arbitrary unaligned video footages. Existing methods rely on supervision signals to optimise a projected space under which the distances between inter/intra-videos are maximised/minimised. However, this demands exhaustively labelling people across camera views, rendering them unable to be scaled in large networked cameras. Also, it is noticed that learning effective video representations with view invariance is not explicitly addressed for which features exhibit different distributions otherwise. Thus, matching videos for person re-ID demands flexible models to capture the dynamics in time-series observations and learn view-invariant representations with access to limited labeled training samples. In this paper, we propose a novel few-shot deep learning approach to video-based person re-ID, to learn comparable representations that are discriminative and view-invariant. The proposed method is developed on the variational recurrent neural networks (VRNNs) and trained adversarially to produce latent variables with temporal dependencies that are highly discriminative yet view-invariant in matching persons. Through extensive experiments conducted on three benchmark datasets, we empirically show the capability of our method in creating view-invariant temporal features and state-of-the-art performance achieved by our method. Copyright © 2019, The Authors. All rights reserved.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a topic discovery and tracking system with application to news items 2nd

Towards a topic discovery and tracking system with applicati...

引用

2nd International Workshop on Future and Emerging Trends in Language Technology, FETLT 2016

作者： Brüggermann, Daniel Hermey, Yannik Orth, Carsten Schneider, Darius Selzer, Stefan Spanakis, Gerasimos Department of Data Science and Knowledge Engineering Maastricht University Maastricht6200 MD Netherlands

ISBN: (纸本)9783319693644

Rapid proliferation of the World Wide Web led to an enormous increase in the availability of textual corpora. In this paper, the problem of topic detection and tracking is considered with application to news items. The proposed approach explores two algorithms (Non-Negative Matrix Factorization and a dynamic version of Latent Dirichlet Allocation (DLDA)) over discrete time steps and makes it possible to identify topics within storylines as they appear and track them through time. Moreover, emphasis is given to the visualization and interaction with the results through the implementation of a graphical tool (regardless the approach). Experimental analysis on Reuters RCV1 corpus and the Reuters 2015 archive reveals that explored approaches can be effectively used as tools for identifying topic appearances and their evolutions while at the same time allowing for an efficient visualization. © 2017, Springer International Publishing AG.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

An OLAP endpoint for RDF data analysis using analysis graphs

An OLAP endpoint for RDF data analysis using analysis graphs

引用

2017 ISWC Posters and Demonstrations and Industry Tracks, ISWC-P and D-Industry 2017

作者： Hilal, Median Schuetz, Christoph G. Schre, Michael Department of Business Informatics - Data and Knowledge Engineering Johannes Kepler University Linz Austria

Exploiting Resource Description Framework (RDF) data for Online Analytical Processing (OLAP), especially Linked Open data (LOD), could allow analysts to obtain interesting insights. To conduct OLAP analysis over RDF data, analysts should know the specific semantics, structure, and querying mechanisms of such data. Furthermore, these data should ideally adhere to a multidimensional structure to be accessible to OLAP. In this demo paper, we present an OLAP endpoint that allows casual analysts to perform self-service OLAP analysis over RDF datasets. Specifically, analysts can instantiate semantic web analysis graphs, which are predefined models of the analysis processes. Semantic web analysis graphs are built on top of multidimensional structures that can be superimposed over arbitrary RDF datasets.

关键词： Resource Description Framework (RDF)

来源：评论

学校读者我要写书评

暂无评论

Relevant attributes in formal contexts

arXiv

引用

arXiv 2018年

作者： Hanika, Tom Koyda, Maren Stumme, Gerd Knowledge & Data Engineering Group University of Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Germany

Computing conceptual structures, like formal concept lattices, is in the age of massive data sets a challenging task. There are various approaches to deal with this, e.g., random sampling, parallelization, or attribute extraction. A so far not investigated method in the realm of formal concept analysis is attribute selection, as done in machine learning. Building up on this we introduce a method for attribute selection in formal contexts. To this end, we propose the notion of relevant attributes which enables us to define a relative relevance function, reflecting both the order structure of the concept lattice as well as distribution of objects on it. Finally, we overcome computational challenges for computing the relative relevance through an approximation approach based on information *** Codes 68T30 03G10 Copyright © 2018, The Authors. All rights reserved.

关键词： Information analysis

来源：评论

学校读者我要写书评

暂无评论

Towards contextualized rule repositories for the semantic web

Towards contextualized rule repositories for the semantic we...

引用

2017 Joint Web Stream Processing Workshop and the 2nd International Workshop on Ontology Modularity, Contextuality, and Evolution, WSP+WOMoCoE 2017

作者： Burgstaller, Felix Schuetz, Christoph G. Neumayr, Bernd Steiner, Dieter Schrefl, Michael Department for Business Informatics - Data and Knowledge Engineering Johannes Kepler University Linz Austria

Central to the semantic web are ontologies: shared conceptualizations of domains of interest expressed in an ontology language such as OWL. Rule languages complement ontology languages. For large heterogeneous bodies of knowledge on the semantic web, contextualized knowledge repositories facilitate the organization of ontological concepts. In this paper we propose a similar mechanism - contextualized rule repositories - for organizing and executing large sets of context-specific rules. We investigate feasibility of a SPARQL Inferencing Notation (SPIN) based implementation using a real-world use case from the aeronautical domain. Furthermore, we compare SPIN-based contextualized rule repositories to a context-unaware SPIN implementation.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Do Positive Twitter Messages Have Impact on Stock Liquidity?

Do Positive Twitter Messages Have Impact on Stock Liquidity?

引用

作者： Abdirahmani, Aliasghar Angulo, Cecilio Automatic Control Dept. Universitat Politècnica de Catalunya Pau Gargallo 14. BacelonaTech08028 Spain Knowledge Engineering Research Group Intelligent Data Science and Artificial Intelligence Research Center Univ. Politècnica Catalunya BarcelonaTech Spain

ISBN: (纸本)9781614999171

Social media is a phenomenon that has transformed the interaction and communication of individuals throughout the world. In recent times, social media has affected many aspects of human communication, as well as business. The main objective of our research is to figure out about the role of Twitter on stock market to find out how social media impacts on the business that predictions fail. © 2018 The authors and IOS Press.

关键词： Sentiment analysis

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：