sesetoto sesetoto sesetoto sesetoto jaditoto sontogel sontogel jaditoto sesetoto sesetoto ltdtoto https://www.slot88resmitoto.com/ akuntoto akuntoto akuntoto akuntoto akuntoto akuntoto akuntoto akuntoto jaditoto ltdtoto
slot gacor slot gacor slot gacor sesetoto ketuatoto rajajudi88 slot777 ketuatoto ketuatoto ketuatoto ketuatoto sontogel slot gacor mahjong bobatoto slot gacor slot gacor emon77 bobatoto bobatoto bobatoto bobatoto emon77 akuntoto toto slot bobatoto toto toto mahjong mahjong ltdtoto ltdtoto mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong mahjong slot gacor
kientoto kientoto kientoto bobatoto toto slot togel online TOTO JP kientoto slot slot SLOT THAILAND slot88 SLOT777 SLOT777 slot AKUNBOS slot88 kientoto kientoto kientoto kientoto kientoto kientoto kadin jakarta barat slot gacor logototo logototo logototo logototo logototo logototo logototo logototo logototo
logo

Volume 5, No. 12

Published 31 December 2017

Articles

  1. Krzysztof Węcel, Bartosz Perkowski, Agata Filipowska, Dawid Węckowski, Piotr Zwolenkiewicz

    Badanie wydajności baz danych na potrzeby eksploracji dużych sieci społecznych

    In this article we present the results of the benchmarking of various data and knowledge-based systems for use while analysing a big social graph. MySQL, Neo4J, Titan and Virtuoso have been tested on data describing communication events among ca. 7 million users. We have proposed queries regarding the real-world scenarios derived from the requirements analysis of the data owner. Execution time has been measured for basic, aggregation, and networking types of queries. While MySQL was good at queries requiring calculations, Virtuoso outperformed it in graph-related queries.

  2. Dominik Filipiak, Agata Filipowska

    Wikipedia, Dbpedia and the Polish Art Market: Data Enrichment and Analysis of Concepts' Frequency in the Descriptions of Paintings and Authors

    Wikilinks are internal hyperlinks on Wikipedia, a popular Internet encyclopaedia. A unique article identifi er is hidden behind so-called surface form, which is a grammatical match of a given term accordingly to the context in which it occurs. Therefore, a given term can have multiple surface forms. Due to this fact it is possible to discover concepts (entries on Wikipedia) automatically in artists' and lots' descriptions on the pages of auction houses by searching for surface forms. Combining these data with traditional quantitative methods of art market research, such as linear regression, it is possible to discover, inter alia, popular motives and explore their statistical signifi cance and their impact on hammer price.

  3. Anna Lamek, Włodzimierz Lewoniewski

    Application Logistic Regression in Assessing the Quality of Information - Wikipedia Articles Case

    Th e use of the logistic regression in the assessment of the quality of data may have a significant impact on data management in the era of big data, where we are all dealing with a number of variables and amount of information describing some interesting phenomenon or behaviour. Th e calculation of actual an information value (IV) indicator allows to eliminate these variables which are irrelevant or just constitute an information overload. The article presents the use of logistic regression in the assessment of variables describing the quality of articles published on the English version of Wikipedia. A classification of variables because of the results of the information value indicator have been presented. Also the predictive capabilities of variables have been evaluated.

  4. Adam Maciaszek, Jacek Małyszko, Milena Stróżyna

    Identification of Port Calls Based on AIS Messages Analysis

    The article concerns the issue of the identification of port calls based on data retrieved from the AIS system. Such identifi cation may play an important role in increasing maritime awareness, for example for the needs of coast guards. In the article we discuss experiments, which were performed and based on data from the AIS system as well as from the MarineTraffic.com portal, where the latter data was used for the purpose of the evaluation of the proposed method of port calls identifi cation. Th e experiments showed that the development of reliable data collection is vital if further research in this area is to be performed.

  5. Krzysztof Gruszczyński, Jacek Małyszko

    Software Failure Impact on a Company's Business Process Efficiency

    Th e article discusses the subject of measuring the influence of softwarefailure rate on a company's business process effi iency. We put forward the thesisthat it is possible to measure the impact of increasing failure rate on a user's financial condition. The research is based on real data provided by KRUK S.A., which consists of two subsets: system failure logs and operational data. By searching for data outliers and by conducting a causal analysis, we tried to identify the days, which presented a high dependence of process effi ciency on the observed failure rate. As a result, we have shown that it is possible to discover a measurable outlier in the process effi ciency that is caused by a specifi c set of failures.

  6. Jacek Małyszko, Dawid Węckowski

    User Profiling Based on the Identities of Information Sources

    Along with the increased activity of people on the web, more and more information about them can be gathered based on the analysis of which web pages they visit, what data about themselves they put on the web and who they make contact with. Such information can be used to build so-called virtual identities of web users. Th is article presents the results of research on the problem of building an initial user identity in a situation, when the information about the user is limited very much, i.e. in the early stages of interaction with the system. A solution to this problem is proposed, in which the initial identities are constructed and based on the identity of information sources, which have been declared by the users as relevant to their information needs. Th e conducted experiment revealed that such identities of information sources can be used to build initial user identities.

  7. Włodzimierz Lewoniewski, Krzysztof Węcel

    Features of Wikipedia Articles and their Extraction Methods for Automatic Information Quality Assessment

    Th is article presents and classifi es features that can be extracted from Wikipedia articles for the purpose of automatic information quality assessment. Based on a state of the art analysis and our own experiments, specific measures for various aspects of quality have been defined. Additionally, an extraction method for various sources of features has been proposed. The links between articles in various languages off er opportunities for the comparison and verifi cation of the quality of information delivered by wikipedians. The elaborated model can be used for the relative quality assessment of data contained in the structural parts of Wikipedia articles, namely info boxes.

  8. Michael Vaknin, Agata Filipowska

    Modelowanie zależności między danymi w wykonywalnych procesach biznesowych

    Th e correctness, effectiveness, and efficiency of the business processes supported by information systems are becoming vital to organizations. Poor data quality may be the cause of losses related to organizational processes. There are numerous methods to assess and improve the quality of data within information systems. However, these methods oft en do not address the original source of these problems. Th is article presents a conceptual solution for dealing with the data quality issue within information systems. It focuses on an analysis of business processes being a source of requirements for information systems design and development. This analysis benefits information quality requirements, in order to improve data quality within systems emerging from these requirements.