relational data
Recently Published Documents


TOTAL DOCUMENTS

1174
(FIVE YEARS 133)

H-INDEX

46
(FIVE YEARS 4)

2021 ◽  
Vol 25 (5) ◽  
pp. 50-60
Author(s):  
M. V. Smirnov ◽  
R. S. Tolmasov

Goals and objectives. Graphical models have proven to be a reliable, clear and convenient tool for creating sketch models of databases. Most of the existing notations are designed for the relational data model, the dominant data model for the last thirty years. However, the development of information technologies has led to an increase in the popularity of non-relational data models, primarily the document model. One of the problems of its application in practice is the lack of suitable tools that allow performing graphical modeling of the database, taking into account the features of the document model, at the stage of logical design. The development of appropriate tools is an important and actual task, since their application in practical research makes it possible to identify, classify and analyze typical modeling errors that allow the designer to reduce the risk of their occurrence in the future. The purpose of this article is to develop a graphical notation that, on the one hand, providing convenience for the designer, and on the other hand, taking into account the peculiarities of creating and functioning of the noSQL document storage model.Materials and methods. The materials for the study were numerous publications devoted to the development of graphical notations in problems and their application to database design for various information systems. The selected materials were analyzed and the main graphical notations used to describe the relational data model were identified. Three notations were selected from them, a set of graphic stereotypes, which were most different from each other, the analysis of which allowed us to identify the main image patterns of the components of the relational model.The resulting patterns were applied to the main elements of the document database, which were obtained by analyzing the documentation of the popular MongoDB DBMS.Results. The result of the research was the creation of a new tool for modeling document databases at the logical level, which consists of a set of graphic stereotypes and rules for their application. On the one hand, the development is well known to practitioners who have previously worked with relational data models, since its development took into account many years of experience in using graphical models in the field of relational database design, and on the other hand, it reflects the features of the structure of the document model.Conclusion. The practical application of the developed model has shown the convenience of its use both in the process of designing document databases and in the process of teaching students within this subject area. The use of graphical models constructed in the proposed graphical notation will allow researchers to create and illustrate typical patterns of document databases, which will undoubtedly have a positive impact on the dynamics of the development of promising data storage technologies.


Author(s):  
Aman Paul ◽  
Daljeet Singh

Data mining is a technique that finds relationships and trends in large datasets to promote decision support. Classification is a data mining technique that maps data into predefined classes often referred as supervised learning because classes are determined before examining data. Different classification algorithms have been proposed for the effective classification of data. Among others, Weka is an open-source data mining software with which classification can be achieved. It is also well suited for developing new machine learning schemes. It allows users to quickly compare different machine learning methods on new datasets. It has several graphical user interfaces that enable easy access to the underlying functionality. CBA is a data mining tool which not only produces an accurate classifier for prediction, but it is also able to mine various forms of association rules. It has better classification accuracy and faster mining speed. It can build accurate classifiers from relational data and mine association rules from relational data and transactional data. CBA also has many other features like cross validation for evaluating classifiers and allows the user to view and to query the discovered rules.


2021 ◽  
Author(s):  
Yi-Chiao Wu ◽  
Cheng-Hung Hu ◽  
Hung-Shin Lee ◽  
Yu-Huai Peng ◽  
Wen-Chin Huang ◽  
...  

Author(s):  
NITESH KUMAR ◽  
ONDŘEJ KUŽELKA ◽  
LUC DE RAEDT

Abstract Relational autocompletion is the problem of automatically filling out some missing values in multi-relational data. We tackle this problem within the probabilistic logic programming framework of Distributional Clauses (DCs), which supports both discrete and continuous probability distributions. Within this framework, we introduce DiceML – an approach to learn both the structure and the parameters of DC programs from relational data (with possibly missing data). To realize this, DiceML integrates statistical modeling and DCs with rule learning. The distinguishing features of DiceML are that it (1) tackles autocompletion in relational data, (2) learns DCs extended with statistical models, (3) deals with both discrete and continuous distributions, (4) can exploit background knowledge, and (5) uses an expectation–maximization-based (EM) algorithm to cope with missing data. The empirical results show the promise of the approach, even when there is missing data.


2021 ◽  
Author(s):  
Yaqiong Li ◽  
Xuhui Fan ◽  
Ling Chen ◽  
Bin Li ◽  
Scott A. Sisson
Keyword(s):  

Author(s):  
Christopher Morris ◽  
Matthias Fey ◽  
Nils Kriege

In recent years, algorithms and neural architectures based on the Weisfeiler-Leman algorithm, a well-known heuristic for the graph isomorphism problem, emerged as a powerful tool for (supervised) machine learning with graphs and relational data. Here, we give a comprehensive overview of the algorithm's use in a machine learning setting. We discuss the theoretical background, show how to use it for supervised graph- and node classification, discuss recent extensions, and its connection to neural architectures. Moreover, we give an overview of current applications and future directions to stimulate research.


Sign in / Sign up

Export Citation Format

Share Document