
The analysis of information security problems solved by clustering methods
Author(s) -
Andrey R. Aidinyan,
Olga L. Tsvetkova,
A. N. Gerasimenko,
O Ja Kravets
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1679/2/022084
Subject(s) - cluster analysis , fuzzy clustering , data mining , computer science , correlation clustering , cluster (spacecraft) , artificial intelligence , programming language
The actual problem of information security is achieved by using a variety of methods and technologies. The level of information protection depends on the quality of the methods used. The article deals with information security problems, and provides a classification and analysis of clustering algorithms. The clustering methods considered during the classification process have certain advantages and disadvantages, the correct choice of which ensures their effective application in solving specific problems. Clustering methods k-means and k-medians in most cases give better results with the right choice of clustering criteria. These methods are simple, contain a small number of calculations, and avoid the problem of sensitivity to the initial choice of cluster centers. It also makes sense to use fuzzy clustering if cluster elements cannot be clearly assigned to one of the clusters.