Open AccessInformativity assessment and attributes selection in a computer system state identification
Author(s) -
Svitlana Gavrylenko,
Illia Sheverdin,
Hennadii Heiko
Publication year - 2021
Publication title -
sučasnì ìnformacìjnì sistemi
Language(s) - English
Resource type - Journals
ISSN - 2522-9052
DOI - 10.20998/2522-9052.2021.2.01
Subject(s) - c4.5 algorithm , computer science , identification (biology) , data mining , selection (genetic algorithm) , state (computer science) , novelty , decision tree , artificial intelligence , machine learning , feature selection , set (abstract data type) , support vector machine , naive bayes classifier , philosophy , botany , theology , algorithm , programming language , biology
The subject of the article is a study of methods of determining the informativeness of attributes. The aim of the article is improvement of the classification quality of a computer system state by selecting the most informative features. Objective: To explore methods for selecting optimal information features to identify a computer system state based on an analysis of the Windows operating system events. The methods used are: machine learning methods, ensemble methods, methods of selecting the optimal information features. The following results were obtained: analysis of the Windows operating system events was performed, methods of selection the optimal information features were investigated: wrapper methods (Wrappers), embedded methods (Embedded) and filter methods (Filters). The informativeness assessment and selection features were performed for identifying a computer system state. An ensemble method for classifying a computer system state based on a bagging and J48 decision tree was developed to evaluate the effectiveness of selected features. The dependency of the classification accuracy of a computer system state on the selected features was investigated, and the attributes set that provides the maximum classification accuracy of a computer system state was determined. Conclusions. The scientific novelty of the results is in the analysis of the Windows operating system events, assessment of their informativeness and selection of features in the identification a computer system state.