Research of methods for improving the quality of classification on highly correlated and unbalanced data

Abstract

The object of the study is the process of identifying the state of a computer systems and network. The subject of the study are the methods of identifying the state of computer systems and networks. The purpose of this paper is to develop a method for detecting intrusions in computer networks on highly correlated and unbalanced data. The results obtained. The paper analyzes traditional machine learning algorithms, deep learning methods and considers the advantages of using ensemble models. The scientific novelty of the obtained results lies in the comprehensive use of the developed procedure for reducing feature correlation, the use of the SMOTEENN data balancing method, and the tuning of parameters for basic classifiers and meta-algorithm. The developed methods are implemented using Python and the GOOGLE COLAB cloud service with Jupyter Notebook. Conclusions. Experiments confirmed the efficiency of the proposed method. The comprehensive use of the above procedures and methods allowed to improve the quality of models by 30% in solving the task of intrusion detection in the operation of computer systems and networks. This makes it possible to recommend it for practical use, in order to improve the accuracy of identifying the state of a computer system.