eISSN: 2574-8092
Submit manuscript...
Mini Review Volume 11 Issue 2
Research and analysis machine learning methods in network security in telecommunication system
Bayram Ibrahimov
Received: July 23, 2025 | Published: August 15, 2025
Citation: Ibrahimov B. Research and analysis machine learning methods in network security in telecommunication system. Int Rob Auto J. 2025;11(2):40-42. DOI: 10.15406/iratj.2025.11.00299
Abstract
The effectiveness of the use of machine learning in network safety in the telecommunication system is analyzed. This is due to the fact that the use of machine learning technology (ML, Machine Learning) in the field of telecommunication systems, information security, or cybersecurity is extremely in demand for experts. Given a complete and labeled training dataset, it makes sense to build a cluster using Machine Learning and Data Mining technologies, which have proven to be the most effective in network security for implementing systems and tools for detecting various attacks using machine learning methods. In particular, machine learning tools are used to identify threats of network safety in telecommunication systems, respectively, threats with confidential data that are stored, processed, transmitted and accepted in these networks. In this work, the tasks of studying machine learning methods in network safety in the telecommunication system and analysis of the metric assessment of the quality of algorithms clustering algorithms are considered. The aim of the study is to increase the quality indicators of machine learning models in solving problems of clustering the state of telecommunication systems. Analytical expressions are given to assess the quality of trained models that use various metrics to evaluate the advantages and disadvantages of clustering methods.
Keywords: machine learning method, recall, unsupervised learning, precision, clustering
©2025 Ibrahimov. This is an open access article distributed under the terms of the, which permits unrestricted use, distribution, and build upon your work non-commercially.