NORMA eResearch @NCI Library

Application of Machine Learning Models for Network Intrusion Detection Systems Based on Feature Selection Approach

Murugesan, Shibi (2019) Application of Machine Learning Models for Network Intrusion Detection Systems Based on Feature Selection Approach. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (2MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (895kB) | Preview

Abstract

The amount of internet usage among the industry has grown rapidly in day to day life. Network intrusion has become the major thread in terms of security and various attacks are affecting the system. Intrusion Detection Systems is one such key technique which helps in protecting the system information and detect the various attack more accurately. Proposing machine learning schemes has been increased rapidly to detect the intrusion detection.In this research study, NSL-KDD dataset is been experiments with various machine learning algorithms to classify the attack type. However, among implementing the classification models a little consideration is given to Feature Selection. In order to improve the accuracy performance two feature selection methods (Embedded Method and Filter Method) is proposed in this study. This study Results are analysed on one vs Rest class classification based of the proposed model with metrics such as Accuracy, Precision, f1- Score.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software > Computer Security
T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 17 Jun 2020 15:43
Last Modified: 17 Jun 2020 15:43
URI: http://norma.ncirl.ie/id/eprint/4302

Actions (login required)

View Item View Item