Open AccessAn Enhanced Hybrid Intrusion Detection Mechanism Based on Chicken Swarm Optimization and Naïve-Bayes Method
Author(s) -
Mrs. A.Shanthi Sona*,
N. Sasirekha
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.c4737.098319
Subject(s) - naive bayes classifier , computer science , intrusion detection system , classifier (uml) , data mining , swarm behaviour , artificial intelligence , feature selection , machine learning , bayes' theorem , swarm intelligence , pattern recognition (psychology) , particle swarm optimization , support vector machine , bayesian probability
The major important factor of network intrusion detection is to avoid malicious process in network. Since, existing modules are out-dated because of improper authentication and the network may get affected because of new attacks and malwares. In this research, Hybrid module is formed by using Chicken Swarm Optimization and Naive Bayes classifier (HCSONB) for classification of intrusion data. The hybrid method is introduced to detect the features efficiently in complex dataset because strategy which is designed to be capable of detecting huge data in network. Some traditional methods results in serious limitations in case of complex datasets. The algorithms are shared their properties together to discover better optimization results and the classification precisions values. This paper examines the feature selection performance by utilizing NSLKDD-99 dataset and comparing it with the Swarm Intelligence (SI), Naïve-Bayes classifier and proposed HCSO-NB algorithms. The proposed classification process designed in NETBEANS 8.2 tool. Experiments show that proposed HCSO-NB successfully improved the accuracy