Prediction of Network Intrusion using an Efficient Feature Selection Method
K. Rani, H. Roopa, V. Nithya Vani · 2019
Intrusion Detection System (IDS) is a model for detecting malevolent attacks and illegitimate network access. Improved intrusion detection system can be achieved by adapting an efficient method in analyzing the characteristics of the network data and selecting it based on its importance. This work proposes a feature selection method by applying Random Forest method on the network data. The attributes are selected and analyzed with various machine learning classifiers like Naïve Bayesian, k-Nearest Neighbor, Logistic Regression and Decision Tree. The performance of Decision Tree obtain is 99.95% which outperformed other classifiers.