Performance Comparison of Network Intrusion Detection System Based on Different Pre-processing Methods and Deep Neural Network

Abstract

There is a crucial need to have an intelligent and effective intrusion detection system to overcome network intrusion and cyber security attacks. Through this paper, the author compares various data pre-processing methods categorized as Feature selection, Feature encoding, and Feature scaling. The pre-processed data and an Autoencoder are used for further processing to get the best features and use them with a deep neural network for classification. Finally, the paper concludes a comparative analysis of pre-processing methods to determine the best for performing network intrusion detection.