Analysis and Implementation of Normalisation Techniques on KDD’99 Data Set for IDS and IPS

The rapid expansion of the Internet, numerous types of network attacks have emerged, making the ability to identify aberrant behaviour and accurately recognise attack categories an essential study topic in the field of network security with the help of Intrusion Detection System and Intrusion Prevention System. Many popular machine learning-based approaches have recently been used to build a data-driven model in the intrusion detection system (IDS). The methods can help save time and money by reducing the amount of manual detection required. However, real-time network data contain a plethora of duplicated phrases and sounds, and some present intrusion detection methods have low accuracy and feature extraction capabilities. In order to solve the above problems, this research work proposes new machine learning algorithm for avoid intrusion. Pre-processing work for the final ML method is proposed in this paper. This pre-processing includes data cleaning and normalisation. To perform normalisation, this paper compares alternative normalisation algorithms and implements the chosen normalisation approach with the KDD’99 data set.