Abstract
In recent times, with the advancement in technology and revolution in digital information, networks generate massive amounts of data. Due to the massive and rapid transmission of data, keeping up with security requirements is becoming more challenging. Machine learning (ML)-based intrusion detection systems (IDSs) are considered as one of the most suitable solutions for big data security. Despite the progress in ML, unrelated features can drastically influence the performance of an IDS. Feature selection plays a significant role in improving ML-based IDSs. However, the recent growth of dimensionality in data poses quite a challenge for current feature selection and extraction methods. Due to high data dimensionality, feature selection methods suffer in terms of efficiency and effectiveness. In this paper, we are introducing a new process flow for filter-based feature selection with the help of a transformation technique. Generally, normalization or transformation is implemented before classification. In our proposed model, we implemented and evaluated the effects of normalization before feature selection. To present a clear analysis on the effects of power transformation, five different transformations were implemented and evaluated. Furthermore, we implemented and compared different feature selection methods with the proposed process flow. Results show that compared with existing process flow and feature selection methods, our proposed process flow for feature selection can locate a more relevant set of features with high efficiency and accuracy.
Highlights
In recent years, the use of smart devices has grown at a rapid rate
In our proposed process flow, we experimented by using power transformation before filter-based feature selection, as normalizing data before applying a statistical-based Feature selection (FS) can improve the probability of selecting relevant features
The proposed method is compared with the traditional process flow and two wrapper-based feature selection methods
Summary
The use of smart devices has grown at a rapid rate This increase has led to a significant upsurge of network traffic. In the past few years, a number of different methods were proposed to improve the efficiency of IDSs over big data [6]. ML-based IDSs consider network security as a classification problem to distinguish between normal and malicious traffic. Due to the density of data in today’s communication networks, providing an efficient and effective method for FS is essential for ML-based IDSs. this paper focuses on providing a detailed experimental finding of a filter-based FS method with optimized process flow. The proposed process flow achieved high accuracy by using a deep neural network (DNN)-based IDS. Proposing a flow for filter-based feature selection using power transformation to achieve higher accuracy and efficiency
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
