Development of an Intrusion Detection System using ANOVA Feature Selection and Support Vector Machine Algorithms
Loading...
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
Journal Press India - COMPUTOLOGY: Journal of Applied Computer Science and Intelligent Technologies, 4(1), 89 – 108
Abstract
The escalating sophistication and frequency of cyber-attacks have necessitated the
development of more advanced intrusion detection systems (IDS). This research presents the
development of an innovative IDS employing Analysis of Variance (ANOVA) for feature
selection and a Support Vector Machine (SVM) algorithm for intrusion detection. The aim is
to enhance detection accuracy while reducing computational overhead. ANOVA was used to
identify significant features from vast and complex network traffic data, simplifying the high
dimensional data and improving the detection system’s efficiency. The selected features are
then classified using the Radial Basis Function (RBF) SVM algorithm, renowned for its high
accuracy and robustness in handling high-dimensional data. A comparative analysis with
existing IDS models demonstrates the improved efficiency and accuracy of the proposed
model. This work provides an advanced methodology for cyber security, contributing to the
ever-evolving battle against cyber threats.
Keywords: Intrusion detection; Machine learning; Feature selection; Support vector
machine; ANOVA.