Application of support vector machine model based on an improved elephant herding optimization algorithm in network intrusion detection

Abstract

In order to improve the accuracy of network intrusion detection, it is necessary to optimize Support Vector Machine (SVM) parameters. In view of the advantages of Elephant Herding Optimization (EHO) algorithm, such as simple control parameters and easy combination with other algorithms, this paper tries to optimize these parameters by using an Improved EHO (IEHO) algorithm. The IEHO-SVM algorithm is then proposed for parameters optimization, in order to improve the accuracy of network intrusion detection. The simulation experiment uses the KDD CUP99 data set for verification analysis. The experimental results show that, compared with the Particle Swarm Optimization (PSO)-SVM algorithm, Month-flame Optimization (MFO)-SVM algorithm and the basic EHO-SVM algorithm, the IEHO-SVM algorithm not only improves the global search ability of network intrusion, but also increases the accuracy rate of network intrusion detection by an average of 7.36%, 4.23% and 5.56% respectively, and reduces the false alarm rate by an average of 3.04%, 2.41% and 3.07% respectively, which aims at improving the efficiency of network intrusion detection.