Abstract: The objective of this dissertation is to propose an improved ensemble classifier method based on Neural Network and Gaussian Support Vector Machines, for cyber-attack classification problem. Previous work done [1] using hybrid techniques for Cyber attack classification was suffering while working with less amount of data also the structure of hybrid technique is very complex. The improved ensemble classifier is built using two different types of classification techniques. In the proposed method base classifier is the Support Vector Machine and another one is Neural Network classifier. The process of ensemble is done by bagging process, which uses multiple kernel function. The multiple kernels are Gaussian in nature.
Keywords: Cyber,Neural network, SVM, Optimize, GSVM.
|
DOI:
10.17148/IJARCCE.2022.11529
