Ad hoc-based feature selection and support vector machine classifier for intrusion detection
Xiao Hai-jun, Peng Fang, Ling Wang, Hongwei Li · 2007
In order to gain the result of identifying a good detection mechanism in intrusion detection, several intelligent techniques such as ANNs, SVMs, and data mining techniques are being used to build IDSs. Instead examining all data features to detect intrusion or misuse patterns, the approach of Adhoc-based feature selection and support vector machine classifier for detect intrusion is performed. In this performance of IDS, Ad hoc technology is used to optimize the feature subset for raw data and 10-fold cross validation is used to optimize the parameters of SVM for intrusion detection. The result of our experiments shows that the FS & SVM is not only superior to the famous data mining strategy, but also superior to other intelligent paradigms.