Comparison of Two Feature Selection Methods in Intrusion Detection Systems

Author

Fadaeieslam, M.J. ; Minaei-Bidgoli, B. ; Fathy, M. ; Soryani, M.

fYear

2007

fDate

16-19 Oct. 2007

Firstpage

83

Lastpage

86

Abstract

The quality of features directly affects the performance of classification. Many feature selection methods introduced to remove redundant and irrelevant features, because raw features may reduce accuracy or robustness of classification. In this paper we proposed a new method for feature selection based on Decision Dependent Correlation (DDC). We have used SVM classifier and the results on DARPA KDD99 benchmark dataset indicate that the proposed method outperforms Principal Component Analysis (PCA).

Keywords

pattern classification; principal component analysis; security of data; support vector machines; SVM classifier; classification; decision dependent correlation; feature selection method; intrusion detection system; principal component analysis; support vector machine; Information technology; Intrusion detection; Mutual information; Principal component analysis; Robustness; Support vector machine classification; Support vector machines; Telecommunication traffic; Testing; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer and Information Technology, 2007. CIT 2007. 7th IEEE International Conference on

Conference_Location

Aizu-Wakamatsu, Fukushima

Print_ISBN

978-0-7695-2983-7

Type

conf

DOI

10.1109/CIT.2007.99

Filename

4385061