Kernel principal component analysis (KPCA) has been effectively applied as an unsupervised non-linear feature extractor in many machine learning applications and suggested for various data stream classification tasks requiring a nonlinear transformation scheme to reduce dimensions. However, the dimensionality reduction ability is restricted because of KPCA’s high time complexity. So the practicality of KPCA on large datasets is rare. Therefore in this paper, we proposes a novel kind of incremental kernel principal component analysis algorithm: Data characteristic extraction based on IPCA algorithm –DCEIPCA, which allows efficient processing of large datasets and overcome the insufficient of KPCA. On the basis of DCEIPCA, we propose Classification expert system (CES) for intrusion detection system. Extensive experiments on KDDcup99 datasets confirm the superiority of Intrusion detection system based on CES(IDSCES) over other recent Intrusion detection system[4-11].
[1]
Salvatore J. Stolfo,et al.
A framework for constructing features and models for intrusion detection systems
,
2000,
TSEC.
[2]
Sun Jian,et al.
An Intrusion Detection Ensemble System Based on the Features Extracted by PCA and ICA
,
2006
.
[3]
Sandeep Kumar,et al.
A Software Architecture to Support Misuse Intrusion Detection
,
1995
.
[4]
Dorothy E. Denning,et al.
An Intrusion-Detection Model
,
1987,
IEEE Transactions on Software Engineering.
[5]
S. E. Smaha.
Haystack: an intrusion detection system
,
1988,
[Proceedings 1988] Fourth Aerospace Computer Security Applications.
[6]
Huan Liu,et al.
Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution
,
2003,
ICML.
[7]
Biswanath Mukherjee,et al.
DIDS (distributed intrusion detection system)—motivation, architecture, and an early prototype
,
1997
.