By Topic

Support Vector Machines Improved by Artificial Immunisation Algorithm for Intrusion Detection

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Zhenguo Chen ; Dept. of Comput. Sci. & Technol., North China Inst. of Sci. & Technol., Beijing, China ; Guanghua Zhang

In this paper, a new intrusion detection method based on support vector machines improved by artificial immunization algorithm is presented. Support vector machines (SVM) has been well recognized as a powerful computational tool for problems with nonlinearity had high dimensionalities. Right setting parameters are very crucial to learning results and generalization ability of SVM. But empirical parameters are used frequently in SVM RFE, this has hampered its efficiency in practical application. Artificial immunisation algorithm (AIA) is a new intelligent algorithm which integrates global search with local search, and can effectively overcome the prematurity and slow convergence speed of traditional genetic algorithm. To improve the capability of the SVM classifier, The artificial immunisation algorithm is applied to optimize the parameter of SVM in this paper. The experimental result shows that the intrusion detection based on support vector machines improved by artificial immunisation algorithm can give higher recognition accuracy than the general SVM.

Published in:

Information Engineering and Computer Science, 2009. ICIECS 2009. International Conference on

Date of Conference:

19-20 Dec. 2009