System Maintenance:
There may be intermittent impact on performance while updates are in progress. We apologize for the inconvenience.
By Topic

A Research on Intrusion Detection Based on Support Vector Machines

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

4 Author(s)
Xiaozhao Fang ; Fac. of Comput., Guangdong Univ. of Technol., Guangzhou, China ; Wei Zhang ; Shaohua Teng ; Na Han

Mass of the training samples and setting parameters of SVM artificially will affect badly the efficiency to find an optimal decision hyper plane for SVM. In this paper, FCM clustering algorithm and heuristic PSO algorithm are applied to Intrusion Detection. FCM clustering algorithm is designed to help SVM to find the optimal training samples from vast amounts of data; heuristic PSO algorithm is designed to find optimal parameters for SVM intelligently. The result of simulations run on the data of KDDCUP1999 shows that this approach can not only reduce the number of training samples and training time for SVM, but also detect unknown and known intrusions efficiently in the network.

Published in:

Communications and Intelligence Information Security (ICCIIS), 2010 International Conference on

Date of Conference:

13-14 Oct. 2010