Intrusion Feature Selection Method Based on Neighborhood Distance
Shaobo Du · 2017 International Conference on Computer Systems, Electronics and Control (ICCSEC) · 2017
Aiming at problem that independent and redundant attributes of intrusion data cause intrusion detection algorithms' slow detection speed and low detection rate in intrusion detection. An intrusion feature selection method based on neighborhood distance is proposed. The approach clustered again on the selected feature subset. The use of the selected feature subset can improve clustering accuracy and speed. Simulation experiment is done in KDD99. Result shows that compared with Genetic algorithm and Relief algorithm, the approach is more effective for feature selection of intrusion data and improvement of intrusion detection speed of classification algorithms.