Study of Intrusion Detection Feature Selection Based on Rough Set and Information Entropy
Jiang Yi-ting · Journal of Yunnan University of Nationalities · 2011
Feature selection is the removing process for the smallest feature subset satisfying the needs from the collection and application of selected characteristics related with great importance.It is important in the intrusion detection.For solving the problem of the existing intrusion detection system with less prior knowledge,the paper describes the intrusion detection feature set with the rough set knowledge representation system and determines the relative importance of each feature by calculating its information entropy.Finally,it gets a streamlined feature set.As a result,it simplifies the intrusion detection training set,reduces the detection time and effectively improves the classification accuracy of the invasion.