An Approximation Decision Entropy Based Decision Tree Algorithm and Its Application in Intrusion Detection

Abstract

In this paper, we propose a novel decision tree algorithm DTADE within the framework of rough set theory, and apply DTADE to intrusion detection. We define a new information entropy model -- approximation decision entropy (ADE) in rough sets, which combines the concept of conditional entropy in Shannon's information theory and the concept of approximation accuracy in rough sets. In algorithm DTADE, ADE is adopted as the heuristic information for the selection of splitting attributes. Moreover, we present a method of decision tree pre-pruning based on the concept of knowledge entropy proposed by Duntsch and Gediga. Finally, the KDDCUP99 data set is used to verify the effectiveness of our algorithm in intrusion detection.