Big data classification using belief decision trees: application to intrusion detection

Abstract

Over the past few years, the data volume explosion fueled by exciting progression in computer technologies, made the Big Data the focus of widespread attention. Big Data is nebulous since it is an interaction result of several dimensions of scale, among them the veracity which refers to biases and noise in data. Therefore, Big Data veracity is a challenge because it requires a different approach in order to cope with this imperfection. We propose to involve the belief function theory and the belief decison tree as a classification technique to accommodate large applications where the uncertainty reigns. In this paper, we will be firstly concerned with the construction of the belief decision tree, using MapReduce programming model and the averaging approach as a classification method under uncertainty. Then, we will conduct experiments on intrusion detection massive data set, to distinguish between attacks and normal connections in such uncertain context.