Explainable Internet Traffic Classification

The problem analyzed in this paper deals with the classification of Internet traffic. During last years, has experienced a new hype, as traffic become essential to perform advanced network management. As result, many different methods based on classical Machine Learning and Deep have been proposed. Despite success achieved by these techniques, existing are lacking because they provide output that does not help practitioners any information regarding criteria taken given or what input data makes them arrive at their decisions. To overcome limitations, we focus an “explainable” method for able about output. More specifically, our proposed solution is multi-objective evolutionary fuzzy classifier (MOEFC), which offers good trade-off between accuracy explainability generated models. experimental results, obtained over two well-known publicly available sets, namely, UniBS UPC, demonstrate effectiveness method.