作者: Silas Santiago Lopes Pereira , Jorge Luiz De Castro e Silva , Jose Everardo Bessa Maia
DOI: 10.1109/CNSM.2014.7014196
关键词: Data mining 、 Bottleneck 、 Preprocessor 、 Packet analyzer 、 Decision tree 、 Computer science 、 Naive Bayes classifier 、 Ensemble learning 、 Traffic classification 、 AdaBoost
摘要: This work presents the design and implementation of a real time flow-based network traffic classification system. The classifier monitor acts as pipeline consisting three modules: packet capture preprocessing, flow reassembly, with Machine Learning (ML). modules are built concurrent processes well defined data interfaces between them so that any module can be improved updated independently. In this pipeline, reassembly function becomes bottleneck performance. implementation, was used efficient method which results in average delivery delay 0.49 seconds, aproximately. For module, performances K-Nearest Neighbor (KNN), C4.5 Decision Tree, Naive Bayes (NB), Flexible (FNB) AdaBoost Ensemble Algorithm compared order to validate our approach.