An Accurate and Extensible Machine Learning Classifier for Flow-Level Traffic Classification

作     者：Gang Lu Ronghua Guo Ying Zhou Jing Du 

作者机构：Chinese Luoyang electronic equipment centerLuoyang 471003China 

出 版 物：《China Communications》 (中国通信（英文版）)

年 卷 期：2018年第15卷第6期

页      面：125-138页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0814[工学-土木工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 082301[工学-道路与铁道工程] 0823[工学-交通运输工程] 

基　　金：supported by the National Natural Science Foundation of China under Grant No.61402485 National Natural Science Foundation of China under Grant No.61303061 supported by the Open fund from HPCL No.201513-01 

主　　题：traffic classification class imbalance dircriminator bias encrypted traffic machine learning 

摘      要：Machine Learning(ML) techniques have been widely applied in recent traffic ***, the problems of both discriminator bias and class imbalance decrease the accuracies of ML based traffic classifier. In this paper, we propose an accurate and extensible traffic classifier. Specifically, to address the discriminator bias issue, our classifier is built by making an optimal cascade of binary sub-classifiers, where each binary sub-classifier is trained independently with the discriminators used for identifying application specific traffic. Moreover, to balance a training dataset,we apply SMOTE algorithm in generating artificial training samples for minority *** evaluate our classifier on two datasets collected from different network border *** with the previous multi-class traffic classifiers built in one-time training process,our classifier achieves much higher F-Measure and AUC for each application.