Research of Network Traffic Classification Based on Ensemble Learning

Abstract

In order to improve the accuracy and generalization ability of network traffic classification model, this thesis proposes an ensemble learning model which combining three different kinds of model classifiers namely Logistic Regression(LR), Support Vector Machine(SVM) and K-Nearest Neighbors (KNN). In the integration model, LR, SVM and KNN are used to classify the network traffic separately, and then the classification results of the three different kinds of classifier are used to make the final prediction of the traffic category through Majority Voting ensemble learning. Compared with the single classification model, the ensemble learning model has better accuracy and generalization ability.