关键词: 机器学习, 集成学习, 数据不平衡, 网络流量, 重采样

Abstract:

Since the data imbalance affects the accuracy of the traffic classification based on machine learning, a traffic classification algorithm based on ensemble learning and resampling RES-LGBM is tailored. The algorithm uses statistical features of traffic flows, and optimizes the feature set by backtracking search method. After determination of optimal tree structure, the RES-LGBM is employed to eliminate the data imbalance and test the classification result. The test result shows that the algorithm enhances the classification of imbalanced data with high efficiency and stablility.

Key words: machine learning, ensemble learning, data imbalance, network flow, resampling