Multimedia Traffic Classification for Imbalanced Environment

With ever-increasing volume and variety of multimedia traffic on the Internet, machine learning-empowered techniques nowadays tend to become indispensable for future intelligent network management. To realize automatic management with Quality Service (QoS) guarantees, there is a pressing need accurate classification. However, inherent characteristics networks cause imbalanced class distribution in classification, which could degrade performance especially minority classes. address issue imbalance both stationary nonstationary environments, this paper proposes novel scheme called CHS (chain hierarchical structure) able characterize from new perspective. By building an error model, we can compute propagation generated by analyze factors that affect it. More importantly, two key methods involving classifier ranking combination structure are devised mitigate produced classifier. The effectiveness developed framework validated through experiments over real-world datasets environments. experimental results demonstrate our proposed outperform state-of-the-art approaches terms classification accuracy running time. particularly effective environment.