An Improved Classification Method of Unstructured P2P Multicast Video Streaming

The classification of unstructured P2P multicast video streaming is the premise for playing online linkage and real-time evidence in the process of network monitoring management. Based on the classification method in the preliminary research, an improved classification method is proposed. The method uses an optimal feature vector extraction algorithm to filter the proposed behavior features in the original method, which greatly lower the feature vector dimension. An improved multi-class support vector machines is also used in the improved method, which not only solves the problem of rejecting sub-regional, but also reduces the computational complexity and improves the identification accuracy. Experiments show that the improved method has less computational and storage overhead, and has higher identification accuracy.