SVM-based QoE estimation model for video streaming service over wireless networks

In this paper, we propose a quality of experience (QoE) estimation model for HTTP video streaming service over wireless networks. In the proposed model, the comprehensive QoE influence factors are grouped into two types, namely the objectivity-aware parameters and the psychology-aware parameters. The considered factors include video content features, the encoding parameters, the network transmission metrics, and the playout buffer parameters. Moreover, we use support vector machine (SVM) to estimate the integrated QoE with the comprehensive parameters, which achieves a tradeoff between the learning ability and the computational complexity of the QoE estimation model. Simulation results show that the proposed SVM-based QoE estimation model performs well in terms of high Pearson correlation coefficient, low root mean square error, and low computational complexity.