HAS QoE prediction based on dynamic video features with data mining in LTE network

• Published in: Science China. Information sciences 2017-04, Vol.60 (4), p.192-205, Article 042404
• Main Authors: Wang, Fei, Fei, Zesong, Wang, Jing, Liu, Yifan, Wu, Zhikun
• Format: Article
• Language: English
• Subjects: Accuracy; Bandwidths; Classification; Computer Science; Data mining; Information Systems and Communication Service; LTE; Methods; Quality standards; Regression; Research Paper; Segments; Signal to noise ratio; Streaming media; Video data; Video on demand; 分类方法; 回归分析; 峰值信噪比; 网络数据挖掘; 视频功能; 评价方法; 预测
• ISSN: 1674-733X; 1869-1919
• DOI: 10.1007/s11432-015-1044-3

Evaluation of HTTP adaptive streaming（HAS） quality of experience（Qo E） over LTE network is a challenging topic because of multi-segment and multi-rate features of dynamic video sequences. Different from the traditional Qo E evaluation methods based on network parameters, this paper proposes the HAS Qo E prediction methods based on its dynamic video segment features with data mining. Considering the application requirement of the trade-off between accuracy and complexity, two sets of methodologies are designed to evaluate the HAS Qo E including regression and classification. In regression method, we propose the evolved PSNR（e PSNR） model using differential peak signal to noise ratio（d PSNR） statistics as the segment features to evaluate HAS Qo E. In classification method, we propose the improved weighted k-nearest neighbors（Wk NN）by using dynamic weighted mapping according to the position of video chunk to meet the dynamic segment and rate features of HAS. In order to train and test these methods, we build a real-time HAS video-on-demand（VOD） system in LTE network and do subjective test in different video scenes. With the mean opinion score（MOS）, the regression and classification methods are trained to predict the HAS Qo E. The validated results show that the proposed e PSNR and Wk NN methods outperform other evaluation methods.