An LSTM-based Approach for Overall Quality Prediction in HTTP Adaptive Streaming
An LSTM-based Approach for Overall Quality Prediction in HTTP Adaptive Streaming
复制标题
基于 LSTM 的 HTTP 自适应流媒体整体质量预测方法
DOI：
10.1109/infcomw.2019.8845041
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
T. Thang
中科院分区：
文献类型：
--
作者：
Huyen T. T. Tran;Duc V. Nguyen;Duong D. Nguyen;N. P. Ngoc;T. Thang
HTTP自适应流（HAS）已经成为当今流行的多媒体传输解决方案。在HAS中，视频质量通常在每个流会话中变化。因此，HTTP自适应流中的一个关键问题是如何评估流会话的整体质量。在本文中，我们提出了一种机器学习方法的整体质量预测HTTP自适应流。在所提出的方法中，每个段由段质量、停顿持续时间、内容特性和填充四个特征表示。这些特征被输入到一个长短期记忆（LSTM）网络中，该网络能够探索片段之间的时间关系。使用线性回归模块根据LSTM网络的输出预测流媒体会话的整体质量。实验结果表明，该方法可以有效地预测流媒体会话的整体质量。此外，它被发现，我们提出的方法优于现有的四种方法。
HTTP Adaptive Streaming (HAS) has become a popular solution for multimedia delivery nowadays. In HAS, video quality is generally varying in each streaming session. Therefore, a key question in HTTP Adaptive Streaming is how to evaluate the overall quality of a streaming session. In this paper, we propose a machine learning approach for overall quality prediction in HTTP Adaptive Streaming. In the proposed approach, each segment is represented by four features of segment quality, stalling durations, content characteristics, and padding. The features are fed into a Long Short Term Memory (LSTM) network that is capable of exploring temporal relations between segments. The overall quality of the streaming session is predicted from the outputs of the LSTM network using a linear regression module. Experiment results show that the proposed approach is effective in predicting the overall quality of streaming sessions. Also, it is found that our proposed approach outperforms four existing approaches.