Quality of Experience Measurement for Video Streaming Based On Adaptive Neural Fuzzy Inference System

Abstract

Technological development in recent years leads to increase the access speed in the networks that allow a huge number of users watching videos online. Video streaming is one of the most popular applications in networking systems. Quality of Experience (QoE) measurement for transmitted video streaming may deal with data transmission problems such as packet loss and delay. This may affect video quality and leads to time consuming. We have developed an objective video quality measurement algorithm that uses different features, which affect video quality. The proposed algorithm has been estimated the subjective video quality with suitable accuracy. In this work, a video QoE estimation metric for video streaming services is presented where the proposed metric does not require information on the original video. This work predicts QoE of videos by extracting features. Two types of features have been used, pixel-based features and network-based features. These features have been used to train an Adaptive Neural Fuzzy Inference System (ANFIS) to estimate the video QoE.

Inference Analysis of Video Quality of Experience in Relation with Face Emotion, Video Advertisement, and ITU-T P.1203

“…In addition, our proposed method is in line with that employed in Ghani and Ajrash's [14] study on QoE prediction using alternative methods that do not rely on decrypted traffic data, such as psychophysiological measures, facial emotion recognition, and subjective feedback from viewers under E2E environmental conditions. Porcu et al [15] conducted a study to test this hypothesis.…”