Research Repository

A hybrid prediction model for video quality by QoS/QoE mapping in wireless streaming

Danish, E and Fernando, A and Alreshoodi, M and Woods, J (2015) A hybrid prediction model for video quality by QoS/QoE mapping in wireless streaming. In: UNSPECIFIED, ? - ?.

Full text not available from this repository.

Abstract

© 2015 IEEE. In the video streaming arena, and especially within the wireless transmission domain, measuring users' quality of experience (QoE) has become a pressing issue for it offers several benefits to both the service provider and the end user. However, available measurement techniques that adopt a full reference model (FR) are impractical in real-time transmission scenarios since they require the original video sequence available at the receiver's end. Hence, no-reference (NR) models fill this gap by providing less accurate measurement but sufficiently reliable for real-time video streaming. In this paper, we propose and evaluate a hybrid no-reference prediction model for the perceptual quality of video in the wireless domain. The model is based on fuzzy inference systems (FIS), and exploits several key parameters from both the application layer and physical layer. Hence the model is realized by means of mapping quality of service to quality of experience (QoS/QoE). The model is evaluated in contrast to random neural networks (RNN), and simulation results show considerable prediction accuracy of the model with a correlation coefficient of 92.17% and 0.1098 root mean square error.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2015 IEEE International Conference on Communication Workshop, ICCW 2015
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 24 Sep 2016 11:26
Last Modified: 04 Feb 2019 11:16
URI: http://repository.essex.ac.uk/id/eprint/17638

Actions (login required)

View Item View Item