An ANFIS-Based Hybrid Video Quality Prediction Model for Video Streaming over Wireless Networks

Abstract

There are many parameters that affect video quality but their combined effect is not well identified and understood when video is transmitted over mobile/wireless networks. In this paper our aim is twofold. First, to study and analyze the behaviour of video quality for wide range variations of a set of selected parameters. Second, to develop a learning model based on ANFIS to estimate the visual perceptual quality in terms of the mean opinion score (MOS) and decodable frame rate (Q value). We trained three ANFIS-based ANNs for the three distinct content types using a combination of network level and application level parameters such as frame rate, send bitrate, link bandwidth and packet error rate and tested the ANN models using unseen dataset. We found that the video quality is more sensitive to network level parameters compared to application level parameters. Preliminary results show that a good prediction accuracy was obtained from the ANFIS-based ANN model. The work should help in the development of a reference-free video prediction model and quality of service (QoS) control methods for video over wireless/mobile networks.