QoE Prediction Model Based on Fuzzy Logic System for Different Video Contents

A model that can predict end user satisfaction or QoE (Quality of Experience) directly from the network QoS (Quality of Service) is still illusive in the field of image processing. This motivates the derivation of a meaningful QoS to QoE mapping function to allow one to be predicted in the absence of the other. This paper presents an affine fuzzy logic based model that can estimate the visual perceptual quality for different video content types using a combination of network level and application level QoS parameters. Video contents are classified based on their spatio-temporal feature extraction. The video QoE is predicted in terms of the Mean Opinion Score (MOS). From the results it is clear that the QoE is video content dependent. Also, the network level parameters have more impact on video quality than the application level parameters. Results show that the Fuzzy logic-based model provides high prediction accuracy. The performance of the model was evaluated using a public dataset with good prediction accuracy (similar to 95%). The developed model has use in control methods for streaming standard encoded video.