Model for estimating QoE of Video delivered using HTTP Adaptive Streaming

The end user QoE (quality of experience) of content delivered over a radio network is (mainly) influenced by the radio conditions in the RAN (radio access network). This paper analyses various QoE models for video delivered over a radio network (e.g. LTE) using HAS (HTTP adaptive streaming). All QoE models analyzed are based on the HAS profiles obtained by intercepting the HTTP get messages. The performance of the models is compared for optimally trained settings. The sensitivity of the models to unseen profiles, content and errors in the input of the models is investigated as well