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 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 (long term evolution)) using HAS (HTTP adaptive streaming). All QoE models analyzed are based on the HAS profiles constructed by intercepting the HTTP get messages. The performance of all optimally trained models is compared and the sensitivity of the models to unseen profiles, content and devices is investigated.