Quality of Experience analysis for VoLTE services through Artificial Neural Network fitting
Alessandro Vizzarri, Fabrizio Davide · 2016
We consider Quality of Experience (QoE), measured in terms of Mean Opinion Score Listening Quality Subjective (MOS_LQS) for a Voice over LTE (VoLTE) application in realistic situations. Groups of service scenarios have been identified and the network performance simulated. We organized a listening panel to measure MOS according to standard procedures. MOS-LQS results and QoS metrics have been correlated using a set of Artificial Neural Network (ANN) models. As a clear result the ANN accurately models the relationship. This confirms again the need for an approach that is non linear and capable of generalization, as made by the human judgment. Future research is necessary to generalize the ANN model to a far larger scale while controlling the combinatorial explosion of scenarios and technical parameters.