Predicting quality of experience in multimedia streaming

Abstract

Measuring and predicting the user's Quality of Experience (QoE) of a multimedia stream is the first step towards improving and optimizing the provision of mobile streaming services. This enables us to better understand how Quality of Service (QoS) parameters affect service quality, as it is actually perceived by the end user. Over the last years this goal has been pursued by means of subjective tests and through the analysis of the user's feedback. Existing statistical techniques have lead to poor accuracy (order of 70%) and inability to evolve prediction models with the system's dynamics. In this paper, we propose a novel approach for building accurate and adaptive QoE prediction models using Machine Learning classification algorithms, trained on subjective test data. These models can be used for real-time prediction of QoE and can be efficiently integrated into online learning systems that can adapt the models according to changes in the environment. Providing high accuracy of above 90%, the classification algorithms become an indispensible component of a mobile multimedia QoE management system

Survey on Qoe\Qos Correlation Models Formultimedia Services

“…al [33] × × × × Machado et al [37] × × × × Du et al [39] × × Kim et al [21] × × × Khan et al [42] × × Malinovski et al [44] × × × × Han et al [50] × × × × × × Laghari et al [51] × × × Ramos et al [28] × × × Koumaras et al [22] × × × Frank et al [40] × × × Calyam et al [41] × × × × × × Mok et al [23] × × Elkotob et al [32] × × × × × × Mushtaq et al [38] × × × × Hoßfeld et al [45] × × × ×…”

Quality of experience management in mobile content delivery systems

“…Initial findings seem to indicate that Support Vector Machines and Decision Tree based approaches may be more accurate than linear models [17]. Furthermore the amount of subjective data required can be reduced via automated online learning tools [18].…”

State-of-the-Practice in Evaluation of Quality of Experience in Real-Life Environments

“…Nowadays, a considerable effort is being invested into the development of such models (read e.g. [17,35,36,37,38]). …”