Context-Aware QoE Modelling, Measurement and Prediction in Mobile Computing Systems
2015 (English)In: IEEE Transactions on Mobile Computing, ISSN 1536-1233, E-ISSN 1558-0660, Vol. 14, no 5, 920-936 p.Article in journal (Refereed) Published
Quality of Experience (QoE) as an aggregate of Quality of Service (QoS) and human user-related metrics will be the key success factor for current and future mobile computing systems. QoE measurement and prediction are complex tasks as they may involve a large parameter space such as location, delay, jitter, packet loss and user satisfaction just to name a few. These tasks necessitate the development of practical context-aware QoE models that efficiently determine relationships between user context and QoE parameters. In this paper, we propose, develop and validate a novel decision-theoretic approach called CaQoEM for QoE modelling, measurement and prediction. We address the challenge of QoE measurement and prediction where each QoE parameter can be measured on a different scale and may involve different units of measurement. CaQoEM is context-aware and uses Bayesian networks and utility theory to measure and predict users' QoE under uncertainty. We validate CaQoEM using extensive experimentation, user studies and simulations. The results soundly demonstrate that CaQoEM correctly measures range-defined QoE using a bipolar scale. For QoE prediction, an overall accuracy of 98.93\% was achieved using 10-fold cross validation in multiple diverse network conditions such as vertical handoffs, wireless signal fading and wireless network congestion.
Place, publisher, year, edition, pages
2015. Vol. 14, no 5, 920-936 p.
QoE, Quality of Experience, Context-Awareness, context, Mobile IP, mobile computing, Bayesian Networks, Prediction, wireless networks, decision making, Decision Theory, use cases, subjective test, experimentation, Information technology - Telecommunication
Informationsteknik - Telekommunikation
Research subject Mobile and Pervasive Computing
IdentifiersURN: urn:nbn:se:ltu:diva-9731DOI: 10.1109/TMC.2013.155Local ID: 865f01a9-1f24-4f6b-88a5-502fb8072562OAI: oai:DiVA.org:ltu-9731DiVA: diva2:982669
Validerad; 2015; Nivå 2; 20131114 (karan)2016-09-292016-09-29Bibliographically approved