Multimedia services quality prediction based on the association mining between context and QoS properties

With the increasing presence and adoptionof multimedia services over the Internet, quality has become an essential factor in choosing a service from a set of functionally similar services. To address the time-consuming, inaccurate and expensive multimedia quality evaluations in traditional methods, this paper proposes a context-aware matrix factorization (CAMF) approach to collaborative and personalized quality prediction for multimedia services. We first mine the association rules between context and QoS properties oriented to multimedia services to determine how a QoS value to be predicted is dependent on context properties. Then the service QoS experiences collected from other users are filtered out according to the context which is similar to current user. Based on the collected QoS data, a context-aware approach is designed for personalized service QoS value prediction. Experimental results demonstrate that this approach can make significant improvement on the accuracy of QoS prediction.