PROJECT TITLE :

Socially-Driven Learning-Based Prefetching in Mobile Online Social Networks - 2017

ABSTRACT:

Mobile on-line social networks (OSNs) are rising as the popular mainstream platform for info and content sharing among individuals. In order to produce the quality of experience support for mobile OSN services, in this paper, we tend to propose a socially-driven learning-based mostly framework, specifically Spice, for the media content prefetching to reduce the access delay and enhance mobile user's satisfaction. Through a large-scale data-driven analysis over real-life mobile Twitter traces from over 17 000 users throughout a period of five months, we tend to reveal that the social friendship has a great impact on user's media content click behavior. To capture this result, we have a tendency to conduct the social friendship Clustering over the set of user's friends, and then develop a cluster-based Latent Bias Model for socially-driven learning-primarily based prefetching prediction. We have a tendency to then propose a usage-adaptive prefetching scheduling scheme by taking under consideration that different users might possess heterogeneous patterns in the mobile OSN app usage. We have a tendency to comprehensively evaluate the performance of Spice framework using trace-driven emulations on smartphones. Evaluation results corroborate that the Spice can achieve superior performance, with a median eighty.vi% access delay reduction at the low cost of cellular data and energy consumption. Furthermore, by enabling users to offload their Machine Learning procedures to a cloud server, our style can achieve up to a issue of one thousand speed-up over the native information training execution on smartphones.