Optimal Allocation of Mobile Learning Resources Based on a Complex Network

Abstract

Currently, centralized online learning can no longer meet the fragmented learning needs of learners. It is a hot topic in mobile learning to allocate reasonable mobile learning resources (MLRs) for user terminals and servers. However, the existing studies have rarely discussed the matching relationship between the MLR features of user terminals and servers. To fill up the gap, this paper tries to optimize the allocation of MLRs based on the theory of mobile knowledge complex network. Firstly, a local bidirectional fitness model was established to optimize MLR allocation, and the core nodes were mined from the complex network of MLRs. Next, the authors clarified the causality between the density of MLR complex network and resource integration, constructed an evaluation index system (EIS) for MLR integration ability, and evaluated the overall resource integration ability of MLR network resources. The proposed network was proved effective in optimizing the resource allocation of mobile learning networks through experiments.

Effective Mobility Identification in Mobile Fog Environment with the Internet of Things

“…Mobility prediction improves the efficiency when the user moves from one location to another without any delay the computation is carried by a nearby fog node. dynamic mobility prediction can be implemented in the real time applications like mobile phone use in class room [25] mobile learning [26], micro teaching video resources [27].…”