Crowd Flow Prediction for Social Internet-of-Things Systems Based on the Mobile Network Big Data

Abstract

Accurate crowd flow prediction has gained increasing importance for the development of social Internet-of-Things (IoT) systems. In this article, we provide an efficient crowd flow prediction for social IoT systems in urban space based on the mobile network big data. In particular, the usage detail records (UDRs) are used in the prediction. The feasibility of using UDRs in the prediction is first analyzed. Then, a graph data model is exploited to record and represent the mobile behavior of users. In particular, we propose to apply the heterogeneous information network (HIN) representing the UDR data and characterize the users’ behavior through the embedding methods of HIN. Moreover, an attention-based spatiotemporal graph convolution network with embedded vectors (EA-STGCN) is proposed for the final prediction. Through experimental evaluation, the advantages of the proposed model are shown in comparison to benchmarks.