Social-aware mobile user location prediction algorithm in participatory sensing systems

Mobile user location predication is critical to efficient data acquisition and message forwarding in participatory sensing systems. This paper proposes a Social-aware Mobile user Location Prediction algorithm (SMLP). The SMLP algorithm models application scenarios based on geographic locations, and extracting social relationships of mobile nodes from nodes' mobility. The SMLP algorithm preliminarily predicts node's mobility based on the Markov model, and then amends the prediction results using location information of other nodes which have strong relationship with the node. Two algorithms, SMLP1 and SMLPN, are proposed based on the Markov model and the weighted Markov model, respectively. Finally, the UCSD WTD data sets are exploited for simulations. Simulation results show that SMLP1 acquires higher prediction accuracy than the Markov model. SMLPN achieves more accuracy on prediction compared with SMLP1, and obtains comparable prediction accuracy with order-2 Markov model while presents extra lower algorithm complexity. Due to the introduction of weighting coefficients, both SMLP1 and SMLPNdemonstrate high flexibility. ©, 2015, Science Press. All right reserved.