Context-Aware Estimation Approach Based on Participatory Sensing

In participatory sensing applications, the inaccuracy and conflict of the reported data, commonly caused by the error rate of participants or the differences of observation context, have received more and more attention. Estimating the real status of facilities according to observations becomes a big challenge for participatory sensing. Towards this end, we propose a context-aware estimation approach based on participatory sensing in this paper. We first model the effects of observation context, and then propose an iterative method to infer the error rate of participants and estimate the real status with high precision. Our method is verified using a public facilities monitoring application in our campus, and tested via extensive simulations. The results demonstrate that the proposed method outperforms recent popular three-estimates algorithm and OtO EM algorithm.