Truthful Incentive Mechanisms for Dynamic and Heterogeneous Tasks in Mobile Crowdsourcing

Crowdsourcing has received tremendous attention for collecting various data with the distributed smartphones of people. For the mobile crowdsourcing applications to obtain high-quality data, stimulating user participation is of paramount importance. Although many incentive mechanisms have been designed, most of them ignore the dynamic arrivals and different sensing requirements of tasks. Thus, the existing mechanisms will fail when being applied to the realistic scenario where tasks are publicized dynamically and heterogeneous with different sensing requirements of locations, time durations and sensing times. In this work, we propose two auction-based truthful mechanisms, TRIMS and TRIMG, for realistic mobile crowdsourcing under special user model and more general model, respectively. Through extensive simulations and theoretical analysis, we demonstrate that our mechanisms can satisfy the desired properties of truthfulness, individual rationality, computational efficiency with both low social cost and low total payment.