Learning-based Incentive Mechanism Design for Crowd Sensing

Crowd sensing campaigns encourage ordinary people to collect and share sensing data by using their portable smart devices like smartphones, iPad and iWatch. However, how to encourage participants to contribute sensing data is still a challenge. In this paper, we propose a learning-based incentive mechanism to maximize the collected amount of data under the constrained condition of limited task budget. Essentially, the mechanism sets different data collected price of every block based on the historical collection condition. The set price on one hand should make sure of that the total cost doesn't exceed the limited budget, on the other hand, that participants are willing to contribute sensing data. It has been shown by simulation results that our proposed algorithm collects more amount of sensing data than that of the other two comparison algorithms.