Multi-Task Allocation in Mobile Crowd Sensing With Mobility Prediction

Mobile crowd sensing (MCS) is a popular paradigm that leverages the power of massive mobile workers to perform various location-based tasks. To assign with suitable tasks, recent research works investigated mobility prediction methods based on probabilistic and statistical models estimate worker’s moving behavior, which allocation algorithm designed match tasks such do not need deviate from their daily routes can be completed as many possible. In this paper, we propose new multi-task method prediction, differs existing by (1) making use workers’ historical trajectories more comprehensively using fuzzy logic system obtain accurate (2) designing global heuristic searching optimize overall task completion rate result, jointly considers tasks’ spatiotemporal features. We evaluate proposed two real-world datasets. The experimental results validate effectiveness compared against baselines.