Improved Task Allocation in Mobile Crowd Sensing Based on Mobility Prediction and Multi-objective Optimization

Mobile Crowd Sensing(MCS), a novel data sensing paradigm, its success largely depends on the design of a reasonable and feasible task allocation strategy. Recent research works have increasingly focused on exploring task allocation scenarios that are more realistic and specific, involving heterogeneous tasks and participants, and often incorporating multi-objective optimization techniques. In this paper, we consider the spatial-temporal sensing properties of the tasks and the participants, and design a novel multi-objective multi-task allocation scheme with mobility prediction(M3P). Experiments on the real-world dataset validate the effectiveness of our proposed methods compared against baselines.