PROJECT TITLE :

Multi-Objective Optimization Based Allocation of Heterogeneous Spatial Crowdsourcing Tasks - 2018

ABSTRACT:

With the speedy development of mobile networks and the proliferation of mobile devices, spatial crowdsourcing, that refers to recruiting mobile employees to perform location-based mostly tasks, has gained emerging interest from both research communities and industries. In this Project, we tend to contemplate a spatial crowdsourcing scenario: in addition to specific spatial constraints, each task includes a valid length, operation complexity, budget limitation, and the quantity of required employees. Every volunteer worker completes assigned tasks whereas conducting his/her routine tasks. The system includes a desired task chance coverage and budget constraint. Underneath this situation, we investigate an vital downside, specifically heterogeneous spatial crowdsourcing task allocation (HSC-TA), which strives to look a collection of representative Pareto-optimal allocation solutions for the multi-objective optimization downside, such that the assigned task coverage is maximized and incentive value is minimized simultaneously. To accommodate the multi-constraints in heterogeneous spatial crowdsourcing, we tend to build a worker mobility behavior prediction model to align with allocation process. We tend to prove that the HSC-TA drawback is NP-laborious. We tend to propose effective heuristic ways, as well as multi-round linear weight optimization and enhanced multi-objective particle swarm optimization algorithms to attain adequate Pareto-optimal allocation. Comprehensive experiments on each real-world and artificial data sets clearly validate the effectiveness and efficiency of our proposed approaches.