Forecasting fine-grained sensing coverage in opportunistic vehicular sensing

Abstract

Vehicles equipped with portable sensors can be used to collect data for large-scale urban sensing. However, the independent movement and non-uniform distribution of vehicles in opportunistic vehicular sensing raises questions about the quality of the sensing coverage. Appropriate vehicles are typically selected based on their historic trajectories, but this means that forecasting the sensor coverage for new vehicles is challenging. In this paper, we propose a method for tailored vehicle selection based on the forecast fine-grained sensing coverage without trajectory data. First, we propose a model, which is able to forecast fine-grained sensing coverage by coarse-grained information of candidate vehicles instead of trajectories. Then, by integrating the forecast sensing coverage with the genetic algorithm, a vehicle selection algorithm is proposed to select the appropriate vehicle fleet from the candidate vehicles to maximize the sensing quality. The method is assessed using taxi trajectory data in the evaluation experiments. The results demonstrate that the selected vehicles based on our method can achieve a higher sensing quality than two other baselines. This research provides fundamental guidelines for coverage estimation and vehicle selection in urban vehicular sensing applications. The demo is available at https://github.com/WenyanClaraHu/FiSC.