Crowdsensing is an effective method to map physical spatial fields by exploiting sensors embedded in smartphones. Enclosing humans in the loop increases the amount of data available for the mapping process, with benefits in terms of accuracy and cost. On the other hand, the huge amount of data generated and the irregular spatial distribution of measurements are serious issues to be addressed. In this paper we propose a combined Gaussian process (GP)-State space method for crowd mapping whose complexity and memory requirements for field representation do not depend on the number of data measured. The method is validated through an experimental campaign and simulations.
Dardari, D., Pasolini, G., Zabini, F. (2018). An efficient method for physical fields mapping through crowdsensing. PERVASIVE AND MOBILE COMPUTING, 48, 69-83 [10.1016/j.pmcj.2018.06.001].
An efficient method for physical fields mapping through crowdsensing
Dardari, Davide;Pasolini, Gianni;Zabini, Flavio
2018
Abstract
Crowdsensing is an effective method to map physical spatial fields by exploiting sensors embedded in smartphones. Enclosing humans in the loop increases the amount of data available for the mapping process, with benefits in terms of accuracy and cost. On the other hand, the huge amount of data generated and the irregular spatial distribution of measurements are serious issues to be addressed. In this paper we propose a combined Gaussian process (GP)-State space method for crowd mapping whose complexity and memory requirements for field representation do not depend on the number of data measured. The method is validated through an experimental campaign and simulations.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.