ICT

Abstract

Recent years have witnessed a growing interest in urban air pollution monitoring, where hundreds of low-cost air quality sensors are deployed city-wide. To guarantee data accuracy and consistency, these sensors need periodic calibration after deployment. Since access to ground truth references is often limited in large-scale deployments, it is difficult to conduct city-wide post-deployment sensor calibration. In this work we propose In-field Calibration Transfer (ICT), a calibration scheme that transfers the calibration parameters of source sensors (with access to references) to target sensors (without access to references). On observing that (i) the distributions of ground truth in both source and target locations are similar and (ii) the transformation is approximately linear, ICT derives the transformation based on the similarity of distributions with a novel optimization formulation. The performance of ICT is further improved by exploiting spatial prediction of air quality levels and multi-source fusion. Experiments show that ICT is able to calibrate the target sensors as if they had direct access to the references.