In vehicular mobility applications, sensor devices are exposed to rapidly varying concentrations of pollutants. Therefore, more than a conventional data set containing features such as sensor output, temperature and humidity is required to calibrate mobile sensors. We propose a new data set having additional features to address possible error sources encountered in vehicular-mobility LCS applications. We show that the proposed data set is a better choice for calibrating mobile LCS devices when compared to the conventional data set. Further, we propose and investigate two different tandem configurations involving a two-phase calibration approach to improve the calibration accuracy of mobile sensors. The calibration is done with real-time data obtained from an LCS device, SensurAir, which we developed and deployed in Chennai, India.