Transitive statistical sensor error characterization and calibration

TL;DR: This work has developed an on-line and in-field error modeling technique, which is a generalization of the calibration problem, that relies on a small number of inaccurate sensors with known error distributions to develop error models for the deployed in- field sensors.

Abstract: Calibration is the process of identifying and correcting for the systematic bias component of the error in the sensor measurements. On-line and in-field sensor measurement calibration is particularly crucial since manual calibration is expensive and sometimes infeasible. We have developed an on-line and in-field error modeling technique, which is a generalization of the calibration problem, that relies on a small number of inaccurate sensors with known error distributions to develop error models for the deployed in-field sensors. We demonstrate the applicability of our transitive error modeling technique and evaluate its performance in various scenarios by conducting experiments using traces of the light intensity measurements recorded by in-field deployed light sensors. In addition, statistical validation and evaluation methods such as resubstitution are used in order to establish the interval of confidence