Calibration of small resistive commercial sensors to measure ozone with the interference of temperature and humidity

In this work we present a novel calibration procedure for resistive commercial sensors that consists on modeling the ozone sensor responses in presence of ambient humidity and temperature extracting its parameters and behavior and then combine it with a standard Partial Least Squares (PLS) regression. To assure the validity of the method then we apply it to the measurements of 19 different small commercial sensors from 5 different commercial brands in different conditions of ozone concentration, humidity and temperature. We compare the method with a regression without temperature and humidity and with a PLS regression in which we have taken into account the temperature and humidity but not modeled it. We see that this procedure has a mean decrease in the Root Mean Square Error, of 19.8%.