A calibrant-free drift compensation method for gas sensor arrays

Gas sensors lack repeatability over time. They are affected by drift, the result of changes at sensor level and in environment. A solution is to design software methods that compensate for drift. Existing often based on calibration samples acquired start each new measurement session. However, finding a good reference compound difficult task generating time-consuming. We propose model-based correction method which does not require any sample time, operating ‘blindly’. In this study, we focus drift affecting electronic noses. To end, built real data set 9 months real-life conditions. By using proposed method, show partly compensated, thus increasing reliability nose. Besides, also algorithm can easily adapt if target compounds all sampled during every