Performance on prediction of concentration of gas A under drift-free conditions.

Two methods, linear PLS and non-linear SVR, were tested on the regression task of analyte A given at concentration 0.01, 0.02, 0.05 and 0.1 vol.%. Three arrays composed of 24 sensors, different in the types of sensor, were compared in terms of the root-mean-square error in prediction (RMSEP). For each array, the non-linear models outperform the linear models. The first array and the SVR method yield the best performance.