9.2.   Methanol, Ethanol and 1-Propanol by SPR

Although the measurements of methanol, ethanol and 1-propanol by a single sensor SPR device can be seen as an extension of the previous sections with 1 more analyte to be quantified, this data set was recorded as the first data set of the series. Thereby the measurement parameters like the thickness of the sensitive layers, the number of recorded time points and the measurement time had been less optimized. Details of the measurements and data sets are explained in section 4.5.2.2 and in [194]. An interesting point with consequences for some data analysis methods is the fact that the validation data set in contrast to the calibration data set was measured by averaging 2 repeated measurements. Several common data analysis method, like PLS, INLR, NN, PCA-NN and the new methods like the genetic algorithm framework and the parallel growing neural network framework are applied to the data set. This allows a comparison of the performance of the different methods on the basis of a second data set in addition to the refrigerant data.