ABSTRACT
The Neural Network (NN) technique was applied to the calibration of an ion selective electrode (ISE) array comprising a bromide selective electrode, two chloride ISEs and one thiocyanate ISE. The measured samples were synthetic mixture solutions of chlorides and bromides in concentration ranges such that interference occurs. The NN method allowed to perform the calibration without estimating the coefficients of the Nikolskii-Eisenman theoretical relation. Only the determination of bromide was detailed. The results obtained using this method were better than those obtained using linear multivariate calibration methods.
ABSTRACT
The calibration of several ions (Cl(-), Br(-), F(-) and OH(-)) measured with an ion selective electrodes (ISE) array has been carried out in the presence of interferents using an experimental design and multivariate calibration methods. Partial least squares regression and principal component regression do not seem to improve the test set prediction compared to multivariate linear regression. In the case of very slight or no interference on the ISE, each ion can be determined using the corresponding ISE and univariate calibration methods, but the use of multivariate methods does not lead to worse results.
