Artificial neural network (ANN) was applied for data treatment as a multivariate calibration tool in a potentiometric acid base flow injection titration.
The performance of all the multivariate calibration methods, in all selected wavelength regions for both drugs, was evaluated by calculating a fitness function based on the root mean square error of calibration and validation.
Therefore, the objective of this study was to develop and validate a multivariate calibration model in association with the near infrared spectroscopy technique (NIR) for the simultaneous determination of rifampicin, isoniazid, pyrazinamide and ethambutol.
A comparison of the derivative and multivariate calibration results obtained in pharmaceutical formulations was performed resulting in agreement of the values obtained.
Second, the enzymatic electrochemical detection coupled with a multivariate calibration method based in the partial least-squares technique was optimized for the determination of a mixture of five phenolic compounds, i.e. phenol, p-aminophenol, p-chlorophenol, hydroquinone and pyrocatechol.
SPA has been compared to the genetic algorithm, which is a popular method for variable selection in multivariate calibration, and the results proved to be in favour of SPA (Araújo et al. 2011).
The results obtained by OSC-PLS are better than the PLS and this indicate the successful application of the OSC filter as a good preprocessing method in multivariate calibration methods.
In multivariate calibration with the spectral dataset, variable selection is often applied to identify relevant subset of variables, leading to improved prediction accuracy and easy interpretation of the selected fingerprint regions.
In multivariate calibration, SPA is aimed at screening variables for building multiple linear regression (MLR) models.
