A digital image smartphone-based approach to Slovak Tokaj wine authentication chemometric assisted.

The authentication of Slovak wines in comparison to other similar wines from various geographical regions, namely Hungary, France, Austria, and Ukraine, was conducted using the OC-PLS, DD-SIMCA, and PLS-DM models, all of them operating in rigorous way. The study involved 63 samples, of which 41 originated from Slovakia, covering diverse wine types such as varietal wines, cuvée selections (different "putnový"), and essence. To capture digital images under controlled conditions, a custom-made cardboard box with white inner surfaces was devised and equipped with a smartphone. During the training phase, sensitivities of 96%, 100%, and 96% were attained for OC-PLS, DD-SIMCA, and PLS-DM, respectively. In the subsequent stages of validation and testing for DD-SIMCA and PLS-DM, the proposed methods displayed optimal efficiency, achieving both sensitivity and specificity rates of 100%. However, such results were not achieved in the case of OC-PLS, which exhibited efficiency levels of 90% in validation and 80% in testing.

Handling multiblock data in wine authenticity by sequentially orthogonalized one class partial least squares.

New approach to deal with food authentication by modelling methods based on data recorded from different sources is proposed and called OC-PLS, combines an orthogonalization step between the different data sets to eliminate redundant information followed by definition of an acceptance area for a target class by OC-PLS. The proposed method was evaluated in two case studies. The first study used a controlled scenario with simulated data. In the second case study, the approach was applied using UV-VIS and IR data, in order to differentiate Slovak Tokaj Selection wines of high quality from other lower market value wines from the Slovak Tokaj wine region. In both cases, better results were reached than when individual blocks of data were achieved. The proposed method proved to be effective in properly exploring common and distinct information in each data block. The best compromise between sensitivity and selectivity in the prediction step was achieved.