Data fusion of GC-IMS data and FT-MIR spectra for the authentication of olive oils and honeys-is it worth to go the extra mile?

Abstract

The potential benefit of data fusion based on different complementary analytical techniques was investigated for two different classification tasks in the field of foodstuff authentication. Sixty-four honey samples from three different botanical origins and 53 extra virgin olive oil samples from three different geographical areas were analyzed by attenuated total reflection IR spectroscopy (ATR/FT-IR) and headspace gas chromatography-ion mobility spectrometry (HS-GC-IMS). The obtained datasets were combined in a low-level data fusion approach with a subsequent multivariate classification by principal component analysis-linear discriminant analysis (PCA-LDA) or partial least squares-discriminant analysis (PLS-DA). Performing a back projection of PCA loadings, the influence of variables in the FT-IR spectra (one-dimensional) and the GC-IMS profiles (two-dimensional) on the discrimination was visualized within the original axis of the two data sources. Validation results of the classification models were compared to the results that could be obtained by using the individual data blocks separately. For both the honey and olive oil samples, a decreased cross-validation error rate and more robust model was obtained due to the low-level data fusion. The results show that data fusion is an effective strategy for improving the classification performance, particularly for challenging classification tasks such as the discrimination of olive oils with different geographical origin. Graphical abstract.