7^th European Food Safety & Standards Conference

Extra virgin olive oil (EVOO) is one of the most important foods of the Mediterranean diet. EVOO is one of the few oils that comes from the juice of a fruit, the olive. Its color depends on the quantity of pigments contained in the olive, like chlorophylls and carotenoids. Thanks to the properties possessed by the pigments present in the oil to absorb and emit radiation in the UV-Vis region of the electromagnetic spectrum, spectroscopic techniques can be used to relate the content of these pigments with the quality of the oil.

In this research, the detection and quantification of adulterants in one of the most common variety of EVOO has been successfully carried out. Visible absorption information was collected from binary mixtures of Picual EVOO with one of four adulterants; refined olive oil, orujo olive oil, sunflower oil, and corn oil. The data gathered from the absorption spectra was used as input to create a neural network (NN) model based. NNs are mathematical models with the outstanding ability to find non-linear relations between dependent and independent variables in databases. The designed mathematical tool was able to detect the type of adulterant with an identification rate higher than 95%, and to quantify the volume percentage of EVOO in the samples with a mean prediction error less than 1.5%. These significant results make NNs coupled with visible spectroscopy a reliable, inexpensive, user friendly,and real- time method for difficult tasks, given that the matrices of the different adulterated oils are practically alike.