Self-organizing maps and learning vector quantization networks as tools to identify vegetable oils and detect adulterations of extra virgin olive oil

Abstract Unsupervised models have been explored for the identification of edible and vegetable oils and to detect adulteration of extra virgin olive oil (EVOO) using the most common chemicals in these oils such as saturated fatty, oleic and linoleic acids. The optimization and validation processes of the models have been carried out using bibliographical sources. A database for developing learning process and internal validation, and six other different databases to perform their external validation has been used. In the worst of the cases, the unsupervised models are able to classify more than the 94 % of samples and detect adulterations of EVOO with promising results. The adulteration of EVOO with corn, soya, sunflower and hazelnut oils can be detected when their oil concentrations are higher than 10, 5, 5 and 10 %, respectively.