Application of artificial neural networks to authenticate Virgin Groundnut Oil adulterants using FTIR spectral data

Abstract The aim of the present study is to detect the presence of palm oil and rice bran oil in virgin groundnut oil by Artificial Neural Networks (ANN) model. The oil samples were analyzed by FT-IR spectroscopy. They were classified as virgin groundnut oil, and two types of adulterated edible oil samples, such as palm oil and rice bran oil in different proportions (i.e.5, 10 and 15%). On the basis of cross validation procedure, the best models were selected and were further used for blend samples for prediction. The results obtained show that the models clearly separate different groups and classify correctly the virgin groundnut oil from the palm and rice bran oils. Moreover a reasonable discrimination between both mixtures and virgin oil was achieved.

[Full Text: PDF]

Updated: May 5, 2018 — 2:46 pm
© The Pharmaceutical and Chemical Journal Frontier Theme