Estimation of quality parameters in virgin olive oil treated with olive leaf extract: application of artificial neural networks

Abstract

In this paper, virgin olive oil was treated by olive leaf extract to increase the quality of the product by means of ultrasound-assisted extraction. A multilayer perceptron layer artificial neural network (MLP-ANN) was applied to model the enrichment process and to estimate the quality parameters such as total biophenols, oleuropein, total carotenoids and peroxide value (PV) in virgin olive oil treated with olive leaf extract. Oxidative stability of the oil was assessed by means of Rancimat, which is an accelerated method for prediction of shelf life based on the measurement of the induction time. Free radical scavenging activity (FRSA) in addition to the mentioned quality parameters of the treated oils was compared to those of pure olive oil. The shelf life of the product was increased by almost 25%, while oleuropein content was doubled in the oil. FRSA of the olive oil was also doubled, whereas PV of the product decreased by ≈ 12% comparing to that of untreated oil. The estimation by MLP-ANN was found satisfactory with 3% of error rate.