Estimation of quality parameters in virgin olive oil treated with olive leaf extract: application of artificial neural networks
- 155 Downloads
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.
KeywordsEdible oils Natural antioxidants Mathematical modeling Multilayer perceptron layer Artificial neural networks
This research was funded by The Scientific and Technological research Council of Turkey (TÜBİTAK), Grant number 114M728.
- Clodoveo ML, Moramarco V, Paduano A, Sacchi R, Di Palmo T, Crupi P, Corbo F, Pesce V, Distaso E, Tamburrano P, Riccardo A (2017) Engineering design and prototype development of a full scale ultrasound system for virgin olive oil by means of numerical and experimental analysis. Ultrason Sonochem 37:169–181. https://doi.org/10.1016/j.ultsonch.2017.01.004 CrossRefGoogle Scholar
- Esfe MH, Bahiraei M, Hajmohammad MH, Afrand M (2017) Rheological characteristics of MgO/oil nanolubricants: experimental study and neural network modeling. Int Commun Heat Mass 86:245–252. https://doi.org/10.1016/j.icheatmasstransfer.2017.05.017 CrossRefGoogle Scholar
- Ghahdarijani AM, Hormozi F, Asl AH (2017) Convective heat transfer and pressure drop study on nanofluids in double-walled reactor by developing an optimal multilayer perceptron artificial neural network. Int Commun Heat Mass 84:11–19. https://doi.org/10.1016/j.icheatmasstransfer.2017.03.014 CrossRefGoogle Scholar
- Haykin S (2009) Neural networks and learning machines. Prentice-Hall, New JerseyGoogle Scholar
- Jacotet-Navarro M, Rombaut N, Deslis S, Fabiano-Tixier AS, Pierre FX, Bily A, Chemat F (2016) Towards a “dry” bio-refinery without solvents or added water using microwaves and ultrasound for total valorization of fruit and vegetable by-products. Green Chem 18:3106–3115. https://doi.org/10.1039/c5gc02542g CrossRefGoogle Scholar
- Javed S, Murthy YVVS, Baig RU, Rao DP (2015) Development of ANN model for prediction of performance and emission characteristics of hydrogen dual fueled diesel engine with Jatropha Methyl Ester biodiesel blends. J Natural Gas Sci Eng 26:549–557. https://doi.org/10.1016/j.jngse.2015.06.041 CrossRefGoogle Scholar
- Karaman S, Ozturk I, Yalcin H, Kayacier A, Sagdic O (2012) Comparison of adaptive neuro-fuzzy inference system and artificial neural networks for estimation of oxidation parameters of sunflower oil added with some natural byproduct extracts. J Sci Food Agric 92:49–58. https://doi.org/10.1002/jsfa.4540 CrossRefGoogle Scholar
- Vermerris W, Nicholson R (2008) Phenolic compounds and their effects on human health. Phenolic compound biochemistry. Springer, DordrechtGoogle Scholar
- Vicente H, Martins MR, Barrucho I, Santos M, Fernandes R, Costa J, Ribeiro J, Neves J (2018) Olive oil screening. In: Machado J, Abelha A, Gomes LM, Guerra H (eds) Proceedings of industrial simulation conference’ 2018, Eurosis-ETI Publication, Ghent, Belgium, pp 41–46Google Scholar
- Zhao R, Yan Y, Li M, Yan H (2008) Selective adsorption of tea polyphenols from aqueous solution of the mixture with caffeine on macroporous crosslinked poly (N-vinyl-2-pyrrolidinone). React Funct Polym 68:768–774. https://doi.org/10.1016/j.reactfunctpolym.2007.11.016 CrossRefGoogle Scholar