EXTRACTION OF PHENOLIC COMPOUNDS FROM FENUGREEK SEEDS: MODELLING AND ANALYSIS USING ARTIFICIAL NEURAL NETWORKS

Abstract

This study introduces the modeling and analysis of the extraction process of bioactive compounds from fenugreek seeds in different solid-to-solvent ratios (0.5-60 g/L) and extraction times. Maceration was applied with agitation for the extraction processes and total phenolic compounds, total flavonoid content and antioxidant activity of the extracts were measured as experimental data. The amount of extractable phenolic compounds having antioxidant effect was increased by adjusting the solid-to-solvent ratio. According to obtained results, the highest values were determined as 12564.08±376.88 mg gallic acid/100 g dry sample, 7540.44±39.67 mg quercetin/100 g dry sample and 1904.80±17.43 mM Trolox/100 g dry sample for total phenolic compounds, total flavonoid content, and antioxidant activity, respectively. The extraction process was modeled using standard Artificial Neural Networks (ANN) and Pi-Sigma Neural-Networks (PSNN). The PSNN model had a higher prediction efficiency with lower RMSE (%) values varied between 0.94% and 1.30% for both training and testing.