Extraction of Phenolic Compounds with Antioxidant Activity from Strawberries: Modelling with Artificial Neural Networks (ANNs)

Abstract

This research study focuses on the evaluation of the total phenolic compounds (TPC) and antioxidant activity (AOA) of strawberries according to different experimental extraction conditions by applying the Artificial Neural Networks (ANNs) technique. The experimental data were applied to train ANNs using feed- and cascade-forward backpropagation models with Levenberg-Marquardt (LM) and Bayesian Regulation (BR) algorithms. Three independent variables (solvent concentration, volume/mass ratio and extraction time) were used as ANN inputs, whereas the three variables of total phenolic compounds, DPPH and ABTS antioxidant activities were considered as ANN outputs. The results demonstrate that the best cascade- and feed-forward backpropagation topologies of ANNs for the prediction of total phenolic compounds and DPPH and ABTS antioxidant activity factors were the 3-9-1, 3-4-4-1 and 3-13-10-1 structures, with the training algorithms of trainlm, trainbr, trainlm and threshold functions of tansig-purelin, tansig-tansig-tansig and purelin-tansig-tansig, respectively. The best R2 values for the predication of total phenolic compounds and DPPH and ABTS antioxidant activity factors were 0.9806 (MSE = 0.0047), 0.9651 (MSE = 0.0035) and 0.9756 (MSE = 0.00286), respectively. According to the comparison of ANNs, the results showed that the cascade-forward backpropagation network showed better performance than the feed-forward backpropagation network for predicting the TPC, and the FFBP network, in predicting the DPPH and ABTS antioxidant activity factors, had more precision than the cascade-forward backpropagation network. The ANN technique is a potential method for estimating targeted total phenolic compounds and the antioxidant activity of strawberries.

Growth and Physiological Characteristics of Strawberry Plants Cultivated under Greenhouse-Integrated Semi-Transparent Photovoltaics

“…The free-radical-scavenging activity of the extract was evaluated using the 1,1-diphenyl-2-picryl-hydrazyl (DPPH) method [ 32 ]. More precisely, a DPPH solution (Cayman Chemical, Ann Arbor, MI, USA) was prepared fresh in MeOH.…”

Extraction of Phenolic Compounds from Cherry Seeds: A Preliminary Study

“…The Folin-Ciocalteu method is one of the relatively simple spectrophotometric assays used to determine the content of total phenolic compounds [6]. For measurements, 125 µL of samples (or standard solution) were mixed with 750 µL of distilled water and 125 µL of Folin-Ciocalteu reagent.…”

“…The extraction process is one of the fundamental steps for the recovery of phenolic compounds from the food industry and the related by-products or residues [5]. Different methodologies are available to perform this operation [6] but the choice will also depend on the kind of food product or residue under analysis [7]. The extraction of phenolic compounds can be performed by techniques such as infusion, decoction, maceration, percolation, digestion, Soxhlet extraction, aqueous alcoholic extraction by phytonics processes, supercritical fluid extraction, counter current extraction, ultrasound extraction, or by fermentation [8].…”

“…Naczk and Shahidi [10] showed that extraction times longer than 24 h could increase the oxidation process of phenolic compounds, therefore they should not be used in order to preserve the antioxidant properties of the phenolic compounds. Golpour et al [6] evaluated the effect of different operating conditions on the extraction of phenolic compounds form strawberry, namely time, solvent concentration and volume/mass ratio. They found that total phenolic compounds were better extracted when using a volume/mass ratio of 12 mL/g, using a methanol aqueous solution with a concentration of 70% methanol and extraction time of 40 min.…”

Neural Network Modelling of Phenolic Content, Antioxidant Capacity and Microbial Population Dynamics of a Household Scale Spontaneous Fermentation of Carica Papaya Leaf

“…This learning capability of the ANN allows the optimization and prediction of various process responses e.g., growth, yield, aging time, which are normally encountered during complex biological processes [14]- [15]. ANN was also employed to predict the effect of extraction conditions on total phenolic compounds (TPC), anthocyanin (ANT) and antioxidant activity (AOA) of beetroot [16] and strawberries [17]. It is also more advantageous than the other tools e.g., response surface method (RSM), since input-output relationship can be established by exploiting the mathematical models even without prior information of the physical relationship between them [18].…”