Ultrasound Assisted Extraction and Response Surface Methodology and Artificial Neural Network Optimization of Pectin from Orange Peel

The objective of study was ultrasound-assisted extraction of pectin from orange peel using response surface method and artificial neural network technique. The following findings are absorbed from the effects of extraction parameters and technique used. The pH solution was highly significant compared to ultrasound power. As well as interaction between ultrasound and pH were found to be strongly influenced the extraction yield of pectin. The optimal parameters for extraction were irradiation time of 22.5min, pH of 1.5, and ultrasound power of 155W and liquid-solid ratio 22.5:1 mL/ g. Under these conditions, yield of pectin was 26.87% experimentally, while 26.74 and 26.93% of yield were predicted by response surface and artificial neural network model respectively. The extracted pectin was categorized as high methoxyl pectin, since it has 63.13% degree of esterification, which is above 50% affirmed by Fourier transform infrared spectroscopy detection. Both response surface methodology and artificial neural network model prediction was in good agreement with experimental data; however, the prediction of artificial neural network prediction was better than artificial neural network. Therefore, artificial neural network model is much more accurate in estimating the values of pectin yield and mean square error when compared with the response surface methodology.


Introduction
Industrial wastes and accumulation generated per year are direct consequence associated with universe population growth that brings the environmental pollution issues. Food processing industry wastes and agricultural wastes rich in reusable materials are used for the bioconversion to value added products like additive product, biofuel and active biochemical materials (Salleh et al., 2011). One of, the largest product in worldwide per year are citrus fruits. Almost about fifty percent quantities of fruits are disposed as a waste by citrus-processing industries (Sharma et al., 2017). Air quality, soil purity and sources of water around citrus processing industry, are directly consequences of problems, generated from these uncontrolled waste of this industry to the environmental (Zema et al., 2018). However, these products (citrus peels) are used in several industries as polymethoxylated flavonoids that are applied as phytochemical, pharmaceuticals, food products (Kim et al., 2004) . Conversion of these wastes to valuable product is considered as an alternate and common practices for recycling of byproduct and environmental management systems (Ng et al., 2020).
One of the most source of raw materials largely produced in the worldwide are orange fruits used for extraction of complex compound known as pectin. Pectin is a complex polysaccharide substance contains one third of the mobileular wall of the plants. The larger amount of pectins are located within the middle part of lamella of cell wall and small amount of pectins are between the cell wall of plant (Hamai et. al., 2020). Pectin is used; as gelling, stabilizing and thickening agent jams and jellies confectionery in food as well as in pharmaceutical industry. In industrial level, pectin is divided as: Pectins with a degree of methylation (DM) above 50% (high methoxyl: HM) and pectins with a degree of methylation (DM) below 50% (low methoxyl: LM) (Hosseini, Khodaiyan and Yarmand, 2016b). High methoxyl pectin makes gel between pH of 2-3.5 in the presence of concentrated co-solutes between 55-75%; while low methoxyl pectin forms gel in the absence of co-solutes, with the mixture of bivalent ions between pH of 2-6 (Chan and Choo, 2013).
Therefore both types of pectins have dissimilar physical and chemical properties lead to dissimilar applications (Hosseini, Khodaiyan and Yarmand, 2016c). In addition, properties of pectin primarily based on the plant source, the extraction technique chosen for separation as well as purity of final product.
To increase extraction quality as well as the final yield of pectin, the use of an appropriate method is critical point (Berkani et al., 2020).
Extraction of pectins from different plant sources haven been reported in several literatures.
Anciently, extraction of pectins from citrus peels have done using hot acidified water that results destroying and make dissimilar its structure and instinctive character and usage of chemicals results wastewater which brings the higher environmental pollution (Hosseini et al., 2019a;Shivamathi et al., 2019  The second-order models generated by RSM are often used to determine the critical points and can be written in a general form as (Kleijnen, 2008): Where, Y, xi and xj, β0, βi, βi, βii, k and are

Comparison of ANN & RSM performance:
The coefficient of determination; R 2 , Root Mean Squared Error; RMSE, mean average error; MAE, standard error of prediction; SEP, and absolute average deviation; AAD were determined to check the accuracy and predictive ability of ANN and RSM using Eq. (4−9): Where; r = number of run, yp = predicted values from model, ye = experimental values and m = average experimental values

Extraction of Pectin
By using previous study as reference with modification and it should also be declared that the degrees of parameters were selected depend on previous study [23,24] . In all runs, fifteen gram

FT-IR spectroscopy
The produced pectin contents were analyzed by using prinks Elmer spectrum 65 FT-IR technique with the help of IR correlation. The wavenumber region for the analysis was 4000-400cm-1(in the mid-infrared range) and IR spectrum was reported by % transmittance.

Product (Pectin) characterization
The pectin extracted at the optimum processing conditions (the highest yield) was analyzed by determining the following properties.

Final Equation in Terms of Coded Factors
Pectin Yield=+23

Effect of extraction variables on the pectin yield
The result in  (Hosseini et al., 2019b andDranca, 2019). Another efficient variable that had a direct influence on the extraction was ultrasound power.

ANN-based modeling
The ANN anticipation has been carried out successfully using information shown in table 1.

Comparison of RSM and ANN Performance:
To identify the best model that accurately

Product Characterization
The analyzed characteristics of the extracted pectins were indicated with their values and summarized in table 5.  et al., 2012;Dominiak et al., 2014). However, esterification capacity shows only the ratio between methanol-esterified carboxyl groups and free carboxyl groups, whereas the methoxyl rate represents to the amount of methoxyl groups in a sample (Fakayode and Abobi, 2018

Conclusion
The ultrasound-assisted extraction of pectin was optimized by the combination of both response surface methodology (RSM) and artificial neural network multi-layer back propagation (ANNMBP).
The objectives of study were extraction of pectin from orange peel using ultrasound assisted extraction and response surface method and artificial neural network technique. The accuracy of the two models was studied to compare the performances of the two models to making decision for achievement of optimum process parameters during extraction of the pectin.
The following findings are absorbed from the effects of extraction parameters and technique used. The ultrasound assisted extraction and pH of citric acid solution applied for the extraction of pectin were found to be strongly influenced the yield. However, pH solution was highly significant compared to ultrasound power. As well as interaction between ultrasound and pH solution were found to be strongly influenced the extraction yield of pectin. The optimal conditions for extraction were irradiation time of 22.5min, pH of 1.5, and ultrasound power of 155W and liquid-solid ratio 22

Ethics approval and consent to participate
Not applicable" in this section.

Consent for publication
The manuscript does not contain data from any individual person, therefore "Not applicable" in this section.

Availability of data and materials
The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Authors' contributions
The author completed the research with the help of Chemical engineering and chemistry laboratory assistances for data analysis.