Environmental sustenance via melon seed peel conversion to fermentable sugars using soft computing models

Abstract

There is a shift in focus on agro-wastes constituting menace through their disposal in the environment by converting them to value-added products within the sustainability framework. This study aimed at predicting melon seed peel (MSP) hydrolysis parameters using soft computing models such as Artificial Neural Network (ANN) and Adaptive neuro-fuzzy inference system (ANFIS). The capability of the models was evaluated using the correlation coefficient (R 2 ), mean square error (MSE), mean absolute deviation (MAD) and average absolute relative error (AARE). The experiments were conducted at an acid concentration (2.5–3.5 M), time (1–3 h), and temperature (80–100 °C) with output as sugar yield. The characterization results from the proximate analysis, FTIR, SEM, EDX, XRF and XRD indicated that MSP contains a significant amount of cellulose for fermentable sugar production. The sugar yield estimation performance indicators are: ANN (R 2 = 0.999, MSE = 1.2698E-12, MAD = 1.2%, AARE = 0.00231) and ANFIS (R 2 = 0.9782, MSE = 0.0334, MAD = 2.7%, AARE = 0.0054), these suggested a good agreement between the experimental and predicted values. The results showed that the ANN and ANFIS models effectively predict accuracy. It was concluded that soft computing models could be considered a viable chemical process modelling and simulation techniques.