Evaluation of RSM and ANFIS modeling performance in fermentable sugar production from Enzymatic Hydrolysis Of Colocynthis vulgaris shrad seeds shell

Abstract

This study is on the modeling of fermentable sugar production process; obtained by enzymatic hydrolysis of Colocynthis vulgaris Shrad seeds shell (CVSSS) using the response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS). The sugar was hydrolysed from the CVSSS using Aspergillus Niger isolated from soil. The RSM and ANFIS models were evaluated by considering the hydrolysing temperature, time and pH as input variables, whereas the percentage yield of sugar was the response factor or the output factor. Four statistical error tasks were additionally, applied to relate the adequacy of the two models. The result showed that, fermentable sugar can be obtained from the CVSSS with A. niger as a biocatalyst. The ANFIS and RSM tools presented a nigh perfection, in predicting the yield of fermentable sugar from CVSSS with R squared value of 0.9986 and 0.9975, correspondingly. Additional statistical guides gave acceptance to ANFIS as a better predictive tool, in the enzymatic hydrolysis of CVSSS. Optimization result with ANFIS tool, presented an optimum hydrolysis efficiency of 60.65%.