Application of the artificial neural network and response surface methodology models for predicting the enzymatic synthesis of betulinic acid ester: A comparative study

1Citations
Citations of this article
7Readers
Mendeley users who have this article in their library.

Abstract

In this paper, the estimation capabilities of the response surface methodology and artificial neural network, in an enzymatic reaction catalyzed by Candida antarctica lipase (Novozym 435), were investigated. The experiments were conducted based on a five-level, fourvariable central composite rotatable design. The yield of ester in the enzymatic reaction was considered as a function of four independent variables, namely reaction time, reaction temperature, enzyme amount and substrate molar ratio. After predicting the model using response surface methodology and artificial neural network, two methodologies were then compared for their modeling. The results showed that the artificial neural network model is much more accurate in prediction as compared to the response surface methodology.

Cite

CITATION STYLE

APA

Moghaddam, M. G., Ahmad, F. B. H., Basri, M., & Rahman, M. B. A. (2013). Application of the artificial neural network and response surface methodology models for predicting the enzymatic synthesis of betulinic acid ester: A comparative study. Asian Journal of Chemistry, 25(1), 301–305. https://doi.org/10.14233/ajchem.2013.13010

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free