|
|||||
|
|
Comparison of Response Surface Methodology and Artificial Neural Network for Modeling Xylose‐to‐Xylitol Bioconversion |
|
| Authors: | Fábio Coelho Sampaio Janaína Teles de Faria Gabriel Dumond de Lima Silva Ricardo Melo Gonçalves Cristiano Grijó Pitangui Alessandro Alberto Casazza Saleh Al Arni Attilio Converti |
| Affiliation: | 1. Department of Pharmacy, Federal University of Vales do Jequitinhonha e Mucuri, Campus JK, Rod. MGT 367, Km 583, n. 5000 – Alto da Jacuba, 39100‐000 Diamantina, Minas Gerais, Brazil.;2. Institute of Agricultural Sciences, Federal University of Minas Gerais, Av. Universitária, n. 1000 – Bairro Universitário, 39400‐401 Montes Claros, Minas Gerais, Brazil.;3. Department of Technology and Civil Engineering, Computation, Humanities, Federal University of S?o Jo?o Del‐Rei, Campus Alto Paraopeba, Rod.: MG 443, Km 7, 36420‐000, Ouro Branco, Minas Gerais, Brazil.;4. Department of Civil, Chemical, and Environmental Engineering, University of Genoa, via Opera Pia 15, 16145 Genoa, Italy.;5. Department of Chemical Engineering, Kind Saudi University, P.O. Box 800, Riyadh 11421, Saudi Arabia. |
| Abstract: | Previous experimental data of xylose‐to‐xylitol bioconversion by Debaryomyces hansenii carried out according to a 33 full factorial design were used to model this process by two different artificial neural network (ANN) training methods. Models obtained for four responses were compared with those of response surface methodology (RSM). ANN models were shown to be superior to RSM in the predictive capacity, whereas the latter showed better performance in the generalization capability step. RSM with optimization using a genetic algorithm was revealed as a whole to be the best modeling option, which suggests that the comparative performances of RSM and ANN may be a highly problem‐specific issue. |
| Keywords: | Artificial neural networks Debaryomyces hansenii Response surface methodology Xylitol Yeast |