General Information
    • ISSN: 2010-0221
    • Frequency: Bimonthly
    • DOI: 10.18178/IJCEA
    • Editor-in-Chief: Dr. Eldin W. C. Lim
    • Executive Editor: Mr. Ron C. Wu
    • Abstracting/ Indexing: Chemical Abstracts Services (CAS), Ulrich's Periodicals Directory, CABI, DOAJ, Electronic Journals Library, Google Scholar, Engineering & Technology Digital Library, ProQuest, and Crossref
    • E-mail: ijcea@ejournal.net
  • Oct 16, 2017 News! The papers published in Vol.8, No.4-5 have all received dois from Crossref.
  • Oct 16, 2017 News! Vol.8, No.5 has been published with online version. 6 peer reviewed papers are published in this issue.   [Click]
Editor-in-chief
Dr. Eldin W. C. Lim
Dept. of Chemical and Biomolecular Engineering,
National University of Singapore, Singapore
IJCEA 2011 Vol.2(2): 98-100 ISSN: 2010-0221
DOI: 10.7763/IJCEA.2011.V2.83

Modeling and Optimization of L-asparaginase Productionby Enterobacter Aerogenes Using Artificial Neural Network Linked Genetic Algorithm

G.Baskar, V.Rajasekar, and S.Renganathan

Abstract—In the present work the artificial neural network linked genetic algorithm was applied for the optimization of fermentation media components like carbon and nitrogen sources for L-asparaginase production by Enterobacter aerogenes MTCC 2823 in submerged fermentation. Artificial neural network (ANN) based back propagation algorithm was used to train and test the neural network using the experimental activity obtained by central composite design. Higher value of coefficient of determination (R2=0.984) of artificial neural network justified an excellent correlation between the media components and L-asparaginase activity, the artificial neural network model fitted well with high statistical reliability and significance than RSM model (R2=0.871) developed by central composite design. The predicted optimum concentration of the media components using artificial neural network linked genetic algorithm was sodium citrate 2.09%, DAHP 0.25% and L-asparagine 0.92% with the maximum predicted L-asparaginase activity of 18.59 IU/mL which was close to the experimental L-asparaginase activity of 18.72 IU/mL at simulated optimum conditions.

Index Terms—Fermentation; Optimization; Polynomialmodel; Artificial Neural Network; Response SurfaceMethodology.

G.Baskar is with the Department of Biotechnology, St. Joseph’s Collegeof Engineeirng, Chennai-600119, India. (corresponding author to providephone: +91 94436 78571;email: basg2004@gmail.com)
V. Rajasekar is with the Department of Chemical Engineering, ManipalInstitute of Technology, Manipal-576 104, India. (corresponding author toprovide +91 9916824207S;email: rajashekardv@gmail.com)
.Renganathan is with the Department of Chemical Engineering,A.C.Technology, AnUniversity Chennai, Chennai-600 025, India.( corresponding author to provide +91 9941613532;email:rengsah@rediffmail..com,)

[PDF]

Cite: G. Baskar, V. Rajasekar, and S. Renganathan, "Modeling and Optimization of L-asparaginase Productionby Enterobacter Aerogenes Using Artificial NeuralNetwork Linked Genetic Algorithm," International Journal of Chemical Engineering and Applications vol. 2, no. 2, pp. 98-100, 2011.

Copyright © 2008-2015. International Journal of Chemical Engineering and Applications. All rights reserved
E-mail: ijcea@ejournal.net