Nonlinear process modeling of fructosyltransferase (FTase) using bootstrap re-sampling neural network model

被引:2
作者
Ahmad, Zainal [1 ]
Don, Mashitah Mat [1 ]
Mortan, Siti Hatijah [1 ]
Noor, Rabiatul Adawiah Mat [1 ]
机构
[1] Univ Sci Malaysia, Sch Chem Engn, Nibong Tebal 14300, Penang, Malaysia
关键词
Fermentation; Nonlinear process; Neural networks; Bootstrap re-sampling; Fructosyltransferase; AUREOBASIDIUM-PULLULANS; FRUCTO-OLIGOSACCHARIDES; FRUCTOOLIGOSACCHARIDES; REGULARIZATION; TRANSFERASE; PREDICTION; SUCROSE; ENZYME;
D O I
10.1007/s00449-009-0381-2
中图分类号
Q81 [生物工程学(生物技术)]; Q93 [微生物学];
学科分类号
071005 ; 0836 ; 090102 ; 100705 ;
摘要
Recently, the increased demand of fructooligosaccharides (FOS) as a functional food has alarmed researchers to screen and identify new strains capable of producing fructosyltransferase (FTase). FTase is the enzyme that converts the substrate (sucrose) to glucose and fructose. The characterization of complex sugar such as table sugar, brown sugar, molasses, etc. will be carried out and the sugar that contained the highest sucrose concentration will be selected as a substrate. Eight species of macro-fungi will be screened for its ability to produce FTase and only one strain with the highest FTase activity will be selected for further studies. In this work, neural networks (NN) have been chosen to model the process based on their excellent 'resume' in coping with nonlinear process. Bootstrap re-sampling method has been utilized in re-sampling the data in this work. This method has successfully modeled the process as shown in the results.
引用
收藏
页码:599 / 606
页数:8
相关论文
共 33 条
  • [1] [Anonymous], 1994, NEURAL NETWORKS
  • [2] [Anonymous], NEURAL NETWORKS NATU
  • [3] Chromatographic separation and kinetic properties of fructosyltransferase from Aureobasidium pullulans
    Antosova, Monika
    Illeova, Viera
    Vandakova, Marcela
    Druzkovska, Alexandra
    Polakovic, Milan
    [J]. JOURNAL OF BIOTECHNOLOGY, 2008, 135 (01) : 58 - 63
  • [4] Bishop CM., 1995, NEURAL NETWORKS PATT
  • [5] Caruana R, 2000, NEURAL INF PROCESS S, V13, P402
  • [6] Bayesian learning for recurrent neural networks
    Crucianu, M
    Boné, R
    de Beauville, JPA
    [J]. NEUROCOMPUTING, 2001, 36 (01) : 235 - 242
  • [7] Bootstrap re-sampling for unbalanced data in supervised learning
    Dupret, G
    Koda, M
    [J]. EUROPEAN JOURNAL OF OPERATIONAL RESEARCH, 2001, 134 (01) : 141 - 156
  • [8] Process identification with multiple neural network models
    Eikens, B
    Karim, MN
    [J]. INTERNATIONAL JOURNAL OF CONTROL, 1999, 72 (7-8) : 576 - 590
  • [9] Identification of three inducible and extracellular enzymatic activities working on sucrose in Bacillus subtilis NCIMB 11871 and 11872 supernatant
    Le Gorrec, K
    Connes, C
    Guibert, A
    Uribelarrea, JL
    Combes, D
    [J]. ENZYME AND MICROBIAL TECHNOLOGY, 2002, 31 (1-2) : 44 - 52
  • [10] On the underfitting and overfitting sets of models chosen by order selection criteria
    Guyon, X
    Yao, JF
    [J]. JOURNAL OF MULTIVARIATE ANALYSIS, 1999, 70 (02) : 221 - 249