AN ARTIFICIAL NEURAL NETWORK AS A TOOL FOR KOMBUCHA FERMENTATION IMPROVEMENT

Scientific paper

Authors

  • Dragoljub Cvetković University of Novi Sad, Faculty of Technology Novi Sad, Bulevar cara Lazara, 1, 21000 Novi Sad, Serbia
  • Olja Šovljanski University of Novi Sad, Faculty of Technology Novi Sad, Bulevar cara Lazara, 1, 21000 Novi Sad, Serbia https://orcid.org/0000-0002-9118-4209
  • Aleksandra Ranitović University of Novi Sad, Faculty of Technology Novi Sad, Bulevar cara Lazara, 1, 21000 Novi Sad, Serbia https://orcid.org/0000-0002-9666-7373
  • Ana Tomić University of Novi Sad, Faculty of Technology Novi Sad, Bulevar cara Lazara, 1, 21000 Novi Sad, Serbia https://orcid.org/0000-0002-6338-342X
  • Siniša Markov University of Novi Sad, Faculty of Technology Novi Sad, Bulevar cara Lazara, 1, 21000 Novi Sad, Serbia
  • Dragiša Savić University of Niš, Faculty of Technology, Bulevar Oslobođenja 124, 16000 Leskovac, Serbia https://orcid.org/0000-0002-2182-9948
  • Bojana Danilović University of Niš, Faculty of Technology, Bulevar Oslobođenja 124, 16000 Leskovac, Serbia https://orcid.org/0000-0002-4444-2746
  • Lato Pezo Institute for General and Physical Chemistry, Studenski trg 12/V, Belgrade, Serbia https://orcid.org/0000-0002-0704-3084

DOI:

https://doi.org/10.2298/CICEQ211013002C%20

Keywords:

experimental design, fermentation improvement, kombucha production, mathematical modelling

Abstract

Kombucha as a tea-based fermented beverage has become progressively widespread, mainly in the functional food market, because of health-improving benefits. As part of a daily diet for adults and children, kombucha was a valuable non-alcoholic drink containing beneficial mixtures of organic acids, minerals, vitamins, proteins, polyphenols, etc. The influence of the specific surface area of the vessel, the inoculum size, and the initial tea concentration as operating factors and fermentation time as output variable on the efficiency of kombucha fermentation was examined. The focus of this study is optimization and standardization of kombucha fermentation conditions using Box-Behnken experimental design and applying an artificial neural network (ANN) predictive model for the fermentation process. The Broyden-Fletcher-Goldfarb-Shanno iterative algorithm was used to accelerate the calculation. The obtained ANN models for the pH value and titratable acidity showed good prediction capabilities (the r2 values during the training cycle for output variables were 0.990 and 0.994, respectively). Predictive ANN modeling has been proven effective and reliable in establishing the optimum kombucha fermentation process using the selected operating factors.

References

J. Kim, K. Adhikari, Bevarages 6 (2020) 1—19.

J. Islam, Y. Kabir, Yects and Mechanisms of Antioxidant-Rich Functional Beverages on Disease Prevention, Woodhead Publishing: Duxford, UK (2019) p. 118.

D. Laureys, S. Britton, J. De Clippeleer, J. Am. Soc. Brew. Chem.78 (2020) 165—174.

R. Jayabalan, R.V. Malbaša, M. Sathishkumar, Kombucha Tea: Metabolites. In Fungal Metabolites. Springer International Publishing (2017) p. 965—978.

M. Coton, A. Pawtowski, B. Taminiau, G. Burgaud, F. Deniel F, FEMS Microb. Ecol.93 (2017) 1—16.

J.M. Kapp, W. Sumner, A. Ann. Epidemiol.30 (2019) 66—70.

C.J. Greenwalt, K.H. Steinkraus, R.A. Ledford, J. Food Prot.63 (2000) 976—981.

Al. Teoh, G. Heard, J. Cox, Int. J. Food Microbiol.95 (2004) 119—126.

S.C. Chu, C. Chen, Food Chem.98 (2006) 502—507.

Y. Yamada, P. Yukphan, Int. J. Food Microbiol.125 (2008) 15—24.

Y. Yamada, P. Yukphan, H.T. Lan Vu, Y. Muramatsu, D. Ochaikul, S. Tanasupawat, Y. Nakagawa, J. Gen Appl. Microbiol.58 (2012) 397—404.

C.P. Kuerzman, C.J. Robnett, E. Basehoar-Powers, FEMS Yeast Res.1 (2001) 133—138.

S. Chakravorty, S. Bhattacharya, D. Bhattacharya, S. Sarkar, R. Gachhui, Kombucha: A Promising Functional Beverage Prepared from Tea, Sawston, Cambridge (2019).

Z.W. Yang, B.P. Ji, F. Zhou, B. Li, Y. Luo, L. Yang, T. Li, J. Sci. Food Agric.89 (2009) 150—156.

K. Neffe-Skocinska, B. Sionek, I. Scibisz, D. Kolozyn-Krajewska, Cyta J. Food 15 (2017) 601—607.

A.J. Marsh, O. O’Sullivan, C. Hill, R.P. Ross, P.D. Cotter, Food Microbiol.38 (2014) 171—178.

D. Cvetković, S. Markov, M. Djurić, D. Savić, A. Velićanski, J. Food Eng.85 (2008) 387—392.

F. De Filippis, A.D. Troise, P. Vitaglione, D. Ercolini, Food Microbiol.73 (2018) 11—16.

A. Vidaković, O. Šovljanski, A. Ranitović, D. Cvetković, S. Markov, Acta Period. Technol.48 (2017) 295—305.

O. Šovljanski, A. Tomić, L. Pezo, A. Ranitović, S. Markov, J. Serb. Soc. Chem.85 (2020) 1417—1427.

P. Manivasagan, J. Venkatesan, K. Sivakumar, S. Kim, Microb. Res.169 (2020) 262—278.

S. Markov, R. Malbaša, M. Hauk, D. Cvetković, Acta Period. Technol. 32 (2001) 133—138.

A. Velićanski, D. Cvetković, S. Markov, Rom. Biotechnol. Lett. 18 (2012) 8034—8042.

J.L. Jacobson, Introduction to Wine Laboratory Practices and Procedures. Springer Science, New York (2006).

D.P. Johnson, A. Stanforth, V. Lulla, G. Luber, Appl. Geogr. 35 (2012) 23—31.

T.S. Yun, Y.J. Jeong, T.S. Han, K.S. Youm, Energ. Buildings 61 (2013) 125—132.

J.P.C. Kleijnen, Design and Analysis of Simulation Experiments. Springer Proceedings in Mathematics and Statistics, Italy (2018).

T. Kollo, D. von Rosen, Advanced Multivariate Statistics with Matrices, Springer, Berlin (2005).

L. Pezo, B.Lj. Ćurčić, V.S. Filipović, M.R. Nićetin, G.B. Koprivica, N.M. Mišljenović, Lj.B. Lević, Hem. Ind.67 (2013) 465—475.

C.I. Ochoa-Martínez, A.A. Ayala-Aponte, LWT40 (2007)

—645.

L.A. Berrueta, R.M. Alonso-Salces, K. Héberger, J. Chromatogr. A1158 (2007) 196—214.

M. Doumpos, C. Zopounidis, Eur. J. Oper. Res. 209 (2011) 203—214.

B.J. Taylor, Methods and Procedures for the Verification and Validation of Artificial Neural Networks, Springer Science and Business Media, New York (2006).

Y. Yoon, G. Swales, T.M. Margavio, J. Oper. Res. Soc.44 (1993) 51—60.

O. Šovljanski, L. Pezo, A. Tomić, A. Ranitović, D. Cvetković, S. Markov, J. Basic Microb.61 (2021) 835—848.

G. Sreeramulu, Y. Zhu, W. Knol, J. Agri. Food Chem.48 (2000) 2589—2594.

D. Cvetković, A. Ranitović, D. Savić, N. Joković, A. Vidaković, L. Pezo, S. Markov, Pol. J. Food Nutr. Sci. 69 (2019) 407—415.

B.H. Junker, J. Biosci. Bioeng. 97 (2004) 347—364.

S. Villarreal-Soto, S. Beaufort, J. Bouajila, J.P. Souchard, T. Renard, S. Rollan, P. Taillandier, Process Biochem. 83 (2019) 44—54.

M.J. Santos, Kombucha: Caracterizaçao da microbiota e desenvolvimento de novos produtos alimentares para uso em restauraçao. Universidade Nova de Lisboa, Lisboa (2016).

E. Lončar, K. Kanurić, R. Malbaša, M.S. Đurić, S.D. Milanović,.CICEQ 20 (2014) 345—352.

L. Kallel, V. Desseaux, M. Hamdi, P. Stocker, E.H. Ajandouz, Food Res. Int. 49 (2012) 226—232.

D.C. Montgomery, Design and Analysis of Experiments, John Wiley and Sons, New York (1984).

T. Turanyi, A.S. Tomlin, Analysis of Kinetics Reaction Mechanisms. Springer, Berlin (2004).

Z. Erbay, F. Icier, J. Food Eng. 91 (2009) 533—541.

Downloads

Published

03.03.2022 — Updated on 15.08.2022

Issue

Section

Articles

How to Cite

AN ARTIFICIAL NEURAL NETWORK AS A TOOL FOR KOMBUCHA FERMENTATION IMPROVEMENT: Scientific paper. (2022). Chemical Industry & Chemical Engineering Quarterly, 28(4), 277-286. https://doi.org/10.2298/CICEQ211013002C

Similar Articles

11-20 of 89

You may also start an advanced similarity search for this article.

Most read articles by the same author(s)