Optimization Using Decision Trees Method in Multivariable Food Engineering Experiments and Its Sample of Applicability on Experiment Related with the Nisin Production of Lactococcus lactis N8

Year 2017, Volume: 1 Issue: 1, 50 - 57, 30.08.2017

Selahaddin Batuhan Akben

Abstract

In this study, the ranges of independent
variables resulting the optimum result of experiment should be selected was
determined using decision trees method. Thus, the applicability of decision
trees method has been proposed to food engineering experiments aiming the
optimization. The sample application of the decision tree method proposed in
the study was performed in the experiment aiming optimum nisin production of Lactococcus lactis N8. According to the
findings obtained from the sample application it was observed that the decision
trees method determines both optimum variable values and their tolerance
ranges. Furthermore, the method proposed was not only determined the optimal ranges
of variable values also it was determined the variable ranges for all possible
experimental results. Accordingly, at the end of the study, advantages of the
proposed method were explained by comparing with similar methods and how the
experimental design should be to make the method more effective was proposed.

Keywords

Decision Trees, Modelling, Nisin Production, Optimization, Prediction

References

• Akben S. B., Alkan A. 2016. Analysis of Yatch Hydrodynamics Scale-Effect and Optimal Scale Range Determination by Using Decision Tree Algorithm, International Conference on Natural Science and Engineering (ICNASE' 16), Kilis/Turkey, 412- 418.
• Banga J. R., Balsa-Canto E., Moles C. G., Alonso A. A. 2003. Improving food processing using modern optimization methods, Trends Food Sci & Tech, 14, 131-144.
• Baş D., Boyacı İ. H. 2007. Modeling and optimization I: Usability of response surface methodology, J Food Eng., 78, 836-845.
• Cazals F., Pouget M. 2005. Estimating differential quantities using polynomial fitting of osculating jets, Computer Aided Geometric Design, 22(2), 121-146.
• Kalkan S., Ünal E., Erginkaya Z. 2014 Nisin ilave edilmiş metil selüloz filmlerin antimikrobiyel etkilerinin belirlenmesi, Gıda ve Yem Bilimi-Teknolojisi Dergisi/Journal of Food and Feed Science-Technology 14, 1-7, 2014.
• Kalkan S. 2016. Probiyotik Laktik Asit Bakterilerinin Staphylococcus aureus'a Karşı Antimikrobiyel Etkilerinin Farklı Matematiksel Modeller ile Analizi, Sinop Üniversitesi Fen Bilimleri Dergisi, 1(2), 150-159.
• Kördikanlıoğlu“B. 2014. Lactococcus lactis’te solunumun hemin ile teşvik edildiği yarı- kesikli fermentasyon sisteminde nisin üretiminin optimizasyonu, Msc. thesis, Pamukkale University, Institute of Science, Denizli, Turkey.
• Kördikanlıoğlu B. Şimşek Ö, Saris P. E. J. 2015. Nisin production of Lactococcus lactis N8 with hemin-stimulated cell respiration in fed-batch fermentation system, Biotechnology Progress, 31(3), 678-685.
• Mandenius C. F., Brundin A. 2008. Bioprocess optimization using design of experiments methodology, Biotechnology progress, 24(6), 1191-1203.
• Myers R. H., Montgomery D. C. 1995. Response Surface Methodology, Process and Product Optimization Using Designed Experiments, 2nd ed. John Wiley and Sons, New York.
• Koç B., Ertekin F. K. 2010. Yanıt Yüzey Yöntemi ve Gıda İşleme Uygulamaları, GIDA/The Journal of Food, 35(1), 1-8.
• Rokach L, Maimon O. 2014. Data mining with decision trees: theory and applications, World scientific.
• Saguy I., Mishkin M. A., Karel M. 1984. Optimization methods and available software, part1, CRC Critical RevFood Sci and Nutr, 20(4), 275-299.
• Ville B. D. 2006. Decision tree for business intelligence and data mining, SAS Publishing.