Çok Katmanlı Perceptron Yapay Sinir Ağı Kullanılarak Maya Hücrelerinin Yaşam Döngüsü Parametrelerinin Araştırılması

Authors : Eyyüp GÜLBANDILAR, Serel ÖZMEN AKYOL, Aysel GÜLBANDILAR, Gıyasettin ÖZCAN, Necati KARAKUŞ

Pages : 662-668

Doi:10.35414/akufemubid.535991

View : 25 | Download : 7

Publication Date : 2019-12-31

Article Type : Research Paper

Abstract :Examining the growth parameters of yeast cells in the food industry causes to increase both time and labor costs. Simulation models can be put forward to reduce these costs. In this study aimed that design a simulation model for growth cycle parameters of Saccharomyces cerevisiae by using the Multi-Layer Perceptron Neural Network (MLPNN). While cultivation time is defined as input parameter in this model, the cell count per hour and growth rate is determined as output parameters. In the designed model, two hidden layer back propagation neural networks are preferred. The first hidden layer uses 10 nodes, while the second hidden layer uses 2 nodes. For the training of this model, 144 experimental data are used, whereas 72 of these experimental data were used for testing the trained model. The developed model showed a high correlation on the growth curve and growth rate in the process both training and test (R 2 training =0.9993 and R 2 test =0.9993 for growth curve; R 2 training =0.9381 and R 2 test =0.9404 for growth rate). The results demonstrate that our developed model can be successfully used in culture in experimental work in the food industry.
Keywords : Saccharomyces Cerevisiae, Growth Curve, Growth Rate, neural network