Scientific journal

61 2022

Journal of Food and Nutrition Research
Summary No. 4 / 2022

Tarlak, F. – Yücel, Ö.
Application of a machine learning-based regression method to describe Listeria monocytogenes behaviour in milk
Journal of Food and Nutrition Research, 61, 2022, No. 4, s. 380-388

Fatih Tarlak, Department of Nutrition and Dietetics, Faculty of Health Sciences, Istanbul Gedik University, Cumhuriyet Street 1, 34876 Kartal, Istanbul, Turkey. E-mail: ftarlak@gtu.edu.tr

Received 17 August 2022; 1st revised 27 September 2022; 2nd revised 22 October 2022; accepted 25 October 2022; published online 23 November 2022.

Summary: The main aim of the present study was to develop a prediction tool to describe Listeria monocytogenes behaviour in milk by employing traditionally used models (the re-parametrized Gompertz, Baranyi and Huang models) and an alternatively proposed machine learning-based regression model. The fitting capability of both groups of models was evaluated and compared considering their statistical indices (coefficient of determination R2, root mean square error RMSE). The machine learning-based regression model provided better predictions (with R2 of 0.958 and RMSE of 0.407) than the traditionally used models. The prediction capability of both methodologies was tested considering externally collected data from the literature. The machine learning-based regression model in the validation process gave satisfactory statistical indices (bias factor of 1.016 and accuracy factor of 1.056), which is better prediction power than the traditionally used models. These results indicated that the machine learning-based regression method can be reliably employed as an alternative way of describing the growth behaviour of L. monocytogenes in milk. Therefore, the software developed in this work has a significant potential to be used as an alternative simulation method to traditionally used approach in the field of predictive microbiology.

Keywords: data mining; prediction tool; gaussian process regression; predictive microbiology

Download:
  (pdf, 796.9 Kb, 69x)