Evaluation of Microbiological Properties in Kefir Production with Fuzzy Logic-Based Decision Support System

Abstract

Parallel to rising consumer interest in functional foods, attention to probiotic and natural-content products such as kefir has significantly expanded in recent years. As in all instruments related to food production, the aim in the kefir production process is to obtain a high-quality product, and to ensure the sustainability of production in a healthy manner. In this study, the aim is to develop a fuzzy logic-based decision support system for the quality evaluation of kefir samples categorized into somatic cell and fat (low/high) measurement groups. For this purpose, the system inputs were determined as incubation temperature, incubation time, storage time, total bacterial count, and pH. In the model output, kefir quality indices were calculated for each observation, and quality classes were obtained. In the comparative quality evaluations between the system and expert decisions, the fuzzy logic-based decision support system was found to have achieved a success rate of 93.75%. In addition, the Chi-square statistic and Kappa statistic regarding the decisions made by both the expert and the system were found to be statistically significant (P<0.05). The results indicate that fuzzy logic can be effectively used as a decision support tool in the quality evaluation of kefir samples.