Predicting Salmonella in Rolled Omelette Filling in Real Time

Development of Real-Time Safety Management Technology for Foodborne Pathogens in Ingredients
Predicting Pathogen Growth Using Dynamic Models and IoT

[Asia Economy Reporter Junho Hwang] Domestic researchers have developed a technology that can detect contamination by food poisoning bacteria in real time. This technology analyzes contamination levels and temperature information in real time from the shipment of ingredients to the completion of distribution to predict the growth of food poisoning bacteria. It is expected to be a technology that contributes to minimizing damage from food poisoning, which frequently occurs in summer.

Real-time Prediction of Food Poisoning Bacteria Occurring During Distribution Process

The Korea Food Research Institute announced on the 16th that it has developed a dynamic prediction model that can manage the safety of ingredients in real time by linking with IoT that collects distribution temperature information. The results of this research were recently published in the international journal Food Control.

This prediction model is a system that predicts the quantitative changes of food poisoning bacteria in real time according to various temperature histories that are inevitably involved in the complex food supply chain such as production-processing-distribution-consumption of ingredients.

The institute developed this prediction model assuming contamination by six types of Salmonella and three types of Staphylococcus aureus in egg yolks among various ingredients. Through this, contamination levels were verified in the temperature ranges of 10~25℃ and 15~30℃, and the growth of the two bacteria was predicted with high accuracy, with a root mean square error (RMSE) of 0.095-0.31 on average. RMSE closer to 0 means higher accuracy.

Accurate Prediction of Salmonella in Rolled Omelet

In particular, the prediction model for egg yolk accurately predicted the growth of Salmonella in rolled omelet with high accuracy (0.04~0.48). It also detected the growth (0.05-0.23) of Staphylococcus aureus with various toxin gene profiles. The institute explained that this result proves that it can be applied not only to standard strains but also to food-isolated strains with various characteristics.

The Korea Food Research Institute stated, "We plan to enhance the usability of food safety management in the food supply chain by installing the developed prediction model in the institute’s own safety management system, and to promote its use as a food safety management tool in production and distribution-related companies by additionally developing various safety quality models in the future."

This content was produced with the assistance of AI translation services.