91.2% Accurate, 88% Safer: RL-Powered Decision Systems for Microbial Risk Mitigation in Food Logistics

Abstract

The current paper concentrates on the data of food safety sensors on four key environmental parameters, including the temperature, humidity, microbial load, and transport time. The parameters were observed with histograms of 1000 samples, thus providing the information about the refrigeration controls, risks of microbial contamination and hazards in transit. The results potentially will be used to design reinforcement learning (RL) tools to plan dynamic inspection and routing to enhance food safety management.