Detection of bacteria in food and agriculture environments is vital for ensuring the safety, shelf life, and security of food. Current detection technologies, however, require significant human and laboratory resources to process and prepare samples, run analysis, and interpret the results, ultimately limiting the efficiency and scalability of existing on-site pathogen detection systems. To address these challenges, the proposed research aims to develop an artificial intelligence (AI) platform for the detection of viable bacterial pathogens that can deliver results within a single work shift (less than 6 hours) at a food production facility. The specific goals of this research are: (a) Develop an AI-based framework for specific detection of viable bacterial pathogens in mixed microbial cultures containing commensal microbes and (b) Evaluate point-of-use detection of target pathogens in a simulated limited testing resource environment using an automated, low-cost "edge AI" data acquisition and analysis platform for food and environmental samples.
FACT-AI: DATA-EFFICIENT AI PLATFORM FOR LABEL AND LABEL-FREE DETECTION OF FOOD BACTERIAL PATHOGENS
Earles, J. M.
University of California - Davis