Smart Portable Microscope for Live Microbial Monitoring Systems

Microorganisms, such as bacteria, are spread in various environments but also pose challenges, including food safety risks and antibiotic resistance. There is a growing demand for rapid and accurate methods to identify and counting the growth of bacteria. With conventional microscope, counting and identification is ineffective in terms of size and accuracy. This study aims to address these issues by developing a portable smart microscope with AI-driven automation to minimize human intervention and error, specifically for E. coli detection. The system incorporates a Raspberry Pi 4 Model B, Pi HQ camera with a 180 ×lens, LEDs, and a power bank, utilizing YOLOv8n for detection. Experimental results show that while the AI model alone had an RMSE of 1.97, the inclusion of the camera and lens in the entire system improved performance, achieving a lower RMSE of 1.47. The results suggest that it is possible to develop a system incorporating an AI model to detect microorganism growth effectively.