A Kennesaw State University researcher is developing technology aimed at improving food safety by detecting contamination through smell rather than sight. Taeyeong Choi, assistant professor of information technology in the College of Computing and Software Engineering, is working on an electronic nose (e-nose) that uses artificial intelligence to identify harmful bacteria such as salmonella and E. coli.
The e-nose analyzes volatile organic compounds (VOCs), which are chemicals released from spoiled or contaminated food. By training AI models on thousands of VOC samples, the device aims to not only detect contaminants but also distinguish between different types of foods.
“Food safety is a really important issue for the public, and I realized that millions of people are affected by foodborne illness each year,” Choi said.
According to the Centers for Disease Control and Prevention, foodborne illnesses lead to about 128,000 hospitalizations and 3,000 deaths annually in the United States. This means roughly one in six Americans experience food poisoning each year.
Traditional methods for detecting contamination are accurate but can be time-consuming, resource-intensive, and often require destroying part of the sample being tested. Current image-based approaches using artificial intelligence offer faster results but are limited to what can be seen visually.
Choi’s project received funding from the National Science Foundation. He explained his motivation: “Currently, we are mainly interested in pathogens like salmonella and E. coli, since they’re the most common and impact a lot of people,” Choi said. “Over time, and through continued discussions with my colleagues who have expertise in food safety, we will continue to increase the number of pathogens we are able to detect.”
In addition to its use in food safety, Choi says the e-nose could have applications in healthcare—such as disease detection from breath samples—as well as robotics and security.
