Scientists Develop AI-Powered ‘Electronic Tongue’ for Food Safety and Freshness

Last Updated on October 20, 2024 by SPN Editor

Scientists have made a breakthrough in food safety technology by developing an AI-powered “electronic tongue” capable of distinguishing between different coffee blends and detecting when food or drink may be nearing spoilage. This innovative device harnesses artificial intelligence to identify issues related to food safety and freshness, providing valuable insights into AI decision-making, as highlighted in the journal Nature on October 9th.

This electronic tongue is created using an ion-sensitive field-effect transistor, a device designed to detect chemical ions. The sensor collects data about the ions present in a liquid and converts this information into an electrical signal that a computer can interpret. “We’re trying to make an artificial tongue, but the process of how we experience different foods involves more than just the tongue,” explained Saptarshi Das, an engineer at Penn State University and co-author of the study. “We have the tongue itself, consisting of taste receptors that interact with food species and send their information to the gustatory cortex—a biological neural network.”

When tested on real-world beverages, the electronic tongue demonstrated impressive capabilities. It effectively distinguished between similar soft drinks and coffee blends, detected whether milk had been diluted, identified spoiled fruit juice, and even sensed harmful substances such as per- and poly-fluoroalkyl substances (PFAS) in water.

The researchers used Shapley Additive Explanations, a method that helped them understand which parameters the neural network considered most important in making its conclusions. “We found that the network looked at more subtle characteristics in the data—things we, as humans, struggle to define properly,” Das noted. “And because the neural network considers the sensor characteristics holistically, it mitigates variations that might occur day-to-day.”

This adaptability could make the electronic tongue more robust in other applications. By accounting for variations that typically make ion-sensitive field-effect transistors unreliable, the neural network enhances the device’s overall reliability. “We figured out that we can live with imperfection,” Das said. “And that’s what nature is—it’s full of imperfections, but it can still make robust decisions, just like our electronic tongue.”

This groundbreaking technology not only advances AI and food safety but also showcases the potential for Artificial Intelligence to revolutionize how we ensure the quality and safety of consumables. As AI continues to evolve, its applications could extend far beyond food safety, promising a future where technology seamlessly integrates with our everyday lives to enhance our well-being.