Can The Electronic Nose Detect Stale Food?

Did you think that the milk in your fridge smells a little off but somehow you don't want to dump it down the drain just yet? A few scientists at the University of California, Berkeley may have just invented the solution: an electronic nose.

According to the Centers for Disease Control and Prevention (CDC), an estimated 48 million Americans get sick with a foodborne illness each year. For most people, it's a passing (yet still awful) event that usually subsides after a day or two. However, the CDC notes that an estimated 3,000 Americans die from it each year, making it a problem well worth solving. Hence, this high-tech nose.

In June, a team from UC Berkeley showcased their new device in Science Advances, explaining that the technology can detect the scents associated with spoiled food far more accurately than we can and even detect common food allergens like peanuts. As Carla Bassil, a Ph.D. student in electrical engineering and computer sciences at Berkeley and the study's lead author, shared with UC Berkeley News, the technology could one day be added to our kitchen appliances, making detection a breeze.

"I think 'smart' fridges — which come with sensors that you can control on your phone — would be a great application for this kind of technology," Bassil, who worked under senior author Ali Javey, the Lam Research Distinguished Chair in Semiconductor Processing at Berkeley, said. "How great would it be if your fridge could tell you, 'Hey, your broccoli's going to go bad soon, so you should probably eat that'? Or, 'Your chicken is on its last day'?"

The nose uses its 16 gas sensors, each of which is programmed to detect different combinations of compounds associated with spoiled food or allergens. The nose then uses machine learning that Bassil trained to recognize the scents associated with seven foods: strawberry, blueberry, banana, walnut, hazelnut, cashew, and peanut. She also trained it on the scents of raw chicken, milk, and eggs, both fresh and after being left out at room temperature for 24 and 48 hours.

"You can think of it like a set of digital taste buds, where each sensor on this chip responds uniquely to the various gas molecules presented to it," Bassil said. "Each of these 16 sensors has a different sensing film on it, and it works by converting chemical reactions between the sensor surface and the gas molecule into electrical signals."

According to Bassil, the nose is sensitive enough to detect 0.05 grams of "isolated walnut," which UC Berkeley News noted is equivalent to one hundredth of an average shelled walnut. She did, however, explicitly state that the nose still has limitations, as she has not tested whether it can detect those same scents when other gases are present (i.e., when it's in a salad or pre-made meal, or in the fridge with other foods). Still, it's a start.

"The idea is that we can use the relative selectivity of the gas sensors, paired with the pattern-recognition abilities of machine learning, to sort out which gas fingerprint is associated with each food," Bassil said. "The result is a sensor chip that is far more sensitive and far more objective than any human nose can be."