A new "electronic nose" developed at University of California, Berkeley, may not look like the real thing, but this device outperforms it in key tasks, including sniffing out food spoilage and identifying allergens with impressive accuracy. 

The device has 16 gas sensors built in, which help turn chemical reactions from the food into electronic signals. 

A UC Berkeley-led study found that the device identified walnuts and cashews 100% of the time, hazelnuts 91.96% of the time and peanuts 80.65% of the time. Researchers stated that the largest confusion from the electronic nose "arose between hazelnut and peanut VOCs, indicating some cross-over between nut odorants or shared dominant compounds that elicit a similar sensor response." This means that the device sometimes got the two nuts confused due to similar chemical smells. 

If this technology could be expanded to more food groups, it could be a major advancement in food allergy detection, as more than 33 million Americans have at least one food allergy. However, the study was conducted with the nuts individually rather than mixed with other foods, so it's unclear how accurate the results would be in real-world conditions. 

In addition to smelling out common food allergens, the researchers also trained the model to detect spoiled food. Overall, the electronic nose had a 92.6% accuracy in detecting allergens and food spoilage in the study.

"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," study lead author Carla Bassil, a doctorate student in electrical engineering and computer sciences at Berkeley, said in a statement. "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 researchers' next goal is to add more sensors to help the device recognize more smells, whether that be additional food spoilage or allergens.