Scientists Create a Beer-Tasting Robot

(LatinPost) - The age of robots with a taste for beer has arrived, thanks to researchers in Spain.

Scientists at the Autonomous University of Barcelona say they've created an electronic device capable of distinguishing between beer varieties and their alcohol content about 82 percent of the time.

The new research, reported in the journal Food Chemistry, examined several brands of beer with a so-called electronic tongue, based on the human sense of taste.

Manel del Valle, the main author of the study, said in a media release the concept of the electronic tongue "consists in using a generic array of sensors, in other words with generic response to the various chemical compounds involved, which generate a varied spectrum of information with advanced tools for processing, pattern recognition and even artificial neural networks."

The the array of sensors in question was formed with 21 ion-selective electrodes, each designed to detect and respond to various types of charged particles found in consumable substances.

The research team recorded the dynamic responses generated by the array as it was introduced to different types of beers with varying alcohol content.

"Using more powerful tools - supervised learning - and linear discriminant analysis did enable us to distinguish between the main categories of beer we studied: Schwarzbier, lager, double malt, Pilsen, Alsatian and low-alcohol," Del Valle said, "and with a success rate of 81.9%."

The researchers explained the electronic tongue only provided readings for specific types of beer it was programmed to recognize --- and didn't respond to those that weren't programmed into its system, an important step in validating the generated data, as the tongue did not offer readings for anomalous data . that varieties of beers that the tongue is not trained to recognize, such as beer/soft drink mixes or foreign makes, were not identified (discrepant samples), which, according to the experts, validates the system as it does not recognize brands for which it was not trained.