Electronic tongue could replace human tasters, researchers say

Spanish researchers have developed what they call an “electronic tongue” - an analysis system based on the human sense of taste that can distinguish between several brands of beer.

The electronic tongue, developed by scientists at the Universitat Autonoma de Barcelona, uses a generic array of sensors that respond to the various chemical compounds involved, generating a varied spectrum of information with advanced tools for processing, pattern recognition and even artificial neural networks.

The array of sensors was formed of 21 electrodes which were each responsive to a different ion, including ammonium, sodium, nitrate and chloride.

The researchers recorded the sensors’ responses to the different types of beers. Initially, however, they were not able to use the information to classify the beers.

“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, Alsation and low-alcohol,” said Manel del Valle, the main author of the study.

The electronic tongue was eventually able to distinguish between different beers with a success rate of 81.9%.

Varieties of beers that the tongue was not trained to recognise, such as beer/soft drink mixes or other beer styles, were not identified. According to some experts, this validates the system as it does not recognise beers for which it was not trained.

The machine is also capable of ordering beers according to their alcohol content.

“This application could be considered a sensor by software, as the ethanol present does not respond directly to the sensors used, which only respond to the ions present in the solution,” del Valle said.

The scientists say their research could be used to one day give robots a sense of taste, even eventually supplanting panels of tasters in the food industry, improving the quality and reliability of products for consumption.

The research was published in the journal Food Chemistry.