An electronic tongue developed by Spanish researchers has achieved an 82 per cent success rate in distinguishing between various beer brands.
The device used in the experiment consisted of 21 ion-selective electrodes capable of detecting chemical elements including sodium, ammonium, chloride and nitrate.
"The electronic tongue uses a generic array of sensors with generic response to various chemical compounds involved,” said Manel del Valle from the University of Barcelona, the main author of the study published in the journal Food Chemistry. “The device generates a varied spectrum of information with advanced tools for processing, pattern recognition and even artificial neural networks."
The authors recorded the multidimensional response generated by the array of sensors and analysed how the spectrum was influenced by the type of beer considered.
"Using more powerful tools - supervised learning - and linear discriminant analysis enabled us to distinguish between the main categories of beer we studied: Schwarzbier, lager, double malt, Pilsen, Alsatian and low-alcohol, and with a success rate of 81.9 per cent," Del Valle said.
The system only recognised brands for which it was previously ‘trained’, failing to correctly pick out beer-soft drink mixes or foreign makes. The tongue also wasn’t able to detect the amount of alcohol content in given beer samples.
"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," explained Del Valle.
In the future, the researchers believe, electronic tongues could provide robots with a sense of taste, possibly enabling them to become extremely accurate food industry testers.