IBM announced over the holiday weekend that it has developed Hypertaste, an AI-assisted “e-tongue,” which can be used to identify liquids. This, according to IBM, can be helpful for situations where you want to test a substance… without actually putting in your mouth. Examples might be testing water quality at lakes or rivers, or identifying counterfeit wines.
Big Blue said that up until now, the issue with such testing was that portable sensors were too limited in what they could detect, and more powerful sensors were too big to be portable. Read the full blog post for a detailed explanation, but in a nutshell, Hypertaste works using a handheld sensor, a mobile phone app and the cloud. Put the Hypertaste device in a liquid and its electrochemical sensors (covered in polymer coatings) measure voltage in response to different combinations of molecules.
These recordings are sent to a mobile app, which shoots them up to the cloud where they are analyzed. Machine learning algorithms trained to know what that particular liquid should “look” like compare the sample, with results coming back in less than a minute. Hypertaste then can be used to test any liquid, as the algorithms just need to be trained on what to look for.
One of the applications for this technology is authenticating ingredients in food. From the IBM blog post:
…think of the supply chain safety from producer to consumer for packaged food and drinks. At present, once food and drinks are packaged, there is little ability to verify that the package actually contains what is on the label, apart from sending the product to a lab for testing. So, suppliers acting in bad faith may insert lower-quality products into the supply chain with little risk of getting caught, or counterfeiters may even fake a real product by adding the few analytes which are most likely to be tested for in a lab. Fooling a combinatorial sensing system such as Hypertaste is much harder as there is no single substance on which the identification relies, and it is more difficult for wrong-doers to access the sensor training parameters which provide the “key” to interpreting the chemical fingerprints.
E-tasting is becoming quite the cottage industry lately. The Chinese government has been using AI-powered robots to see, smell and taste food to ensure quality and authenticity. And in May, researchers at Washington State University developed an e-tongue for durable spiciness testing.
Right now, the applications for Hypertaste appear to be B2B based, but perhaps it could find its way into consumer products for home testing of water and other liquids.