IBM Hypertaste is an Artificial Intelligence System To Classify Liquids
By Maria Deutscher
Distinguishing different beverages and food items is usually a trivial task for humans, but the same can’t be said for the machines that experts use when the taste test doesn’t cut it.
IBM developed Hypertaste for scenarios where a detailed chemical analysis is necessary but it’s not possible or economically feasible to send a sample to a lab. One application the company envisions for the system is evaluating the water quality of rivers. Another is finding counterfeit goods, such as low-quality perishable items shipped to a grocery chain by an untrustworthy supplier.
Hypertaste checks chemicals with an array of miniature sensors developed in-house by IBM. Each sensor is comprised of a pair of electrodes coated with special, chemically sensitive polymer coatings. They produce an electrical signal when they come into contact with specific compounds.
Hypertaste doesn’t process this information on its own. Instead, the device sends measurements to a cloud-based analytics environment, where a machine learning model compares the analyzed liquid against a database of known chemicals. The algorithm identifies the closest matches and sends them to a companion app meant to run on researchers’ smartphones.
The entire process takes less than a minute, according to IBM. “Hypertaste proves that a portable device could be capable of rapid fingerprinting of complex liquids – a capability currently lacking in the toolkit of chemical analytics,” Ruch wrote.