RESEARCH TRIANGLE PARK – Scientists at the tech giant that brought Watson Artificial Intelligence into the world to beat humans at chess and Jeopardy! is now advancing AI into the world of taste.
Yes, IBM researchers have created an AI-assisted “e-tongue” they are calling it for use in chemical sensing.
Called Hypertaste, the technology of course also includes an app.
“For the rapid and mobile fingerprinting of beverages and other liquids less fit for ingestion, our team at IBM Research is currently developing Hypertaste, an electronic, AI-assisted tongue that draws inspiration from the way humans taste things,” writes Patrick Ruch on behalf of IBM researchers in Zurich, Switzerland.
“Hypertaste caters to a wide range of industrial and scientific users with a growing need to identify liquids swiftly and reliably without access to high-end laboratories. Consider a government agency interested in an on-the-fly water quality check of a lake or river at a remote location. Or a manufacturer wanting to verify the origin of raw materials. Or a food producer trying to identify counterfeit wines or whiskeys. The quick, in-situ identification and classification of liquids is relevant also in the pharmaceutical and healthcare industries, to name just a few more examples.”
Here’s a video from IBM about the project:
Watson has a growing number of uses within IBM from cancer research to drug development, advertising and marketing.
With the e-tongue, IBM says its technology closes a “gap” between specialized portable sensors and “very powerful” stationary machines.
“Closing this gap is crucial as most liquids of practical use are complex, meaning they comprise a rather large number of chemical compounds, none of which can serve as an identifier alone,” Ruch writes. “In these liquids, it’s not so much the single components that matter but rather the properties that arise from combining them. And yet, routinely sending such liquids to a lab for analysis is costly, time-consuming and often impractical. This is where Hypertaste comes in.”
The AI helps Hypertaste utilize what Ruch calls “combinational sensing.”
On the heels of Red Hat deal, IBM lands AT&T contract worth ‘billions’
“In that respect, it resembles our natural senses of taste and smell where we don’t have a receptor for each molecule occurring in every kind of food or drink. Combinatorial sensing relies on the ability of individual sensors to respond simultaneously to different chemicals,” he explains.
“By building an array of such cross-sensitive sensors one can obtain a holistic signal, or fingerprint, of the liquid in question.”
The sensors are “electrochemical,” including pairs of electrodes that measure avoltage signal from a combination of molecules, creating a “fingerprint” for a liquid.
The data is related to a mobile device and then via the app is delivered to a cloud server.
There, “a trained machine learning algorithm compares the digital fingerprint just recorded to a database of known liquids,” Ruch notes. “The algorithm figures out which liquids in the database are most chemically similar to the liquid under investigation, and reports the result back to the mobile app.”
IBM says it’s not dropping Watson AI product targeting drug development
Ruch explains that ab ig advantage of “having the machine learning models running on the cloud is that the sensors can be rapidly reconfigured from anywhere without alterations to the hardware. All that is needed to ‘rewire’ the sensors is change the parameters of the machine learning models to make them adjust to a new task. Sensors could learn from one another by exchanging information about new liquids they encounter.
The end result?
“Deploying many such sensors in the field would add an important but missing building block to the Internet of Things: chemical sensors,” he writes.
IBM, which operates one of its largest campuses in RTP and employs several thousand people across North Carolina, sees potential uses from ” industrial supply chains, food and beverages and environmental monitoring to the pharmaceutical and healthcare sectors, to name just a few,” the researcher adds.
“In the long term, we also envision using Hypertaste in fingerprinting even more challenging liquids, like those occurring in the life sciences.
“Besides possible applications in diagnostic or preventive medicine, such a tool could also allow sub-grouping of patients in clinical trials for new drugs by matching the individual responses of patients to a treatment with information on their personal metabolomes. The spectrum of possible applications is vast and spurs the imagination.”
