An Electronic Tongue Can Taste When Juice Starts to Go Bad
The electronic tongue can taste your drink better than you can! This mind-blowing electronic sensor hold the potential to revolutionize how we check food and beverage quality
The electronic tongue is the ultimate result of the search for an automated way to “taste-test” products at mass-production speed and scale, a quest that has stumped the food and beverage industry for decades. In a new study, researchers used machine learning to overcome the limitations of a promising type of chemical sensor, meaning that a robotic tongue may soon assess your milk or wine before you do.
The Magic Behind the “Robo-Tongue”
Picture this: a super-smart electronic tongue that doesn’t just taste, but analyzes your drink’s entire chemical profile. Researchers have cracked the code using some killer combination of:
- Ion-sensitive transistors
- Machine learning algorithms
- Graphene sensor technology
When ions in a liquid—say, a delicious drink—touch the conductive sheet of an ion-sensitive field-effect transistor (ISFET), the electric current that flows through changes based on the liquid’s exact composition and the voltage applied. This lets scientists use ISFETs to convert chemical changes into electrical signals. The chemical makeup of any drink, and thus its taste, is influenced by contamination and freshness—which ISFETs can discern.
How it works
These tech wizards developed a sensor that detects chemical changes in liquids, uses AI to classify drinks with 97% accuracy, can distinguish between different beverage brands., checks drink freshness in milliseconds.
This breakthrough proves once again that when engineering meets creativity, magic happens! The sensor can:
- tell if milk is diluted
- identify coffee blends
- detect subtle chemical changes humans can’t perceive
A research that goes a long way back
The food industry has a lot of problems in terms of figuring out whether food is adulterated or has something toxic in it. The first ISFETs were demonstrated more than 50 years ago, but the sensors aren’t used much commercially. The advent of graphene, an ideal conductive material, helped researchers create improved ISFET sensors that detect specific chemical ions. But a big problem remained: readings varied from sensor to sensor and with changes in conditions such as temperature or humidity.
Marrying ISFET with neural networks
In Nature, a research team addressed this issue by marrying ISFETs with neural networks, training a machine-learning algorithm to classify drinks using the sensors’ readings. The resulting system could tell whether milk was diluted, distinguish among soda brands or coffee blends, and identify different fruit juices while judging their freshness.
During development, the research team tried training based on human-selected data points, but the scientists found that designations were more accurate if the algorithm was given all device measurements and chose its own data features to base decisions on. Human-chosen features were vulnerable to variations in the devices, whereas the algorithm analyzed all the data at once, finding elements that change less. Machine learning is able to figure out more subtle differences that humans would find hard to define. The system managed more than 97 percent accuracy on practical tasks.
Pros and Cons of ISFET
The data are very convincing, say University of California, San Diego, engineer Kiana Aran, who co-founded a company to commercialize graphene-based biosensors. Unlike the human tongue, which detects specific molecules, this type of ISFET system detects only chemical changes—“which limits it to specific, predefined chemical profiles” such as brand formulations or ranges of freshness, she says.
Further developments and applications
Imagine a world where a robotic system could instantly tell if your milk was fresh, if your fruit juice was pure, or if your favorite soda matched its promised flavor profile. With over 97% accuracy, this electronic tongue isn’t just a scientific curiosity—it is a potential game-changer for food and beverage industries, healthcare monitoring, and quality control.
What started as a challenge in food safety had become something extraordinary: an electronic tongue that could detect the subtle chemical changes in a drink before a human palate could even begin to sense something was off. Using graphene-based sensors and sophisticated machine learning algorithms, the research team had developed a technology that could distinguish between beverage brands, detect dilution, and assess freshness with remarkable precision.
Next, researcher will test larger, more diverse training datasets and more complex algorithms, as they expand the system’s reach. For example, it can this technology could be used for healthcare applications: blood glucose level or sweat monitoring, Another area worth exploring.
Pro Maker Tip: keep an eye on this technology. It’s not just a lab experiment—it’s the future of smart sensing!
source: Scientific American
cover image: MDPI
author: Barbara Marcotulli
Maker Faire Rome – The European Edition, promossa dalla Camera di Commercio di Roma e organizzata dalla sua Azienda speciale Innova Camera, si impegna da ben nove edizioni a rendere l’innovazione accessibile e fruibile con l’obiettivo di non lasciare indietro nessuno offrendo contenuti e informazioni in un blog sempre aggiornato e ricco di opportunità per curiosi, maker, startup e aziende che vogliono arricchire le proprie conoscenze ed espandere il proprio business, in Italia e all’estero.
Seguici, iscriviti alla nostra newsletter: ti forniremo solo le informazioni giuste per approfondire i temi di tuo interesse
