A group of South Korean engineers from KAIST University and DGIST Institute of Science and Technology have developed an artificial taste sensor that mimics the capabilities of tongue receptors using artificial intelligence (AI) technologies. The study was published in the scientific journal magazine ACS Applied Materials and Interfaces (ACSAMI).
The team used four separate sensors to measure levels of saltiness, sourness, bitterness and sweetness and applied a custom machine learning algorithm for flavor analysis.
The scientists tested their invention on six different wines and conducted experiments to compile the taste characteristics of each variety. Using an “electronic language,” an AI sommelier classified recommended drinks with over 95% accuracy and offered suggestions for choosing wines with similar flavors.
The system is expected to be used in various industries such as food, beverages, cosmetics and pharmaceuticals. It will allow not only to measure the taste, but also to control the quality of the products.
Previously in Russia was created “Electronic nose” for quality control of food plastic.