• Login
  • Register

Work for a Member company and need a Member Portal account? Register here with your company email address.

Project

RFIQ: Food quality and safety detection using wireless stickers

Unsoo Ha & Fadel Adib

We have developed a wireless system that leverages the inexpensive RFID tags already on hundreds of billions of products to sense potential food contamination. Our system, called RFIQ (Radio Frequency IQ), aims at democratizing food quality and safety, bringing it to the hands of consumers. 

More Information

  1. Why is food safety sensing so important?

    Over the past decade, we have witnessed many safety hazards that could've been avoided if we had access to ubiquitous food quality and sensing technologies. For example, in 2008, more than 50,000 babies were hospitalized in China for eating baby formula that was contaminated by mixing it with melamine. Similarly, every year, hundreds of people die or go blind because of drinking fake alcohol. Alcohol is faked by mixing it with cheaper methanol, and this remains an ongoing problem in many countries including Mexico, China, and Turkey. Another example of food safety is the Flint water crisis in 2016, which exposed the Flint community to unsafe water, and the crisis led to the elevation of toxic lead levels in children's blood. We could avoid all these hazards, and more, if we could bring food quality and safety sensing to everyone—if consumers had the power to test their own products at home, cheaply and accurately.

  2. How does RFIQ work?

    Our system leverages RFID (Radio Frequency Identification) stickers that are already attached to hundreds of billions objects. When an RFID powers up and transmits its signal, it interacts with material in its near vicinity (i.e., inside a container) even if it is not in direct contact with that container. This interaction is called "near-field coupling," and it impacts the wireless signal transmitted by an RFID. Our system, RFIQ, extracts features from this signal and feeds it to a machine learning model that can classify and detect different types of adulterants in the container. 

  3. How well does the system work?

    We built an initial prototype of our system, and tested it in two applications.  Our first set of results are promising. They demonstrated the ability to identify fake alcohol with an accuracy higher than 97% and identify tainted infant formula with an accuracy higher than 96%.

    To learn more about how the system works, read our paper.

    If you're interested in exploring the potential of using RFIQ for detecting different kinds of contaminants or material properties, contact us at rfiq@media.mit.edu.