Food safety detection system uses existing product RFID tags
The simple, scalable system requires no hardware modifications, say the researchers, and promises to bring food-safety detection to the general public. Such a system could help address the food safety incidents that cause illness and death every year.
The system, called RFIQ, includes a reader device that senses miniscule changes in the wireless signals emitted from RFID tags when the signals interact with food. Specific changes in the signals from an RFID tag correspond to levels of certain contaminants within that product.
A machine-learning model “learns” those correlations and – given a new material – can predict if the material is pure or tainted, and at what concentration. For this study, the researchers focused on baby formula and alcohol, but in the future, say the researchers, consumers might have their own reader and software to conduct food-safety sensing before buying virtually any product. The system could also be implemented in supermarket back rooms or in smart fridges to continuously ping an RFID tag to automatically detect food spoilage.
In experiments, say the researchers, the system detected baby formula laced with melamine with 96% accuracy, and alcohol diluted with methanol with 97% accuracy.
“In recent years, there have been so many hazards related to food and drinks we could have avoided if we all had tools to sense food quality and safety ourselves,” says Fadel Adib, an assistant professor at the Media Lab and co-author on a paper describing the system. “We want to democratize food quality and safety, and bring it to the hands of everyone.”
Other sensors designed for detecting chemicals or spoilage in food are typically highly specialized systems, where the sensor is coated with chemicals and trained to detect specific contaminations. The MIT Media Lab researchers instead aimed for broader sensing, relying on very cheap RFID sensors – typically costing around three to five cents – and moving the detection function to the computation side.
Their system leverages the fact that, when RFID tags power up, the small electromagnetic waves they emit travel into – and are distorted by – the molecules and ions of the contents in the container. This process – known as “weak coupling” – means that if the material’s property changes, so do the properties of the wireless signal.
In the researchers’ system, a reader emits a wireless signal that powers the RFID tag on a food container. Electromagnetic waves penetrate the material inside the container and return to the reader with distorted amplitude (strength of signal) and phase (angle).
When the reader extracts the signal features, it sends that data to a machine-learning model on a separate computer. In training, the researchers tell the model which feature changes correspond to pure or impure materials. For the study, they used pure alcohol and alcohol tainted with 25%, 50%, 75%, and 100% methanol; baby formula was adulterated with a varied percentage of melamine, from 0 to 30%.
“Then,” says Adib, “the model will automatically learn which frequencies are most impacted by this type of impurity at this level of percentage. Once we get a new sample, say, 20 percent methanol, the model extracts [the features] and weights them, and tells you, ‘I think with high accuracy that this is alcohol with 20 percent methanol.'”
The system’s concept, say the researchers, derives from a technique called radio frequency spectroscopy, which excites a material with electromagnetic waves over a wide frequency range and measures the various interactions to determine the material’s makeup. A major challenge in adapting this technique for the MIT system, however, was that RFID tags only power up at a very tight bandwidth wavering around 950 MHz – too limited a bandwidth for extracting any useful information.
So the researchers used a “two-frequency excitation” sensing technique, where two sets of frequencies – one for activation, and one for sensing – are sent to measure hundreds more frequencies. Here, the reader first sends a signal at around 950 MHz to power the RFID tag. When it activates, the reader then sends another signal that sweeps a range of frequencies from around 400 to 800 MHz. It detects the feature changes across all these frequencies and feeds them to the reader.
“Given this response,” says Adib, “it’s almost as if we have transformed cheap RFIDs into tiny radio frequency spectroscopes.”
Looking ahead, the researchers are currently working on ensuring that the system can account for variables such as the shape of the container and other environmental aspects. They are also seeking to expand the system’s capabilities to detect many different contaminants in many different materials.
For more, see “Learning Food Quality and Safety from Wireless Stickers.” (PDF)
Related articles:
Walmart to require blockchain to track leafy greens for food safety
Blockchain consortium takes aim at food safety
IBM blockchain-enabled food safety network expands
Alibaba launches blockchain food tracking system
IoT data logger tracks temps of perishable goods