Researchers with the National Institute of Standards and Technology (NIST) and the Food and Drug Administration (FDA) have discovered Wi-Fi signals can can be used to detect breathing problems, according to an NIST announcement.
NIST has developed a "deep learning" algorithm that can detect minute changes in the radio frequencies that travel between internet routers and devices, the agency announced Dec. 20. The algorithm, called BreatheSmart, can analyze those changes to help identify if a person is struggling to breathe, according to the announcement.
"Wi-Fi routers continuously broadcast radio frequencies that your phones, tablets and computers pick up and use to get you online," the NIST states in the announcement. "As the invisible frequencies travel, they bounce off or pass through everything around them — the walls, the furniture and even you. Your movements, even breathing, slightly alter the signal’s path from the router to your device."
The discovery of how to use already available routers and devices to detect minuscule changes in broadcast frequencies started with NIST scientists in 2020 searching for a way to assist doctors in the fight against Covid-19, according to the announcement.
“As everybody’s world was turned upside down, several of us at NIST were thinking about what we could do to help out,” Jason Coder, head of NIST’s research in shared spectrum metrology, said in the statement. “We didn’t have time to develop a new device, so how can we use what we already have?”
Coder, research associate Susanna Mosleh and colleagues at the Office of Science and Engineering Labs (OSEL) in the FDA’s Center for Devices and Radiological Health, developed a way to use existing routers to to measure the breathing rate of a person in the same room.
They set up a medical-training mannequin designed to simulate various breathing conditions and an off-the-shelf Wi-Fi router and receiver in an anechoic chamber, then recorded distortions to the frequencies as the mannequin "breathed," the statement reports.
Mosleh helped develop the BreatheSmart algorithm to go through the data and identify patterns that suggested various breathing problems. BreatheSmart was successful in classifying 99.4% of the mannequin-simulated respiratory patterns, according to the report.
“Most of the work that’s been done before was working with very limited data,” Mosleh said in the report. “We were able to collect data with a lot of simulated respiratory scenarios, which contributes to the diversity of the training set that was available to the algorithm.”
Coder said the way data is gathered on router software could be done by an app, and that there is a lot of interest in using Wi-Fi signals in sensing applications. Coder and Mosleh are hopeful software and app developers will use their work to create programs to monitor breathing remotely, the report states.
“This work tries to lay out how somebody can develop and test their own algorithm," Coder said in the report. "This is a framework to help them get relevant information.”
