NIST has developed a deep learning algorithm that can analyse changes in Wi-Fi frequencies to identify whether someone in the room is struggling to breathe.
Scientists at the US National Institute of Standards and Technology (NIST) have created BreatheSmart, an algorithm to determine whether someone is having trouble breathing using available Wi-Fi routers and devices.
Wi-Fi routers continuously broadcast radio frequencies that phones, tablets and computers are able pick up. As the signals travel, they bounce off or pass through everything around them — the walls, the furniture and even people.
Due to the frequencies' sensibilities any movements - including breathing patterns - slightly alter the signal’s path from the router to a device. These are the changes that BreatheSmart has been trained to pick up and analyse.
The team behind the algorithm started looking at ways to better track people's health at home with the goal of helping doctors fight the Covid-19 pandemic, at a time when patients were isolated and ventilators were scarce.
Previous research had explored using Wi-Fi signals to sense people or movement, but these setups often required custom sensing devices, and data from these studies were very limited.
“As everybody’s world was turned upside down, several of us at NIST were thinking about what we could do to help out,” says Jason Coder, who leads NIST’s research in shared spectrum metrology. “We didn’t have time to develop a new device, so how can we use what we already have?”
Thus, they advanced a new way to use existing “channel state information,” or CSI to measure breathing patterns. CIS is a set of signals sent from the client (such as a cellphone or laptop) to the access point (such as the router).
These CSI streams are small, less than a kilobyte, so it doesn’t interfere with the flow of data over the channel. The team modified the firmware on the router to ask for these CSI streams more frequently, up to 10 times per second, to get a detailed picture of how the signal was changing and be able to analyse the distortion.
To test the algorithm, the team set up a manikin used to train medical professionals in an anechoic chamber with a commercial off-the-shelf Wi-Fi router and receiver. This manikin is designed to replicate several breathing conditions, from normal respiration to abnormally slow breathing (called bradypnea), abnormally rapid breathing (tachypnea), asthma, pneumonia and chronic obstructive pulmonary diseases, or COPD.
The teams collected the data provided by the CIS streams, and used deep learning to analyse it.
Deep learning is a subset of artificial intelligence, a type of machine learning that mimics humans’ ability to learn from their past actions and improves the machine’s ability to recognise patterns and analyse new data.
Using this technology, the team created BreatheSmart, which was able to successfully classify a variety of respiratory patterns simulated with the manikin 99.54 per cent of the time.
“Most of the work that’s been done before was working with very limited data,” said NIST research associate Susanna Mosleh. “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.”
In the future, the researchers hope that app and software developers can use the process presented in the work as a framework to create programs to remotely monitor breathing.
“All the ways we’re gathering the data is done on software on the access point (in this case, the router), which could be done by an app on a phone,” Coder said. “This work tries to lay out how somebody can develop and test their own algorithm. This is a framework to help them get relevant information.”
The scientists' findings were detailed in an article recently published in IEEE Access.
Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.