A university research team developed a novel technique to measure heart rates using Wi-Fi. According to the University of California, Santa Clara (UCSC), the team, which included Computer Science and Engineering Professor Katia Obraczka, Ph.D. student Nayan Bhatia, and high school student and visiting researcher Pranay Kocheta, used a low-cost ESP32 chip and paired it with a machine learning algorithm to detect changes in the Wi-Fi signal caused by the heart. They then run it through a machine learning algorithm, which can estimate the heart rate with an accuracy of around half a beat per minute after five seconds of monitoring (with the margin of error improving after longer observation and with the use of more powerful Wi-Fi devices).
This project, called Pulse-Fi, works as far as 10 feet away from the hardware, meaning you don’t have to wear it to get accurate readings. “What we found was that because of the machine learning model, that distance apart basically had no effect on performance, which was a very big struggle for past models,” said Pranay Kocheta. “The other thing was position — all the different things you encounter in day-to-day life, we wanted to make sure we were robust to however a person is living.”
Aside from counting your heart’s beat per minute, the team behind Pulse-Fi is also working to develop the system for measuring breathing rate. This can be useful for detecting conditions like sleep apnea, which is often done with a portable monitor that the patient must wear. If the team can prove that Pulse-Fi can do it wirelessly and accurately, this will make detection and diagnosis easier and much more comfortable.
Follow Tom's Hardware on Google News, or add us as a preferred source, to get our up-to-date news, analysis, and reviews in your feeds. Make sure to click the Follow button!
