Engineers at the University of California, Santa Cruz have developed a new method to measure heart rate using WiFi signals, eliminating the need for wearable devices. The research team, led by Professor Katia Obraczka and Ph.D. student Nayan Bhatia from the Baskin School of Engineering, designed a system called “Pulse-Fi” that uses low-cost WiFi hardware combined with a machine learning algorithm to detect heartbeats.
WiFi devices emit radio frequency waves that interact with objects in their environment. When these waves pass through a person’s body, they experience subtle changes that can be detected and analyzed. The Pulse-Fi system uses both a transmitter and receiver to process these signals and filter out environmental noise.
“The signal is very sensitive to the environment, so we have to select the right filters to remove all the unnecessary noise,” said Bhatia.
The researchers conducted experiments with 118 participants and reported that after five seconds of signal processing, heart rate could be measured with clinical-level accuracy. The error margin was about half a beat per minute after five seconds of monitoring. Testing showed consistent results regardless of where people were positioned or whether they were sitting, standing, lying down, or walking.
The study used affordable ESP32 chips costing between $5 and $10 as well as Raspberry Pi chips priced around $30. According to the researchers, commercial-grade WiFi equipment could further improve accuracy.
“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, high school student and visiting researcher on the project. “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.”
To train their algorithm, the team created its own dataset by collecting data from an ESP32 device alongside standard oximeter readings at UC Santa Cruz’s Science and Engineering library. They also tested Pulse-Fi using an existing dataset produced by Brazilian researchers who used Raspberry Pi hardware.
The group is now working on expanding their technology’s capabilities to include breathing rate detection for potential applications such as sleep apnea monitoring.
For commercial inquiries about this technology, interested parties are directed to contact Marc Oettinger at marc.oettinger@ucsc.edu.
