Engineers at the University of California, Santa Cruz have developed a new method for measuring heart rate using WiFi signals, eliminating the need for wearable devices. This research introduces “Pulse-Fi,” a system that uses standard household WiFi equipment and machine learning algorithms to monitor heart rate with high accuracy.
The study, published in the proceedings of the 2025 IEEE International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), demonstrates that low-cost WiFi devices can be repurposed for health monitoring. The research team included Professor Katia Obraczka, Ph.D. student Nayan Bhatia, and visiting researcher Pranay Kocheta.
WiFi devices emit radio frequency waves that are altered as they pass through objects, including people. The Pulse-Fi system employs a transmitter and receiver to capture these changes and processes them with a machine learning algorithm trained to detect variations caused by human heartbeats while filtering out other 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.
In experiments involving 118 participants, researchers found that after just five seconds of data collection, Pulse-Fi measured heart rates with an error margin of only half a beat per minute. The accuracy improved with longer monitoring periods. The system was tested across 17 body positions—sitting, standing, lying down, or walking—and maintained consistent performance regardless of position or distance up to three meters from the device.
“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 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.”
To develop their detection system, researchers created their own dataset by pairing data from an ESP32 WiFi chip with ground truth measurements from an oximeter in UC Santa Cruz’s Science and Engineering library. They also validated Pulse-Fi using an external dataset collected by Brazilian researchers with Raspberry Pi hardware.
Future work aims to expand this technology’s capabilities to measure breathing rate and potentially detect conditions such as sleep apnea. Unpublished results indicate promise for these applications.
Those interested in commercial applications can contact Marc Oettinger at UC Santa Cruz’s Office of Innovation Transfer.
