Tejal Somvanshi
Engineers at the University of California, Santa Cruz have developed a system that uses everyday WiFi signals to measure a person’s heart rate without any wearable devices. Their technology, called “Pulse-Fi,” achieves clinical-level accuracy using hardware that costs as little as $5.
Heart rate provides critical information about physical activity, stress levels, and overall health. Traditionally, measuring it required some type of wearable device like a smartwatch or medical equipment. Pulse-Fi eliminates this need by detecting subtle changes in WiFi signals as they pass through the body.
“The signal is very sensitive to the environment, so we have to select the right filters to remove all the unnecessary noise,” explained Nayan Bhatia, a PhD student working on the project.
The research team, led by Professor Katia Obraczka at UC Santa Cruz’s Baskin School of Engineering, included Bhatia and high school student Pranay Kocheta. They tested their system with 118 participants and found impressive results. After just five seconds of monitoring, Pulse-Fi measured heart rates with only half a beat-per-minute of error. Longer monitoring periods further improved accuracy.
The system proved remarkably versatile, working regardless of whether people were sitting, standing, lying down, or walking. Tests across 17 different body positions all yielded accurate results. The technology maintained accuracy up to 10 feet (3 meters) away from the WiFi hardware.
“What we found was that because of the machine learning model, that distance apart basically had no effect on performance,” 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.”
How does it work? WiFi devices send out radio waves that change slightly when passing through objects, including the human body. The Pulse-Fi system uses a WiFi transmitter and receiver running special software that filters out environmental noise and focuses on the tiny signal variations caused by heartbeats.
To train their system, the researchers created a custom dataset, combining readings from their WiFi setup with measurements from a standard medical device called an oximeter. This “ground truth” data helped teach their algorithm to recognize which signal patterns corresponded to actual heartbeats.
Similar Posts
The team achieved these results using budget-friendly hardware: ESP32 chips costing $5-10 and Raspberry Pi devices around $30. Tests showed the Raspberry Pi performed even better, suggesting that standard home WiFi routers might deliver even greater accuracy.
The study was published in the proceedings of the 2025 IEEE International Conference on Distributed Computing in Smart Systems and the Internet of Things. This technology could be particularly valuable in settings where continuous monitoring is beneficial but wearable devices are impractical—such as sleep studies, elder care facilities, or low-resource healthcare environments. The low cost of the required hardware makes it accessible for widespread use.
The researchers are now expanding their work to detect breathing rates and potentially identify conditions like sleep apnea. Early unpublished results show promise for these applications.
While not mentioned in the current research, future development would likely need to address privacy concerns, multi-person households, and varying home router configurations before widespread adoption.
Those interested in commercial applications can contact Marc Oettinger, Assistant Director of Innovation Transfer at UC Santa Cruz.
