Tech breakthrough uses Wi-Fi signals to measure heart rate with no wearable devices needed

Your heartbeat is one of the simplest signals your body gives off, but it reveals a lot about your health. It changes with your activity, stress, and even how hydrated you are.

Until recently, though, monitoring your heartrate meant using special devices like hospital monitors or smartwatches.

But now, researchers at the University of California, Santa Cruz (UCSC), have shown that something as common as Wi-Fi can measure this vital sign with surprising accuracy.

The new system, called Pulse-Fi, transforms ordinary wireless signals into health trackers.

It promises a future where people can monitor their heart health without strapping on devices or relying on costly hospital machinery – all of this can be achieved using Wi-Fi devices that already exist in most homes.

Understanding Wi-Fi – the basics

Wi-Fi works by sending information through the air using radio waves, the same type of waves that carry music to your car radio. The difference is that Wi-Fi uses much higher frequencies, which lets it carry far more data.

Inside your router, a tiny transmitter turns digital information – like a video or a message – into patterns of radio waves.

Your phone or laptop has an antenna and receiver that catch those waves and turn them back into the pictures, sounds, or words you see on your screen.

It’s like tossing a ball back and forth, but instead of a ball, the “catch” is a stream of invisible energy carrying coded information.

Those radio waves don’t travel forever, though. Walls, floors, and even water in the human body can block or weaken them, which is the basic premise behind Pulse-Fi.

Turning Wi-Fi into Pulse-Fi

The UC Santa Cruz team included Professor Katia Obraczka, Ph.D. student Nayan Bhatia, and visiting high school researcher Pranay Kocheta.

Together, they created a low-cost method that pairs Wi-Fi transmitters and receivers with machine learning algorithms.

Wi-Fi waves move through space, bouncing and bending around objects. When those waves encounter the human body, tiny signal shifts occur.

Pulse-Fi’s algorithms analyze those faint disturbances to pick out the rhythm of a heartbeat while filtering out unrelated movements or environmental noise.

“The signal is very sensitive to the environment, so we have to select the right filters to remove all the unnecessary noise,” Bhatia said.

Heartbeats measured in seconds

The study involved 118 participants, and the results were impressive. After only five seconds of analysis,

Pulse-Fi measured heartrate with an error margin of just half a beat per minute. Longer monitoring improved accuracy even further.

The researchers tested people in varied body positions – sitting, standing, lying down, and even walking.

Regardless of position, the system worked reliably. Hardware placement in the room also made little difference, proving the system’s adaptability.

Low-cost components powered the tests. ESP32 chips, which cost under ten dollars, performed well.

Raspberry Pi devices, though more expensive, achieved even better results. Commercial-grade Wi-Fi hardware could improve performance further.

Distance doesn’t break accuracy

Another breakthrough was range. Pulse-Fi measured heart rate accurately at distances up to three meters, or nearly ten feet. Additional tests suggest it can perform even farther.

“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,” Kocheta said.

“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.”

Creating Pulse-Fi datasets

To train their system, the team needed data. No existing dataset captured heartbeat effects on Wi-Fi signals from ESP32 devices, so they built their own. In the UC Santa Cruz Science and Engineering Library, they carefully set up ESP32 units alongside standard oximeters to generate parallel data streams.

This pairing provided a dependable “ground truth” for training, ensuring that every pulse recorded through Wi-Fi could be accurately matched with the medically verified heart rate.

They then trained a neural network to recognize which subtle signal changes represented heartbeats, focusing on even the faintest variations in the wireless data.

Alongside their newly built dataset, they validated Pulse-Fi using a large dataset from Brazil collected with Raspberry Pi hardware – one of the most comprehensive Wi-Fi-based health monitoring datasets available.

That cross-testing confirmed the system’s broad reliability and showed that Pulse-Fi could adapt across device types, room conditions, and participant groups. It demonstrated that a low-cost approach could achieve remarkable accuracy under diverse real-world scenarios.

Wi-Fi as health guardian

Pulse-Fi’s creators are not stopping here. They are now adapting the system to detect breathing rates. Early results show strong potential for diagnosing issues like sleep apnea, where subtle breathing patterns are crucial for detection.

Such a capability could give doctors new insights into sleep quality, respiratory problems, and long-term health risks – without the need for intrusive overnight monitoring.

By combining affordability, accuracy, and non-intrusiveness, Pulse-Fi points to a future where everyday Wi-Fi doubles as a quiet guardian of health.

Smart homes could eventually integrate the system, providing continuous tracking of both heart and lung function.

This advancement would make preventive care more accessible, offering people the chance to detect health issues early and share reliable data with clinicians.

What once required specialized devices might soon be handled by the invisible signals already surrounding us.

The study is published in the journal IEEE Xplore.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–