Well, that's scary.
-
Well, that's scary.
A team of researchers at UC Santa Cruz’s Baskin School of Engineering that included Professor of Computer Science and Engineering Katia Obraczka, Ph.D. student Nayan Bhatia, and high school student and visiting researcher Pranay Kocheta designed a system for accurately measuring heart rate that combines low-cost WiFi devices with a machine learning algorithm.
WiFi devices push out radio frequency waves into physical space around them and toward a receiving device, typically a computer or phone. As the waves pass through objects in space, some of the wave is absorbed into those objects, causing mathematically detectable changes in the wave.
Pulse-Fi uses a WiFi transmitter and receiver, which runs Pulse-Fi’s signal processing and machine learning algorithm. They trained the algorithm to distinguish even the faintest variations in signal caused by a human heart beat by filtering out all other changes to the signal in the environment or caused by activity like movement.
The "machine learning" part probably does not really matter, except possibly for the exploratory and prototyping phases of the work. Once we know tht the low-resolution signal is there, hidden in the high-frequency raw data, the signal can be filtered out by some combination of old-fashioned and fairly cheap DSP techniques. Even if fancy machine learning has detected some sort of useful regulatory patterns in the context of building the prototype, I'm confident that these patterns can be replicated by some sort of much simpler feedback system.
A computer can potentially make a lot of interesting uses of being able to observe its human user's biological processes, particularly including real-time stress response, like that. Some of these interesting uses will be very, very, abusive.
(Source: https://news.ucsc.edu/2025/09/pulse-fi-wifi-heart-rate/.)
-
Well, that's scary.
A team of researchers at UC Santa Cruz’s Baskin School of Engineering that included Professor of Computer Science and Engineering Katia Obraczka, Ph.D. student Nayan Bhatia, and high school student and visiting researcher Pranay Kocheta designed a system for accurately measuring heart rate that combines low-cost WiFi devices with a machine learning algorithm.
WiFi devices push out radio frequency waves into physical space around them and toward a receiving device, typically a computer or phone. As the waves pass through objects in space, some of the wave is absorbed into those objects, causing mathematically detectable changes in the wave.
Pulse-Fi uses a WiFi transmitter and receiver, which runs Pulse-Fi’s signal processing and machine learning algorithm. They trained the algorithm to distinguish even the faintest variations in signal caused by a human heart beat by filtering out all other changes to the signal in the environment or caused by activity like movement.
The "machine learning" part probably does not really matter, except possibly for the exploratory and prototyping phases of the work. Once we know tht the low-resolution signal is there, hidden in the high-frequency raw data, the signal can be filtered out by some combination of old-fashioned and fairly cheap DSP techniques. Even if fancy machine learning has detected some sort of useful regulatory patterns in the context of building the prototype, I'm confident that these patterns can be replicated by some sort of much simpler feedback system.
A computer can potentially make a lot of interesting uses of being able to observe its human user's biological processes, particularly including real-time stress response, like that. Some of these interesting uses will be very, very, abusive.
(Source: https://news.ucsc.edu/2025/09/pulse-fi-wifi-heart-rate/.)
@riley
It goes well beyond that.
It is accurate enough that it can enable a person to "see" your fingers move on your keyboard as you enter a password.They don't even need to use your WiFi to spy on you. They can use a travel router or similar device to "see" you in your home.
-
R relay@relay.mycrowd.ca shared this topic
