"This was so interesting that I had to buy the paper to take a look, and it's rather fascinating. To verify their results, the group collected two datasets -- one using two , which retail for about $5, and another using the , which costs about $30 to $50. The data collected using Wi-Fi was compared to data collected simultaneously using traditional methods."
"After collecting the data -- isolating the part of the CSI signal that relates to movements caused by a beating heart, removing environmental noise, applying a bandpass filter to target the 0.8 to 2.17 Hz range (corresponding to 48 to 130 beats per minute), and adding another filter to reduce noise while preserving signals needed -- the data is crunched using a a low-compute Long Short Term"
Pulse‑Fi is a non-intrusive continuous heart rate monitoring system that uses variations in Wi‑Fi Channel State Information caused by cardiac motion to estimate heart rate. Data collection used low-cost modules including $5-class devices and $30–$50 Raspberry Pi–class hardware, with Wi‑Fi measurements compared simultaneously to traditional medical methods. Signal processing isolated heart-related CSI components, removed environmental noise, applied a bandpass filter targeting 0.8–2.17 Hz (48–130 bpm), and added an additional filter to reduce noise while preserving vital signals. A low-compute long short-term memory model processed the filtered data, achieving 99.81% accuracy versus medical methods.
Read at ZDNET
Unable to calculate read time
Collection
[
|
...
]