Summary
- Wi-Fi signals and machine learning can noninvasively process heart rate with clinical-level accuracy in under 5 seconds.
- After being tested on 118 people, it read pulse during motion using a $30 Raspberry Pi chip.
- If successful, it could enable contactless heart monitoring without wearables.
When you want to track your health, you’d usually have to shell out for a wearable that you have to have on you for it to work. However, what if someone could read your heart rate using wireless technology? It sounds like something out of science fiction, but a team of researchers believes it’s not as far-fetched as you may believe. They’ve published a paper claiming that, not only can Wi-Fi signals help detect heart rates with extremely good accuracy, but you can achieve these results with a super-cheap Raspberry Pi Wi-Fi chip.
Researchers believe that Wi-Fi heart monitoring is possible, accurate, and affordable
As reported by UC Santa Cruz News (thanks for the spot, Notebook Check!), researchers have been exploring ways to track heart rate via Wi-Fi. As part of their study, they uploaded a paper titled “Pulse-Fi: A Low-Cost System for Accurate Heart Rate Monitoring Using Wi-Fi Channel State Information.” Here’s the abstract for the paper:
Non-intrusive monitoring of vital signs has become increasingly important in various healthcare settings. In this paper, we present Pulse-Fi, a novel low-cost system that uses Wi-Fi Channel State Information (CSI) and machine learning to accurately monitor heart rate. Pulse-Fi operates using low-cost commodity devices, making it more accessible and cost-effective. […] Our results show that Pulse-Fi can effectively estimate heart rate from CSI signals with comparable or better accuracy than hardware with multiple antenna systems, which can be expensive.
Sounds cool, doesn’t it? To achieve this, the technology leverages a phenomenon where Wi-Fi signals are sometimes absorbed by the objects they pass through. The idea is that a scientist can set up a Wi-Fi emitter to send a signal through someone, then pick up what emerges from the other side via a receiver. They then feed the data through a machine learning algorithm, which is especially trained to find the exact disturbances in the signal that correlate with a heartbeat. From here, they can monitor someone’s heartbeat without even touching the patient.
The researchers tested Pulse-Fi on 118 people. After five seconds, the researchers could read someone’s heartbeat at a “clinical-level accuracy,” and best of all, they could do it regardless of if the patient was standing, sitting, moving, or even walking. And while you’d expect such hardware to cost an arm and a leg, the researchers found the best results while using a $30 Raspberry Pi board.
Obviously, given the health-based nature of this project, I do not recommend you try to build a Pulse-Fi at home using your own Raspberry Pis. However, if this technology takes off, it shouldn’t be long until we see Pi chips monitoring our heart health without a wearable device in sight. In the meantime, you can make these Raspberry Pi projects that are actually useful (and not just a novelty).
Source link