Shulou(Shulou.com)11/24 Report--

CTOnews.com, December 21 (Xinhua)-- researchers at the National Institute of Standards and Technology (NIST) have developed a method to monitor human breathing based on small changes in WiFi signals, named BreatheSmart deep learning algorithm.

The ▲ map source NISTNIST indicates that BreatheSmart can be used with routers and devices already on the market. It only needs a router and a connected device.

Specifically, the researchers changed the firmware on the router to check the "channel state information (CSI)" more frequently. CSI refers to a signal sent to a router from a device (such as a mobile phone or laptop). Due to environmental deviations, such as changes in the signal due to surface or motion, the researchers increased the frequency of router requests for CSI signals to 10 times per second in order to better understand how the signal was modified.

CTOnews.com learned that the team used mannequins to simulate several breaths and used existing routers and receiving equipment to monitor changes in CSI signals. To understand the data they collected, Susanna Mosleh, a NIST research assistant, developed the BreatheSmart algorithm. The researchers pointed out in the paper that the correct recognition rate of BreatheSmart under simulated breathing conditions is 99.54%.

Mosleh and Jason Coder are the heads of NIST shared spectrum metrology research, and they hope that developers will be able to build on the research to produce software that can remotely monitor breathing using existing hardware. " All the ways we collect data are done on the software on the access point (in this case, the router) and viewed through the App on the phone, which tries to clarify how people develop and test their own algorithms. This is a framework to help them get relevant information. "

Paper address: click here to view

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.