Paper Slides(ppt) Slides(html)
Extracting Multi-Person Respiration from Entangled RF Signals
Shichao Yue Hao He Hao Wang Hariharan Rahul Dina Katabi
Computer Science & Artificial Intelligence Laboratory
Massachusetts Institute of Technology
Responsive image
When multiple people sitting close to each other, RF reflections off bodies super-impose over the wireless medium and interfere at the receiver, preventing traditional approaches from monitoring breathing. DeepBreath has a breathing separation module that reconstructs the correct breathing signals of multiple co-located individuals. As shown in the figure, even when five people sit in the same couch, DeepBreath can extract the breathing of each person accurately.
DeepBreath is the first RF-based respiration monitoring system that can recover the breathing signals of multiple individuals even when they are separated by zero distance. We model interference due to multiple reflected RF signals and demonstrate that the original breathing can be recovered via independent component analysis (ICA). We design a full system that eliminates interference and recovers the original breathing signals. It also provides continuous monitoring throughout the night for people who share the same bed. DeepBreath is very accurate. Specifically, the differences between the breathing signals it recovers and the ground truth are on par with the difference between the same breathing signal measured at the person’s chest and belly.
Extracting Multi-Person Respiration from Entangled RF Signals
Shichao Yue, Hao He, Hao Wang, Hariharan Rahul, Dina Katabi
ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp 2018)
DeepBreath has been used to let doctors monitor COVID-19 patients from a distance ( Tech Crunch, Engadget, VentureBeat ).
Line of Research
©2018 Massachusetts Institute of Technology