On July 12, MIT (Massachusetts Institute of Technology) News released new information regarding an artificial intelligence wireless smart-home system that could monitor diseases by sensing people through walls.
MIT’s Computer Science and Artificial Intelligence Laboratory professor Dina Katabi led a group of researches in creating their latest project, “RF-Pose.” The system is dedicated to sensing people’s movement, posture, and detecting diseases—Parkinson’s, multiple sclerosis, and muscular dystrophy—through walls. Also, RF-Pose allows senior citizens to live more independently by tracking sudden falls, injuries, and rapid changes in activity. Currently, Katabi’s team is working on introducing RF-Pose health care applications for doctors to oversee their patients.
“We’ve seen that monitoring patients’ walking speed and ability to do basic activities on their own gives health care providers a window into their lives that they didn’t have before, which could be meaningful for a whole range of diseases,” Katabi said on MIT News. “A key advantage of our approach is that patients do not have to wear sensors or remember to charge their devices.”
In addition to the health care benefits, RF-Pose serves as means for entertainment, specifically in video games. The system’s sensors stimulates a virtual reality environment by allowing players to walk around their house and participate in search-and-rescue missions to save survivors. However, the team was surprised that the network could sense activity behind walls given that regular cameras cannot capture through-wall motion.
“If you think of the computer vision system as the teacher, this is a truly fascinating example of the student outperforming the teacher,” MIT Professor and team member Antonio Torralba said on MIT News.
With the help of wireless signals, the RF-Pose is able to identify individuals with a success rate of 83 percent. The team is currently working on new advancements for their project.
“By using this combination of visual data and AI to see through walls, we can enable better scene understanding and smarter environments to live safer, more productive lives,” PhD student and team member Hang Zhao said on MIT news.