The MIT Computer Science and Artificial Intelligence Lab has created a system that can see your body through walls and reproduce your posture. The system uses radio waves to sense your location and then recreate your body as a simple stickman image. This system is called RF-Pose. The research report shows: Researchers use neural networks to analyze RF signals that bounce off the human body, and then create a dynamic stick figure that can perform the actions of walking, stopping, sitting, and moving limbs. The team said that the system can be used to monitor diseases such as Parkinson's disease and multiple sclerosis (MS) to better understand disease progression and allow doctors to adjust drugs accordingly. It can also help older people live more independently while providing more security for falls, injuries and changes in activity patterns. The team is mainly interested in using the system in the healthcare field. The system allows for passive monitoring of subjects in the room without cameras or other intruders. "All data collected by the team were subject to the subject's consent and were anonymous and encrypted to protect user privacy," the researchers wrote. "As for the practical application in the future, the team plans to implement a 'consent mechanism' under which the person who installed the device can perform a series of specific actions to start monitoring the environment." The researchers trained the neural network by showing the machine a video of radio frequency interference while the person was moving. Then they superimposed the bar chart on the move and trained the neural network to repeat the action automatically. Because RF signals are ubiquitous, it is easier to use than other sensing technologies. Interestingly, the researchers never trained the system perspective walls, but it was able to "self-evolve to be able to handle the movements outside the walls." "If you think of the computer vision system as a teacher, then this is a typical case of blue outdoer than blue," said researcher Antonio Torralba. The research team has not stated whether the system can be used for other commercial purposes. Children's Bicycle Lights Jiaxing Love Riding Electronic Technology Co.Ltd. , https://www.loveriding.cn