Yikes!!

Several recent experiments have focused on using Wi-Fi signals to identify people, either based on their body shape or the specific way they tend to move. Earlier this month, a group of computer-science researchers at Northwestern Polytechnical University in China posted a paper to an online archive of scientific research, detailing a system that can accurately identify humans as they walk through a door nine times out of ten.

The system must first be trained: It has to learn individuals’ body shapes so that it can identify them later. After memorizing body shapes, the system, which the researchers named FreeSense, watches for people walking across its line of sight. If it’s told that the next passerby will be one of two people, the system can correctly identify which it is 95 percent of the time. If it’s choosing between six people, it identifies the right one 89 percent of the time.

The researchers proposed using their technology in a smart-home setting: If the router senses one person’s entry into a room, it could communicate with other connected devices—lights, appliances, window shades—to customize the room to that person’s preferences.

FreeSense mirrored another Wi-Fi-based identification system that a group of researchers from Australia and the UK presented at a conference earlier this year. Their system, Wi-Fi ID, focused on gait as a way to identify people from among a small group. It achieved 93 percent accuracy when choosing among two people, and 77 percent when choosing from among six. Eventually, the researchers wrote, the system could become accurate enough that it could sound an alarm if an unrecognized intruder entered.

Something in the way? No problem. A pair of MIT researchers wrote in 2013 that they could use a router to detect the number of humans in a room and identify some basic arm gestures, even through a wall. They could tell how many people were in a room from behind a solid wooden door, a 6-inch hollow wall supported by steel beams, or an 8-inch concrete wall—and detect messages drawn in the air from a distance of five meters (but still in another room) with 100 percent accuracy.

(Using more precise sensors, the same MIT researchers went on to develop systems that can distinguish between different people standing behind walls, and remotely  monitor breathing and heart rates with 99 percent accuracy. President Obama got a glimpse of the latter technology during last year’s White House Demo Day in the form of Emerald, a device geared towards elderly people that can detect physical activity and falls throughout an entire home. The device even tries to predict falls before they happen by monitoring a person’s movement patterns.)

Beyond human identification and general gesture recognition, Wi-Fi signals can be used to discern even the slightest of movements with extreme precision.

A system called “WiKey” presented at a conference last year could tell what keys a user was pressing on a keyboard by monitoring minute finger movements. Once trained, WiKey could recognize a sentence as it was typed with 93.5 percent accuracy—all using nothing but a commercially available router and some custom code created by the researchers.

The lip reading takes the cake. 

Yeah, I had not considered that case until now. Scary.