Machine learning is one thing, but the 'EQ-Radio' device from researchers at MIT's Computer Science and Artificial Intelligence Laboratory, or CSAIL, is developing machine feeling. About the size of a Wi-Fi router, the device uses wireless signals to detect the bodily conditions of people in its vicinity and make predictions about their emotional states.
While machine learning algorithms have been able to do similar emotive guesswork through facial recognition or body sensors, EQ-Radio is the first device to do so without a camera or any bodily contact. Rather, its wireless waves bounce off of people's bodies and return to the machine, giving it information about their respiration and heartbeat. It then uses this data to make predictions that, in lab tests, have been 90 percent accurate.