MIT Machine Uses Radio Waves To Read Human Emotions


Researchers from MIT's Computer Science and Artificial Intelligence Lab have developed a device that can detect four human emotions using radio signals.

The EQ-Radio is a device that emits and captures reflected radio frequency (RF) waves that are bounced off to a subject to measure his or her heart rate and breathing patterns. The waves that return to the device are analyzed for changes in breathing and heartbeat. Based on this information, the EQ-Radio can tell if a person is happy, angry, sad or excited.

In a demonstration of the technology, the researchers showed that the device is 87 percent accurate at predicting feelings if it has a person's measurements on file. Even without these, the accuracy of the device in predicting emotions is still high at 70 percent.

The researchers also revealed that heart rates are the biggest indicator of a person's emotional state and not the breathing rates, which makes sense since it is easier to mask breathing patterns but harder to control the heartbeat.

The technology is comparable to that of an ECG, which can recognize emotions using electrical signals that are picked up by electrodes on a person's body. The new device, however, is not as invasive. It can work in the background without requiring a person to wear any device.

"We describe the design and implementation of EQ-Radio, and demonstrate through a user study that its emotion recognition accuracy is on par with state-of-the-art emotion recognition systems that require a person to be hooked to an ECG monitor," the researchers reported.

The device can eventually be used as a lie detector for people who are good at hiding their feelings, but besides this, there are still a number of potential applications for the technology.

Film companies, for instance, can use it during test screenings to see how their movie affects people. It can also be used to adjust a house's heating and lighting to suit the residents' mood.

The technology can even be used in the field of medicine. Doctors can use it as a non-invasive way of keeping an eye on patients who suffer from anxiety, depression and other medical conditions. It may even shed light on certain health conditions because the system is capable of detecting if a person's heart skips a beat.

"This opens up the possibility of learning more about conditions like arrhythmia, and potentially exploring other medical applications that we haven't even thought of yet," said team member Fadel Adib.

ⓒ 2018 All rights reserved. Do not reproduce without permission.
Real Time Analytics