New MIT Machine can Detect Emotions Using Wireless Signal

By Ana Verayo, | September 21, 2016

Professor Dina Katabi (center) explains how PhD student Fadel Adib's (right) face is neutral but that EQ-Radio's analysis of his heartbeat and breathing show that he is sad.

Professor Dina Katabi (center) explains how PhD student Fadel Adib's (right) face is neutral but that EQ-Radio's analysis of his heartbeat and breathing show that he is sad.

Scientists have figured out a way to predict human emotions using wireless signals to measure physiological signals emitted by the body. In the past, this could only be achieved using electrocardiography (ECG) monitors, where electrodes are attached to the body.

In this new study, a team from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) created a device that can measure human emotions without wires. Known as the EQ-Radio, this ingenious machine works similarly like Wi-Fi.

Like Us on Facebook


The machine sends out wireless signals, which the human body receives and bounces back to the device. These reflected signals are then measured to determine if a person is happy, angry, sad or excited.

It might sound somewhat creepy that a computer can recognize your emotion from a distance even without wires. According to lead researcher MIT professor, Dina Katabi, the machine measures your heartbeat and breathing patterns that can strongly convey emotions.

Katabi said there are small differences in our heart rate and breathing patterns that can reveal emotions that are not obvious on the outside.

The MIT team believes that this device can measure those "inner emotions" since it can connect to the autonomic nervous system.

The machine can classify the correct emotions with an 87 percent accuracy. Researchers claim that this machine is more accurate than image-based systems that use cameras to analyze emotions on human faces.

©2017 Telegiz All rights reserved. Do not reproduce without permission
Real Time Analytics