Poker face no more: MIT unveils device that reads human emotions (VIDEO, POLL)
The device operates by accurately measuring a person’s breathing and heart rhythms without using on-body sensors, and using that information to detect a related emotion.
The developers of the EQ-Radio device say that it is 87 percent accurate at detecting if a person is excited, happy, angry or sad.
One of the researchers involved in the project, MIT PhD student Fadel Adib, explains that the device’s success lies in the frequency with which the signals are sent back and forth.
“By recovering measurements of the heart valves actually opening and closing at a millisecond time-scale, this system can literally detect if someone’s heart skips a beat,” Adib says.
“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.”
MIT professor and project leader Dina Katabi says she sees the EQ-Radio being especially useful in healthcare, consumer behavior and entertainment.
“Our work shows that wireless signals can capture information about human behavior that is not always visible to the naked eye,” Katabi says.
“We believe that our results could pave the way for future technologies that could help monitor and diagnose conditions like depression and anxiety.”
Apart from medical purposes, researchers suggest that advertising agencies could test clients’ reactions to the merchandise in real-time, smart homes could use the information about the owner’s mood to adjust heating, lighting or air quality.
“Just by knowing how people breathe and how their hearts beat in different emotional states, we can look at a random person’s heartbeat and reliably detect their emotions,” says PhD student Mingmin Zhao, co-author of the research paper on EQ-Radio.
Unlike existing emotion-detection methods, which are based mostly on audiovisual monitoring or on-body sensors, EQ-Radio is not in actual contact with the body. It sends wireless signals that reflect off of people’s bodies and are sent back to the device. It then studies the waveforms within each heartbeat and analyzes their variations to assess them.
For the experiment, researchers used two-minute videos or music to evoke a series of memories in their subjects, each connected with one of the four most common emotions - joy, anger, excitement and sadness, as well as a neutral state, in which you don’t experience any of those. The device accurately determined the person’s emotions in 87 percent of the tests.
But what’s in it for us? How would it change our daily lives? Tell us - would you like it if your emotions were easily read?