Welcome Stranger to OCC!Login | Register

Wireless Signals Used to Detect Emotions

Category: Science & Technology
Posted: 11:53AM
Author:

Reading someone's emotions can be very difficult, as some people do not obviously emote and others may try to hide their emotions, but it can be valuable information. For example, when testing a new product or reviewing media, accurately reading a subject's emotions can inform you about what works and what does not. To that end, as well as some valuable healthcare applications, researchers at MIT have developed a means of reading and tracking emotions using wireless signals.

This is hardly the first time MIT researchers, and the specific researchers on this project, have worked with wireless signals for some unexpected purpose as previously they were used to track people falling in a house. In that and this work, the key is measuring how the signals reflect off of a person's body and extracting information from that. In this case it is heart rate and breathing that is tracked by analyzing the acceleration recorded in the signals reflected off of the person's front and back. By using acceleration, the heart rate and breathing can be distinguished, as your pulse is much faster than your breathing. By reading these measurements, it is possible to determine the subject's emotional state and if they are happy, sad, angry, or excited.

When the researchers tested this they found this system, named EQ-Radio, has 70% accuracy at predicting emotions without any training and 87% accuracy after having learned the subject's emotions. Separate from monitoring emotions, this technology could also be used for tracking someone's heart rate with ECG accuracy without any on-body sensors, or for monitoring diagnosing conditions such as depression and anxiety.

 

 

Source: MIT



Register as a member to subscribe comments.
Waco on September 22, 2016 01:48
AKA radar. :P

This news has comment postings disabled because it is now archived.

© 2001-2017 Overclockers Club ® Privacy Policy
Elapsed: 0.0927391052   (xlweb1)