A research team in Massachusetts Institute of Technology has created a device called EQ Radio, which will determine a person's emotional state using WiFi. The team, led by Prof. Dina Katabi of MIT's CSAIL (Computer Science and Artificial Intelligence Laboratory), created the device as tool for detecting human emotions without the need for attaching body sensors.
A simple video explains how EQ Radio gathers heartbeat and breathing signals via Wi-Fi and enters the information into a machine learning algorithm. The algorithm interprets data and shows the emotional state of the person. The machine will know whether a person is happy, angry, excited, or sad and is said to have 87 percent accuracy.
The creators suggest real-life application of the device, such as audience reception of movies, detecting depression in the workplace, and the ability of home appliances like music and lights to adjust to its resident's emotional state. It can also be a helpful tool for police interrogations, court hearings, and doctor's patient evaluations.
While emotions can be detecting using the device, the team states that it can be used even for any situation where heartbeat and breathing patterns are needed.
"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," said Fadel Adib, a member of the research team. "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," he added.
In their research paper, a section compares EQ radio with ECG devices, and suggests that the former is more convenient for the subject as it requires no physical attachment.
EQ radio complies with the FCC regulations in terms of using signals, and only generates a range of 5.46 GHz to 7.25 GHz every 4 milliseconds. It runs on an Ubuntu 14.04 with an i7 processor and 32 GB of RAM.