MIT researchers have created a portable device called AlterEgo that can recognize nonverbal cues, essentially "read your mind". The system is composed of a device that rotates around the ear of a user, follows its jaw and adheres under the mouth. and a computer system. The portable device has electrodes that pick up neuromuscular signals in the jaw and face that are triggered by internal verbalizations (also called words in your head) but that can not be seen by the human eye. These signals are then given to an automatic learning system that analyzes the data, associating specific signals with words.
"Our idea was: Could we have a more internal computing platform that combines humans and machines in some way and that feels like an internal extension of our own cognition?" Says Arnav Kapur, a graduate student at MIT Media . Laboratory in a statement.
In addition, the system can communicate with the user through a pair of "bone conduction headphones" by transmitting vibrations from the face to the ear. The headphones are intended to transmit information effectively to the user without interrupting their conversation or hearing.
The researchers tested the device with different tasks, including chess games and basic problems of multiplication and addition, using limited vocabularies of 20 words. While the device is quite intelligent, it is still limited; Researchers say it has 92% accuracy with only 20 words. They hope that it will expand over time. "We are in the middle of collecting data, and the results look good," says Kapur. "I think we'll get a full conversation someday." Another example of the use of headphones is to select a movie to watch by controlling what is selected on a television, as shown in the video.
To create the device, the researchers had to discover locations on the face that had the most reliable neuromuscular signals. To do this, the subjects were asked to "subvocalize the same series of words four times" and used 16 electrodes in different facial locations to detect the signals. They then generated a code to analyze the data, which found that seven particular places on the face were able to recognize non-verbal words. The resulting portable device uses sensors in those locations, although researchers are working on a device that can do the same with only four sensors along the jaw.
Researchers hope that future applications of the device will be as varied as helping people with disabilities even to be used in noisy environments such as in the flight deck of an aircraft carrier.