Ever had trouble knowing when to call it a night and quit working? Now, computers might be able to tell you when you’re overdoing it and how to push through the task at hand.
Scientists at MIT, Indiana University and Tufts University have developed a wearable brain scanner that can tell a computer when its user is overwhelmed. Sensing that a user is stressed, the portable headwear can adjust the computer’s interface to make things more manageable.
While the tool could surely find a useful place in any workaholic’s home, the scanner also has practical applications in air traffic control rooms and other occupational settings in which workers must stay alert for hours at a time.
The device, which scientists have named Brainput, works by using functional near-infrared spectroscopy (fNIRS), a type of brain scan that detects activity. Since active brain areas use more blood, fNIRS locates specific areas of activity by using light to locate changes in hemoglobin.
Using this technique, the researchers were able to identify when a user was multitasking and could even distinguish between different types of the activity. Researchers used this information to create a device that could respond to changes in a user’s state, modifying behavior to better support different types of multitasking.
To test Brainput, scientists created an experiment using virtual robots. Study volunteers wearing the headwear were required to simultaneously guide two different robots through a maze. When the robots began to sense that the volunteers were having a difficult time completing both tasks at once, they started to take on more navigation tasks themselves.
The researchers found that when the robots' autonomous mode kicked in, the overall performance of the human-robot team improved. The drivers didn't seem to notice or get frustrated by the autonomous behavior of the robot when they were multitasking. The researchers also tried increasing the autonomy of the robots when Brainput did not indicate that users were mentally overloaded. When they did this, they found that overall performance decreased. In other words, increased autonomy only helped when users were struggling to cope.
The research team presented their results last week at the Computer Human Interaction Conference in Austin, Texas. To see the full study, click here (pdf).
Image: Erin Treacy Solovay
This post was originally published on Smartplanet.com