Research Highlight: Brain-Computer Interaction

In Human-Computer Interaction, Tufts' CS researchers are seeking to expand and improve the communication pathways between people and computers. Computer scientists in Prof. Robert Jacob's Human Computer Interaction Lab are collaborating with Professor Sergio Fantini's group in the Biomedical Engineering Department to create a direct connection between the brain and the computer, using a cutting-edge, non-invasive form of brain-imaging technology known as functional near infrared spectroscopy (fNIRS). Unlike other, more intrusive technologies, fNIRS involves a small headband that users can wear while performing other activities. It measures blood flow in the brain by shining near infrared light into the head and measuring the light returned. From this, researchers can obtain information about a person's brain state, using machine learning techniques to analyze and classify the measurements in real time.

In their research to date, they have developed measurements for short-term memory workload and for multitasking. They are now developing adaptive user interfaces that will subtly change in response to changes in the user's brain state.  For example, if it detected an increase in the workload of an air traffic controller, the system could assign new tasks to another less busy controller or reduce the frequency of status messages and interruptions for that person.

The new Human-Robot Interaction Laboratory under Professor Matthias Scheutz has begun working with a group to devise new application scenarios and evaluation paradigms for these adaptive interfaces. In these tests, a person is doing one task while monitoring a robot, which is doing another. The robot will continuously adjust the level of monitoring it requests from the person based on his or her current mental workload.

Learn more about projects in this area