DETERMINE TASK DEMAND FROM BRAIN ACTIVITY

Our society demands ubiquitous mobile devices that offer seamless interaction with everybody, everything, everywhere, at any given time. However, the effectiveness of these devices is limited due to their lack of situational awareness and sense for the users’ needs. To overcome this problem we develop intelligent transparent human-centered systems that sense, analyze, and interpret the user’s needs. We implemented learning approaches that derive the current task demand from the user’s brain activity by measuring the electroencephalogram. Using Support Vector Machines we can discriminate high versus low task demand with an accuracy of 92.2% in session dependent experiments, 87.1% in session independent experiments, and 80.0% in subject independent experiments. To make brain activity measurements less cumbersome, we built a comfortable headband with which we achieve 69% classification accuracy on the same task.