Timely Constraints of EEG in Cognitive Distraction and Focus Detection while Driving
Term
4. term
Education
Publication year
2018
Submitted on
2018-06-14
Abstract
Previous studies have shown that it is possible to distinguish cognitive distraction from cognitive focus using electroencephalography (EEG). However, there is still a lack on research regarding the possibility to distinguish cognitive distraction from cognitive focus over time. We create Animus, a system to distinguish between cognitive distraction and focus of drivers. Using a driving simulator, we collected EEG data from 8 subjects over the course of 2 days with 7 days between. When training and evaluating Animus on data for one day, Animus achieved an average classification accuracy over all subjects of 98.01%. When training on data from day 1, and evaluating on data from day 2, Animus achieved an average accuracy of 77.95%. These results suggest that brain waves are consistent enough over time, for Animus to distinguish between cognitive distraction and focus on future days. To identify the impact of the EEG helmets placement, we performed a second experiment. Two driving sessions were performed, one where the helmet was reattached, and one where it stayed on. Reattachment of the helmet reduced the classification accuracy from 84.06% to 77.11%. This implies that the placement of the EEG helmet impacts the classification accuracy.
Keywords
Documents