Understanding Driver Behavior after Concussion: A Machine-Learning Approach

Abstract

Concussions are common cognitive impairments, but their effects on task performance in general, and on driving in particular, are not well understood. To better understand the effects of concussion on driving, we investigated previously gathered data on twenty-two people with a concussion, driving in a virtual-reality driving simulator (VRDS), and twenty-two non-concussed matched drivers. Participants were asked to per-form a behavioral task (either coin sorting or a verbal memory task) while driving. In this study, we chose a few common metrics from the VRDS and tracked their changes through time for each participant. Our pro-posed method—namely, the use of convolutional neural networks for classification and analysis—can accu-rately classify concussed driving and extract local features on driving sequences that translate to behavioral driving signatures. Overall, our method improves identification and understanding of clinically relevant driv-ing behaviors for concussed individuals and should generalize well to other types of impairments.