In Partial Fulfillment of the Requirements for the Degree of Master of Science
will defend his thesis
Predicting Types of Drivers
Driver types and their associated behaviors not only shape our driving habits but our reactions in unintended driving events as well. The open road reflects life by placing us in situations where we are forced to act and react in particular ways. Here, in this paper, we propose a method that produces short term predictions of types of drivers and their reaction during unexpected moments. We demonstrate our method of predicting with two simulations-- On-road Driving (ORD), and Test Track Driving 1 (TTD1). For the On-road Driving Study (n=8), we construct a between-variable predicting model to predict the level of arousal of perinasal perspiration for the next 5 seconds based on driving parameters of the last 30 seconds. Furthermore, we use TTD1 (n=21) data records to develop a within-variable model to predict the arousal of drivers during an unexpected acceleration event based on their arousal levels in normal, cognitive, and motoric driving tests. We achieve a classification performance AUC at 0.92 and 0.78 for between-variable prediction model and within-variable predicting models, respectively. The proposed method can also be used in future vehicles with advanced automation and personalization accordingly to the types of drivers.
Date: Friday, July 17, 2020
Time: 9:00 AM
Place: Online Presentation - MS Teams
Advisor: Dr. Ioannis Pavlidis
Faculty, students, and the general public are invited.