Understanding Driving Behavior Using fNIRS and Machine Learning
According to the latest statistics by the National Highway Safety Administration, approximately 1,830 young drivers (15–20 age) are involved in fatal crashes. Driving tasks such as keeping the vehicle within the lane, observing traffic signs, turning, and identifying any sudden danger involve various cognitive processes including attention, memory, vision, spatial orientation, motor control, executive function, and decision making. This study proposes an innovative way to assess driver’s behavior, especially focusing on young drivers, by applying the emerging sensing technologies, functional near infrared spectroscopy (fNIRS), driving simulator, and analytical methods (e.g., machine learning). Study findings show machine learning can achieve an average of 97.5% accuracy when using fNIRS data and 70% accuracy when using driving data. While the team acknowledges the limited data set is used in this paper, this study opens the doors for applying the emerging machine learning methods to driver’s cognitive processes to further understand young individual’s driving behavior.
- Record URL:
-
Availability:
- Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784483534
-
Supplemental Notes:
- © 2021 American Society of Civil Engineers.
-
Corporate Authors:
American Society of Civil Engineers
1801 Alexander Bell Drive
Reston, VA United States 20191-4400 -
Authors:
- Izzetoglu, M
- Jiao, X
- Park, S
- Publication Date: 2021
Language
- English
Media Info
- Pagination: pp 367 - 377
- Monograph Title: International Conference on Transportation and Development 2021: Transportation Operations, Technologies, and Safety
Subject/Index Terms
- TRT Terms: Behavior; Cognition; Data analysis; Data files; Drivers; Driving simulators; Fatalities; Infrared spectroscopy; Innovation; Machine learning; Remote sensing; Young adults
- Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;
Filing Info
- Accession Number: 01777559
- Record Type: Publication
- ISBN: 9780784483534
- Files: TRIS, ASCE
- Created Date: Jul 23 2021 3:26PM