Steering Wheel Behavior Based Estimation of Fatigue

This paper examined a steering behavior based fatigue monitoring system. The advantages of using steering behavior for detecting fatigue are that these systems measure continuously, cheaply, non-intrusively, and robustly even under extremely demanding environmental conditions. The expected fatigue induced changes in steering behavior are a pattern of slow drifting and fast corrective counter steering. Using advanced signal processing procedures for feature extraction, we computed 3 feature set in the time, frequency and state space domain (a total number of 1251 features) to capture fatigue impaired steering patterns. Each feature set was separately fed into 5 machine learning ethods (e.g. Support Vector Machine, K-Nearest Neighbor). The outputs of each single classifier were combined to an ensemble classification value. Finally the authors combined the ensemble values of 3 feature subsets to a of meta-ensemble classification value. To validate the steering behavior analysis, driving samples are taken from a driving simulator during a sleep deprivation study (N=12). The authors yielded a recognition rate of 86.1% in classifying slight from strong fatigue.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/139780874141627
• Corporate Authors:

  University of Iowa, Iowa City

  Public Policy Center
  227 South Quadrangle
  Iowa City, IA  United States  52242-1192
• Authors:
  • Krajewski, Jarek
  • Sommer, David
  • Golz, Martin
  • Trutschel, Udo
  • Edwards, David J
• Conference:
  • Driving Assessment 2009: 5th International Driving Symposium on Human Factors in Driving Assessment, Training and Vehicle Design
  • Location: Big Sky MT, United States
  • Date: 2009-6-22 to 2009-6-25
• Publication Date: 2009

Language

• English

Media Info

• Media Type: Print
• Features: CD-ROM; Figures; References; Tables;
• Pagination: pp 118-124
• Monograph Title: Proceedings of the 5th International Driving Symposium on Human Factors in Driver Assessment and Design

Subject/Index Terms

• TRT Terms: Behavior; Driver monitoring; Driving simulators; Fatigue (Physiological condition); Human factors in crashes; Steering; Steering wheels; Traffic safety; Travel behavior
• Subject Areas: Highways; Safety and Human Factors; I83: Accidents and the Human Factor;

Filing Info

• Accession Number: 01157984
• Record Type: Publication
• ISBN: 139780874141627
• Files: TRIS
• Created Date: May 30 2010 7:44AM