Abstract
The behavioral measures such as neck vending angle and tracking error in steering maneuvering during the simulated driving task was recorded under the low arousal condition of all participants who stayed up all night without sleeping. We conducted trend analysis where time and the behavioral measure of drowsiness corresponded to an independent variable and a dependent variable, respectively. Applying the trend analysis technique to the experimental data of participants from whom the point in time when the participant would have encountered a crucial accident if he or she continued driving a vehicle (virtual accident), we proposed a method to predict in advance (before virtual accident occurs) the point in time with high risk of crash. By applying the proposed trend analysis method to behavioral measures, we found that the proposed approach could identify the point in time with high risk of crash and eventually predict in advance the symptom of the occurrence of point in time of virtual accident.
Original language | English |
---|---|
Pages (from-to) | 2434-2441 |
Number of pages | 8 |
Journal | Procedia Manufacturing |
Volume | 3 |
DOIs | |
Publication status | Published - 2015 |
Keywords
- Behavioral measures
- Point in time of crash
- Prediction of drowsiness
- Trend analysis
ASJC Scopus subject areas
- Industrial and Manufacturing Engineering
- Artificial Intelligence