All published articles of this journal are available on ScienceDirect.
KASSANDRA Model: Detecting Dangerous Traffic Conditions By Modeling Drivers’ Internal Stress Energy
iD
Nick Bearman2
iD
Authors Info & Affiliations
Abstract
Introduction
This paper introduces an innovative method to reduce car accidents by employing mechanical concepts and energy conservation to model drivers’ reactions in unexpected scenarios.
Methodology
The approach involves formulating equations to define drivers’ “internal stress energy,” indicative of their propensity for aggressive driving under time pressure. A spatiotemporal model was developed using traffic data from Highways England and accident data from Transport for London, analyzing around 200 car accidents with data from 80 cameras over two years.
Results and Discussion
Findings suggest a correlation between drivers’ internal stress energy and car accidents, highlighting the predictive value of the proposed equations in assessing road segment dangers. More specifically, using the proposed model with 15-minute timeframes increased car accident prediction four (4) times compared to the evenly spatiotemporal car accident distribution. With smaller timeframes, e.g., two (2) minutes, or with real-time data, its predictive power would be significantly higher!
Conclusion
The equations developed offer a promising tool for estimating and preventing car accidents by modeling the influence of drivers’ stress on driving behavior.
