KASSANDRA Model: Detecting Dangerous Traffic Conditions By Modeling Drivers’ Internal Stress Energy

Nikolaos Nagkoulis1, 2
, Dimitrios Nalmpantis1, *
, Nick Bearman2

1 School of Civil Engineering, Faculty of Engineering, Aristotle University of Thessaloniki, PO Box 452, 541 24 Thessaloniki, Greece
2 Department of Geography, Faculty of Social and Historical Sciences, University College London, Pearson Building, Gower Street, London WC1E 6BT, United Kingdom

Article Metrics

CrossRef Citations:
Total Statistics:

Full-Text HTML Views: 318
Abstract HTML Views: 204
PDF Downloads: 166
ePub Downloads: 128
Total Views/Downloads: 816
Unique Statistics:

Full-Text HTML Views: 206
Abstract HTML Views: 160
PDF Downloads: 154
ePub Downloads: 122
Total Views/Downloads: 642

Creative Commons License
© 2024 The Author(s). Published by Bentham Open.

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at the School of Civil Engineering, Faculty of Engineering, Aristotle University of Thessaloniki, PO Box 452, 541 24 Thessaloniki, Greece; Tel: +30-2310-995811; E-mail:



This paper introduces an innovative method to reduce car accidents by employing mechanical concepts and energy conservation to model drivers’ reactions in unexpected scenarios.


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!


The equations developed offer a promising tool for estimating and preventing car accidents by modeling the influence of drivers’ stress on driving behavior.

Keywords: Crash prediction, Spatiotemporal dynamics, Traffic psychology, Internal stress energy, Road safety, Behavior modeling.