Title
Deep Hybrid Attention Framework for Road Crash Emergency Response Management
Author
Kashifi, M.T.K. (TU Delft Transport and Planning)
Date
2024
Abstract
Road traffic crash is a global tragedy that leads to economic loss, injury, and fatalities. Understanding the severity of a road crash at the early stages is vital to timely providing emergency medical services to crash victims. This study developed a crash emergency response management framework that requires basic crash information for emergency response decision-making. A Deep Hybrid Attention Network (DHAN) was proposed that captures temporal variations and spatial correlations for dynamic severity prediction. Further, two alternative model architectures that initially required only the approximate location or time of the crash were proposed and compared with the DHAN. The experiment was conducted on seven years French road crash dataset (2011-2017). The DHAN achieved an AUC of 0.820, an accuracy of 0.761, a recall of 0.803, and a false alarm rate of 0.258, outperforming baseline models.
Subject
Analytical models
attention mechanism
Computer crashes
crash severity
Deep learning
emergency response management
Injuries
Long short term memory
Medical services
Predictive models
real-time prediction
Roads
To reference this document use:
http://resolver.tudelft.nl/uuid:014543ad-7969-4cef-baa0-756dc2c07b51
DOI
https://doi.org/10.1109/TITS.2024.3376653
Embargo date
2024-09-28
ISSN
1524-9050
Source
IEEE Transactions on Intelligent Transportation Systems
Bibliographical note
Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.
Part of collection
Institutional Repository
Document type
journal article
Rights
© 2024 M.T.K. Kashifi