TY - JOUR
T1 - The importance of flow composition in real-time crash prediction
AU - BASSO SOTZ, FRANCO FABIAN
AU - Basso, Leonardo J.
AU - Pezoa, Raul
N1 - Funding Information:
We thank Autopista Central, and particularly Cindy Carmona, Elena Hurtado, Victor Montenegro and Christian Barrientos for providing us with data and collaborating enthusiastically with the project. We gratefully acknowledge financial support from Fondecyt 1191010 and CONICYT PIA/BASAL AFB180003.
Publisher Copyright:
© 2020 Elsevier Ltd
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
PY - 2020/3
Y1 - 2020/3
N2 - Previous real-time crash prediction models have scarcely used data disaggregated by vehicle type such as light, heavy and motorcycles. Thus, little effort has been made to quantify the impact of flow composition variables as crash precursors. We analyze the advantages of having access to this data by analyzing two scenarios, namely, with aggregated and disaggregated data. For each case, we build Logistics Regressions and Support Vector Machines models to predict accidents in a major urban expressway in Santiago, Chile. Our results show that having access to disaggregated data by vehicle type increases the prediction power up to 30 % providing, at the same time, much better intuition about the actual traffic conditions that may lead to accidents. These results may be useful when evaluating technology investments and developments in urban freeways.
AB - Previous real-time crash prediction models have scarcely used data disaggregated by vehicle type such as light, heavy and motorcycles. Thus, little effort has been made to quantify the impact of flow composition variables as crash precursors. We analyze the advantages of having access to this data by analyzing two scenarios, namely, with aggregated and disaggregated data. For each case, we build Logistics Regressions and Support Vector Machines models to predict accidents in a major urban expressway in Santiago, Chile. Our results show that having access to disaggregated data by vehicle type increases the prediction power up to 30 % providing, at the same time, much better intuition about the actual traffic conditions that may lead to accidents. These results may be useful when evaluating technology investments and developments in urban freeways.
KW - Automatic vehicle identification
KW - Flow composition
KW - Logistic regression
KW - Real-time crash prediction
KW - Support vector machines
UR - http://www.scopus.com/inward/record.url?scp=85078670661&partnerID=8YFLogxK
U2 - 10.1016/j.aap.2020.105436
DO - 10.1016/j.aap.2020.105436
M3 - Article
C2 - 32014629
AN - SCOPUS:85078670661
VL - 137
JO - Accident Analysis and Prevention
JF - Accident Analysis and Prevention
SN - 0001-4575
M1 - 105436
ER -