In the Melbourne metropolitan area in Australia, an average of 34 pedestrians were killed every year between 2004 and 2013 in traffic crashes, and vehicle–pedestrian crashes accounted for 24% of all fatal crashes. Mid-block crashes accounted for 46% of the total pedestrian crashes in the Melbourne metropolitan area and 49% of the pedestrian fatalities occurred at mid-blocks. This study developed three models using different decision trees (DTs) to identify the factors contributing to the severity of pedestrian crashes. To improve the accuracy, stability and robustness of the DTs, bagging and boosting techniques were used in this study. The results of this study showed that the boosting technique improved the accuracy of individual DT models by 46%. Moreover, the results of boosting DTs showed that neighbourhood social characteristics were as important as traffic and infrastructure variables in influencing the severity of pedestrian crashes.
Modelling pedestrian crash severity at mid-blocks
Transportmetrica A: Transport Science ; 13 , 3 ; 273-297
16.03.2017
25 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
A Multinomial Logit Model of Pedestrian-Vehicle Crash Severity
Taylor & Francis Verlag | 2011
|A Multinomial Logit Model of Pedestrian-Vehicle Crash Severity
Online Contents | 2011
|A Hierarchical Modeling Approach to Predict Pedestrian Crash Severity
Springer Verlag | 2019
|Evaluation of Pedestrian Safety: Pedestrian Crash Hot Spots and Risk Factors for Injury Severity
Online Contents | 2013
|Analysis of vehicle pedestrian crash severity using advanced machine learning techniques
DOAJ | 2023
|