Motorcycles are more prone to serious crashes than other motor vehicles. To analyze factors affecting crash severity in single motorcycle crashes, we tested five classification algorithms. Additionally, to handle the data imbalance embedded in the crash data, we collected data from the National Collision Database of Canada. This study proposes seven data preprocessing approaches. To compare the classification performance of different algorithms, the G-mean (geometric mean) is used. Results indicate that XGBoost and RandomOverSampler are the best combination method, with a G-mean of 0.593, 339% higher than the original model (0.135). The SHAP summary plot reveals that the following features play an important role in classifying injury severity in motorcycle crashes: road safety use, road alignment, traffic control, roadway configuration, road surface, person age, person sex, collision configuration, and weather condition. These results are useful to guide government agencies to develop policies or standards to alleviate the severity of motorcycle crashes.
Analysis of Factors Affecting Injury Severity in Motorcycle Involved Crashes
20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)
CICTP 2020 ; 4207-4219
2020-08-12
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Large Truck-Involved Crashes: Exploratory Injury Severity Analysis
British Library Online Contents | 2013
|Large Truck–Involved Crashes: Exploratory Injury Severity Analysis
Online Contents | 2013
|Severity of motorcycle crashes in Calgary
Elsevier | 2011
|