Elahe Abbasi, Yueqing Li, Xing Wu, Brian Craig
Vehicle crash is one of the leading causes of deaths and results in around 1.35 million fatalities in the world each year. As one of the busiest ports in the United States, Beaumont (TX) has a lot of heavy vehicles in its traffic flow. Between 2010 and March 2019, there were a total of 37,984 crashes involving 103,407 persons in Beaumont. This study identifies the factors influencing crash injury severity on Beaumont. Yet, not only the conventional roadway and temporal factors but also environmental characteristics which need particular attention were considered in the this research. To identify the critical factors influencing crash severity, Classification and Regression Trees (CART) method was used. The CART model had an accuracy of 62% in prediction. The results indicated that “light condition”, “crash time” and “weather condition” are three factors that affect the crash severity. The current investigation can help researchers and policymakers to achieve a better understanding of traffic crashes in humid subtropical climate port cities and assist decision-makers to make more efficient decisions.
Crash Severity, Classification, Regression, Classification and Regression Trees (CART), Data Mining
Cite this paper
Elahe Abbasi, Yueqing Li, Xing Wu, Brian Craig. (2021) Using Classification and Regression Trees (CART) to Identify Factors Contributing to Vehicle Crash Severity in a Port City. International Journal of Transportation Systems, 6, 29-38