Citation

Das S, Dutta A, Sun X. J. Transp. Saf. Secur. 2020; 12(9): 1083-1105.

Copyright

(Copyright © 2020, Southeastern Transportation Center, and Beijing Jiaotong University, Publisher Informa - Taylor and Francis Group)

DOI

10.1080/19439962.2019.1572681

PMID

unavailable

Abstract

Driving in rainy weather is considered as one of most hazardous conditions for driving. There is a need for appropriate countermeasures focusing on the reduction of these crashes, but measuring the key factors under such conditions is very challenging. With a humid subtropical climate, the annual precipitation in Louisiana is about 64 inches, twice above the national average. Approximately 11% of total crashes in Louisiana happen during rainy weather, and nearly 25% of total fatal crashes happen in rainy weather annually. This study applied association rules mining to discover crash patterns during rainy weather with Louisiana crash data (2004-2011). The findings showed that "single-vehicle run-off road crash" is predominant during rainy weather and is associated with grade-curve aligned roadways, curved roadways, and roadways with no streetlights at night. In rainy condition, no injury and sideswipe crashes are also significant in numbers. Moderate injuries are dominant in single-vehicle crashes. Roadways with poor illumination are associated with straight, level aligned roadways in rainy weather crashes. Drivers (age 15 - 44) are vulnerable in run-off crashes when the roadways had poor illumination and curves during rainy condition. The findings of this study will be beneficial for safety practitioners.

Language: en

Keywords

association rules; data mining; market basket analysis; nonparametric statistical method; road safety