Severity Analyses of Single-Vehicle Crashes Based on Rough Set Theory

A single-vehicle crash is a typical pattern of traffic accidents and tends to cause heavy loss. The purpose of this study is to identify the factors significantly influencing single-vehicle crash injury severity, using a data selected from Beijing city for a 4-year period. Rough set theory was applied to complete the injury severity analysis, and followed by applying cross-validation method to estimate the prediction accuracy of extraction rules. Results show that it is effective for analyzing the severity of single-vehicle crashes with rough set theory.