Prediction and interpretation of crash severity using machine learning based on imbalanced traffic crash data.

Journal: Journal of safety research
Published Date: Jul 1, 2025

Abstract

INTRODUCTION: Predicting and interpreting crash severity is essential for developing cost-effective safety measures. Machine learning (ML) models in crash severity studies have attracted much attention recently due to their promising predicted performance. However, the limited interpretability of ML techniques is a common critique. Additionally, the inherent data imbalance in crash datasets, mainly due to a scarcity of fatal injury (FI) crashes, presents challenges for both classifiers and interpreters.

Authors

  • Junlan Chen
    School of Transportation, Southeast University, No.2 Southeast University Road, Nanjing 211189, China; Department of Civil Engineering, Monash University, Melbourne, Australia. Electronic address: junlan.chen@monash.edu.
  • Pei Liu
    School of Life Sciences, Nanjing University, State Key Laboratory of Pharmaceutical Biotechnology, Nanjing 210000, China.
  • Shuo Wang
    College of Tea & Food Science, Anhui Agricultural University, Hefei, China.
  • Nan Zheng
    Key Laboratory of Industrial Biotechnology, Ministry of Education, School of Biotechnology, Jiangnan University, Wuxi, PR China.
  • Xiucheng Guo
    School of Transportation, Southeast University, No.2 Southeast University Road, Nanjing 211189, China. Electronic address: seuguo@163.com.

Keywords

External Resources

Popular Topics
Recent Journals