Application of Advanced Machine Learning Paradigms for Injury Severity Modelling of Motor Vehicle Crashes on Rural Highways in Saudi Arabia
Traffic safety is a major public health issue worldwide. The Kingdom of Saudi Arabia (KSA) is facing alarming road safety concerns with traffic-related injuries being the third leading cause of fatalities in the country. A better understanding of factors influencing injury severity outcomes of traffic crashes is vital for the proactive and effective implementation of suitable countermeasures. Various non-parametric machine learning (ML) based techniques have been increasingly used lately to address the drawbacks of statistical schemes for modeling the injury severity of traffic crashes. The dissertation examines the application of six different ML algorithms for injury severity prediction of traffic crashes based on three years data on interstate rural highways in KSA. Injury severity modeling performance of proposed algorithms was assessed in terms of various evaluation indices. Experimental results revealed that some models outperformed others based on the selected evaluation metrics. To address the ML model's non-interpretability issue, feature importance and SHAP analysis were also employed. An analysis of several significant factors which aggravate the chances of fatal and severe injuries was done. The study also proposes the application of the Information Root Node Variation (IRNV) technique for extraction of significant decision rules highlighting the circumstances for the categorization of specific crash injury severity instances. For comparison purposes, multinomial logit (MNL) models were also developed and the consistency of injury severity risk factors between MNL and ML models was investigated. The outcomes and findings of the current study can yield valuable insights to safety practitioners for timely and effective implementation of suitable mitigation measures.