Deep Q-learning Network-based Imbalanced Classification for Fatality Prediction of Single-Vehicle Motorcycle Crashes

Abstract Even though the number of motorcycle crash accidents in Japan has trended downward over the past decade, there persists a necessity to propose effective safety measures targeting factors associated with fatal crash accidents. Previous studies have demonstrated the utility of various machine-learning models in classifying and investigating crash accidents involving motorcycles. However, the comprehensive examination of fatal cases in single-vehicle motorcycle crashes remains limited due to imbalanced crash data between fatal and non-fatal cases. Despite the ability of several conventional machine learning (ML) models to predict motorcycle crash severity, the imbalanced single-vehicle crash data poses a challenge in accurately classifying fatal crashes using ML models. To address this challenge, the deep q-learning network-based imbalanced classification (DQNIC), a modification of Lin’s DQNimb, was employed to classify single-vehicle motorcycle crashes (fatal and non-fatal). Moreover, SHAP value analysis was utilized to interpret the DQNIC model and explore the factors associated with fatal crashes. The 4-year crashes in Japan nationwide are used for empirical study. The significant findings indicate 1) that the DQNIC model demonstrates effective classification of fatal crashes and 2) that factors such as the crash type, road width, terrain, road alignment, and collision point exert significant influence on fatal crashes. Traffic safety professionals can use the findings of this study to implement effective measures to reduce the fatality rate of single-vehicle motorcycle crashes.