Key feature selection and risk prediction for lane-changing behaviors based on vehicles’ trajectory data

Abstract

Risky lane-changing (LC) behavior of vehicles on the road has negative effects on traffic safety. This study presents a research framework for key feature selection and risk prediction of car’s LC behavior on the highway based on vehicles’ trajectory dataset. To the best of our knowledge, this is the first study that focuses on key feature selection and risk prediction for LC behavior on the highway. From the vehicles’ trajectory dataset, we extract car’s candidate features and apply fault tree analysis and k-Means clustering algorithm to determine the LC risk level based on the performance indicator of Crash Potential Index (CPI). Random Forest (RF) classifier is applied to select key features from car’s candidate features and predict LC risk level. This study also proposes a method to evaluate the resampling methods to resample the LC risk dataset in terms of fitness performance and prediction performance. The cars’ trajectory data collected from the Next Generation Simulation (NGSIM) dataset is used for framework development and verification. The sensitivity analysis of CPI indicates that the following cars in the original lane and target lane are respectively the safest and riskiest cars of the surrounding cars in an LC event. The results of resampling method evaluation show that SMOTETomek, which is less likely to be overfitting and has high prediction performance, is well suited for resampling the LC risk dataset on which RF classifier is trained. The results of key feature selection imply that the individual behaviors of the LC car and its surrounding cars in the original lane, the interactions between the LC car and its surrounding cars, and the interactions between the surrounding cars in the target lane (especially the interaction of the cars’ accelerations) are of importance to the LC risk.