The Prediction of Collisions in Connected Vehicle Systems with A Long Short-Term Memory Model

Abstract

The advances in connected vehicle systems (CVS) allow vehicles to communicate with each other and with infrastructures via wireless communication networks. This technology enables vehicles to detect potential hazards on the road, generate warnings, and assist the driver in taking preventive actions. To date, few mathematical models have been developed to predict the collision rates in connected vehicle systems. In this work, a Long Short-Term Memory model (LSTM) using time-series data of human drivers was developed to predict the collision rates in CVS by quantifying warning parameters and hazard scenario features. The model was validated with the driving performance data before and after warnings from thirty-two drivers in a behavioral experiment. The results indicated the LSTM model showed a prediction accuracy of 74% higher than SVM and logistic regression models. The LSTM model showed the potential to help optimize the warning algorithm in the connected vehicle systems to improve driver safety.