Traffic Volume Prediction Using Improved Kalman Filter

Abstract

Traffic volume prediction has been an interesting topic for decades during which various prediction models have been proposed. In this paper, Kalman filtering (KF) model is applied to predict traffic volume because of its significance in continuously updating the state variable as new observations. In order to enhance the prediction accuracy, an improved KF model is developed based on the current and historical data. To validate the improved KF model, empirical analysis is conducted. The results show that the improved KF model has higher accuracy than the traditional one and is more reliable and powerful in traffic volume prediction.