The 20th and 21st joint COTA International Conference of Transportation Professionals (CICTP 2020-21)

Ensemble learning algorithms train multiple component learners and then combine their predictions. Based on optimizing the diversity of component learners, we proposed a method of short-time traffic state prediction-NNPDAP. In this paper, the perturbation of training data set, input attribute and learning parameter are used to construct eight perturbation modes for optimizing the diversity of component learners. There have built three groups of experiments respectively for comparing the accuracy of traffic state prediction, error distribution, and time efficiency. The experimental results show that, by enhancing the diversity of component learners it can improve the prediction accuracy and robustness, NNPDAP has a stronger competitiveness compared with no perturbation method.

CICTP