Multisource fusion of exogenous inputs based NARXs neural network for vehicle speed prediction between urban road intersections

Abstract

The economy and safety of passages through the urban road intersection environment is an important research topic in the field of intelligent transportation systems, but vehicle speed prediction as its subtopic is still under-researched, and its prediction accuracy is unsatisfactory. Therefore, a model for vehicle speed prediction based on the nonlinear autoregressive model with multisource exogenous inputs (NARXs) neural network is proposed. The model combines the human-vehicle-road model with the NARXs neural network to perform speed prediction between urban road intersections. First, multisource features, including the variables of driving behavior characteristics, vehicle responses, and road conditions, are extracted to construct the human-vehicle-road model. Then, the model is introduced into the NARXs neural network. Finally, the advantages of the proposed model are verified from two perspectives by evaluation indices such as mean absolute error ( MAE), mean absolute percentage error ( MAPE), root mean square error ( RMSE), Theil index ( Theil ic), and goodness-of-fit ( R2) compared with several other models. On the one hand, the analysis results show that the proposed model has higher prediction accuracy than the other comparative models for different prediction durations and has the best performance in 30 s duration backward prediction. On the other hand, the curves of each evaluation index of the proposed model are horizontal, which indicates that the prediction performance of the model hardly varies with the length of the training dataset. These positive results demonstrate the higher accuracy and outstanding characteristics of the proposed model in the subject of vehicle speed prediction.

A Comparative Study of Vehicle Velocity Prediction for Hybrid Electric Vehicles Based on a Neural Network

“…Based on the network architecture of the BPNN used, a non-linear auto-regressive model with exogenous inputs (NARX) is proposed by adding delay and feedback mechanisms to enhance the memory ability of historical data, which can converge more rapidly and generalize well with a lower sensitivity to long-term dependencies. Zhang et al [12] constructed a VVP model with a NARX NN, and the model's prediction accuracy was validated by means of simulation comparison. Although feedforward neural networks (FNNs) and their variants are good at modeling non-linear characteristics, as shown in Figure 2a, they are only applicable for one-to-one prediction.…”