Abstract
In this paper, the expressway traffic flow prediction model based on the Bi-LSTM is designed, and four sections of expressway are applied to the model for training and evaluation. Through training and verification, the results show that the average prediction accuracy, MAPE, RMSE, and MAE of the proposed model is 89.54%, 10.46%, 31.55, and 24.58, respectively. In addition, in order to evaluate the effect of the proposed model, this paper introduces the ARIMA model for comparison. It is found that the prediction accuracy of the Bi-LSTM is 18.30% higher than ARIMA, the RMSE is reduced by 31.85, and the MAE is reduced by 26.32. The results show that the proposed Bi-LSTM model exhibits higher prediction performance. Afterwards, this paper makes a comparative analysis of the predicted value and the original value of each road section. The results show that the proposed model has a certain lag, and the forecast value of traffic flow is low for rush hours, however, the forecast value of traffic flow is higher in the low peak hours.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IOP Conference Series: Earth and Environmental Science
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
