Citation

Wang XH. Adv. Transp. Stud. 2022; (SI 2): 123-132.

Copyright

(Copyright © 2022, Arcane Publishers)

DOI

unavailable

PMID

unavailable

Abstract

An intersection traffic direction prediction method based on wavelet neural network is proposed. The delay coordinate state phase space reconstruction method is used to reconstruct the time series of intersection public transport direction, and the correlation statistics of nonlinear time series are expressed by the correlation integral of the series. Taking statistical data as samples, a wavelet neural network model for intersection traffic direction prediction is established. The results show that compared with the method based on crowdsourcing scheme, the traffic direction prediction error of this method is significantly reduced, and the maximum error is no more than 0.1%, which can better meet the requirements of traffic flow direction prediction.

Language: en

Keywords

Models; Transportation; Vehicles