This paper simulates the traffic flow at upper stream intersection and the actual traffic flow at cross section of accident, and calculates the time for the queue to reach the upper stream intersection through Elman neural network. The result of 500 simulations shows that the probability for the time of the queue length being 140m: in [2.5min~3.5min] is 39.6% and in [3.5min~4min] is 52.0%. The total is 91.6%, which is highly precise. The prediction of queue length of post-accident traffic jam is of great importance to a quick recovery.
Traffic Jam Prediction through Elman Neural Network Based on Monte Carlo Simulation
Applied Mechanics and Materials ; 551 ; 675-678
2014-05-09
4 pages
Article (Journal)
Electronic Resource
English
Short-term traffic flow prediction method based on GWO-Elman neural network
European Patent Office | 2023
|Traffic Prediction of Mobile Communication Base Station Based on Elman Neural Network Model
Springer Verlag | 2024
|Elman neural network-based temperature prediction and optimization for lithium-ion batteries
SAGE Publications | 2024
|