Traffic Jam Prediction through Elman Neural Network Based on Monte Carlo Simulation
2014 ◽
Vol 551
◽
pp. 675-678
◽
Keyword(s):
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.
2013 ◽
Vol 46
(3)
◽
pp. 535-545
◽
Keyword(s):
2014 ◽
Vol 599-601
◽
pp. 2083-2087
Keyword(s):
2013 ◽
Vol 18
◽
pp. 11-17
◽
Keyword(s):
2009 ◽
Vol 72
(10)
◽
pp. 2078-2087
◽
Keyword(s):
Keyword(s):