Title | ||
---|---|---|
Optimal neural networks architectures for the flow–density relationships of traffic models |
Abstract | ||
---|---|---|
Urban traffic is a complex process that is often described by macroscopic flow models. Anyway, the parameters identification of these models remains a heavy work. This paper proposes neural networks architectures that are inspired from the general form of the well-known traffic model but which have the advantage to be easier in identification and which track real traffic data more correctly. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1016/S0378-4754(02)00032-0 | Mathematics and Computers in Simulation |
Keywords | Field | DocType |
Traffic model,Neural networks,Flow–density relationship | Flow network,Mathematical optimization,Traffic flow,Simulation,Flow (psychology),Traffic model,Systems architecture,Artificial neural network,Traffic engineering,Mathematics,Feed forward,Distributed computing | Journal |
Volume | Issue | ISSN |
60 | 3 | 0378-4754 |
Citations | PageRank | References |
3 | 0.59 | 2 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nadhir Messai | 1 | 19 | 4.13 |
P. Thomas | 2 | 78 | 12.59 |
Dimitri Lefebvre | 3 | 362 | 52.36 |
Abdellah El Moudni | 4 | 153 | 26.13 |