Title :
Feed-forward and RTRL neural networks for the macroscopic traffic flow prediction and monitoring: the potential of each other
Author :
Messai, Nadhir ; Thomas, Philippe ; El Moudni, Abdellah ; Leclercq, Edouard ; Druaux, Fabrice ; Lefebvre, Dimitri
Author_Institution :
UTBM, Belfort, France
Abstract :
This paper is about traffic flow short term prediction and monitoring based on magnetic sensors measurements. For these purposes, the advantages and drawbacks of feed-forward and real time recurrent learning neural networks are investigated. Structures determination, weights initialization, networks training and automatic incidents detection are discussed.
Keywords :
computerised monitoring; feedforward neural nets; learning (artificial intelligence); magnetic sensors; recurrent neural nets; traffic engineering computing; RTRL neural networks; automatic incidents detection; feedforward neural networks; macroscopic traffic flow monitoring; macroscopic traffic flow prediction; magnetic sensor measurements; networks training; real time recurrent learning neural networks; structures determination; weights initialization; Equations; Feedforward neural networks; Feedforward systems; Feeds; Fluid flow measurement; Magnetic sensors; Monitoring; Neural networks; Telecommunication traffic; Traffic control;
Conference_Titel :
Intelligent Transportation Systems, 2003. Proceedings. 2003 IEEE
Print_ISBN :
0-7803-8125-4
DOI :
10.1109/ITSC.2003.1251948
