Title :
A neural network application in signal timing control
Author :
Chin, Daniel C. ; Smith, Richard H.
Author_Institution :
Appl. Phys. Lab., Johns Hopkins Univ., Laurel, MD, USA
Abstract :
Generally the most cost-effective means of achieving optimized vehicle flow through a given road network is by improving the timing of traffic signals at network intersections. This paper uses neural networks (NN) as the bases for the control law. The NN weight estimation occurs real time in closed-loop mode via the simultaneous perturbation stochastic approximation algorithm. The approach results in a net 10-percent reduction in vehicle wait time over the performance of the existing, in-place strategy
Keywords :
approximation theory; neural nets; road traffic; traffic control; closed-loop mode; network intersections; optimized vehicle flow; road network; signal timing control; simultaneous perturbation stochastic approximation algorithm; traffic signals; vehicle wait time; weight estimation; Automatic control; Centralized control; Communication system traffic control; Control systems; Intelligent networks; Neural networks; Roads; Timing; Traffic control; Vehicles;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.549226
