Dynamic Division about Traffic Control Sub-area Based on Back Propagation Neural Network

This paper, based on Back Propagation (BP) neural network, proposes a method to divide traffic control sub-area dynamically. Considering three factors - traffic flow, distance of intersections and cycle, it forecasts the coordinatability factor and divides traffic control sub-area. It provides the design of neural network structure, carrying on a simulation experiment with the help of MATLAB which shows that the method is feasible without establishing a precise mathematical model, and the calculation is simple and easy to do.