Research on neural network and application in traffic rules extraction

This paper studied the knowledge reduction problem and discrete continuous attributes and improved the BP neural network. Firstly, methods of attribute reduction of classical are analysis. It establishes the one-dimensional cellular automata model to analyze the performance of right rule in light and heavy traffic in this paper. Subsequently, we can get the change trend of road vehicle density by the simulation of traffic flow. The data shows that the vehicle maximum density is 164veh/km. The decision rules obtained after reduction in order to map to the training sample of neural network. Finally, the simulation results show that the integration of rough set and neural network has obvious complementary and reduce the time to train the neural network.