Applying back-propagation neural network to predict bus traffic

In order to devise bus lines and make daily scheduling more precisely, this paper uses Back-Propagation(BP) neural network to predict bus traffic. As the time factor and meteorological factor are the two important factors which affect traffic, this paper does the data preprocessing for bus data in Guangzhou from August to December in 2014. BP neural network's information processing capacity is determined by the input and output neurons' characteristics, the network structure, the connection weights. The complexity of the neural network structure affects the performance of the neural network. The more complex the network structure is, the better fitted the model will be, meanwhile, it is easy to be over-fitting to the training data and its generalization performs inefficiently. If the network structure is too simple, it can't learn training data very well, and the network can't be converged well and the accuracy of data fitting can't be guaranteed. This paper conducts several experiments to determine the network structure and parameters which are suitable for prediction of bus traffic. Trough Ten-fold cross-validation experiments, the model is demonstrated being able to apply to bus traffic forecast.