Prediction of Residents' Travel Modes Based on GA-BP Neural Network

In order to make up for the shortcomings of the traditional transportation mode split model and improve the accuracy of travel mode prediction, this paper uses genetic algorithm-back propagation (GA-BP) neural network to predict residents' travel mode. This paper firstly uses SPSS to analyze the factors that influence the choice of travel mode and studies the influence of individual, family and travel characteristics on the choice of travel modes. Then the paper establishes the GA-BP neural network using Matlab and uses the survey data of residents in a city in southwest China as the examples of analysis. By selecting different numbers of hidden layer neurons, the accuracy of the total prediction and each travel modes' prediction is compared. The results show that the GA-BP neural network has higher prediction accuracy, which indicates that the GA-BP neural network can be better applied to the prediction of residents' travel modes.