Prediction of Entering Percentage into Expressway Service Areas Based on Wavelet Neural Networks and Genetic Algorithms

Abstract

The study on the vehicle pause rate in the expressway service area provides a theoretical basis for the evaluation and layout optimization of the social and economic adaptability of the expressway service area. This paper constructs a prediction model based on the analysis of explanatory variables using wavelet neural network (WNN) and genetic algorithm (GA). Eight variables, such as major road traffic flow and the distances to neighboring service areas, are selected as input parameters. The pause rates of a freight truck and passenger car are the prediction output. The data from 23 pairs of service areas in Henan province are used to train the model. The GA is used to optimize the initial weights, thresholds, and translation coefficients of the WNN. The experimental results show that the GA-WNN model has a higher prediction precision and a better fitting ability compared with the GA-BP and the WNN prediction models, which can overcome the shortcomings of slow convergence and local optimum of traditional WNN, and combine the advantages of GA and WNN to improve prediction accuracy effectively. The research of this paper can provide new ideas and methods to pause rate prediction of the expressway service area.