Road Speed Fusion Model Based on Wavelet Neural Network Optimized by Genetic Algorithm

摘要

Traffic conditions of the city is the important part in the Intelligence Transport Systems (ITS). In recent years, improving the accuracy of the traffic conditions information is still a significant issue. This paper proposes a new multi-source data fusion model based on the combination of the Genetic Algorithm and the Wavelet Neural Network to promote the low accuracy on the road condition. First, the paper separately analyzes the characteristics of the traffic conditions information expressed by the two data sources. A suitable sample set is selected, which is based on the Green-Shields traffic flow model. Second, this paper presents a data fusion model based on Wavelet Neural Network optimized by Genetic Algorithm. Finally, the parameters are adjusted to iteratively optimize the model according to the characteristics of the data source. The experimental results are verified by using the road test speed. The relative error in the average speed of the road is reduced by approximately 20%.