Road traffic flow prediction method in first-tier cities based on neural network algorithm

Traffic flow prediction is one of the key research topics in the field of smart city and intelligent transportation system. Accurate traffic flow prediction is of great significance in traffic grooming and effective deployment of signal lights. In this paper, the D-FNN method in the neural network algorithm was introduced into the prediction of road traffic flow in four first-tier cities such as Beijing, Shanghai, Guangzhou, and Shenzhen in China. Besides, the predictive effect was verified by the regularized root mean square error and the equalization coefficient. Finally, it’s concluded that the regularized root mean squared error (RMSE) and the equalization coefficient of the traffic flow predicted values and actual values in the four first-tier cities obtained by the D-FNN method are close to the ideal values, indicating that the prediction accuracy is higher and the D-FNN method can effectively predict traffic flow. This can provide theoretical and practical references for the prediction of traffic flow in Chinese cities.