Traffic flow prediction based on convolutional neural network and long and short-term memory network

Under the development demand of intelligent transportation systems, the accuracy of our algorithms for traffic flow prediction has been gradually improved, and the algorithms for traffic flow prediction have gone through the three stages of time series models, traditional machine learning class models and deep learning class models. Recognizing the complexity and nonlinear topological relationship of traffic flow data, this study simulates the fitting of time-series feature data in the same space with two methods of deep learning models, convolutional neural network and long and short-term memory network. From the simulation results, both models constructed in this study are within the error tolerance, and the prediction results of the long and short-term memory network are better than those of the convolutional neural network.