Short-term traffic flow prediction method based on deep method

Abstract

The weather data and traffic intersection passing data are firstly analyzed and preprocessed, and then input into a threshold cyclic neural network (GRU) to extract high-order features of the trafficflow, and the high-order features are input into a gradient lifting decision tree regression model (GBDT) for short-term traffic flow prediction. The method provided by the invention can carry out more in-depth mining analysis on the traffic flow data, and can effectively improve the accuracy of short-term traffic flow prediction after the output layer is changed to GBDT.

Description

technical field [0001] The invention belongs to the technical field of traffic forecasting, in particular to a short-term traffic flow forecasting method based on deep learning. Background technique [0002] With the ever-increasing demand for transportation from all walks of life, the role of transportation in economic development is becoming more and more obvious. The problem of traffic congestion has become a bottleneck restricting social development. Therefore, how to effectively solve the problem of traffic congestion has become the most difficult problem for governments all over the world. It is also one of the most urgent problems to be solved. [0003] Short-term traffic flow forecasting is the main basis for traffic management and control departments to take traffic guidance measures. In order to better reflect traffic conditions in real time, research based on short-term traffic flow forecasting models has become the focus of traffic forecasting research in recent ...

AI Technical Summary

Problems solved by technology

[0004] Traditional traffic flow prediction methods include support vector machines, decision trees, convolutional neural networks, and recurrent neural networks. Most of these traffic flow prediction methods only extract the spatiotemporal features of traffic flow

Images