A short-term traffic flow prediction method based on deep learning

Abstract

First, analyze and preprocess the weather data and traffic crossing data, input them into the threshold recurrent neural network (GRU) to extract the high-order features of traffic flow, and then input the high-order features into the gradient boosting decision tree regression model (GBDT) for short-term traffic flow prediction. The invention can carry out more in-depth excavation and analysis on traffic flow data, and after changing the output layer to GBDT, it can effectively improve the accuracy of short-term traffic flow prediction.

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, while ignoring the potential features that affect traffic flow. , such as weather characteristics, speed characteristics, holiday time characteristics, etc., and there is no in-depth analysis of traffic flow data, so more accurate predictions cannot be obtained

Images