Road traffic condition prediction method and system

Abstract

The invention discloses a road traffic condition prediction method and system. The method comprises a step of: after traffic data recorded by the onboard GPS devices of vehicles driving on each road to be analyzed, predicting the road traffic condition of each road by using a trained recurrent convolutional neural network, wherein the recurrent convolutional neural network successively includes a recurrent convolution layer, an average pooling layer, an exit layer, an all connection layer and an output layer, and the traffic data includes multiple GPS record points each of which includes a current speed, a coordinate and a timestamp. The method uses the recurrent convolutional neural network to predict the road traffic condition, is high in prediction accuracy and stability, and can be widely used in intelligent cities.

Description

technical field [0001] The invention relates to the field of smart cities, in particular to a method and system for predicting road traffic conditions. Background technique [0002] Glossary: [0003] Recurrent Neural Network: The English full name is Recurrent Neural Networks, abbreviated as RNNs. At present, it has achieved great success and wide application in many fields of natural language processing. The specific manifestation is that the network will remember the previous information and apply it to the calculation of the current output, that is, the nodes between the hidden layers are no longer connected but connected, and the input of the hidden layer includes not only the output of the input layer Also includes the output of the hidden layer at the previous moment. [0004] Convolutional Neural Network: The full English name is Convolutional neural networks, abbreviated as CNNs. An important feature of the convolutional neural network is that through the convol...

AI Technical Summary

Problems solved by technology

Although this method can realize the prediction of traffic status to a certain extent, its prediction accuracy is average and it is difficult to meet the development requirements of smart cities.

Images