Traffic flow prediction method based on graph attention convolution network

A technology of traffic flow and convolutional network, which is applied in traffic flow detection, road vehicle traffic control system, traffic control system, etc., can solve problems such as failure, and achieve the effect of reducing training time

Active Publication Date: 2020-06-02
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF7 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method extracts spatial features from grid data, such as videos and images, which means that these methods still fail

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Traffic flow prediction method based on graph attention convolution network
  • Traffic flow prediction method based on graph attention convolution network
  • Traffic flow prediction method based on graph attention convolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] This embodiment explains in detail the complete process of the mid-to-long-term traffic flow prediction of the “a method for traffic flow prediction based on graph attention convolutional network” of the present invention.

[0044] Step 1. In the specific implementation, the experiment uses the PeMSD7 data set. The PeMSD7 data set summarizes traffic data every 5 minutes. Therefore, each node of the road map contains 288 data points per day. The linear interpolation method is used to solve the missing values ​​after the data cleaning problem. In addition, the input data is normalized by the zero-mean method so that the average value of the input data is zero. The adjacency matrix W of the route map is calculated according to the distance between the stations in the transportation network, which is calculated by formula (2).

[0045] During data preprocessing, σ and ε are assigned to 10 and 0.5, respectively. figure 1 (a) is the overall structure of the network, by figure 1...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a traffic flow prediction method based on a graph attention convolution network, aims to predict medium and long time traffic flow, and belongs to the technical field of urbantraffic planning and flow prediction. The method comprises the following steps: step 1, preprocessing traffic flow data, and outputting a preprocessed data sequence; 2, based on the preprocessed datasequence, extracting spatial features and time features of the data sequence; and 3, inputting the extracted features of the two AGA blocks in the step 2, and obtaining a prediction result at the next moment through a full connection layer. According to the method, a recursive structure which cannot be trained in parallel is not used, and all components of the model are convolutional structures,so that the training time can be reduced; and according to the method, spatial features and time features are extracted respectively by trying to combine a spectrum-based graph convolutional network and a space-based convolutional network for the first time, and the algorithm is outstanding on a space-time traffic network.

Description

[0001] The invention relates to a traffic flow prediction method based on a graph attention convolutional network, which aims to predict medium and long-term traffic flow and belongs to the technical field of urban traffic planning and flow prediction. Background technique [0002] The problem of traffic forecasting has long been a matter of great concern. According to a 2018 survey, American drivers spend 50.6 minutes on the road, driving an average of 31.5 miles per day. In this case, accurate traffic volume forecasting is essential for the people and the government to plan ahead and ease congestion. Route planning and other transportation services also rely heavily on traffic forecasts. Usually, traffic prediction is the basis of urban traffic control and also plays an important role in intelligent transportation systems. [0003] The goal of traffic prediction is to use historical traffic parameters, namely traffic speed, volume and density, to predict future traffic paramete...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G08G1/01G08G1/065G06N3/04G06N3/08
CPCG08G1/0125G08G1/0137G08G1/065G06N3/08G06N3/045
Inventor 郑宏张思凯刘佳谋宿红毅闫波
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap