Traffic flow prediction method and system for urban road network

A technology of urban road network and traffic flow, applied in traffic flow detection, traffic control system of road vehicles, traffic control system, etc., can solve problems such as inability to accurately predict traffic flow and lack of flexibility.

Pending Publication Date: 2021-01-05
CHANGCHUN UNIV OF SCI & TECH
View PDF2 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some researchers can extract local features in the graph by improving the graph convolutional network, but lack of flexibility
Since the graph convolutional neural network cannot extract the local spatial features in the graph very well, the spatial-temporal graph convolutional neural network, diffusion convolutional re...

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 and system for urban road network
  • Traffic flow prediction method and system for urban road network
  • Traffic flow prediction method and system for urban road network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] figure 1 It is a flow chart of Embodiment 1 of the traffic flow prediction method for urban road network of the present invention. see figure 1 , the traffic flow prediction methods of the urban road network include:

[0058] Step 101: establish a training data set; the training data set includes an adjacency matrix and a time-series vector matrix; the adjacency matrix indicates whether each road section in the urban road network is adjacent; the time-series vector matrix indicates that each road section used to be Traffic flow for a time period; each of said time periods has the same time interval.

[0059] This step 101 specifically includes:

[0060] The urban road network is modeled to obtain an undirected graph of the urban road network; the undirected graph represents the topological structure of the urban road network; the nodes of the undirected graph represent road sections, and the edges of the undirected graph represent road sections connected.

[0061] ...

Embodiment 2

[0076] figure 2 It is an overview schematic diagram of Embodiment 2 of the traffic flow prediction method for urban road network of the present invention. see figure 2 , the traffic flow prediction method of the urban road network is based on the graph wavelet attention gating recurrent neural network model to predict the traffic flow of the urban road network, such as figure 2 Method overview:

[0077] First, the urban road network is modeled as an undirected graph structure. The nodes of the graph represent road segments, and the edges of the graph represent the connectivity between intersections. The time series of road segments is the attribute feature of the traffic flow of nodes. The time series of a road segment is the traffic flow of a certain road segment within a time period of 5 minutes.

[0078] Second, using the above-mentioned graph and historical traffic time series as input, the graph wavelet attention-gated recurrent neural network model is used to captu...

Embodiment 3

[0129] Figure 6 It is a structural diagram of Embodiment 3 of the traffic flow forecasting system of the urban road network of the present invention. see Figure 6 , the traffic flow prediction system of the urban road network includes:

[0130] The training data set building module 601 is used to set up the training data set; the training data set includes an adjacency matrix and a time series vector matrix; the adjacency matrix indicates whether each road section in the urban road network is adjacent; the time series vector The matrix represents the traffic flow of each road segment for each time period in the past; each said time period has the same time interval.

[0131] In the training data set establishing module 601, the time interval is 5 minutes.

[0132] The training data set building module 601 specifically includes:

[0133] The urban road network modeling unit is used to model the urban road network to obtain an undirected graph of the urban road network; th...

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 discloses a traffic flow prediction method and system for an urban road network, and relates to the technical field of intelligent transportation, and the method comprises the steps: building a training data set comprising an adjacent matrix and a time sequence vector matrix; establishing a graph wavelet attention gating recurrent neural network model; wherein the model comprises a graph convolutional neural network based on wavelet transform and a gating recurrent neural network connected with the graph convolutional neural network; the gating recurrent neural network comprisesgating recurrent units which are in one-to-one correspondence with the time periods and are integrated into the attention mechanism; training and optimizing the graph wavelet attention gating recurrent neural network model by using the training data set; and inputting the adjacency matrix of the urban road network to be predicted and the time sequence vector matrix into the trained and optimized graph wavelet attention gating recurrent neural network model to obtain the traffic flow of each road section in a future time period. The method and the system disclosed by the invention can accurately predict the traffic flow.

Description

technical field [0001] The invention relates to the technical field of intelligent transportation, in particular to a method and system for predicting traffic flow of an urban road network. Background technique [0002] Traffic flow forecasting is an important part of intelligent transportation systems. Timely and accurate traffic flow forecasting can help realize real-time dynamic traffic light control and urban road planning, alleviate huge traffic congestion problems, and improve the safety and convenience of public transportation. However, accurate real-time traffic flow prediction has been challenging due to the complex spatial and temporal dependencies of traffic data. [0003] Spatial dependence means that the change of traffic flow is limited by the topological structure of the urban road network, which is not only reflected in the transmission effect of the traffic state of the upstream section on the downstream section, and the retroactive influence of the traffic ...

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
IPC IPC(8): G06Q10/04G06Q50/26G06K9/62G06N3/04G06N3/08G08G1/01
CPCG06Q10/04G06Q50/26G06N3/08G08G1/0104G06N3/044G06N3/045G06F18/214
Inventor 李松江吴宁王鹏
Owner CHANGCHUN UNIV OF SCI & TECH
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