Traffic flow prediction method based on global diffusion convolution residual network

A forecasting method, traffic forecasting technology, applied in traffic flow detection, road vehicle traffic control system, forecasting, etc., can solve the problem of failing to simultaneously capture the global and local temporal and spatial correlations of the traffic network, and achieve good forecasting performance
CN112071065AInactive Publication Date: 2020-12-11SHANDONG UNIV OF TECH
10 Cites 29 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Current Assignee / Owner
SHANDONG UNIV OF TECH
Publication Date
2020-12-11
Estimated Expiration
Not applicable ยท inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a traffic flow prediction method based on a global diffusion convolution residual network, and belongs to the technical field of intelligent traffic systems. The method comprises the following steps of: 1, establishing a traffic prediction model based on a global diffusion convolution residual network; 2, learning dynamic correlation and local and global spatial correlation; 3, capturing time correlation and global space-time correlation; and 4, fusing branch results and outputting a final result. According to the traffic flow prediction method, a global diffusion convolution residual network is provided, the model is composed of a plurality of periodic branches with the same structure, and the global attention diffusion convolution network and the global residual network of each branch are used for obtaining the spatial-temporal correlation of each period. Particularly, the global attention diffusion convolution network uses a PPMI matrix based on an attentionmechanism to capture dynamic space-time correlation, and the global residual network uses gating convolution and a global residual unit to capture time correlation and global space-time correlation atthe same time, so that the precision and efficiency of traffic prediction are improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] A traffic flow prediction method based on a global diffusion convolution residual network belongs to the technical field of intelligent transportation systems. Background technique

[0002] Traffic flow prediction is a key problem in intelligent transportation systems. Due to the complex topology of the traffic network and the dynamic spatio-temporal patterns of the traffic situation, the forecasting of the traffic flow in the traffic network is still a challenging task. Most existing research methods mainly focus on the local spatio-temporal correlation, while ignoring the global spatial correlation and the global dynamic spatio-temporal correlation.

[0003] Traffic forecasting is a challenging task due to its complex nonlinear dynamic spatio-temporal dependencies. Researchers have put a lot of effort into traffic prediction. Statistical regression methods such as ARIMA and its variants are representative models in early research on traffic foreca...

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