Unlock instant, AI-driven research and patent intelligence for your innovation.

Traffic flow prediction method based on LSTM-Attention

A technology of traffic flow and forecasting method, which is applied in traffic flow detection, road vehicle traffic control system, forecasting, etc., and can solve the problems of not taking historical information into account, increasing uncertain factors, and low forecasting accuracy

Active Publication Date: 2021-06-08
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF10 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, long-term historical information is not considered, resulting in low prediction accuracy
[0005]Although the above three types of methods have achieved good results in scenarios such as traffic prediction, image recognition, and trajectory data analysis, they are all aimed at short time spans. It does not take into account the impact of long-term historical information on the future flow of mobile objects, and cannot fully reflect the nature of road network traffic flow
If the long-term historical information is ignored, the uncertain factors will increase, which will have a greater impact on the prediction of future traffic flow, and the accuracy of the prediction needs to be improved

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 LSTM-Attention
  • Traffic flow prediction method based on LSTM-Attention
  • Traffic flow prediction method based on LSTM-Attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments and descriptions of the present invention are used to explain the present invention, and do not constitute an improper limitation of the present invention.

[0033] Such as figure 1 The present invention provides that the present invention provides a kind of traffic flow prediction method based on LSTM-Attention, it is characterized in that, specifically comprises the following steps:

[0034] Step 1, collect the traffic flow data of the intersection w at q historical moments, collect the traffic flow data of the intersection w at the first n moments of the jth historical moment, j=1, 2, ... q, n≥1;

[0035] Step 2, preprocessing all traffic flow data;

[0036] Step 3, combine the LSTM model with the Attention model to obtain the LSTM-Attention model;

[0037] Step 4, take the traffic flow data of 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 based on LSTM-Attention, and the method comprises the steps: collecting historical data, carrying out the preprocessing of the historical data, inputting the processed data into an established LSTM-Attention model, carrying out the training of the LSTM-Attention model, and predicting the traffic flow at a next moment through employing the trained LSTM-Attention model. The prediction accuracy of the method is higher than that of machine learning models such as traditional statistics and single LSTM.

Description

technical field [0001] The invention belongs to the field of traffic big data analysis. Background technique [0002] Mobile object traffic prediction is an important technical part of location-based services (LBS). It is of great value and significance to use an algorithm with low time complexity and high accuracy to process massive amounts of mobile object data and make efficient predictions. . [0003] Today, with the rapid development of the fifth-generation communication technology, highly intelligent mobile devices affect people's daily necessities of life, such as clothing, food, housing and transportation, and thus generate a large amount of traffic data, and quickly mine the movement information of mobile objects in these data. become the focus of our research. Location information is the most important context information for moving objects. Historical location information is of great significance to traffic flow prediction, and can provide technical support for ...

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): G08G1/01G06N3/04G06N3/08G06Q10/04G06Q50/26
CPCG08G1/0129G08G1/0137G06Q10/04G06Q50/26G06N3/08G06N3/045
Inventor 秦小麟刘嘉琛宋力翔朱润泽
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS