Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Traffic congestion prediction method and system

A technology of traffic congestion and prediction method, which is applied in the field of transportation, can solve the problems of slow training speed and low prediction accuracy, and achieve the effects of fast training speed, improved prediction accuracy, and reduced complexity

Active Publication Date: 2019-06-14
张家口东出科技有限公司
View PDF6 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of this application is to provide a traffic congestion prediction method and system to solve the problems of slow training speed, low prediction accuracy, diversity and dynamics of the global road network in the prior art traffic congestion prediction

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 congestion prediction method and system
  • Traffic congestion prediction method and system
  • Traffic congestion prediction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as figure 1 As shown, the application provides a traffic jam prediction method, comprising the following steps:

[0043] Step 110, clustering and dividing the traffic data of the whole road network into a plurality of cluster sub-models according to the attributes and characteristics of road sections;

[0044] Step 120, input the feature data of each cluster sub-model into different ELM sub-predictors for training and learning, and obtain the predicted congestion value at a certain time point corresponding to each cluster sub-model;

[0045] Step 130, integrate the predicted congestion values ​​of each cluster sub-model at each time point into the predicted congestion value of the whole road network.

[0046] Among them, the calculation formula of the congestion value of the clustering sub-model is:

[0047]

[0048] Among them, i represents the road section, t represents the vehicle speed, is a parameter of different road sections, e represents an irrationa...

Embodiment 2

[0080] Such as figure 2 As shown, the application also provides a traffic jam prediction system, including:

[0081] The clustering sub-model 210 is formed by clustering and dividing the traffic data of the whole road network according to the attribute characteristics of road sections;

[0082] The extreme learning machine sub-predictor 220, each clustering cluster sub-model 210 corresponds to an extreme learning machine sub-predictor 220, the extreme learning machine sub-predictor 220 trains and learns the feature data of the clustering cluster sub-model 210, and obtains each road section The predicted congestion value of ;

[0083] The integration module 230 integrates the predicted congestion value of each road section into the predicted congestion value of the whole road network;

[0084] The floating car data receiver is used to acquire floating car data, and the floating car data includes the number of floating cars and the driving speed of the floating cars at a cert...

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 congestion prediction method and system, relates to the technical field of traffic, and solves the problems of slow training speed, low prediction accuracy, and diversity and dynamics of the global road network in the traffic congestion prediction in the prior art. A traffic congestion prediction method comprises the following steps of dividing the traffic data ofthe whole road network into a plurality of clustering cluster sub-models according to the feature of the road segment attribute; inputting the feature data of each clustering cluster sub-model into different transfinite learning machine predictors respectively to obtain a predicted congestion value at a certain time point corresponding to each clustering cluster sub-model; and integrating the predicted congestion values of each clustering cluster sub-model at each time point into an integral predicted congestion value of the whole road network.

Description

technical field [0001] The present application relates to the field of traffic technology, in particular to a traffic congestion prediction method and system. Background technique [0002] With the development of the economy, people's living standards continue to improve. The older and more people use private cars to travel, resulting in urban traffic congestion, which seriously affects the quality of people's travel. Accurate and real-time traffic congestion prediction can alleviate traffic congestion. Drivers avoid traffic jams. With the increase of traffic flow, the original vehicle congestion prediction method can no longer meet the current traffic prediction problem of large-scale traffic data of the whole road network. The current traffic congestion prediction method faces challenges such as large scale and complex road conditions. However, there are deficiencies in prediction accuracy and generalization, and it cannot solve the diversity and dynamics of the global ro...

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): G08G1/01G06K9/62
Inventor 苑贵全
Owner 张家口东出科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com