Real-time traffic stream short-time prediction method

A prediction method and real-time traffic technology, applied in the field of intelligent transportation, can solve problems such as low accuracy, complex traffic flow prediction, and no consideration of data uncertainty, and achieve good flexibility, control adverse effects, and high prediction accuracy. Effect

Active Publication Date: 2018-07-31
HUNAN UNIV
View PDF8 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, traffic flow prediction is very complex, and the uncertainty of large-scale data makes it very challenging to predict traffic flow
The existing deep learning models for traffic flow prediction are deterministic and do not consider the uncertainty of the data, which leads to low prediction accuracy

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
  • Real-time traffic stream short-time prediction method
  • Real-time traffic stream short-time prediction method
  • Real-time traffic stream short-time prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The present invention will be described in detail below with reference to the accompanying drawings and the embodiments thereof, but the protection scope of the present invention is not limited to the scope described in the embodiments.

[0054] The short-term traffic flow prediction method based on fuzzy self-adaptation of the present invention mainly comprises the following steps:

[0055] Step 1, data preprocessing. Collect city-wide traffic flow data, sample every 30 minutes, and get 48 samples per day. The selection range is from July 1, 2013 to April 10, 2016. The data type is the traffic flow of the entire region.

[0056] Remove incomplete data, normalize the data, and obtain the preprocessed data set. If the number of data samples in one day is less than 48, it will be removed as incomplete data; normalization processing method: perform linear transformation on the original data, so that the result value is mapped to the range of [-1,1], the conversion functio...

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 real-time traffic stream short-time prediction method which comprises the following steps: 1, confirming a target city range to be predicted; 2, acquiring historical trafficstream observation data of the selected target city range according to time cycles; 3, preprocessing the acquired historical traffic stream observation data of the selected target city range so as toform corresponding training sets and testing sets; 4, establishing a traffic stream prediction model based on fuzzy self-adaptation; 5, training the traffic stream prediction model by utilizing the formed training sets and testing sets; 6, predicting traffic streams within the target city range by utilizing the trained traffic stream prediction model.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular, fuzzy rules are adaptively generated by using a deep convolutional network, which is a short-term traffic flow prediction method based on fuzzy self-adaptation. Background technique [0002] In modern society, with the increase of the number of vehicles, many problems also appear, such as traffic jams and traffic accidents. These problems cause people to waste more time on the road, so obtaining timely and accurate traffic flow forecast information has become an urgent need for travelers. [0003] In today's big data era, traffic flow data is also growing explosively. Using traffic big data to predict traffic flow will further ensure safe travel and plan efficient travel. Large-scale traffic flow prediction depends heavily on historical traffic data and other relevant information, such as weather conditions, traffic accidents, etc., and is considered an important part of ...

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): G08G1/01G06N3/04G06Q10/04
CPCG06Q10/04G08G1/0129G06N3/045
Inventor 陈伟宏安吉尧付丽胡梦李仁发
Owner HUNAN UNIV
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