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

Deep learning method for predicting urban traffic jam based on GPS

A technology of deep learning and urban traffic, applied in the direction of neural learning methods, traffic flow detection, traffic control system of road vehicles, etc., can solve the problems of limiting the practicability of research results, ignoring the complex traffic road topology, etc., to achieve practicality strong, good effect

Inactive Publication Date: 2018-10-09
TONGJI UNIV
View PDF10 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

This invention relates to improving road networks by utilizing advanced technology such as location sensors or cameras that track vehicles over their route. By combining these technologies into an algorithm called Deep Learning Network (DLN), it becomes possible to predict how well roads will be used without being limited only at certain points along its way. Overall, DLNA helps improve transportation efficiency while reducing delays caused by heavy usage patterns like car accidents.

Problems solved by technology

The technical problem addressed by this patented method relates to predicting how well different parts or areas are being used for better road use efficiency during heavy usage times such as commuting between cities without causing delays due to overcrowding at intersections where there may be multiple lanes intersecting with each other. Traditional approaches involve simplifying certain aspects like lane assignment based upon geometry but also neglects important factors that affect driving behavior (such as speed).

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
  • Deep learning method for predicting urban traffic jam based on GPS
  • Deep learning method for predicting urban traffic jam based on GPS
  • Deep learning method for predicting urban traffic jam based on GPS

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] The preferred embodiments of the GPS-based deep learning method for predicting urban traffic congestion of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Figure 1 to Figure 7 Show the specific implementation of the GPS-based urban traffic congestion prediction deep learning method of the present invention:

[0050] like figure 1 As shown, the GPS-based deep learning method for predicting urban traffic congestion includes the following steps:

[0051] (1) Store the original GPS data generated by the driver in the process of using the mobile phone terminal navigation software, wherein the original GPS data includes the field information of time, latitude and longitude, user id, speed, and direction angle;

[0052](2) Traffic network characterization. Traffic network characterization is divided into three specific steps. First, the urban transportation network considering the time dimension is transformed i...

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 deep learning method for predicting urban traffic jam based on GPS, and relates to the field of intelligent traffic management. Through the deep learning method, a unsupervised large-scale urban network traffic jam prediction method (CRC3D) is innovatively constructed based on GPS real-time data on urban taxies. The method is characterized in that a recursion neural network (RNN), a convolutional neural network (CNN) and a three-dimensional convolutional neural network (C3D) are combined. The recursion neural network and the three-dimensional convolutional neural network can efficiently capture time-varying characteristics of continuous traffic states from different angles. The method is good in effect and high in practicability.

Description

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

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
Owner TONGJI UNIV
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