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

Collaborative prediction method of spatio-temporal traffic status in urban road network based on dynamic factor model

A dynamic factor, traffic state technology, applied in traffic flow detection, traffic control systems based on specific mathematical models, road vehicles, etc., to enhance interpretability, speed up model learning, and improve prediction accuracy.

Active Publication Date: 2022-05-27
NANJING UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

On the other hand, the existing methods basically use traffic flow parameters such as traffic flow to evaluate the traffic state.

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
  • Collaborative prediction method of spatio-temporal traffic status in urban road network based on dynamic factor model
  • Collaborative prediction method of spatio-temporal traffic status in urban road network based on dynamic factor model
  • Collaborative prediction method of spatio-temporal traffic status in urban road network based on dynamic factor model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] A collaborative prediction method of urban road network spatiotemporal traffic state based on dynamic factor model, the specific steps are as follows:

[0079] Step 1. Obtain traffic area data, and perform preprocessing and spatial correlation verification.

[0080] In some embodiments, such as figure 1 As shown, a study area is determined, which includes 12 traffic areas. Each record of collected data includes fields such as area name, area ID, timestamp, TPI, etc. The sampling interval is 2 minutes. The traffic performance index TPI is recorded as a value from 0 to 100. The larger the TPI value, the more crowded the area is. The relationship between traffic state and TPI is shown in Table 1, and the diagram of traffic performance index TPI is shown in Table 1. figure 2 .

[0081] Table 1 Relationship between traffic state and TPI

[0082]

[0083] In a further embodiment, the time series of TPI is analyzed, the seasonal and temporal correlations of the traff...

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 collaborative prediction method of urban road network spatio-temporal traffic state based on a dynamic factor model, including: acquiring traffic area data, and performing preprocessing and spatial correlation verification; based on a static factor model SFM, establishing a dynamic factor model DFM, And determine the probability density function of traffic state observations; use the expectation maximization EM algorithm to solve the quasi-maximum likelihood estimation of the DFM parameter set; use the vector autoregressive model VAR to predict the common factor in the future time period; use the autoregressive model AR to predict The individualized components of each region in the future time period; predict the traffic status of each region in the future time period through the factor load matrix, common factor components and individualized components of different regions. The invention improves the accuracy and efficiency of network-level traffic state prediction, and has important practical significance in urban road network traffic state prediction.

Description

technical field [0001] The invention belongs to the field of traffic state prediction, in particular to a method for coordinating the spatiotemporal traffic state of an urban road network based on a dynamic factor model. Background technique [0002] At present, more and more urban road network systems have different degrees of traffic congestion, which not only seriously affects the efficiency of traffic operation, but also causes great damage to the environment. In order to effectively improve the current situation of traffic congestion, accurate traffic status information is crucial at multiple levels of traffic operation and management. However, due to the inherent uncertainty of traffic conditions in signalized urban road networks, it is extremely challenging to accurately and efficiently predict the traffic conditions of urban road networks. [0003] Existing traffic state prediction methods are usually limited to a certain location or area, lack of collaborative pred...

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 Patents(China)
IPC IPC(8): G08G1/01G06Q10/04G06Q50/26G06F17/16G06N7/00
CPCG08G1/0104G08G1/0125G06Q10/04G06Q50/26G06F17/16G06N7/01
Inventor 唐坤郭唐仪何流刘英舜徐永能杨洁
Owner NANJING UNIV OF SCI & TECH