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

Transportation data loss recovery method based on tensor reconstruction

A traffic data loss recovery technology, applied in the field of intelligent transportation

Inactive Publication Date: 2013-06-05
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the limitations of existing traffic data loss recovery methods, the technical problem to be solved by the present invention is to provide a traffic data loss recovery method based on tensor reconstruction, which can not only improve the recovery accuracy of lost values, but also can handle random loss up to 90% % and special cases such as missing one or more days

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
  • Transportation data loss recovery method based on tensor reconstruction
  • Transportation data loss recovery method based on tensor reconstruction
  • Transportation data loss recovery method based on tensor reconstruction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0061] This embodiment is aimed at the random loss of traffic data, according to figure 1 As shown, the recovery process is carried out in the following three steps:

[0062] 1. Organize the traffic data into a tensor form and mark the lost points

[0063] Since the traffic data in Figure 4(a) is 16-day traffic data, it can be formed as tensor traffic data by the following expression:

[0064] A∈R 16×12×24 (11)

[0065] Among them, A contains 16 days, 24 hours a day, 12 5 minutes an hour. According to the size of A is 16*12*24, mark the tensor The size is also 16*12*24, and the lost traffic data is determined by the following expression:

[0066] A'=Ω*A (12)

[0067] Among them, A represents the missing traffic data.

[0068] 2. Obtain the weight of each mode

[0069] For the specific flow chart of this process, please refer to figure 2 .includes the following steps:

[0070] First, expand the tensor traffic data to each mode. Because t...

Embodiment 2

[0082] For 10*12*24 traffic data, the tensor form is A∈R 10×12×24 , the corresponding tag tensor is The value of the tag tensor of the lost k days is determined according to the following expression:

[0083] in,

[0084] Among them, k represents the number of days lost, and then the lost traffic tensor data can be obtained.

[0085] The rest of the steps are the same as in Example 1. By calculating the weights of each model and bringing them into the objective function, and finally estimating the loss value, we get Figure 5 recovery effect. Figure 4 with Figure 5 The restoration effects in the method are all obtained under the Matlab environment. If the method of the present invention adopts C++ programming to realize, the running time will be greatly reduced, thereby realizing the automaticity and real-time performance of traffic data loss restoration.

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 transportation data loss recovery method based on tensor reconstruction. The transportation data loss recovery method based on the tensor reconstruction aims to resolve the problem that precision is low and loss in a plurality of days can not be processed when an existing traditional transportation data loss recovery method based on a vector or a matrix form is used for recovering loss data. The transportation data loss recovery method based on the tensor reconstruction comprises that (a) transportation data are set in a multi-dimensional tensor form, loss tensor data are expressed through marked tensor, (b) the tensor data are spread on each mode, the relevance of all modes is calculated, and the weight of each mode is obtained, and (c) an objective function of loss data value recovery is set up and the loss data value of the objective function is solved according to the set tensor data and the calculation of the weight of each mode. The transportation data loss recovery method based on the tensor reconstruction is based on a multi-dimensional tensor model, all transportation time-space information is contained, the relevance of multi-mode is fully utilized, at the same time the original structure of multi-dimensional properties and the like of the transportation data is maintained, recovery precision is obviously superior to the traditional recovery method based on the vector or the matrix form, and an extreme case of the loss of a plurality of days can be solved well.

Description

technical field [0001] The invention belongs to the field of intelligent traffic, and particularly relates to a traffic data loss recovery method. Background technique [0002] The traffic data loss recovery is a very meaningful problem in the intelligent transportation system. The recovery of the traffic lost data can improve the function of the intelligent transportation system, such as the traffic information release system, the traffic management system, etc., all need complete and accurate traffic data, but In actual traffic, traffic data is often incomplete due to equipment failures, transmission errors and other reasons. According to relevant research reports, the loss rate is 16%-93%, resulting in some intelligent transportation subsystems not working properly. Therefore, it is necessary to target the incomplete traffic data. Estimate its missing value. [0003] At present, the recovery methods for traffic data loss are mainly divided into two categories: the recove...

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
IPC IPC(8): G06F17/30
Inventor 谭华春王武宏冯广东冯建帅成斌夏红卫吴艳新朱湧阳钟兴
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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