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

Tensor-based vehicle networking data loss multiple estimation new method

A technology of missing data and Internet of Vehicles, applied in the field of Internet of Vehicles, can solve the problems of data errors and reducing overall performance.

Active Publication Date: 2019-08-23
TIANJIN UNIVERSITY OF TECHNOLOGY
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When there is serious data loss, this method can often stably show the applicability better than the first method, but there are also some disadvantages, such as data errors generated during repair will also reduce the overall performance

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
  • Tensor-based vehicle networking data loss multiple estimation new method
  • Tensor-based vehicle networking data loss multiple estimation new method
  • Tensor-based vehicle networking data loss multiple estimation new method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0037] Step 1, model building:

[0038] The basic idea of ​​the tensor model:

[0039] figure 2 The third-order tensor cp decomposition model is given. The main idea of ​​CP decomposition is: a high-order tensor can be regarded as composed of several one-dimensional factor matrices, then the decomposed factor matrix can be used for calculation .

[0040] Create a tensor of order k where n l Represents the dimension along the l-th direction (l∈{1,2,...,k}). For the built tensor T, the indices of the elements are given by express. According to the basic idea of ​​CP decomposition, the construction tensor can be approximated by a low-rank structure, as follows:

[0041]

[0042] in is the l factorization factor matrix The j-th column vector of , the symbol ο represents the vector outer product, and r is the CP rank of the tensor T. If analyzed from the perspective of each element, formula (1) is equivalent to

[0043]

[0044] in is the mth factor matrix a...

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 provides a tensor-based vehicle network data loss multiple estimation method for the problem of data loss of the Internet of Vehicles, which is integrated Bayesian tensor decomposition (IBTD), and belongs to the field of Internet of Vehicles. According to the algorithm, in a data model construction stage, a random sampling principle is utilized, missing data is randomly extracted togenerate a data subset, and an optimized Bayesian tensor decomposition algorithm is used for interpolation. An integration idea is introduced, multiple interpolated error results are analyzed and sorted, space-time complexity is considered, and an optimal result is obtained through preferred average. the performance of the proposed model is carried out by an average absolute percentage error (MAPE) and a root-mean-square error (RMSE). Experimental results show that the new method provided by the invention can effectively carry out interpolation on traffic data sets with different missing amounts, and can obtain a very good interpolation result.

Description

technical field [0001] The invention belongs to the field of the Internet of Vehicles, and in particular relates to a tensor-based new method for estimating missing data of the Internet of Vehicles. Background technique [0002] The Internet of Vehicles actually aims to build an intelligent transportation network. With the rapid development of modern sensing technology, communication technology, computer technology and information technology, the intelligent transport system (Intelligent Transport System, referred to as ITS) is gradually promoted, and the traffic information collection system is an important part of ITS. , Real-time traffic information can grasp the urban road traffic conditions and changes, and provide scientific basis for urban traffic planning and decision-making. [0003] The data required for the application of the Internet of Vehicles should have high spatial and temporal resolutions in order to achieve the purposes of modeling, traffic management, fo...

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): G06F17/16G06F17/18H04L29/08
CPCG06F17/16G06F17/18H04L67/12
Inventor 张德干张婷吴昊高瑾馨颜浩然
Owner TIANJIN UNIVERSITY OF TECHNOLOGY
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