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

Radio frequency tomography method based on low-rank data driving weight model

A radio frequency tomography, data-driven technology, applied in the field of radio frequency, to achieve the effect of improving the effect and improving the efficiency

Active Publication Date: 2020-06-19
WUYI UNIV
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a radio frequency tomography method based on a low-rank data-driven weight model. The method performs radio frequency tomography based on a data-driven weight model, so as to avoid the problems caused by the elliptical weight model and improve radio frequency tomography. The effect of imaging

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
  • Radio frequency tomography method based on low-rank data driving weight model
  • Radio frequency tomography method based on low-rank data driving weight model
  • Radio frequency tomography method based on low-rank data driving weight model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Please refer to figure 1 , the present embodiment provides a radiofrequency tomography method based on a low-rank data-driven weight model, comprising the following steps:

[0057] S1. Construct a wireless sensor network including a plurality of sensor nodes, and the sensor nodes communicate with each other to form a plurality of links;

[0058] S2. Construct a mathematical weight matrix, the mathematical weight matrix is ​​used to represent the relationship between the shadow loss and the pixel extra loss of each link;

[0059] S3. Constructing a training weight model based on the low-rank characteristics of the mathematical weight matrix;

[0060] S4. Input the training data into the training weight model for training to obtain the training weight matrix;

[0061] S5. Perform radio frequency tomography based on the training weight matrix.

[0062] Wherein, the training weight matrix includes weight factors of each pixel corresponding to each link.

[0063] In this...

Embodiment 2

[0111] In this embodiment, a hands-free positioning experiment is carried out to test the actual positioning effect of the training weight model provided by the present invention.

[0112] In this embodiment, scene 1 and scene 2 are respectively used as training data to input the training weight model, and the training weight matrix based on scene 1 and the training weight matrix based on scene 2 are obtained, and the weight matrices obtained from different scene data are reconstructed respectively. Hands-free target and compare with the localization results of the ellipse weight model. In this embodiment, the Bayesian target estimation algorithm is used for sparse image reconstruction, and the parameter settings in the reconstruction algorithm are the same. In this embodiment, the pixel width is set to 0.2m and 0.4m respectively, which is mainly based on the fact that the width of the human body is generally between 0.2m-0.4m, if the pixel width is set to be greater than 0.4m...

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 radio frequency tomography method based on a low-rank data driven weight model, and the method comprises the following steps: constructing a wireless sensor network comprising a plurality of sensor nodes which are communicated with one another to form a plurality of links; constructing a mathematical weight matrix, wherein the mathematical weight matrix is used for representing a relationship between shadow loss and pixel extra loss of each link; constructing a training weight model based on the low-rank characteristics of the mathematical weight matrix; inputting thetraining data into a training weight model, and training to obtain a training weight matrix; and performing radio frequency tomography based on the training weight matrix. In the radio frequency tomography weight model design method provided by the invention, the weight model is not based on the traditional elliptical weight model, the change information of the RSS value in the link caused by thetarget can be accurately expressed, and the calculation is not influenced by the parameters of the elliptical weight model.

Description

technical field [0001] The invention relates to the radio frequency field, in particular to a radio frequency tomographic imaging method based on a low-rank data-driven weight model. Background technique [0002] The shadow attenuation weight matrix is ​​the link between the RSS value (signal attenuation strength) and the pixel shadow attenuation in the perception area, and the setting of the weight factor reflects the contribution of the link signal attenuation to the corresponding pixel attenuation value. The design of the weight matrix needs to reflect the coverage of the measurement link to the pixel and the size of the weight under the coverage. [0003] The current mainstream weight matrix is ​​generally designed based on the elliptic weight model. That is, the receiving and sending nodes are taken as the focus of the ellipse, and L (=d+λ) is taken as the long axis of the ellipse, d is the distance between the receiving and sending nodes, and λ is the ellipse paramete...

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): H04B17/391H04W24/06H04W84/18
CPCH04B17/3911H04W24/06H04W84/18
Inventor 郝晓曦郑成勇王国利
Owner WUYI 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

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