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

A Fingerprint Localization Method Based on Robust Sparse Representation Clustering

A technology of sparse representation and fingerprint positioning, applied in the field of wireless positioning, it can solve the problems of sensitivity to noise and data, and achieve the effect of strong robustness and high positioning accuracy

Active Publication Date: 2020-11-13
XIDIAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing fingerprint-based positioning algorithm requires a lot of offline training, is sensitive to noisy data, and the positioning accuracy needs to be further improved

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
  • A Fingerprint Localization Method Based on Robust Sparse Representation Clustering
  • A Fingerprint Localization Method Based on Robust Sparse Representation Clustering
  • A Fingerprint Localization Method Based on Robust Sparse Representation Clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] The present invention is further described below in conjunction with embodiment.

[0030] by figure 1 As an example, a fingerprint location method based on robust sparse representation clustering includes the following steps:

[0031] 1) After processing the offline sampled data, the original database is obtained

[0032]

[0033] where R ij Indicates that the i-th access point receives the fingerprint strength of the j-th sensor, 1≤i≤M, 1≤j≤N, M represents the number of offline sampling points, and N represents the number of sensors in the sampling area.

[0034] 2) The optimized fingerprint library is obtained by affine propagation clustering

[0035]

[0036] where S ab Indicates that the a-th class center receives the fingerprint strength of the b-th sensor, 1≤a≤P, 1≤b≤N, and P represents the number of classes.

[0037] 3) Using the sparse prior information of the test points, the fingerprint strength of the test points is sparsely expressed through the R...

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 fingerprint location method based on r robust-sparse represented clustering. The problems of inadequate location precision, overlong acquisition time and insufficient robustness in the prior art are mainly solved. The fingerprint location method comprises the following steps: sparsely representing the fingerprint data of a testing point under a fingerprint base after theclustering by mainly using the sparse prior information of the testing point, thereby realizing an aim of accurate location, wherein the core is the use of the RSRC algorithm; firstly constructing anoffline fingerprint base, and then optimizing the fingerprint through affinity propagation clustering; performing fingerprint intensity sparsity representation on the testing point by using the RSRC algorithm at an online stage, determining candidate classes by minimally modifying the residue, thereby realizing the estimation on a testing location. The experiment shows that the scheme provided bythe invention has better location effect.

Description

technical field [0001] The invention belongs to the field of wireless positioning, and in particular relates to a fingerprint positioning method based on robust sparse representation clustering. Background technique [0002] With the development of WLAN, the way of obtaining location information by means of communication devices such as smartphones, PADs, and laptops is becoming more and more popular. Location-based services are widely used in fields such as medical treatment, first aid, and navigation, and accurate positioning technology is the key. Therefore, the research on positioning technology has great theoretical value and market application prospect. [0003] Due to the popularization of wifi devices, the received signal fingerprint strength can be used for positioning, no other sensors are needed, the cost is low, and the operation is convenient. The positioning algorithm based on fingerprints has become the mainstream. The existing fingerprint-based positioning ...

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): H04W64/00G01S5/02
Inventor 杨刚叶新泉陈蒙刘荣芳
Owner XIDIAN UNIV