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

Two-stage positioning method based on Wi-Fi signal space partition

A positioning method and signal space technology, applied in positioning, wireless communication, measuring devices, etc., can solve the problems of signal fingerprints that do not follow similar position coordinate signal fingerprint relationships, positioning result errors, and inability to reflect the distribution of signal fingerprints, etc. The effect of accurate dependencies and improved positioning accuracy

Active Publication Date: 2016-11-16
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF3 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, these small physical areas cannot reflect the actual distribution of signal fingerprints. Signal fingerprints in the same small area sometimes do not follow the similar relationship between position coordinates and signal fingerprints, resulting in errors in positioning results.

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
  • Two-stage positioning method based on Wi-Fi signal space partition
  • Two-stage positioning method based on Wi-Fi signal space partition
  • Two-stage positioning method based on Wi-Fi signal space partition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The training phase is divided into two parts: sub-area division and two-level positioning model establishment:

[0025] 1) According to the collected Wi-Fi signal clustering and positioning each position reference point in the area, the clustering result is used as a divided sub-area; according to the Wi-Fi signal clustering positioning sub-area includes: using the K-Means clustering algorithm to Divide the signal space into sub-regions, optimize the K-Means clustering model multiple times to obtain more accurate model parameters, and correct the discrete points generated after K-Means clustering.

[0026] 2) Calculate the two-stage WLAN positioning model. The SVM classification and regression algorithms are used to realize two-stage indoor positioning. The first stage is the rough positioning stage, also called sub-area positioning. Each sub-area is trained with an SVC classifier model to determine whether a test signal fingerprint is collected within this sub-region....

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 two-stage positioning method based on Wi-Fi signal space partition. The optimization and outlier processing are further performed after the K-Means clustering is adopted to perform the partition in a sub-region. Compared with the operation of only performing the signal space clustering on the Wi-Fi fingerprint in the prior art, the clustering optimization and the outlier correction are introduced after the signal space clustering in the invention, the clustering is corrected from the physical space, namely, the signal space and the physical space are clustered in the invention, the partition to the sub-region is more accurate. The large signal space region is partitioned into smaller sub-regions with more obviously centralized features through the adoption of the space clustering algorithm, and then the SVM classification algorithm and the SVM regression algorithm are used for modeling the unknown dependency, and then the positioning precision is improved.

Description

technical field [0001] The invention relates to the field of indoor positioning, in particular to a method for dividing a Wi-Fi signal space into several subspaces and performing two-stage positioning. Background technique [0002] Wireless local area network WLAN has the characteristics of high transmission rate and convenient installation, so that people can quickly access the network anytime and anywhere in daily life and work. Wi-Fi fingerprint refers to the multiple surrounding Wi-Fi wireless access points that can be scanned by the Wi-Fi wireless network card and the corresponding signal strength. Wi-Fi wireless access point AP is usually a wireless router. Taking Wi-Fi fingerprint as a typical indoor positioning solution, it does not need to add additional hardware devices, makes full use of existing wireless network facilities, expands the application range of the positioning system to buildings and indoors, and reduces positioning costs , and meet the needs of use...

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): H04W64/00G01S5/02
CPCG01S5/0257H04W64/00
Inventor 周瑞李志强陈结松桑楠罗磊张洋铭陈俊铭
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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