A k-means clustering method for access points based on received signal strength signal zca whitening

A technology of received signal strength and clustering method, which is applied in the directions of nan, wireless communication, wireless communication service, etc., can solve the problems of insufficient clustering accuracy and limited positioning accuracy, and achieves convenient operation, improved accuracy, and simple method. Effect

Active Publication Date: 2017-09-05
ZHEJIANG NORMAL UNIVERSITY
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the embodiments of the present invention is to provide a k-means clustering method for access points based on ZCA whitening of received signal strength signals, which aims to solve the problem that the accuracy of clustering is not high enough due to the correlation between received signal strength signals. positioning accuracy problem

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 k-means clustering method for access points based on received signal strength signal zca whitening
  • A k-means clustering method for access points based on received signal strength signal zca whitening
  • A k-means clustering method for access points based on received signal strength signal zca whitening

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] Such as figure 2 As shown, the embodiment of the present invention specifically includes the following steps:

[0049] The first step is to determine the number of clusters k, calculate the RSS mean value from all reference points and normalize;

[0050] The second step is to whiten the normalized data;

[0051] The third step is to initialize k cluster centers;

[0052] The fourth step is to calculate the distance between the normalized RSS mean value corresponding to RP and the k cluster centers;

[0053] The fifth step is to divide the reference point into the class of the nearest cluster center, and suppress the update of each cluster center;

[0054] The sixth step is whether the cluster center is fixed or not, otherwise, return to the fourth step, if yes, execute the next step;

[0055] The seventh step is to output k cluster centers and corresponding RP sets.

[0056] The present invention whitens received signal strength (RSS) signals first, and then combi...

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 k-means clustering method for access points based on ZCA whitening of received signal strength signals. Each position fingerprint in RM is represented by the mean value of received signal strength vectors on corresponding reference points, and the mean value is normalized. Then by whitening the mean value of the received signal strength, the correlation is removed; k-means clustering selects k fingerprints in the entire RM as the initial clustering center; for all other mean values ​​of received signal strength except k clustering centers, According to their Euclidean distances from these cluster centers, they are assigned to the clusters with the closest Euclidean distances; after all the fingerprints are executed, a new cluster is obtained, and the average value of all fingerprints of the new cluster is used as the new The clustering centers; repeat steps 3 and 4 until the k clustering centers no longer change, and the iteration is terminated. The invention fully reduces the correlation between received signal strength signals, improves the accuracy of clustering, and further improves the positioning accuracy of the system.

Description

technical field [0001] The invention belongs to the technical field of indoor positioning area clustering, and in particular relates to an access point k-means clustering method for indoor positioning based on ZCA whitening of received signal strength signals. Background technique [0002] For a large positioning target area, the statistical characteristics of the received signal strength (RSS) change greatly. For a learning-based positioning algorithm, if the entire positioning area is learned, the complexity of the algorithm will be increased, and the established positioning model is not optimal. , which is not conducive to improving the positioning accuracy of the system. Therefore, it is necessary to cluster and block the positioning area, divide the larger positioning area into several small positioning areas, and model them separately, so as to reduce the computational complexity and improve the positioning accuracy. None of the existing clustering algorithms consider...

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): H04W64/00H04W4/04
Inventor 陈丽娜苗春雨赵建民
Owner ZHEJIANG NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap