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

Position fingerprint-based WLAN indoor positioning error correction method and system

An indoor positioning and error correction technology, which is applied to services based on location information, services based on specific environments, positioning, etc., can solve problems such as unsatisfactory positioning accuracy, and achieve the effect of reducing the impact of positioning accuracy.

Active Publication Date: 2018-07-20
武汉创驰蓝天信息科技有限公司
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The existing technology uses online RSS average samples to calculate the position fingerprint positioning algorithm of the positioning results, and the RSS changes of the relevant reference points do not introduce correlation coefficients, resulting in unsatisfactory positioning accuracy

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
  • Position fingerprint-based WLAN indoor positioning error correction method and system
  • Position fingerprint-based WLAN indoor positioning error correction method and system
  • Position fingerprint-based WLAN indoor positioning error correction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] Such as figure 1 As shown, a WLAN indoor positioning error correction method based on location fingerprints, which includes the following steps:

[0074] S1. After the position fingerprint has been established, select a preset number of training points and record their position coordinates, collect RSS samples on the training points to establish a training point database; use the nearest neighbor selection algorithm to match the RSS samples with the static position fingerprint and calculate the positioning As a result, the location coordinates of the training points are used to calculate the positioning error; and the artificial neural network ANN is used to fuse the RSS samples and positioning coordinates of the training points as the input data of the ANN, and the positioning error of the training points is used as its output data to establish the relationship between input and output. The non-linear mapping relationship; use the genetic algorithm to optimize the init...

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

Provided is a position fingerprint-based WLAN indoor positioning error correction method. The method includes the following steps: S1, after a position fingerprint map is established, selecting a preset number of training points and recording position coordinates of the points, collecting RSS samples in the training points and establishing a training point database; enabling the RSS samples to match the static position fingerprint map through the nearest neighbor selection algorithm, calculating a positioning result, and calculating position errors through the position coordinates of the training points; merging the RSS samples of the training points and the positioning coordinates through an artificial neural network (ANN), taking the merged RSS samples and the positioning coordinates asinput data of the ANN, taking the positioning errors of the training points as output data, and establishing a nonlinear mapping relation between the input and the output; S2, during online positioning, calculating positioning coordinates through the nearest neighbor selection algorithm when a user receives the RSS samples from all APs, and then inputting the online RSS samples and the positioningcoordinates into an ANN model trained during an offline stage to estimate the positioning errors.

Description

technical field [0001] The invention relates to the technical field of indoor positioning, in particular to a WLAN indoor positioning error correction method and system based on location fingerprints. Background technique [0002] In the prior art, the position fingerprint positioning algorithm using the online RSS average sample to calculate the positioning result does not introduce a correlation coefficient into the RSS change of the relevant reference point, resulting in unsatisfactory positioning accuracy. Contents of the invention [0003] In view of this, the present invention proposes a location fingerprint-based WLAN indoor positioning error correction method and system. [0004] A WLAN indoor positioning error correction method based on location fingerprints, comprising the steps of: [0005] S1. After the position fingerprint has been established, select a preset number of training points and record their position coordinates, collect RSS samples on the training...

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): G01S5/02H04W4/021H04W4/33
CPCG01S5/021G01S5/0252
Inventor 刘芬
Owner 武汉创驰蓝天信息科技有限公司