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

Wireless positioning method based on improved machine learning algorithm

A wireless positioning and machine learning technology, applied in wireless communication, electrical components, etc., can solve problems such as low positioning accuracy

Active Publication Date: 2019-12-13
NANJING UNIV OF POSTS & TELECOMM
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Purpose of the invention: In order to overcome the deficiencies in the prior art, the present invention provides a wireless positioning method based on an improved machine learning algorithm, which uses the improved AKF algorithm to perform noise reduction processing on the received RSS value, and overcomes the existing AKF algorithm The problem of low 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
  • Wireless positioning method based on improved machine learning algorithm
  • Wireless positioning method based on improved machine learning algorithm
  • Wireless positioning method based on improved machine learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be further described below in conjunction with the accompanying drawings.

[0065] Such as Figure 1-Figure 2 as shown,

[0066] A wireless positioning method based on an improved machine learning algorithm, comprising the following steps:

[0067] Step 1: Construct fingerprint database FP;

[0068] Step 2: Measure the signal strength RSS values ​​from all access points AP multiple times at the test point to obtain the RSS matrix Z to be denoised;

[0069] Step 3: Use the improved traditional adaptive Kalman filter algorithm AKF, and use the first column of Z as the improved AKF algorithm initial value of Set the threshold gate for the tth iteration of the improved AKF algorithm t , for the t-th column Z of Z based on the AKF denoising process t Noise reduction, get the output result Calculate the error ε between the expected output value and the measured value t covariance of Compare with the gate t ;if Then correct get ...

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 wireless positioning method based on an improved machine learning algorithm. The method is based on an existing fingerprint identification method WKNN algorithm, an improvedAKF algorithm and an AHP analytic hierarchy process model are introduced; an improved AKF algorithm is used to reduce noise in RSS at a test point, a denoised RSS value is used to select a fingerprintmeeting requirements from a fingerprint database, then an AHP is used to assign a weight to a selected fingerprint coordinate, and then a WKNN algorithm is used to obtain optimal position estimation.According to the invention, the improved AKF algorithm is adopted to carry out noise reduction processing on the received RSS value, and the problem of low positioning precision of the existing AKF algorithm is overcome. Meanwhile, an AHP algorithm is adopted as a weight distribution mode, the influence of RSS difference between reference points on the weight is reasonably enlarged, and thereforethe positioning precision is improved.

Description

technical field [0001] The invention relates to the technical field of indoor positioning, and mainly relates to a wireless positioning method based on an improved machine learning algorithm. Background technique [0002] With the popularity of the Internet and smart phones, people's demand for high-precision positioning and navigation in indoor scenes is also increasing. WLAN indoor positioning can make full use of widely deployed access points (APs) to achieve high-performance positioning, which makes it the best choice for future indoor positioning and navigation services. [0003] At present, WLAN-based positioning methods mainly include triangle algorithm and position fingerprinting. The triangle algorithm uses the distance information between the target to be measured and at least three known APs to estimate the target position. The distance is estimated by measuring the RSS from the AP. The WLAN localization based on the triangle algorithm largely depends on the accu...

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): H04W64/00
CPCH04W64/003H04W64/006
Inventor 潘甦华胜
Owner NANJING UNIV OF POSTS & TELECOMM