WLAN (Wireless Local Area Network) indoor step-type RD-ANFIS (Region Division-Adaptive Network-based Fuzzy Inference System) positioning method

A positioning method, a step-by-step technology, applied to electrical components, wireless communication, network topology, etc., can solve problems such as complex models, poor positioning accuracy, and reduced environmental adaptability

Inactive Publication Date: 2010-10-27
HARBIN INST OF TECH
View PDF3 Cites 36 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problems of over-matching, reduced environmental adaptability and poor positioning accuracy in the ANFIS

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
  • WLAN (Wireless Local Area Network) indoor step-type RD-ANFIS (Region Division-Adaptive Network-based Fuzzy Inference System) positioning method
  • WLAN (Wireless Local Area Network) indoor step-type RD-ANFIS (Region Division-Adaptive Network-based Fuzzy Inference System) positioning method
  • WLAN (Wireless Local Area Network) indoor step-type RD-ANFIS (Region Division-Adaptive Network-based Fuzzy Inference System) positioning method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0017] Specific implementation mode one : combine Figure 13 Describe this embodiment, the WLAN indoor step-by-step RD-ANFIS positioning method of this embodiment, its specific process is as follows:

[0018] Step 1. Determine the target positioning area under the WLAN indoor environment, and determine the positions of AP, RP and test points according to the coverage area of ​​the WLAN wireless AP transmission signal and the area of ​​the target positioning area, so that each RP can collect at least The signal SNR value of an AP; among them, AP is the abbreviation of AccessPoint, which indicates the access point; RP is the abbreviation of ReferencePoint, which indicates the pre-marked reference point in the target positioning area; the signal power collected by RP should be greater than that of the receiving end network card Sensitivity; the SNR value is the signal-to-noise ratio, the full name is SignaltoNoiseRatio;

[0019] Step 2. Establish a two-dimensional coordinate s...

specific Embodiment approach 2

[0026] Specific implementation mode two : This embodiment is a further description of the WLAN indoor step-by-step RD-ANFIS positioning method of Embodiment 1, and the specific process of the content described in step 3 is:

[0027]According to the FCM clustering method, the WLAN signal strength fingerprint samples are classified using a fuzzy classification matrix; the fuzzy classification matrix is , , where j is the element in matrix The number of rows in , i is the element in matrix The column ordinal number in;

[0028] Through the iterative correction of the fuzzy clustering center, the objective function T(W, V) is minimized. The objective function T(W, V), which represents the weighted sum of the membership of the overall signal sample and different clustering centers, T (W,V) is defined as formula 1:

[0029] Formula one:

[0030] Among them, S is the number of signal strength fingerprint samples, and C is the number of fuzzy cluster centers; repres...

specific Embodiment approach 3

[0042] Specific implementation mode three : This embodiment is a further description of the WLAN indoor step-by-step RD-ANFIS positioning method of Embodiment 1 or 2, and the specific process of the content described in step 4 is:

[0043] Density function for each signal strength fingerprint sample As shown in Formula 6:

[0044] Formula six: , j=1,2,...,S;

[0045] in, , is a positive constant, which represents the curvature of the exponential function; Indicates the valid area of ​​the cluster center;

[0046] According to formula 6, let the signal strength fingerprint sample with the maximum density value be the first fuzzy clustering center;

[0047] Then perform an iterative calculation, and let Indicates the signal strength fingerprint sample at the k-1th iteration the density value, Indicates the density value of the kth fuzzy cluster center, and obtains the signal strength fingerprint sample at the kth iteration according to formula 7 The density ...

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 WLAN (Wireless Local Area Network) indoor step-type RD-ANFIS (Region Division-Adaptive Network-based Fuzzy Inference System) positioning method which relates to a fuzzy-clustering ANFIS indoor positioning method and solves the problems of easy overmatching, reduced environmental suitability and poor positioning precision of an ANFIS system due to large positioning area and complex pattern under the WLAN indoor environment. The positioning method comprises the following steps of: dividing a target positioning area into a plurality of adjacent and communicated subareas according to an FCM (Fuzzy C-Means) clustering technology at the off-line stage, wherein RPs (Reference Points) with similar SNR (Signal to Noise Ratio) distribution characteristics belong to the same subarea; obtaining an initial fuzzy inference principle of each communicated subarea by utilizing a fuzzy subtractive clustering method and building an ANFIS positioning system of each subarea; obtaining a pre-estimated area of the positioning terminal position by comparing an SNR sample average value acquired at a positioning terminal with an Euclidean distance of different clustering centers, and finally realizing accurate coordinate estimation of the position by utilizing the ANFIS positioning system of the area. The invention can be used in the pattern recognition field.

Description

technical field [0001] The invention relates to a fuzzy aggregation type ANFIS indoor positioning method in the field of pattern recognition, in particular to a WLAN indoor positioning method. Background technique [0002] With the increase of people's demand for environmental awareness, the development of short-distance radio communication technology and the increasing demand for new services, the application and demand of LBS (Location Based Services) have attracted more and more attention. Various military and civilian services such as emergency rescue, target search and tracking, resource detection, intelligent guides and material management. Although the Global Positioning System (GPS) and the cellular system are relatively mature in theoretical research and practical application, and can provide high positioning accuracy outdoors; The serious fading phenomenon and multi-path effect caused by it greatly restrict the application of GPS three-ball rendezvous and cellular...

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): H04W16/20H04W64/00H04W84/12
Inventor 马琳徐玉滨周牧孟维晓刘宁庆王孝
Owner HARBIN INST OF TECH
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