Fingerprint indoor positioning method based on binary k-means

An indoor positioning and k-means technology, applied in the field of communication, can solve the problem of poor selection and positioning of the initial clustering center, and achieve the effect of improving accuracy and positioning accuracy

Active Publication Date: 2020-08-25
XIDIAN UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to address the deficiencies of the prior art and propose a fingerprint indoor positioning method based on binary k-means that can effectively improve the poor positioning effect due to the unreasonable selection of the initial clustering center

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
  • Fingerprint indoor positioning method based on binary k-means
  • Fingerprint indoor positioning method based on binary k-means
  • Fingerprint indoor positioning method based on binary k-means

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] In the existing indoor positioning methods, in order to have a better positioning effect, it is often necessary to lay a large number of sensors specially used for positioning in the positioning area, which will lead to waste; when the positioning environment does not change, the positioning effect is better. However, when there are people walking around in the positioning area or obstacles increase or decrease, the positioning accuracy cannot be guaranteed, and the practicability is poor. In some positioning methods, clustering algorithms are used, such as k-means algorithm, so that the positioning results strongly depend on the initial cluster centers of k clusters, so that when the initial cluster centers are not selected properly, the positioning effect is very poor .

[0037] The invention improves the problems existing in the existing positioning method, and proposes a fingerprint indoor positioning method based on bipartite k-means. see figure 1, the positionin...

Embodiment 2

[0057] The fingerprint indoor positioning method based on the binary k-means is the same as that in embodiment 1, step 1b) selects the m APs that have the greatest impact on the positioning result, and generates a simplified fingerprint library, specifically including the following steps;

[0058] 1b1) The n reference points in the positioning area are denoted as (G 1 ,G 2 ,...G n ), using information theory to select m access points with the largest information gain in the location area. When the access point information is not used, that is, when the received signal strength indication data is not collected, the uncertainty of all reference points is:

[0059]

[0060] In the above formula, G j Indicates the jth reference point, P(G j ) is the proportion of the jth reference area in the positioning area in the positioning environment.

[0061] 1b2) When measured from the i-th access point AP i After receiving the signal strength indication data of , the i-th access ...

Embodiment 3

[0069] The fingerprint indoor positioning method based on dichotomous k-means is the same as embodiment 1-2, and the calculation formula of the cluster center in step 2) is:

[0070]

[0071] All the fingerprint data used in the calculation of the above formula come from the simplified fingerprint library. Among them, N i for cluster C i The number of fingerprint data in N ci for cluster C i The number of reference points in c i for cluster C i center of R jl for cluster C i In the lth fingerprint data collected at the jth reference point, n j for cluster C i The number of fingerprint data of the jth reference point in . In the present invention, the i-th cluster C can be calculated by using the above formula i The cluster center c i , c i Can be used to calculate the cluster C i The sum of squared errors.

[0072] The formula for calculating the sum of squared errors is:

[0073]

[0074] The i-th cluster C can be calculated by using the above formula i ...

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 an indoor positioning technology based on bisecting k-means clustering, and solves the problem that the positioning performance is relatively poor due to the fact that an initial clustering centre is selected improperly. The technical scheme comprises the steps of: (1), in an offline stage, acquiring fingerprint data of all reference points, and retaining the fingerprint data from an access point having relatively high resolving power; performing clustering division on the reference points by adopting a bisecting k-means algorithm; and constructing a decision-making tree for each cluster; and (2), in an online stage, acquiring the fingerprint data at an observation point; matching the cluster, which the observation point belongs to, according to the fingerprint data; and performing fine positioning by using the decision-making tree corresponding to the cluster, so that the physical position of the observation point is obtained. On the basis of the fingerprint indoor positioning technology, influence of selection of the initial clustering centre on the positioning effect is considered; clustering division is carried out by selection of the bisecting k-means clustering algorithm; the positioning accuracy rate is increased; and the fingerprint indoor positioning method based on the bisecting k-means in the invention is used in an indoor environment coveredby wifi or capable of being configured with the access point, and is suitable in scenes, such as indoor rescue and personnel positioning in a large place.

Description

technical field [0001] The invention belongs to the technical field of communication, in particular to a fingerprint indoor positioning method, in particular to a fingerprint indoor positioning method based on binary k-means. It can be used for positioning in various indoor environments covered by wifi, and provides users with accurate positioning and a good user experience without additional installation of equipment. Background technique [0002] With the development of communication technology, location-based service has become a new mobile Internet industry and has a good development prospect. Therefore, the need to quickly and accurately obtain location information of a mobile terminal has become increasingly urgent. Positioning information can also be used to support location-based services and improve network management, improving the quality of location services and network performance. Therefore, the positioning technology and its related positioning system that c...

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): H04W4/021H04W4/33H04W64/00G01S5/02
CPCG01S5/0252H04W4/021H04W4/33H04W64/00
Inventor 刘伟陈玉星
Owner XIDIAN UNIV
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