Method for building database for fingerprinting positioning and fingerprinting positioning method using the built database

Patent metadata

Field	Value
Publication number	US-9609615-B2
Application number	US-201514722940-A
Country	US
Kind code	B2
Filing date	May 27, 2015
Priority date	Dec 4, 2014
Publication date	Mar 28, 2017
Grant date	Mar 28, 2017

Abstract

A method for building a database for fingerprinting positioning including: generating, by a database building device, raw data by collecting received signal strengths (RSSs) for access points (APs) at each sample point (SP); and generating a cluster table by clustering SPs for each of the APs according to the RSS for the AP, using the generated raw data.

First claim

What is claimed is:

1. A method for building a database for fingerprinting positioning, comprising:
generating, by a database building device, raw data by collecting received signal strengths (RSSs) for access points (APs) at each sample point (SP);
generating a cluster table by clustering SPs for each of the APs according to the RSS for the AP, using the generated raw data; and
building, by the database building device, a radio map by deleting data of which RSS measurement rates are equal to or less than a predetermined reference value, from the generated raw data,
wherein:
the generating of the cluster table comprises:
estimating, by the database building device, a signal attenuation rate per distance in a state where the SP having the maximum RSS is set to the start point;
determining the number of clusters according to the estimated signal attenuation rate per distance;
calculating the initial center value of a cluster based on a difference between the maximum value and the minimum value of the RSS and the number of clusters for an arbitrary AP; and
calculating a final center value of the cluster for the arbitrary AP by performing an unsupervised learning algorithm using the calculated initial center value as a start value;

in the generating of the raw data, the database building device generates the raw data by repetitively measuring the RSSs for the respective APs at each SP; and
in the calculating of the initial center value based on the difference between the maximum value and the minimum value of the RSS and the number of clusters, the database building device calculates the center value of an m-th cluster by the following equation:

R
min

+

(

m
-

1
2

)

×

R
max

-

R
min

CN

,

where R min represents the minimum value of the RSS, R max represents the maximum value of the RSS, and CN represents the number of clusters.

2. The method of claim 1 , further comprising, after the building of the radio map:
measuring, by the database building device, RSSs for the respective APs at an arbitrary SP;
calculating a gap ratio indicating a difference in RSS stored in the radio map between the arbitrary SP and an SP adjacent to the arbitrary SP, based on the measured RSSs; and
correcting radio map data on the arbitrary SP based on the measured RSSs, when the calculated gap ratio is equal to or less than a predetermined ratio.

3. The method of claim 2 , wherein the calculating of the gap ratio comprises:
calculating, by the database building device, gap values indicating differences between the RSSs stored in the radio map and the measured RSSs for each of SPs existing within a predetermined distance from the arbitrary SP; and
calculating the gap ratio based on the calculated gap values.

4. The method of claim 3 , wherein the calculating of the gap values comprises:
calculating, by the database building device, the differences by subtracting the measured RSSs from the RSSs stored in the radio map for the respective APs at each of the SPs existing within the predetermined distance; and
calculating the gap values for each of the SPs existing within the predetermined distance by calculating a mean of the differences for the respective APs, calculated for each of the SPs.

5. A method for building a database for fingerprinting positioning, comprising:
generating, by a database building device, raw data by collecting received signal strengths (RSSs) for access points (APs) at each sample point (SP);
generating a cluster table by clustering SPs for each of the APs according to the RSS for the AP, using the generated raw data;
building, by the database building device, a radio map by deleting data of which RSS measurement rates are equal to or less than a predetermined reference value, from the generated raw data;
measuring, by the database building device, RSSs for the respective APs at an arbitrary SP;
calculating a gap ratio indicating a difference in RSS stored in the radio map between the arbitrary SP and an SP adjacent to the arbitrary SP, based on the measured RSSs; and
correcting radio map data on the arbitrary SP based on the measured RSSs, when the calculated gap ratio is equal to or less than a predetermined ratio,
wherein:
in the generating of the raw data, the database building device generates the raw data by repetitively measuring the RSSs for the respective APs at each SP;
the calculating of the gap ratio comprises:
calculating, by the database building device, gap values indicating differences between the RSSs stored in the radio map and the measured RSSs for each of SPs existing within a predetermined distance from the arbitrary SP; and
calculating the gap ratio based on the calculated gap values; and

the calculating of the gap ratio based on the calculated gap values comprises:
calculating, by the database building device, a standard deviation of the calculated gap values; and
calculating the gap ratio by dividing a difference between the smallest value and the second smallest value among the calculated gap values by the calculated standard deviation.

6. The method of claim 1 , further comprising building, by the database building device, a radio map by deleting data of which RSS deviations are less than a reference value at each of the APs, from the generated raw data.

7. A fingerprinting positioning method using a built database, comprising:
measuring, by a location estimation device, received signal strengths (RSSs) for access points (APs);
determining a search region for location estimation using the measured RSSs and a cluster table contained in the built database; and
estimating a current location of the location estimation device by performing fingerprinting positioning in the determined search region, wherein:
the built database comprises a radio map and the cluster table, and is built for fingerprinting positioning;
the radio map stores the RSSs for the respective APs at each SP;
the cluster table stores a center value of a cluster for each of the APs, generated by clustering SPs for the AP according to the RSS for the AP, and a list of SPs included in the center value;
the determining of the search region comprises:
selecting, by the location estimation device, a center value which is the closest to the measured RSS among the center values stored in the cluster table, for each of the APs; and
determining the search region based on SPs included in the selected center values;
in the selecting of the center value which is the closest to the measured RSS, the location estimation device selects n APs of which signal states are favorable, and selects the center values for the n APs;
the determining of the search region based on the SPs comprises:
selecting, by the location estimation device, SPs having the largest number of overlap times for the n APs among the SPs, as search points; and
determining the search region based on th

Assignees

• Hyundai Mobis Co Ltd

Inventors

• Jung Jong In

Classifications

• H04W4/029

  Location-based management or tracking services · CPC title

• H04W84/12

  WLAN [Wireless Local Area Networks] · CPC title

• G01S11/06 Primary

  using intensity measurements · CPC title

• H04W4/023

  using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds · CPC title

• H04W64/00 Primary

  Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management · CPC title