CN114449652B - WIFI indoor positioning method based on reliable AP selection - Google Patents

WIFI indoor positioning method based on reliable AP selection Download PDF

Info

Publication number
CN114449652B
CN114449652B CN202210108078.XA CN202210108078A CN114449652B CN 114449652 B CN114449652 B CN 114449652B CN 202210108078 A CN202210108078 A CN 202210108078A CN 114449652 B CN114449652 B CN 114449652B
Authority
CN
China
Prior art keywords
reliable
fingerprint
aps
deletion rate
rssi
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210108078.XA
Other languages
Chinese (zh)
Other versions
CN114449652A (en
Inventor
罗娟
宋亚红
王纯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University
Original Assignee
Hunan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University filed Critical Hunan University
Priority to CN202210108078.XA priority Critical patent/CN114449652B/en
Publication of CN114449652A publication Critical patent/CN114449652A/en
Application granted granted Critical
Publication of CN114449652B publication Critical patent/CN114449652B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W84/00—Network topologies
    • H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
    • H04W84/10—Small scale networks; Flat hierarchical networks
    • H04W84/12—WLAN [Wireless Local Area Networks]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses a WIFI indoor positioning method based on reliable AP selection, which comprises the following steps: offline stage: acquiring RSSI signals of all reference points in the area to be positioned as fingerprint information, and constructing a fingerprint database; and (3) detecting and updating: introducing a dynamic voting mechanism, dynamically observing and judging voting results in real time, detecting the reliability of each AP according to the voting results, and updating a fingerprint database according to the reliability of each AP so as to ensure the effectiveness of the fingerprint database; on-line stage: and acquiring RSSI signals of the to-be-positioned points, and matching the RSSI signals with reliable fingerprint information in a fingerprint database to obtain the position information of the to-be-positioned points. According to the method, a dynamic voting mechanism is introduced, the AP deletion rate and the fluctuation are utilized, reliable APs in the environment are selected in real time for position estimation, the utilization rate of the reliable APs is improved, errors caused by unreliable APs to positioning are reduced, positioning accuracy is improved, positioning errors are effectively reduced, and contradictions between system overhead and positioning accuracy are balanced.

Description

WIFI indoor positioning method based on reliable AP selection
Technical Field
The invention relates to the technical field of indoor positioning, in particular to a WIFI indoor positioning method based on reliable AP selection.
Background
Along with the development of technology, the requirements of various fields on positioning precision and safety are higher and higher. Reliable indoor positioning service is independent of accurate position information, and complicated indoor environment leads to the indoor positioning technology to be influenced, so that the indoor positioning 'cm-level' requirement makes accurate indoor position service more urgent.
The localization process of traditional fingerprints is generally divided into two phases: an off-line sampling phase and an on-line positioning phase. And acquiring RSSI values of all reference nodes in the positioning area in an offline sampling stage, wherein each node has specific information to form an offline fingerprint database. In the online positioning stage, the actual position of the user is determined by matching the fingerprints acquired in real time with the fingerprints in the fingerprint library through measuring the RSSI value of the position of the target user in real time.
Indoor positioning technology based on WIFI mainly depends on the reliability of an AP, that is, the reliability of a fingerprint, and the fingerprint has a certain timeliness, and only reliable fingerprint information can provide reliable Location-based services (LBS). The biggest problem in using indoor positioning technology based on WIFI fingerprint is that the received RSSI shows variability and complexity, such as multipath interference caused by indoor obstacles to the RSSI, signal attenuation caused by increase of signal propagation distance, metal to signal interference, and the like.
At present, some researches focus on redundancy of APs in indoor positioning, and mainly reduce fingerprints used for positioning by improving an AP selection algorithm, so that calculation overhead of a positioning system is reduced, but unreliable APs are brought into position calculation, and improvement of positioning accuracy and reduction of system energy consumption are difficult to achieve. Some studies aim at weighting APs used for positioning, however ignoring the effect of timeliness of the fingerprint library itself on positioning results, and thus it is difficult to provide high accuracy positioning. The indoor environment is dynamically changeable, so that in a period of time with a short distance between the front and back, the difference of successively acquired fingerprint information is large, and the value of information stored in an original fingerprint database is reduced along with the time, so that the reliability of the AP for positioning is reduced. Therefore, how to select reliable APs and guarantee system timeliness in an emergency environment is particularly important for position estimation.
Disclosure of Invention
In view of the shortcomings of the prior art, the invention provides a WIFI indoor positioning method based on reliable AP selection, which aims to identify unstable APs damaged due to external environments under emergency conditions, and reliable APs are selected for establishing fingerprint libraries and extracting effective fingerprints in indoor positioning so as to improve reliable fingerprint utilization rate and positioning accuracy.
A WIFI indoor positioning method based on reliable AP selection comprises the following steps:
offline stage: acquiring RSSI signals of all reference points in the area to be positioned as fingerprint information, and constructing a fingerprint database;
and (3) detecting and updating: introducing the deletion rate and volatility of the APs into a dynamic voting mechanism, detecting the reliability of each AP, selecting the reliable AP, and updating a fingerprint database according to the reliability of the fingerprint database;
on-line stage: and acquiring RSSI signals of the to-be-positioned points, and matching the RSSI signals with reliable fingerprint information in a fingerprint database to obtain the position information of the to-be-positioned points.
Further, the fingerprint database includes: coordinates (X, Y) of each AP, coordinates (X, Y) of reference points, RSSI signals ψ, a fluctuation matrix SD of RSSI, a deletion rate matrix LR of AP.
Further, the offline stage includes:
dividing the area to be positioned into a plurality of grids according to a certain distance, wherein each grid point is used as a reference point, and the position of each reference point is expressed in a coordinate form;
acquiring RSSI signals of all APs at all reference points to form an initial fingerprint database;
expanding an initial fingerprint database and constructing the fingerprint database.
Further, the detecting update phase includes:
calculating the deletion rate from each AP at each reference point, and calculating the volatility of a group of continuous RSSI signals acquired by each AP at different reference points;
taking the deletion rate and volatility of the APs into a dynamic voting mechanism, and voting each AP;
according to the voting result of each AP, calculating the corresponding deletion rate weight and fluctuation weight of each AP;
the obtained weight of each AP is utilized to sort according to descending order, and the first K reliable APs are selected, wherein K is a preset value;
and calculating final weights of the first K reliable APs according to the deletion rate weights and the volatility weights of the first K reliable APs.
Further, the online phase includes:
acquiring RSSI signals of the to-be-positioned points, and calculating the initial similarity between the RSSI signals and reliable fingerprint information in a fingerprint database; the reliable fingerprint information is a fingerprint formed by RSSI values of K reliable APs;
according to final weights and initial similarities of the K reliable APs, calculating fingerprint similarities of RSSI signals of the to-be-positioned points and reliable fingerprint information;
sorting the fingerprint similarity in ascending order, selecting the first T reference points, and calculating weights of the first T reference points; wherein T is a preset value;
and calculating the coordinates of the to-be-positioned point based on the coordinates and the weights of the T reference points.
Further, the deletion rate matrix of the APs comprises deletion rates of the APs at each reference point; determining the missing rate of each AP at each reference point by continuously scanning each AP the same number of times N at each reference point and recording the number of times N of receiving the RSSI value from each AP;
the RSSI fluctuation matrix comprises the fluctuation of a group of continuous RSSI values of each AP obtained at each reference point; the volatility is expressed as the standard deviation of the set of RSSI values.
Further, the step of incorporating the deletion rate and volatility of the APs into a dynamic voting mechanism to vote on each AP specifically includes:
voting the AP based on the deletion rate, and when the deletion rate of one AP at the current moment of the reference point is larger than a preset deletion rate threshold value, considering that the AP at the current moment is unreliable at the reference point, and automatically counting one vote for the AP;
and voting the AP based on the fluctuation, and when the fluctuation of one AP at the current moment at the reference point is larger than a set fluctuation threshold value, considering that the AP at the current moment is unreliable at the reference point, and automatically counting one vote for the AP.
Further, according to the voting result of each AP, the calculating the deletion rate weight and the volatility weight corresponding to each AP specifically includes:
the deletion rate weight of each AP is calculated by the following formula:
Figure BDA0003494038910000031
in the method, in the process of the invention,
Figure BDA0003494038910000032
weight indicating deletion rate of ith AP, < ->
Figure BDA0003494038910000033
Representing the number of votes obtained by the ith AP based on the deletion rate; m represents the total number of reference points;
the volatility weight of each AP is calculated by the following formula:
Figure BDA0003494038910000034
in the method, in the process of the invention,
Figure BDA0003494038910000035
volatility weight of ith AP, < ->
Figure BDA0003494038910000036
Indicating the number of votes obtained by the ith AP based on volatility.
Further, initial similarity D j Using the Euclidean distance representation of the RSSI signal of the to-be-positioned point and the reliable fingerprint;
fingerprint similarity D' j And according to final weights and initial similarity of the K reliable APs, calculating to obtain:
Figure BDA0003494038910000037
wherein W 'is' i Representing the final weight of the ith AP;
weights w of jth reference point of the first T reference points j The calculation formula is as follows:
Figure BDA0003494038910000038
coordinates of the site to be localized
Figure BDA0003494038910000039
The calculation formula is as follows:
Figure BDA00034940389100000310
wherein, (x) j ,y j ) Representing the coordinates of the j-th reference point of the first T selected reference points.
Further, the updating the fingerprint database according to the reliability of the fingerprint database includes:
the detection mechanism is as follows: calculating a certain known position coordinate (x i ,y i ) By calculating the estimated position (x 0 ,y 0 ) Error delta from true position i If the error is greater than a preset error threshold, the fingerprint database is unreliable, and an updating mechanism is entered;
update mechanism: recalculating the deletion rate and volatility of the AP, storing the deletion rate and volatility, and returning to the detection mechanism step; if the recalculated error is smaller than the preset error threshold, the update is effective, and the update result is reserved in the fingerprint database.
Advantageous effects
The invention provides a WIFI indoor positioning method based on reliable AP selection, which is characterized in that in an off-line stage, RSSI signals of all reference points in an area to be positioned are collected, the RSSI signals are used as position fingerprints, and a fingerprint database is constructed; in the detection updating stage, introducing the deletion rate and volatility of the AP into a dynamic voting mechanism, and detecting the reliability of the AP according to requirements; and in the online stage, RSSI signals of the to-be-positioned points are collected and matched with reliable fingerprint information in a fingerprint database, and position coordinates of the to-be-positioned points are calculated. According to the method, a dynamic voting mechanism is introduced, the AP deletion rate and the fluctuation are utilized, reliable APs in the environment are selected in real time for position estimation, the utilization rate of the reliable APs is improved, errors caused by unreliable APs to positioning are reduced, positioning accuracy is improved, and positioning errors are effectively reduced. On the other hand, the effectiveness of the system is ensured, and the updating times of the fingerprint database are controlled according to a dynamic voting mechanism, so that the equilibrium contradiction between the positioning precision and the overhead of the system is solved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a WIFI indoor positioning method based on reliable AP selection according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, based on the examples herein, which are within the scope of the invention as defined by the claims, will be within the scope of the invention as defined by the claims.
As shown in fig. 1, the embodiment of the invention provides a WIFI indoor positioning method based on reliable AP selection, which mainly includes an offline stage, a detection update stage and an online stage, and is specifically as follows.
Offline stage: and acquiring RSSI signals of all reference points in the area to be positioned as fingerprint information, and constructing a fingerprint database.
S1: dividing the area to be positioned into a plurality of grids according to a certain distance, wherein each grid point is used as a reference point; abstracting a region to be positioned into a two-dimensional plane, and establishing a coordinate system; dividing the area to be positioned into M=m×p square grids, wherein the position of each reference point is expressed in a coordinate form; l AP (Access Point) are arranged in the area to be positioned, and the placement form of the AP is not fixed.
S2: RSSI (Received signal strength indication) signals from the various APs were collected q times at each reference point. In order to ensure the signal effectiveness, the embodiment adopts a mode of collecting and calculating the average value for a plurality of times, so that the average value of the RSSI signals of all the reference points is obtained and is used as the final RSSI signal of the corresponding reference point, and an initial fingerprint database is formed. Wherein the RSSI signal of the ith AP of the jth reference pointMean rssi i,j Can be calculated by the following formula:
Figure BDA0003494038910000051
wherein, rssi i,j (τ) represents the RSSI signal of the ith AP acquired the jth time at the jth reference point.
S3: expanding an initial fingerprint database based on the acquired data, and constructing the fingerprint database. The fingerprint database includes: the coordinates (X, Y) of each AP, the coordinates (X, Y) of the reference points, the RSSI signal psi, the fluctuation matrix SD of the RSSI, the loss rate matrix LR of the AP, the distance matrix D between the reference points and the voting matrix V of the fluctuation degree are also included in the embodiment sd Voting matrix V based on deletion rate lr The method is specifically expressed as follows: (X, Y, X, Y; ψ; SD; LR; D; V) sd ；V lr )。
The RSSI signal ψ is specifically expressed as:
Figure BDA0003494038910000052
the loss rate matrix LR of APs includes loss rates of the APs at each reference point, specifically expressed as:
Figure BDA0003494038910000053
wherein lr is i,j Indicating that the deletion rate of the ith AP was acquired at the jth reference point. The missing rate of each AP at each reference point is determined by continuously scanning each AP the same number of times N at each reference point and recording the number of times N that the RSSI value from each AP was received; lr (lr) i,j The concrete steps are as follows: lr (lr) i,j ＝(N-n)/N。
The fluctuation matrix SD of the RSSI comprises the fluctuation of a group of continuous RSSI values obtained from each AP at each reference point; the volatility is expressed as the standard deviation of the set of RSSI values. The fluctuation matrix SD of RSSI is specifically expressed as:
Figure BDA0003494038910000054
the volatility of a set of RSSI signals acquired from the ith AP at the jth reference point is sd i,j The specific calculation formula is as follows:
Figure BDA0003494038910000061
where q represents the number of samples of the RSSI signal of the AP received at the reference point, φ i,j (τ) represents the RSSI signal sample value of the ith AP acquired the jth time at the jth reference point,
Figure BDA0003494038910000062
represents the average value of the RSSI signal sample values of the i-th AP acquired at the j-th reference point.
Voting matrix V of fluctuation degree sd Voting matrix V based on deletion rate for volatility threshold matrix lr Is a matrix of deletion rate thresholds.
And (3) detecting and updating: introducing the deletion rate and volatility of the APs into a dynamic voting mechanism, detecting the reliability of each AP, selecting the reliable AP, and updating the fingerprint database according to the reliability of the fingerprint database. The method specifically comprises the following steps:
s4: the method comprises the steps of calculating the deletion rate of each AP at each reference point in real time, and calculating the fluctuation of a group of continuous RSSI signals acquired by each AP at different reference points in real time.
S5: and incorporating the deletion rate and volatility of the APs into a dynamic voting mechanism, and voting each AP. The more votes, the less reliable the AP is at the reference point, the less stable its signal. The dynamic voting mechanism counts the voting conditions at all moments in a preset time period, so that a dynamic result which changes along with time can be obtained. The dynamic results can also be used to analyze the front-to-back correlation.
The method specifically comprises the following steps:
voting the AP based on the deletion rate, and within a preset time periodWhen the reference point is at the current moment, the deletion rate of a certain AP is larger than a preset deletion rate threshold delta lr The AP is considered unreliable at the reference point at the current moment, and voting is automatically counted into the AP once; wherein the deletion rate threshold delta lr Can be set manually;
and voting the AP based on the fluctuation, and automatically counting the voting for the AP once when the fluctuation of the AP at the current moment at the reference point is larger than a set fluctuation threshold value in a preset time period. Specifically, the current time fluctuation matrix SD' is specifically expressed as:
Figure BDA0003494038910000063
if the fluctuation sd 'of the RSSI signal of the ith AP acquired by the jth reference point at the current moment' i,j Satisfy sd' i,j >sd i,j +Δ sd The ith AP is deemed unreliable and is automatically counted for a vote, where delta sd Is a trust threshold that can be set manually.
S6: and calculating the deletion rate weight and the volatility weight corresponding to each AP according to the voting result of each AP. That is, the decision method of the voting result is to quantitatively determine the weight, and the number of votes obtained is converted into the weight. The method specifically comprises the following steps:
the loss rate weight calculation formula is as follows:
Figure BDA0003494038910000071
wherein,,
Figure BDA0003494038910000072
indicating the deletion rate weight of the ith AP, i.e., the degree of reliability of the reaction,/->
Figure BDA0003494038910000073
Representing the number of votes obtained by the ith AP based on the deletion rate, and M represents the total number of reference points;
the calculation formula of the fluctuation weight is as follows:
Figure BDA0003494038910000074
wherein,,
Figure BDA0003494038910000075
indicating the fluctuation weight of the ith AP, i.e., the degree of reaction stability, +.>
Figure BDA0003494038910000076
Indicating the number of votes obtained by the ith AP based on volatility.
S7: and selecting the first K reliable APs by using the obtained weight of each AP according to descending order, wherein K is a preset value.
S8: and calculating final weights of the first K reliable APs according to the deletion rate weights and the volatility weights of the first K reliable APs. Final weight W 'of ith AP' i The calculation formula is as follows:
Figure BDA0003494038910000077
on-line stage: and acquiring RSSI signals of the to-be-positioned points, and matching the RSSI signals with reliable fingerprint information in a fingerprint database to obtain the position information of the to-be-positioned points.
S9: acquiring RSSI signals of the to-be-positioned points, and calculating the initial similarity between the RSSI signals and reliable fingerprint information in a fingerprint database; the reliable fingerprint information is a fingerprint formed by RSSI values of K reliable APs. Specifically:
initial similarity D j The euclidean distance of the RSSI signal from the reliable fingerprint is used to represent the position to be determined. RSSI signals of K reliable APs at the undetermined site are selected and expressed as [ rsi ] 1 ,rssi 2 ,…,rssi K ]The method comprises the steps of carrying out a first treatment on the surface of the Reliable fingerprint information at the jth reference point, i.e., RSSI signals of K reliable APs, is denoted as [ rsi ] 1,j ,rssi 2,j ,…,rssi K,j ]The method comprises the steps of carrying out a first treatment on the surface of the Initial similarity D j The calculation formula is as follows:
Figure BDA0003494038910000078
wherein D is j Representing the initial similarity of the pending site to the jth reference point.
S10: and calculating the fingerprint similarity of the RSSI signal of the to-be-positioned point and the reliable fingerprint information according to the final weight and the initial similarity of the K reliable APs. The fingerprint similarity calculation formula is as follows:
Figure BDA0003494038910000079
wherein D 'is' j Representing the fingerprint similarity of the pending site to the j-th reference point.
S11: sorting the fingerprint similarity in ascending order, selecting the first T reference points, and calculating weights of the first T reference points; wherein T is a preset value. The weight calculation formula of the j-th reference point is as follows:
Figure BDA0003494038910000081
wherein w is j ' represents the weight of the jth reference point.
S12: and calculating the coordinates of the to-be-positioned point based on the coordinates and the weights of the T reference points. The specific calculation formula is as follows:
Figure BDA0003494038910000082
wherein,,
Figure BDA0003494038910000083
representing coordinates of the anchor point, (x) j ,y j ) Coordinates of a j-th reference point in the corresponding selected T reliable reference points.
In this embodiment, updating the fingerprint database according to the reliability of the fingerprint database includes:
the detection mechanism is as follows: calculating a certain known position coordinate (x i ,y i ) By calculating the estimated position (x 0 ,y 0 ) Error delta from true position i If the error delta i If the error threshold value is larger than the preset error threshold value T, the fingerprint database is unreliable, and an updating mechanism is entered; wherein the error delta i The calculation formula is as follows:
Figure BDA0003494038910000084
update mechanism: recalculating the deletion rate and volatility of the AP, storing the deletion rate and volatility, and returning to the detection mechanism step; if the error delta is recalculated i And if the updating result is smaller than the preset error threshold T, the updating is effective, and the updating result is reserved in the fingerprint database.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and further implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.

Claims (8)

1. The WIFI indoor positioning method based on reliable AP selection is characterized by comprising the following steps:
offline stage: acquiring RSSI signals of all reference points in the area to be positioned as fingerprint information, and constructing a fingerprint database;
and (3) detecting and updating: introducing the deletion rate and volatility of the APs into a dynamic voting mechanism, detecting the reliability of each AP in real time, selecting the reliable AP, and updating a fingerprint database according to the reliability of the fingerprint database;
on-line stage: acquiring RSSI signals of the to-be-positioned points, and matching the RSSI signals with reliable fingerprint information in a fingerprint database to obtain the position information of the to-be-positioned points;
the detection update phase includes:
calculating the deletion rate from each AP at each reference point, and calculating the volatility of a group of continuous RSSI signals acquired by each AP at different reference points;
taking the deletion rate and volatility of the APs into a dynamic voting mechanism, and voting each AP;
according to the voting result of each AP, calculating the corresponding deletion rate weight and fluctuation weight of each AP;
the obtained weight of each AP is utilized to sort according to descending order, and the first K reliable APs are selected, wherein K is a preset value;
calculating final weights of the first K reliable APs according to the deletion rate weights and the fluctuation weights of the first K reliable APs; final weight W of the ith AP of the first K reliable APs i ′ The calculation formula is as follows:
Figure FDA0004096358800000011
wherein (1)>
Figure FDA0004096358800000012
Weight indicating deletion rate of ith AP, < ->
Figure FDA0004096358800000013
The volatility weight of the ith AP;
the online phase includes:
acquiring RSSI signals of the to-be-positioned points, and calculating the initial similarity between the RSSI signals and reliable fingerprint information in a fingerprint database; the reliable fingerprint information is a fingerprint formed by RSSI values of K reliable APs;
according to final weights and initial similarities of the K reliable APs, calculating fingerprint similarities of RSSI signals of the to-be-positioned points and reliable fingerprint information;
sorting the fingerprint similarity in ascending order, selecting the first T reference points, and calculating weights of the first T reference points; wherein T is a preset value;
and calculating the coordinates of the to-be-positioned point based on the coordinates and the weights of the T reference points.
2. The reliable AP selection-based WIFI indoor positioning method according to claim 1, wherein the fingerprint database includes: coordinates of each AP, coordinates of reference points, RSSI signals, a fluctuation matrix of the RSSI and a deletion rate matrix of the AP.
3. The reliable AP selection-based WIFI indoor positioning method according to claim 2, wherein the offline phase includes:
dividing the area to be positioned into a plurality of grids according to a certain distance, wherein each grid point is used as a reference point, and the position of each reference point is expressed in a coordinate form;
acquiring RSSI signals of all APs at all reference points to form an initial fingerprint database;
expanding an initial fingerprint database and constructing the fingerprint database.
4. The reliable AP selection-based WIFI indoor positioning method according to claim 2, wherein the AP deletion rate matrix includes a deletion rate of each AP at each reference point; determining the missing rate of each AP at each reference point by continuously scanning each AP the same number of times N at each reference point and recording the number of times N of receiving the RSSI value from each AP;
the RSSI fluctuation matrix comprises the fluctuation of a group of continuous RSSI values of each AP obtained at each reference point; the volatility is expressed as the standard deviation of the set of RSSI values.
5. The WIFI indoor positioning method according to claim 1, wherein the incorporating the missing rate and the volatility of the APs into the dynamic voting mechanism votes for each AP, specifically includes:
voting the AP based on the deletion rate, and when the deletion rate of one AP at the current moment of the reference point is larger than a preset deletion rate threshold value, considering that the AP at the current moment is unreliable at the reference point, and automatically counting one vote for the AP;
and voting the AP based on the fluctuation, and when the fluctuation of one AP at the current moment at the reference point is larger than a set fluctuation threshold value, considering that the AP at the current moment is unreliable at the reference point, and automatically counting one vote for the AP.
6. The WIFI indoor positioning method according to claim 5, wherein the calculating the deletion rate weight and the volatility weight corresponding to each AP according to the voting result of each AP specifically includes:
the deletion rate weight of each AP is calculated by the following formula:
Figure FDA0004096358800000021
in the method, in the process of the invention,
Figure FDA0004096358800000022
weight indicating deletion rate of ith AP, < ->
Figure FDA0004096358800000023
Representing the number of votes obtained by the ith AP based on the deletion rate; m represents the total number of reference points;
the volatility weight of each AP is calculated by the following formula:
Figure FDA0004096358800000024
in the method, in the process of the invention,
Figure FDA0004096358800000025
volatility weight of ith AP, < ->
Figure FDA0004096358800000026
Indicating the number of votes obtained by the ith AP based on volatility.
7. The reliable AP selection-based WIFI indoor positioning method according to claim 1, wherein the initial similarity D j Using the Euclidean distance representation of the RSSI signal of the to-be-positioned point and the reliable fingerprint;
fingerprint similarity D j ′ And according to final weights and initial similarity of the K reliable APs, calculating to obtain:
Figure FDA0004096358800000027
in which W is i ′ Representing the final weight of the ith AP;
′
weights w of jth reference point of the first T reference points j The calculation formula is as follows:
Figure FDA0004096358800000031
coordinates of the site to be localized
Figure FDA0004096358800000032
The calculation formula is as follows:
Figure FDA0004096358800000033
wherein, (x) j ,y j ) Representing the coordinates of the j-th reference point of the first T selected reference points.
8. The WIFI indoor positioning method according to any of claims 2 to 7, wherein updating the fingerprint database according to the fingerprint database reliability comprises:
the detection mechanism is as follows: calculating a certain known position coordinate by utilizing fingerprints in the existing fingerprint database, calculating the error between the estimated position and the real position of the position for a plurality of times, if the error is larger than a preset error threshold value, making the fingerprint database unreliable, and entering an updating mechanism;
update mechanism: recalculating the deletion rate and volatility of the AP, storing the deletion rate and volatility, and returning to the detection mechanism step; if the recalculated error is smaller than the preset error threshold, the update is effective, and the update result is reserved in the fingerprint database.
CN202210108078.XA 2022-01-28 2022-01-28 WIFI indoor positioning method based on reliable AP selection Active CN114449652B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210108078.XA CN114449652B (en) 2022-01-28 2022-01-28 WIFI indoor positioning method based on reliable AP selection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210108078.XA CN114449652B (en) 2022-01-28 2022-01-28 WIFI indoor positioning method based on reliable AP selection

Publications (2)

Publication Number Publication Date
CN114449652A CN114449652A (en) 2022-05-06
CN114449652B true CN114449652B (en) 2023-05-02

Family

ID=81372650

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210108078.XA Active CN114449652B (en) 2022-01-28 2022-01-28 WIFI indoor positioning method based on reliable AP selection

Country Status (1)

Country Link
CN (1) CN114449652B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118102443B (en) * 2024-04-18 2024-07-02 青岛日日盛智能科技有限公司 High-precision indoor positioning method and system

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926675A (en) * 2021-03-22 2021-06-08 哈尔滨工业大学（深圳） Multi-view multi-label classification method for depth incompletion under dual deficiency of view angle and label

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105282758A (en) * 2015-09-06 2016-01-27 华南理工大学 Self-adaptive dynamic construction method of WIFI indoor positioning system fingerprint database
CN107046680B (en) * 2017-05-22 2019-09-24 湖南大学 A kind of indoor orientation method based on trustworthy location fingerprint
US11122397B2 (en) * 2019-11-20 2021-09-14 Mitsubishi Electric Research Laboratories, Inc. Localization using millimeter wave beam attributes
CN112714493B (en) * 2020-12-29 2023-03-24 北京工业大学 Object position positioning method and positioning system
CN112887904B (en) * 2021-01-27 2022-05-03 电子科技大学 WiFi positioning method suitable for intelligent stadium

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926675A (en) * 2021-03-22 2021-06-08 哈尔滨工业大学（深圳） Multi-view multi-label classification method for depth incompletion under dual deficiency of view angle and label

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
莫永强.基于Wi-Fi信号SLR的AP选取算法.《城市勘测》.2019,118-121. *

Also Published As

Publication number Publication date
CN114449652A (en) 2022-05-06

Similar Documents

Publication Publication Date Title
CN108989976B (en) Fingerprint positioning method and system in intelligent classroom
CN106851573B (en) Log path loss model-based joint weighting K nearest neighbor indoor positioning method
McIntyre et al. A nearest-centroid technique for evaluating the minimum-variance clustering procedure
CN106646338B (en) A kind of quickly accurate indoor orientation method
CN103796305B (en) Indoor positioning method based on Wi-Fi position fingerprint
Wang et al. Learning to improve WLAN indoor positioning accuracy based on DBSCAN-KRF algorithm from RSS fingerprint data
CN107339992B (en) Indoor positioning and landmark semantic identification method based on behaviors
CN105120433A (en) WLAN indoor positioning method based on continuous sampling and fuzzy clustering
CN104394588B (en) Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling
CN103473786A (en) Gray level image segmentation method based on multi-objective fuzzy clustering
CN112887902A (en) Indoor positioning method of WiFi fingerprint based on Gaussian clustering and hybrid measurement
CN106793085A (en) Fingerprint positioning method based on normality assumption inspection
CN114449652B (en) WIFI indoor positioning method based on reliable AP selection
CN111726765A (en) WIFI indoor positioning method and system for large-scale complex scene
Shao et al. Floor identification in large-scale environments with wi-fi autonomous block models
CN108566620A (en) A kind of indoor orientation method based on WIFI
Jin et al. Toward scalable and robust indoor tracking: Design, implementation, and evaluation
CN108810799A (en) A kind of more floor indoor orientation methods and system based on linear discriminant analysis
CN114679683B (en) Indoor intelligent positioning method based on derived fingerprint migration
CN115754199B (en) Water quality detection method based on membership function and principal component analysis
CN111669702A (en) Coarse and fine matching positioning method based on WIFI address and field intensity
CN108519579B (en) WiFi fingerprint positioning method for analyzing optimal AP based on interval overlapping degree
CN111836188A (en) Online cooperative positioning and system based on Wi-Fi RSS
Zhang et al. GraphSLAM-based Crowdsourcing framework for indoor Wi-Fi fingerprinting
CN116819436A (en) Landmark matching PDR positioning method under multi-intersection scene

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant