CN107484123B - WiFi indoor positioning method based on integrated HWKNN - Google Patents

WiFi indoor positioning method based on integrated HWKNN Download PDF

Info

Publication number
CN107484123B
CN107484123B CN201710600157.1A CN201710600157A CN107484123B CN 107484123 B CN107484123 B CN 107484123B CN 201710600157 A CN201710600157 A CN 201710600157A CN 107484123 B CN107484123 B CN 107484123B
Authority
CN
China
Prior art keywords
access point
wifi access
indoor
wifi
positioning
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
CN201710600157.1A
Other languages
Chinese (zh)
Other versions
CN107484123A (en
Inventor
陈绍建
龙云亮
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.)
Sun Yat Sen University
Original Assignee
Sun Yat Sen 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 Sun Yat Sen University filed Critical Sun Yat Sen University
Priority to CN201710600157.1A priority Critical patent/CN107484123B/en
Publication of CN107484123A publication Critical patent/CN107484123A/en
Application granted granted Critical
Publication of CN107484123B publication Critical patent/CN107484123B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/318—Received signal strength
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/391—Modelling the propagation channel
    • 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
    • H04W4/025—Services making use of location information using location based information parameters
    • H04W4/04—

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Quality & Reliability (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)
  • Other Investigation Or Analysis Of Materials By Electrical Means (AREA)

Abstract

The invention discloses a WiFi indoor positioning method based on integrated HWKNN, which comprises the following steps: 1) constructing a reliable indoor WiFi fingerprint database; 2) estimating the position coordinates of each access point and a corresponding indoor path loss model according to the established fingerprint database; 3) when calculating the Euclidean distance between the node to be positioned and the fingerprint database, giving weight to corresponding dimensionality by using the indoor path loss model obtained in the step 2); 4) selecting K reference points with the minimum distance from the Euclidean distances obtained in the step 3), weighting the K reference points according to the signal strength similarity and determining the position of a node to be positioned; 5) and (3) taking the method in the step 2-4) as a weak positioning method, and constructing a plurality of weak positioning estimators by randomly selecting the size of the K value and the number of the access points to finally estimate the position coordinates of the node to be positioned. The positioning algorithm provided by the invention can effectively enhance the robustness of indoor positioning and finally realize accurate indoor positioning.

Description

WiFi indoor positioning method based on integrated HWKNN
Technical Field
The invention relates to the field of machine learning, wireless transmission and indoor positioning, in particular to a WiFi indoor positioning method based on integrated HWKNN.
Background
With the wide application of mobile devices and the popularization of wireless networks, Location Based Services (LBS) can not only acquire user location information but also further mine user behavior information, so the LBS shows good academic development prospects and wide market demands. In the field of outdoor positioning, a Global Positioning System (GPS) has achieved precise positioning, but it is still difficult to achieve precise positioning in an indoor environment.
In the last decade, with the development of WiFi technology and the increasing coverage of wireless access points, a series of methods have been proposed for indoor positioning based on Wireless Local Area Networks (WLANs). However, due to indoor wireless signal propagation complexity, it is not easy to find the location of the Access Point (AP) and determine the coefficients of the propagation model. In the WiFi-based propagation model positioning method, the main technologies are an AOA model, a TOA model, a TDOA model and a signal path loss model. However, due to the complexity of the indoor environment, the user self-blocking, the different directions of the mobile phone and other interference factors make indoor positioning unable to meet the high accuracy requirements. Therefore, there is an urgent need to develop a low-cost, high-accuracy WiFi-based Indoor Positioning System (IPS) for LBS.
Compared with indoor positioning based on a propagation model, indoor positioning based on WiFi fingerprints is easier to deploy, low in cost and capable of effectively tolerating wireless signal noise, and therefore the highest precision is achieved. The traditional K Nearest Neighbor (KNN) algorithm is one of the most commonly used algorithms in indoor positioning, firstly, Euclidean distances between signal strengths of all WiFi access points received by a node to be positioned and signal strengths of reference points in a fingerprint database are calculated, then K nearest reference points are found out, influences of reference points with high similarity on positioning results are increased by utilizing different weighting modes, and finally, the position coordinates of the node to be positioned are estimated. However, due to the complexity of the indoor environment, the signal strengths from different WiFi access points are often interfered by external factors to different degrees, the relationship between the signal strength and the physical location is not a simple linear mapping relationship, and an unstable WiFi access point cannot be determined at a node to be positioned, thereby causing the reduction of the positioning accuracy.
Disclosure of Invention
The invention mainly aims to overcome the technical defects and provides a WiFi indoor positioning method based on integrated HWKNN, which not only considers the Euclidean distance between reference fingerprints, but also considers the nonlinear relation between signal strength and physical positions and the influence of signal values with different strengths on a positioning result during positioning, and a strong positioning estimator is formed by a plurality of weak positioning estimators to increase the robustness of a positioning system, so that the positioning accuracy is improved.
In order to achieve the purpose, the technical scheme of the invention is as follows:
an integrated HWKNN-based WiFi indoor positioning method comprises the following steps:
1) constructing a reliable indoor WiFi fingerprint database;
2) estimating the position coordinates of each access point and an indoor path loss model of each access point according to the established fingerprint database;
3) when calculating the Euclidean distance between the fingerprint information to be positioned and each fingerprint in the constructed fingerprint database, giving weight to corresponding dimensionality by using the indoor path loss models of different access points obtained in the step 2);
4) selecting K fingerprints with the minimum distance from the Euclidean distances obtained in the step 3) as reference points, and weighting the K reference points according to the signal intensity similarity to determine the position of a node to be positioned;
5) taking the method in the step 2-4) as a weak positioning method, randomly selecting the size of the K value and the number of WiFi access points (in the example of the present application, 20 WiFi access points are used in total, the random range of the K value is set to be 5-15, and the random range of the number of WiFi access points is set to be 16-20) to construct a plurality of weak positioning estimators, and a strong positioning estimator composed of the plurality of weak positioning estimators obtains the final position coordinate to be positioned.
Further, the step 1) of building a reliable indoor WiFi fingerprint database includes the following steps:
1-1) taking every other step in a region to be positioned as a reference point;
1-2) carrying out multiple RSS signal data measurement on each reference point, constructing a position fingerprint according to the physical address information, the average value of the signal intensity and the corresponding position information of the wireless access point of each reference point, and then constructing a position fingerprint database according to the position fingerprints corresponding to all the reference points.
Further, the step 2) of estimating the position coordinates of each access point and the indoor path loss model of each access point includes the following steps:
2-1) calculating the physical distance of a reference point which is close to the WiFi access point, wherein the close reference point is a reference point with the signal intensity of less than-60 Dbm, and the RSS signal intensity is strong:
Figure BDA0001356934940000031
wherein the content of the first and second substances,
Figure BDA0001356934940000032
for the signal strength of the jth WiFi access point,i is 1, 2, …, m is the number of reference points which are closer to the position of the jth WiFi access point (the signal strength is less than-60 Dbm), (n is the number of reference points)f,Af) Is a free space path loss propagation model parameter, which is a known value;
2-2) calculating the position coordinates of each WiFi access point:
Figure BDA0001356934940000041
wherein the content of the first and second substances,
Figure BDA0001356934940000042
for the location coordinates of the jth WiFi access point,
Figure BDA0001356934940000043
an ith reference point of a jth WiFi access point;
2-3) taking the coordinate and the signal intensity of a reference point which is close to the position of the WiFi access point (the signal intensity is less than-60 Dbm) as input, and solving the position coordinate of the WiFi access point as output;
2-4) combining the vertical type (1) and the formula (2), and constructing a function group:
Figure BDA0001356934940000044
order:
Figure BDA0001356934940000045
Figure BDA0001356934940000046
Figure BDA0001356934940000047
the equation is expressed as:
wjXj＝Yj(7)
the target function expression is as follows:
min||wjXj-Yj||2(8)
wherein | | · | | is norm, finally obtaining coordinate
Figure BDA0001356934940000048
The position coordinate of the WiFi access point to be solved is obtained;
2-5) the expression of the indoor path loss model is:
Figure BDA0001356934940000051
wherein the content of the first and second substances,
Figure BDA0001356934940000052
the signal strength of the jth WiFi access point for the pth reference point,
Figure BDA0001356934940000053
the position coordinate of the jth WiFi access point as the pth reference point, where p is 1, 2, …, I is the number of reference points that can receive the jth WiFi access point signal, epsilonjDenotes the Gaussian random error of the jth WiFi Access Point, (n)j,Aj) Representing the indoor path loss model parameters of the jth WiFi access point;
2-6) constructing a function group for the formula (9):
order:
Figure BDA0001356934940000054
Figure BDA0001356934940000055
Figure BDA0001356934940000056
the equation is expressed as:
ψjVj＝RSSj(13)
the target function expression is as follows:
min||ψjVj-RSSj||2+λ||Vj|| (14)
2-7) establishing a machine learning model, and learning based on the fingerprint database to obtain indoor path loss model parameters of each WiFi access point.
Further, step 3) gives weights to corresponding dimensions by using indoor path loss models of different WiFi access points, and includes the following steps:
3-1) endowing different weights to the signal strength of different WiFi access points, and assuming that the signal strength vector received by the node to be positioned is
Figure BDA0001356934940000061
Where n is the number of WiFi access points, then the physical distance between the node location to be located and the jth WiFi access point is calculated:
Figure BDA0001356934940000062
weighting the signal strength of the jth WiFi access point by using the distance obtained by the formula (15) by using a weighting coefficient wjThe weighting is:
Figure BDA0001356934940000063
3-2) the calculation formula of the Euclidean distance of the signal strength between the node to be positioned and the ith reference point is as follows:
Figure BDA0001356934940000064
further, step 4) performs different weighting according to differences of euclidean distances between the node to be located and the K reference points, (the closer the distance, the greater the similarity of the signal strength, the greater the contribution degree of the reference points with the greater similarity to the position to be located), including:
if the first K reference points and the node to be positionedThe shortest signal distance between points is: d1,D2…DKThen, the weight corresponding to the qth reference point is:
Figure BDA0001356934940000065
the position coordinates of the node to be positioned are calculated as follows:
Figure BDA0001356934940000071
further, in step 5), the value of K and the number of WiFi access points are randomly selected to construct h weak positioning estimators, and a strong positioning estimator composed of the weak positioning estimators obtains the final position coordinate to be positioned, and the calculation is as follows:
Figure BDA0001356934940000072
the invention has the beneficial effects that:
1) by setting different propagation model parameters for each WiFi access point, the method has higher positioning accuracy compared with the method using the same propagation model parameter in consideration of the relationship between the signal strength and the physical position.
2) And constructing a plurality of HWKNN weak positioning estimators by randomly selecting the K value and the number of WiFi access points, and forming the HWKNN weak positioning estimators. The method can effectively improve the robustness and the positioning precision of the positioning system.
Drawings
Fig. 1 is a schematic structural diagram of a WiFi indoor positioning method based on integrated HWKNN.
Detailed Description
As shown in fig. 1, a WiFi indoor positioning method based on integrated HWKNN includes the following steps:
1) the method for constructing the reliable indoor WiFi fingerprint database comprises the following steps:
1-1) taking every other step in a region to be positioned as a reference point;
1-2) carrying out multiple RSS signal data measurement on each reference point, constructing a position fingerprint by using the physical address information, the average value of the signal intensity and the corresponding position information of the wireless access point of each reference point, setting the value as 100 if signal loss occurs, and then constructing a position fingerprint database according to the position fingerprints corresponding to all the reference points.
2) Estimating the position coordinates of each access point and an indoor path loss model of each access point, comprising the following steps:
2-1) calculating the physical distance of a reference point which is close to the WiFi access point, wherein the RSS signal strength is strong:
Figure BDA0001356934940000081
wherein the content of the first and second substances,
Figure BDA0001356934940000082
the signal strength of the jth WiFi access point, i ═ 1, 2, …, m, m is the number of reference points closer to the jth WiFi access point, and (nf, Af) are free space path loss propagation model parameters, which are known values;
2-2) calculating the position coordinates of each WiFi access point:
Figure BDA0001356934940000083
wherein the content of the first and second substances,
Figure BDA0001356934940000084
for the location coordinates of the jth WiFi access point,
Figure BDA0001356934940000085
an ith reference point of a jth WiFi access point;
2-3) taking the coordinate and the signal intensity of a reference point close to the position of the WiFi access point as input, and solving the position coordinate of the WiFi access point as output;
2-4) combining the vertical type (1) and the formula (2), and constructing a function group:
Figure BDA0001356934940000086
order:
Figure BDA0001356934940000091
Figure BDA0001356934940000092
Figure BDA0001356934940000093
the equation can be expressed as:
wjXj＝Yj(7)
the target function expression is as follows:
min||wjXj-Yj||2(8)
wherein | | · | | is norm, finally obtaining coordinate
Figure BDA0001356934940000094
Namely the position coordinates of the WiFi access point to be solved.
2-5) the expression of the indoor path loss model is:
Figure BDA0001356934940000095
wherein the content of the first and second substances,
Figure BDA0001356934940000096
the signal strength of the jth WiFi access point for the pth reference point,
Figure BDA0001356934940000097
the position coordinate of the jth WiFi access point as the pth reference point, where p is 1, 2, …, I is the number of reference points that can receive the jth WiFi access point signal, epsilonjDenotes the Gaussian random error of the jth WiFi Access Point, (n)j,Aj) Representing the indoor path loss model parameters of the jth WiFi access point;
2-6) constructing a function group for the formula (9):
order:
Figure BDA0001356934940000101
Figure BDA0001356934940000102
Figure BDA0001356934940000103
the equation can be expressed as:
ψjVj＝RSSj(13)
the target function expression is as follows:
min||ψjVj-RSSj||2+λ||Vj|| (14)
2-7) establishing a machine learning model, and learning based on the fingerprint database to obtain indoor path loss model parameters of each WiFi access point.
3) Weighting corresponding dimensionalities by utilizing indoor path loss models of different WiFi access points, and the method comprises the following steps:
3-1) endowing different weights to the signal strength of different WiFi access points, and assuming that the signal strength vector received by the node to be positioned is
Figure BDA0001356934940000104
Where n is the number of WiFi access points, then the physical distance between the node location to be located and the jth WiFi access point is calculated:
Figure BDA0001356934940000105
distance pair obtained by equation (15)Weighting coefficient w for signal strength of jth WiFi access pointjThe weighting is:
Figure BDA0001356934940000111
3-2) the calculation formula of the Euclidean distance of the signal strength between the node to be positioned and the ith reference point is as follows:
Figure BDA0001356934940000112
4) according to the difference of the signal strength similarity between the node to be positioned and the K reference points, different weighting is carried out, and the method comprises the following steps:
if the shortest signal distance between the first K reference points and the node to be positioned is as follows: d1,D2…DKThen, the weight corresponding to the qth reference point is:
Figure BDA0001356934940000113
the position coordinates of the node to be positioned are calculated as follows:
Figure BDA0001356934940000114
5) randomly selecting the size of the K value and the number of the WiFi access points to construct h weak positioning estimators, obtaining the final position coordinate to be positioned by a strong positioning estimator consisting of the weak positioning estimators, and calculating as follows:
Figure BDA0001356934940000115
while specific embodiments of, and examples for, the invention are described above for illustrative purposes only, and not for the purpose of limitation, the invention is not to be limited to the specific embodiments described in the specification, but it is to be understood that equivalent alterations and modifications are possible within the spirit and scope of the invention, as those skilled in the relevant art will recognize.

Claims (4)

1. A WiFi indoor positioning method based on integrated HWKNN is characterized by comprising the following steps:
1) constructing a reliable indoor WiFi fingerprint database;
2) estimating the position coordinates of each access point and an indoor path loss model of each access point according to the established fingerprint database;
the step 2) of estimating the position coordinates of each access point and the indoor path loss model of each access point comprises the following steps:
2-1) calculating the physical distance of a reference point which is close to the WiFi access point, wherein the close reference point is a reference point with the signal intensity of less than-60 Dbm, and the RSS signal intensity is strong:
Figure FDA0002336341090000011
wherein the content of the first and second substances,
Figure FDA0002336341090000012
the signal strength of the jth WiFi access point, i ═ 1, 2, …, m, m is the number of reference points closer to the jth WiFi access point, (n is the number of reference points closer to the jth WiFi access pointf，Af) Is a free space path loss propagation model parameter, which is a known value;
2-2) calculating the position coordinates of each WiFi access point:
Figure FDA0002336341090000013
wherein the content of the first and second substances,
Figure FDA0002336341090000014
for the location coordinates of the jth WiFi access point,
Figure FDA0002336341090000015
an ith reference point of a jth WiFi access point;
2-3) taking the coordinate and the signal intensity of a reference point close to the position of the WiFi access point as input, and solving the position coordinate of the WiFi access point as output;
2-4) combining the vertical type (1) and the formula (2), and constructing a function group:
Figure FDA0002336341090000021
order:
Figure FDA0002336341090000022
Figure FDA0002336341090000023
Figure FDA0002336341090000024
equation (3) is expressed as:
wjXj＝Yj(7)
the target function expression is as follows:
min||wjXj-Yj||2(8)
wherein | | · | | is norm, finally obtaining coordinate
Figure FDA0002336341090000025
The position coordinate of the WiFi access point to be solved is obtained;
2-5) the expression of the indoor path loss model is:
Figure FDA0002336341090000026
wherein the content of the first and second substances,
Figure FDA0002336341090000027
the signal strength of the jth WiFi access point for the pth reference point,
Figure FDA0002336341090000028
the position coordinate of the jth WiFi access point as the pth reference point, where p is 1, 2, …, I is the number of reference points that can receive the jth WiFi access point signal, epsilonjDenotes the Gaussian random error of the jth WiFi Access Point, (n)j，Aj) Representing the indoor path loss model parameters of the jth WiFi access point;
2-6) constructing a function group for the formula (9):
order:
Figure FDA0002336341090000031
Figure FDA0002336341090000032
Figure FDA0002336341090000033
equation (10) is expressed as:
ψjVj＝RSSj(13)
the target function expression is as follows:
min||ψjVj-RSSj||2+λ||Vj|| (14)
2-7) establishing a machine learning model, and learning based on a fingerprint database to obtain indoor path loss model parameters of each WiFi access point;
3) when calculating the Euclidean distance between the fingerprint information to be positioned and each fingerprint in the constructed fingerprint database, giving weight to corresponding dimensionality by using the indoor path loss models of different access points obtained in the step 2);
step 3) endowing weights for corresponding dimensionalities by utilizing indoor path loss models of different WiFi access points, and the method comprises the following steps:
3-1) to different WiFi Access pointsThe signal strength is endowed with different weights, and the signal strength vector received by the node to be positioned is assumed to be
Figure FDA0002336341090000041
Wherein n is the number of WiFi access points, then the physical distance between the position of the node to be located and the jth WiFi access point:
Figure FDA0002336341090000042
weighting the signal strength of the jth WiFi access point by using the distance obtained by the formula (15) by using a weighting coefficient wjThe weighting is:
Figure FDA0002336341090000043
3-2) the calculation formula of the Euclidean distance of the signal strength between the node to be positioned and the ith reference point is as follows:
Figure FDA0002336341090000044
4) selecting K fingerprints with the minimum distance from the Euclidean distances obtained in the step 3) as reference points, and weighting the K reference points according to the signal intensity similarity to determine the position of a node to be positioned;
5) and (3) taking the method in the step 2-4) as a weak positioning method, randomly selecting the size of the K value and the number of the WiFi access points to form a plurality of weak positioning estimators, and obtaining the final position coordinate to be positioned by a strong positioning estimator formed by the plurality of weak positioning estimators.
2. The WiFi indoor positioning method based on integrated HWKNN according to claim 1, wherein the step 1) builds a reliable indoor WiFi fingerprint database, comprising the following steps:
1-1) taking every other step in a region to be positioned as a reference point;
1-2) carrying out multiple RSS signal data measurement on each reference point, constructing a position fingerprint according to the physical address information, the average value of the signal intensity and the corresponding position information of the wireless access point of each reference point, and then constructing a position fingerprint database according to the position fingerprints corresponding to all the reference points.
3. The WiFi indoor positioning method based on integrated HWKNN according to claim 1 or 2, wherein step 4) weights K reference points according to euclidean distance, i.e. signal strength similarity, including:
if the shortest signal distance between the first K reference points and the node to be positioned is as follows: d1，D2...DKThen, the weight corresponding to the qth reference point is:
Figure FDA0002336341090000051
the position coordinates of the node to be positioned are calculated as follows:
Figure FDA0002336341090000052
4. the WiFi indoor positioning method based on integrated HWKNN according to claim 3, wherein the step 5) randomly selects the K value and the number of WiFi access points to construct h weak positioning estimators, and the strong positioning estimator consisting of the weak positioning estimators obtains the final position coordinate to be positioned, and the calculation is as follows:
Figure FDA0002336341090000053
CN201710600157.1A 2017-07-21 2017-07-21 WiFi indoor positioning method based on integrated HWKNN Active CN107484123B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710600157.1A CN107484123B (en) 2017-07-21 2017-07-21 WiFi indoor positioning method based on integrated HWKNN

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710600157.1A CN107484123B (en) 2017-07-21 2017-07-21 WiFi indoor positioning method based on integrated HWKNN

Publications (2)

Publication Number Publication Date
CN107484123A CN107484123A (en) 2017-12-15
CN107484123B true CN107484123B (en) 2020-06-09

Family

ID=60595231

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710600157.1A Active CN107484123B (en) 2017-07-21 2017-07-21 WiFi indoor positioning method based on integrated HWKNN

Country Status (1)

Country Link
CN (1) CN107484123B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109121083B (en) * 2018-09-25 2020-06-19 西安电子科技大学 Indoor positioning method based on fingerprint similarity of AP (Access Point) sequence
CN109275106B (en) * 2018-11-01 2020-07-14 宁波大学 Indoor positioning method based on wireless received signal strength
CN109459016B (en) * 2018-11-15 2022-09-02 上海航天控制技术研究所 Micro-nano satellite cluster relative positioning method based on position fingerprints
CN111726743A (en) * 2019-03-04 2020-09-29 上海光启智城网络科技有限公司 Wifi positioning method and system based on online learning
CN109803234B (en) * 2019-03-27 2021-07-16 成都电科慧安科技有限公司 Unsupervised fusion positioning method based on weight importance constraint
CN110234126A (en) * 2019-05-21 2019-09-13 重庆邮电大学 Single Site Survey precision assessment method based on angle estimation

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102928813A (en) * 2012-10-19 2013-02-13 南京大学 RSSI (Received Signal Strength Indicator) weighted centroid algorithm-based passive RFID (Radio Frequency Identification Device) label locating method
CN103596267A (en) * 2013-11-29 2014-02-19 哈尔滨工业大学 Fingerprint map matching method based on Euclidean distances
CN104902562A (en) * 2014-11-24 2015-09-09 北京航空航天大学 Indoor positioning method based on multi-layer fingerprint matching
CN106851573A (en) * 2017-01-22 2017-06-13 西安交通大学 Joint weighting k nearest neighbor indoor orientation method based on log path loss model
CN106879065A (en) * 2015-12-11 2017-06-20 中南大学 A kind of Wi-Fi indoor orientation methods based on improvement WKNN

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102928813A (en) * 2012-10-19 2013-02-13 南京大学 RSSI (Received Signal Strength Indicator) weighted centroid algorithm-based passive RFID (Radio Frequency Identification Device) label locating method
CN103596267A (en) * 2013-11-29 2014-02-19 哈尔滨工业大学 Fingerprint map matching method based on Euclidean distances
CN104902562A (en) * 2014-11-24 2015-09-09 北京航空航天大学 Indoor positioning method based on multi-layer fingerprint matching
CN106879065A (en) * 2015-12-11 2017-06-20 中南大学 A kind of Wi-Fi indoor orientation methods based on improvement WKNN
CN106851573A (en) * 2017-01-22 2017-06-13 西安交通大学 Joint weighting k nearest neighbor indoor orientation method based on log path loss model

Also Published As

Publication number Publication date
CN107484123A (en) 2017-12-15

Similar Documents

Publication Publication Date Title
CN107484123B (en) WiFi indoor positioning method based on integrated HWKNN
Subedi et al. Improving indoor fingerprinting positioning with affinity propagation clustering and weighted centroid fingerprint
Elbakly et al. A robust zero-calibration RF-based localization system for realistic environments
EP2907354B1 (en) Method and system of semantic indoor positioning using significant places as satellites
KR101260647B1 (en) Wireless localization method based on an efficient multilateration algorithm over a wireless sensor network and a recording medium in which a program for the method is recorded
CN106912105B (en) Three-dimensional positioning method based on PSO _ BP neural network
CN109743777B (en) Positioning method, positioning device, electronic equipment and readable storage medium
WO2017185828A1 (en) Fingerprint positioning method and apparatus
US8738043B2 (en) Apparatus and method for constructing wireless AP map
KR101163335B1 (en) Wireless localization method based on rssi at indoor environment and a recording medium in which a program for the method is recorded
CN111246383A (en) Indoor positioning algorithm optimization based on Bluetooth
CN109379711B (en) positioning method
US20160182164A1 (en) Signal Strength Distribution Establishing Method and Wireless Positioning System
WO2022214002A1 (en) Indoor positioning method and indoor positioning apparatus
CN107547598A (en) A kind of localization method, server and terminal
CN104883737A (en) Hybrid location method for wireless sensor network
CN111148217B (en) Positioning method and device and electronic equipment
CN115066012A (en) Multi-user anchor-free positioning method based on UWB
CN113189541B (en) Positioning method, device and equipment
CN110839279A (en) Intelligent terminal positioning method and device based on 5G signal
Achroufene RSSI-based hybrid centroid-K-nearest neighbors localization method
Aravecchia et al. Gaussian process for rss-based localisation
Labinghisa et al. Improved indoor localization system based on virtual access points in a Wi-Fi environment by filtering schemes
CN111194000B (en) Distance measurement method and system based on Bluetooth fusion hybrid filtering and neural network
CN107484241A (en) Method and apparatus based on geographical fingerprint location under a kind of millimeter wave channel

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