CN107484123A - A kind of WiFi indoor orientation methods based on integrated HWKNN - Google Patents
A kind of WiFi indoor orientation methods based on integrated HWKNN Download PDFInfo
- Publication number
- CN107484123A CN107484123A CN201710600157.1A CN201710600157A CN107484123A CN 107484123 A CN107484123 A CN 107484123A CN 201710600157 A CN201710600157 A CN 201710600157A CN 107484123 A CN107484123 A CN 107484123A
- Authority
- CN
- China
- Prior art keywords
- mrow
- msubsup
- msup
- mtd
- mtr
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000006870 function Effects 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 241001269238 Data Species 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- HUTDUHSNJYTCAR-UHFFFAOYSA-N ancymidol Chemical compound C1=CC(OC)=CC=C1C(O)(C=1C=NC=NC=1)C1CC1 HUTDUHSNJYTCAR-UHFFFAOYSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
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 present invention discloses a kind of WiFi indoor orientation methods based on integrated HWKNN, including:1) reliable indoor WiFi fingerprint databases are built;2)According to the fingerprint database of foundation, the position coordinates of each access point and corresponding indoor path loss model are estimated;3)When calculating the Euclidean distance between node and fingerprint database to be positioned, 2 are utilized)Obtained indoor path loss model is that corresponding dimension assigns weight;4)To step 3)Obtained Euclidean distance selects the K minimum reference point of distance, and K reference point is weighted according to signal intensity similarity and determines node location to be positioned;5)By step 24)Method as a kind of weak fix method, set up several weak fix estimators by randomly selecting the size of K values and the number of access point finally to estimate the position coordinates of node to be positioned.The location algorithm proposed in the present invention can effectively strengthen the robustness of indoor positioning, final to realize indoor precise positioning.
Description
Technical field
The present invention relates to machine learning, it is wirelessly transferred and indoor positioning field, and in particular to one kind is based on integrated HWKNN
WiFi indoor orientation methods.
Background technology
With the extensive use of mobile device and the popularization of wireless network so that location Based service (LBS) not only may be used
User behavior information can also be further excavated to obtain customer position information, therefore LBS shows good academic development
Prospect and the wide market demand.Positioning field out of doors, global positioning system (GPS) have been realized in precision positioning, but
Still it is difficult to accurately position in indoor environment.
In the past decade, with the development of WiFi technology and the gradual increase of wireless access dot coverage, based on wireless
Serial of methods has been proposed in the indoor positioning of LAN (WLAN).But because indoor radio signal propagates complexity, no
Access point (AP) position is easily found, and determines the coefficient of propagation model.It is main in propagation model localization method based on WiFi
Technology is wanted to have AOA models, TOA models, TDOA models and signal path loss model.But due to the complexity of indoor environment, use
Family self stops that the different directions of mobile phone and other disturbing factors prevent indoor positioning from meeting high-precision requirement.Cause
This, is there is an urgent need to be LBS developing low-costs, the high-precision indoor locating system (IPS) based on WiFi.
Compared to the indoor positioning based on propagation model, the indoor positioning based on WiFi fingerprints is easier to dispose, low cost
Wireless signal noise is effectively tolerated, so as to reach highest precision.Traditional K arest neighbors (KNN) algorithm is indoor positioning
In one of the most frequently used algorithm, the signal intensity of each WiFi access points received first by calculating at node to be positioned and
Euclidean distance between the signal intensity of reference point in fingerprint database, K closest reference points are then found out, using not
With weighting scheme increase the influence of the larger reference point positioning result of similarity, finally estimate node location to be positioned
Coordinate.But due to the complexity of indoor environment, the signal intensity from different WiFi access points suffers from different degrees of
External interference, the relation between signal intensity and physical location are not simple linear mapping relation, and in section to be positioned
Unstable WiFi access points can not be determined at point, so as to cause the decline of positioning precision.
The content of the invention
The purpose of the present invention, which essentially consists in, overcomes above-mentioned technological deficiency, there is provided a kind of WiFi based on integrated HWKNN
Indoor orientation method, this method consider not only Euclidean distance between reference fingerprint in positioning, it is also contemplated that signal intensity and
The influence of the non-linear relation of physical location and the signal value of varying strength to positioning result, and estimated by several weak fixs
Device forms strong fix estimator to increase the robustness of alignment system, so as to improve the precision of positioning.
To achieve these goals, the technical scheme is that:
A kind of WiFi indoor orientation methods based on integrated HWKNN, method comprise the following steps:
1) reliable indoor WiFi fingerprint databases are built;
2) according to the fingerprint database of foundation, the position coordinates of each access point and the interior of each access point are estimated
Path loss model;
3) Euclidean distance between each fingerprint in calculating the fingerprint database of finger print information to be positioned and structure
When, the indoor path loss model of the diverse access point obtained using step 2) assigns weight for corresponding dimension;
4) it is as a reference point that the K minimum fingerprint of distance is selected in the Euclidean distance obtained from step 3), and according to signal
Intensity similarity is weighted to K reference point and determines node location to be positioned;
5) using step 2-4) method as a kind of weak fix method, randomly select the size and WiFi access points of K values
Number (employs 20 WiFi access points, the random scope of k values is set to 5-15 and WiFi altogether in the example of the application
The random scope of the number of access point is set to 16-20) several weak fix estimators are set up, estimated by this several weak fix
The strong fix estimator of gauge composition draws final position coordinates to be positioned.
Further, the reliable indoor WiFi fingerprint databases of step 1) structure, comprise the following steps:
1-1) in area to be targeted every a step as a reference point;
1-2) each reference point carries out multiple RSS signal datas measurement, and the WAP of each reference point is physically
Location information, the average value of signal intensity and corresponding positional information structure location fingerprint, then should according to all reference points
Location fingerprint form location fingerprint storehouse.
Further, the step 2) estimates the position coordinates of each access point and the indoor path of each access point
Loss model, comprise the following steps:
The physical distance of the nearer reference point of distance WiFi access point positions 2-1) is calculated, wherein nearer reference point refers to
Signal intensity is less than -60Dbm reference point, and its RSS signal intensity is stronger:
Wherein,For the signal intensity of j-th of WiFi access point, i=1,2 ..., m, m is that j-th of WiFi of distance connects
The number of the reference point of access point position relatively near (signal intensity is less than -60Dbm), (nf,Af) it is free space path loss propagating mode
Shape parameter, it is given value;
2-2) calculate the position coordinates of each WiFi access points:
Wherein,For the position coordinates of j-th of WiFi access point,For the of j-th of WiFi access point
I reference point;
2-3) with the coordinate and signal of the reference point of distance WiFi access point positions relatively near (signal intensity is less than -60Dbm)
Intensity is as input, to solve WiFi access point positions coordinate as output;
2-4) simultaneous formula (1) and formula (2), constructed fuction group:
Order:
Equation is represented as:
wjXj=Yj (7)
Its object function expression formula is:
min||wjXj-Yj||2 (8)
Wherein | | | | it is norm, finally tries to achieve coordinateThe position of the WiFi access points of as required solution
Put coordinate;
The expression formula of indoor path loss model described in 2-5) is:
Wherein,For the signal intensity of j-th of WiFi access point of p-th of reference point,For p-th of reference
The position coordinates of j-th of WiFi access point of point, p=1,2 ..., I, I are that can receive j-th of WiFi access point signals
The quantity of reference point, εjRepresent the gaussian random error of j-th of WiFi access point, (nj,Aj) represent j-th of WiFi access points room
Interior path loss model parameters;
2-6) it is formula (9) constructed fuction group:
Order:
Equation is represented as:
ψjVj=RSSj (13)
Its object function expression formula is:
min||ψjVj-RSSj||2+λ||Vj|| (14)
Machine learning model 2-7) is established, is learnt based on fingerprint database, obtains the interior of each WiFi access points
Path loss model parameters.
Further, step 3) assigns power using the indoor path loss model of different WiFi access points for corresponding dimension
Weight, comprises the following steps:
3-1) different weights is assigned to the signal intensity of different WiFi access points, it is assumed that node to be positioned receives
Signal intensity vector beWherein n is the quantity of WiFi access points, then is treated
The physical distance of the node location of positioning and j-th of WiFi access point is calculated:
The distance obtained using formula (15) is weighted coefficient w to the signal intensity of j-th of WiFi access pointjIt is weighted to:
3-2) calculation formula of the signal intensity Euclidean distance between node to be positioned and the i-th reference point is:
Further, step 4) is carried out not according to the different of the Euclidean distance between node to be positioned and K reference point
Same weighting, (distance is nearer, the bigger reference point position contribution to be positioned for make it that similarity is bigger of the similarity of signal intensity
Degree is bigger), including:
If the unit element distance between preceding K reference point and node to be positioned is:D1,D2…DK, then q-th of reference
Point corresponding to weight be:
Node location coordinate to be positioned is calculated as follows:
Further, step 5) randomly selects the size of K values and the number of WiFi access points to build h weak fix estimation
Device, the strong fix estimator being made up of weak fix estimator draw final position coordinates to be positioned, are calculated as follows:
The beneficial effects of the invention are as follows:
1) by setting different propagation model parameters for each WiFi access point, it is contemplated that signal intensity and physical location
Relation, compared to use same propagation model parameter, the present invention there is higher positioning precision.
2) utilization randomly selects K values size and the mode of WiFi access point numbers builds multiple HWKNN weak fixs estimators,
And formed HWKNN strong fix estimators.This method can effectively improve the robustness and positioning precision of alignment system.
Brief description of the drawings
Fig. 1 is the structural representation of the WiFi indoor orientation methods based on integrated HWKNN.
Embodiment
As shown in figure 1, a kind of WiFi indoor orientation methods based on integrated HWKNN, comprise the following steps:
1) reliable indoor WiFi fingerprint databases are built, are comprised the following steps:
1-1) in area to be targeted every a step as a reference point;
1-2) each reference point carries out multiple RSS signal datas measurement, and the WAP of each reference point is physically
Location information, the average value of signal intensity and corresponding positional information structure location fingerprint, if there is dropout, the value is set
100 are set to, then location fingerprint forms location fingerprint storehouse according to corresponding to all reference points.
2) position coordinates of each access point and the indoor path loss model of each access point are estimated, including it is following
Step:
The physical distance of the nearer reference point of distance WiFi access point positions 2-1) is calculated, its RSS signal intensity is stronger:
Wherein,For the signal intensity of j-th of WiFi access point, i=1,2 ..., m, m is that j-th of WiFi of distance connects
The number of the nearer reference point in access point position, (nf, Af) are free space path loss propagation model parameter, and it is given value;
2-2) calculate the position coordinates of each WiFi access points:
Wherein,For the position coordinates of j-th of WiFi access point,For the of j-th of WiFi access point
I reference point;
2-3) using the coordinate of the nearer reference point of distance WiFi access point positions and signal intensity as input, to solve
WiFi access point positions coordinate is as output;
2-4) simultaneous formula (1) and formula (2), constructed fuction group:
Order:
Equation can be represented as:
wjXj=Yj (7)
Its object function expression formula is:
min||wjXj-Yj||2 (8)
Wherein | | | | it is norm, finally tries to achieve coordinateThe position of the WiFi access points of as required solution
Put coordinate.
The expression formula of indoor path loss model described in 2-5) is:
Wherein,For the signal intensity of j-th of WiFi access point of p-th of reference point,For p-th of ginseng
The position coordinates of j-th of WiFi access point of examination point, p=1,2 ..., I, I are that can receive j-th of WiFi access point signals
Reference point quantity, εjRepresent the gaussian random error of j-th of WiFi access point, (nj,Aj) represent j-th of WiFi access point
Indoor path loss model parameter;
2-6) it is formula (9) constructed fuction group:
Order:
Equation can be represented as:
ψjVj=RSSj (13)
Its object function expression formula is:
min||ψjVj-RSSj||2+λ||Vj|| (14)
Machine learning model 2-7) is established, is learnt based on fingerprint database, obtains the interior of each WiFi access points
Path loss model parameters.
3) weight, including following step are assigned for corresponding dimension using the indoor path loss model of different WiFi access points
Suddenly:
3-1) different weights is assigned to the signal intensity of different WiFi access points, it is assumed that node to be positioned receives
Signal intensity vector beWherein n is the quantity of WiFi access points, then
The physical distance of node location to be positioned and j-th of WiFi access point is calculated:
The distance obtained using formula (15) is weighted coefficient w to the signal intensity of j-th of WiFi access pointjIt is weighted to:
3-2) calculation formula of the signal intensity Euclidean distance between node to be positioned and the i-th reference point is:
4) add according to the progress of the difference of the signal intensity similarity between node to be positioned and K reference point is different
Power, including:
If the unit element distance between preceding K reference point and node to be positioned is:D1,D2…DK, then q-th of reference
Point corresponding to weight be:
Node location coordinate to be positioned is calculated as follows:
5) size of K values and the number of WiFi access points are randomly selected to build h weak fix estimator, is estimated by weak fix
The strong fix estimator of gauge composition draws final position coordinates to be positioned, is calculated as follows:
The specific embodiment of the above-mentioned detailed description present invention, but and it is nonrestrictive, therefore the present invention is not limited only to have
Specific embodiment described in body implementation, it will be understood by those of skill in the art that carrying out equivalent substitution to the solution of the present invention
Or modification, all should be in the scope of protection of the invention.
Claims (6)
1. a kind of WiFi indoor orientation methods based on integrated HWKNN, it is characterised in that comprise the following steps:
1) reliable indoor WiFi fingerprint databases are built;
2) according to the fingerprint database of foundation, the position coordinates of each access point and the indoor path of each access point are estimated
Loss model;
3) during Euclidean distance between each fingerprint in calculating the fingerprint database of finger print information to be positioned and structure, profit
The indoor path loss model of the diverse access point obtained with step 2) is that corresponding dimension assigns weight;
4) it is as a reference point that the K minimum fingerprint of distance is selected in the Euclidean distance obtained from step 3), and according to signal intensity
Similarity is weighted to K reference point and determines node location to be positioned;
5) using step 2-4) method as a kind of weak fix method, randomly select the size of K values and the number of WiFi access points
Several weak fix estimators are set up, the strong fix estimator being made up of this several weak fix estimator draws final undetermined
The position coordinates of position.
2. a kind of WiFi indoor orientation methods based on integrated HWKNN according to claim 1, it is characterised in that described
The reliable indoor WiFi fingerprint databases of step 1) structure, comprise the following steps:
1-1) in area to be targeted every a step as a reference point;
1-2) each reference point carries out multiple RSS signal datas measurement, the physical address letter of the WAP of each reference point
Breath, the average value of signal intensity and corresponding positional information build location fingerprint, then the position according to corresponding to all reference points
Put fingerprint and form location fingerprint storehouse.
A kind of 3. WiFi indoor orientation methods based on integrated HWKNN according to claim 1 or 2, it is characterised in that institute
State step 2) and estimate the position coordinates of each access point and the indoor path loss model of each access point, including following step
Suddenly:
The physical distance of the nearer reference point of distance WiFi access point positions 2-1) is calculated, wherein nearer reference point refers to signal
Intensity is less than -60Dbm reference point, and its RSS signal intensity is stronger:
<mrow>
<msubsup>
<mi>d</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>=</mo>
<msup>
<mn>10</mn>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein,For the signal intensity of j-th of WiFi access point, i=1,2 ..., m, m is j-th of WiFi access points position of distance
Put the number of the reference point of relatively near (signal intensity is less than -60Dbm), (nf,Af) join for free space path loss propagation model
Number, it is given value;
2-2) calculate the position coordinates of each WiFi access points:
<mrow>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>=</mo>
<msubsup>
<mi>d</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein,For the position coordinates of j-th of WiFi access point,For i-th of j-th of WiFi access point
Reference point;
2-3) with the coordinate and signal intensity of the reference point of distance WiFi access point positions relatively near (signal intensity is less than -60Dbm)
As input, to solve WiFi access point positions coordinate as output;
2-4) simultaneous formula (1) and formula (2), constructed fuction group:
<mrow>
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mn>10</mn>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mn>10</mn>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mn>10</mn>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>3</mn>
<mo>)</mo>
</mrow>
</mrow>
Order:
<mrow>
<msup>
<mi>Y</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>e</mi>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>f</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>f</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>4</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msup>
<mi>w</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mn>2</mn>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>2</mn>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>.</mo>
</mtd>
<mtd>
<mo>.</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mn>2</mn>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mrow>
<mn>2</mn>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mrow>
<mi>n</mi>
<mo>-</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>n</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>5</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msup>
<mi>X</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>6</mn>
<mo>)</mo>
</mrow>
</mrow>
Equation (3) is expressed as:
wjXj=Yj (7)
Its object function expression formula is:
min||wjXj-Yj||2 (8)
Wherein | | | | it is norm, finally tries to achieve coordinateThe position of the WiFi access points of as required solution is sat
Mark;
The expression formula of indoor path loss model described in 2-5) is:
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>p</mi>
<mi>j</mi>
</msubsup>
<mo>=</mo>
<mo>-</mo>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>j</mi>
</msup>
<msub>
<mi>log</mi>
<mn>10</mn>
</msub>
<mrow>
<mo>(</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>p</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>p</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msup>
<mi>A</mi>
<mi>j</mi>
</msup>
<mo>+</mo>
<msup>
<mi>&epsiv;</mi>
<mi>j</mi>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>9</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein,For the signal intensity of j-th of WiFi access point of p-th of reference point,For p-th reference point
The position coordinates of j-th of WiFi access point, p=1,2 ..., I, I are the reference that can receive j-th of WiFi access point signals
The quantity of point, εjRepresent the gaussian random error of j-th of WiFi access point, (nj,Aj) represent j-th of WiFi access point Shi Nei road
Footpath loss model parameter;
2-6) it is formula (9) constructed fuction group:
Order:
<mrow>
<msup>
<mi>RSS</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mi>R</mi>
<mi>S</mi>
<msubsup>
<mi>S</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msubsup>
<mi>RSS</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>...</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<mi>R</mi>
<mi>S</mi>
<msubsup>
<mi>S</mi>
<mi>I</mi>
<mi>j</mi>
</msubsup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>10</mn>
<mo>)</mo>
</mrow>
</mrow>
2
<mrow>
<msup>
<mi>&psi;</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>10</mn>
<msub>
<mi>log</mi>
<mn>10</mn>
</msub>
<mrow>
<mo>(</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mn>1</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>10</mn>
<msub>
<mi>log</mi>
<mn>10</mn>
</msub>
<mrow>
<mo>(</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mn>2</mn>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>...</mn>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mo>-</mo>
<mn>10</mn>
<msub>
<mi>log</mi>
<mn>10</mn>
</msub>
<mrow>
<mo>(</mo>
<msqrt>
<mrow>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>l</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>+</mo>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>y</mi>
<mn>0</mn>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>y</mi>
<mi>l</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>)</mo>
</mrow>
</mrow>
</mtd>
<mtd>
<mn>1</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>11</mn>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msup>
<mi>V</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<msup>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msup>
<mi>n</mi>
<mi>j</mi>
</msup>
</mtd>
</mtr>
<mtr>
<mtd>
<msup>
<mi>A</mi>
<mi>j</mi>
</msup>
</mtd>
</mtr>
</mtable>
</mfenced>
<mi>T</mi>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>12</mn>
<mo>)</mo>
</mrow>
</mrow>
Equation (10) is expressed as:
ψjVj=RSSj (13)
Its object function expression formula is:
min||ψjVj-RSSj||2+λ||Vj|| (14)
Machine learning model 2-7) is established, is learnt based on fingerprint database, obtains the indoor path of each WiFi access points
Loss model parameter.
A kind of 4. WiFi indoor orientation methods based on integrated HWKNN according to claim 3, it is characterised in that step
3) weight is assigned for corresponding dimension using the indoor path loss model of different WiFi access points, comprised the following steps:
3-1) different weights is assigned to the signal intensity of different WiFi access points, it is assumed that the letter that node to be positioned receives
Number intensity vector isWherein n is the quantity of WiFi access points, then to be positioned
Node location and j-th of WiFi access point physical distance:
<mrow>
<msubsup>
<mi>d</mi>
<mi>u</mi>
<mi>j</mi>
</msubsup>
<mo>=</mo>
<msup>
<mn>10</mn>
<mrow>
<mo>-</mo>
<mfrac>
<mrow>
<msubsup>
<mi>RSS</mi>
<mi>u</mi>
<mi>j</mi>
</msubsup>
<mo>+</mo>
<msup>
<mi>A</mi>
<mi>j</mi>
</msup>
</mrow>
<mrow>
<mn>10</mn>
<msup>
<mi>n</mi>
<mi>j</mi>
</msup>
</mrow>
</mfrac>
</mrow>
</msup>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>15</mn>
<mo>)</mo>
</mrow>
</mrow>
The distance obtained using formula (15) is weighted coefficient w to the signal intensity of j-th of WiFi access pointjIt is weighted to:
<mrow>
<msup>
<mi>w</mi>
<mi>j</mi>
</msup>
<mo>=</mo>
<mfrac>
<mrow>
<mn>1</mn>
<mo>/</mo>
<msubsup>
<mi>d</mi>
<mi>u</mi>
<mi>j</mi>
</msubsup>
</mrow>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
<mn>1</mn>
<mo>/</mo>
<msubsup>
<mi>d</mi>
<mi>u</mi>
<mi>p</mi>
</msubsup>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>16</mn>
<mo>)</mo>
</mrow>
</mrow>
3-2) calculation formula of the signal intensity Euclidean distance between node to be positioned and the i-th reference point is:
<mrow>
<msub>
<mi>D</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>n</mi>
</msubsup>
<msup>
<mi>w</mi>
<mi>j</mi>
</msup>
<msup>
<mrow>
<mo>(</mo>
<msubsup>
<mi>RSS</mi>
<mi>u</mi>
<mi>j</mi>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>RSS</mi>
<mi>i</mi>
<mi>j</mi>
</msubsup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
</msqrt>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>17</mn>
<mo>)</mo>
</mrow>
<mo>.</mo>
</mrow>
A kind of 5. WiFi indoor orientation methods based on integrated HWKNN according to claim 4, it is characterised in that step
4) K reference point is weighted according to Euclidean distance, i.e. signal intensity similarity, including:
If the unit element distance between preceding K reference point and node to be positioned is:D1,D2…DK, then q-th of reference point
The weight answered is:
<mrow>
<msub>
<mi>&theta;</mi>
<mi>q</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<mn>1</mn>
<mo>/</mo>
<msub>
<mi>D</mi>
<mi>q</mi>
</msub>
</mrow>
<mrow>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</msubsup>
<mn>1</mn>
<mo>/</mo>
<msub>
<mi>D</mi>
<mi>i</mi>
</msub>
</mrow>
</mfrac>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mrow>
<mo>(</mo>
<mn>18</mn>
<mo>)</mo>
</mrow>
</mrow>
Node location coordinate to be positioned is calculated as follows:
<mrow>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mi>u</mi>
<mo>&prime;</mo>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>y</mi>
<mi>u</mi>
<mo>&prime;</mo>
</msubsup>
<mo>)</mo>
<mo>=</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>K</mi>
</msubsup>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mi>i</mi>
</msub>
<mo>)</mo>
<mo>*</mo>
<msub>
<mi>&theta;</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mo>(</mo>
<mn>19</mn>
<mo>)</mo>
<mo>.</mo>
</mrow>
A kind of 6. WiFi indoor orientation methods based on integrated HWKNN according to claim 5, it is characterised in that step
5) size of K values and the number of WiFi access points are randomly selected to build h weak fix estimator, is made up of weak fix estimator
Strong fix estimator draw final position coordinates to be positioned, be calculated as follows:
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>u</mi>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mi>u</mi>
</msub>
<mo>)</mo>
<mo>=</mo>
<msubsup>
<mi>&Sigma;</mi>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>h</mi>
</msubsup>
<mo>(</mo>
<msubsup>
<mi>x</mi>
<mi>i</mi>
<mo>&prime;</mo>
</msubsup>
<mo>,</mo>
<msubsup>
<mi>y</mi>
<mi>i</mi>
<mo>&prime;</mo>
</msubsup>
<mo>)</mo>
<mo>-</mo>
<mo>-</mo>
<mo>-</mo>
<mo>(</mo>
<mn>20</mn>
<mo>)</mo>
<mo>.</mo>
</mrow>
4
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 true CN107484123A (en) | 2017-12-15 |
CN107484123B 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) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109121083A (en) * | 2018-09-25 | 2019-01-01 | 西安电子科技大学 | A kind of indoor orientation method of the fingerprint similarity based on AP sequence |
CN109275106A (en) * | 2018-11-01 | 2019-01-25 | 宁波大学 | A kind of indoor orientation method based on wireless reception of signals intensity |
CN109459016A (en) * | 2018-11-15 | 2019-03-12 | 上海航天控制技术研究所 | A kind of micro-nano satellite cluster relative positioning method based on location fingerprint |
CN109803234A (en) * | 2019-03-27 | 2019-05-24 | 成都电科慧安科技有限公司 | Unsupervised fusion and positioning method based on the constraint of weight different degree |
CN110234126A (en) * | 2019-05-21 | 2019-09-13 | 重庆邮电大学 | Single Site Survey precision assessment method based on angle estimation |
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 |
Citations (5)
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 |
-
2017
- 2017-07-21 CN CN201710600157.1A patent/CN107484123B/en active Active
Patent Citations (5)
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 |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109121083A (en) * | 2018-09-25 | 2019-01-01 | 西安电子科技大学 | A kind of indoor orientation method of the fingerprint similarity based on AP sequence |
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 |
CN109275106A (en) * | 2018-11-01 | 2019-01-25 | 宁波大学 | A kind of indoor orientation method based on wireless reception of signals intensity |
CN109459016A (en) * | 2018-11-15 | 2019-03-12 | 上海航天控制技术研究所 | A kind of micro-nano satellite cluster relative positioning method based on location fingerprint |
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 |
CN109803234A (en) * | 2019-03-27 | 2019-05-24 | 成都电科慧安科技有限公司 | Unsupervised fusion and positioning method based on the constraint of weight different degree |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN107484123B (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107484123A (en) | A kind of WiFi indoor orientation methods based on integrated HWKNN | |
Sadowski et al. | Memoryless techniques and wireless technologies for indoor localization with the internet of things | |
CN103402258B (en) | Wi-Fi (Wireless Fidelity)-based indoor positioning system and method | |
CN103686999B (en) | Indoor wireless positioning method based on WiFi signal | |
Jekabsons et al. | An Analysis of Wi-Fi Based Indoor Positioning Accuracy. | |
CN106912105B (en) | Three-dimensional positioning method based on PSO _ BP neural network | |
Zhang et al. | DeepPositioning: Intelligent fusion of pervasive magnetic field and WiFi fingerprinting for smartphone indoor localization via deep learning | |
CN105704652B (en) | Fingerprint base acquisition and optimization method in a kind of positioning of WLAN/ bluetooth | |
Huang et al. | A fine-grained indoor fingerprinting localization based on magnetic field strength and channel state information | |
CN104853317B (en) | The structure and update method of fingerprint base in a kind of WiFi indoor positionings | |
CN104902562B (en) | A kind of indoor orientation method based on multilayer fingerprint matching | |
CN103596267A (en) | Fingerprint map matching method based on Euclidean distances | |
EP3596486A1 (en) | Wifi multi-band fingerprint-based indoor positioning | |
CN106646356A (en) | Nonlinear system state estimation method based on Kalman filtering positioning | |
CN104936148A (en) | Indoor positioning method for WIFI (Wireless Fidelity) based on fuzzy KNN (k-Nearest Neighbor) | |
CN103747419B (en) | A kind of indoor orientation method based on signal strength difference and dynamic linear interpolation | |
Kim et al. | Mobile beacon-based 3D-localization with multidimensional scaling in large sensor networks | |
CN105043380A (en) | Indoor navigation method based on a micro electro mechanical system, WiFi (Wireless Fidelity) positioning and magnetic field matching | |
CN105301558A (en) | Indoor positioning method based on bluetooth position fingerprints | |
CN104457755B (en) | A kind of location acquiring method | |
CN107547598A (en) | A kind of localization method, server and terminal | |
CN106792554A (en) | A kind of localization method based on Dual Matching fingerprint location technology | |
CN106482738A (en) | Transfinited the indoor fingerprinting localization algorithm of learning machine based on online increment | |
CN106970379A (en) | Based on distance-measuring and positioning method of the Taylor series expansion to indoor objects | |
CN103888979B (en) | Indoor positioning method based on wireless local area network |
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 |