CN114449438B - Indoor positioning method based on iBeacon fingerprint library - Google Patents
Indoor positioning method based on iBeacon fingerprint library Download PDFInfo
- Publication number
- CN114449438B CN114449438B CN202111241688.9A CN202111241688A CN114449438B CN 114449438 B CN114449438 B CN 114449438B CN 202111241688 A CN202111241688 A CN 202111241688A CN 114449438 B CN114449438 B CN 114449438B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- formula
- points
- rss
- ibeacon
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 6
- 125000003275 alpha amino acid group Chemical group 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 150000001875 compounds Chemical class 0.000 claims description 9
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 238000011161 development Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 230000005389 magnetism Effects 0.000 claims description 3
- 238000005316 response function Methods 0.000 claims description 3
- 238000003780 insertion Methods 0.000 claims description 2
- 230000037431 insertion Effects 0.000 claims description 2
- 238000005070 sampling Methods 0.000 abstract description 10
- 230000009467 reduction Effects 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 19
- 238000005516 engineering process Methods 0.000 description 13
- 238000005457 optimization Methods 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000003313 weakening effect Effects 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
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4007—Scaling of whole images or parts thereof, e.g. expanding or contracting based on interpolation, e.g. bilinear interpolation
-
- 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
- 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
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an indoor positioning method based on an iBeacon fingerprint library, which specifically comprises the following specific steps: 1, installing iBeacon and calibrating the positions of reference fingerprint points; 2, collecting fingerprint information of each reference fingerprint point and preprocessing data by utilizing a GM (1, 1) model; reconstructing a high-density off-line fingerprint library; after the RSS obtained by fitting is averaged, fingerprint points are established and built into an offline fingerprint library, and the high-density offline fingerprint library is reconstructed in an IDW interpolation mode; 4, on-line location matching is completed by using WKNN. According to the invention, the GM (1, 1) model is used in the pretreatment process of the sampling data, and the noise reduction treatment can be carried out on the sampling data under the condition of less sampling data. The invention adopts the IDW interpolation method to reconstruct the large-capacity off-line fingerprint library, and can still ensure higher positioning precision of the mobile user in the on-line stage when the acquisition density of off-line fingerprint points is lower.
Description
Technical Field
The invention relates to an indoor positioning method, in particular to an indoor positioning method based on an iBeacon fingerprint library, and belongs to the technical field of indoor positioning.
Background
In recent years, with the popularity of mobile intelligent terminals having a Location-based service (LBS) has been vigorously developed. According to the white paper of the development of 2021 China satellite navigation and position service industry published by China satellite navigation positioning society in Beijing, the total production value of China satellite navigation and position service industry exceeds 4000 hundred million yuan in 2020. Positioning is generally divided into two categories, namely outdoor positioning and indoor positioning according to different application scenes. The outdoor positioning generally utilizes a global navigation satellite system (Global Navigation Satellite System, GNSS) and a base station for positioning, and has the characteristics of mature technology, stable signals, high positioning precision and the like. However, about 80% of the lifetime of a person is indoors, and a great demand has driven innovation in indoor positioning technology. Most of the location services in the indoor environment are provided based on the wireless sensor network, and the user terminal can estimate the current location of the user by utilizing a certain positioning algorithm according to the received radio signal.
The iBeacon technology based on the low-power consumption Bluetooth is widely applied to indoor location service in 2013 because of the characteristics of low power consumption, low cost and the like. Indoor positioning algorithm based on iBeacon is mainly divided into a geometric positioning method and a fingerprint positioning method based on a received signal strength (Received Signal Strength, RSS) propagation model. The method is affected by multipath propagation, shadow effect, deployment mode of iBeacon equipment and the like, and the propagation model based on received signal strength (Received Signal Strength, RSS) is inaccurate in describing the RSS and the position relationship, so that the positioning accuracy of a geometric positioning method is lower. The fingerprint positioning technology can realize the positioning of the mobile equipment based on the multipath characteristics of the signals, so that the invention adopts a fingerprint positioning method to perform indoor positioning.
Fingerprint positioning is divided into an offline stage and an online stage. In the off-line phase, the signal acquisition device acquires the RSS of the surrounding ibeacons at the reference point. Because of the instability of the signal, when the RSS is collected, the RSS can have larger fluctuation, and the RSS needs to be preprocessed so as to achieve the purpose of weakening noise. In an online stage, the mobile device performs similarity measurement and matching with fingerprint database data after preprocessing the data acquired in real time, takes the reciprocal of Euclidean distance as weight, adopts a weighted K nearest neighbor method (Weighted KNearest Neighbor, WKNN) to match to K nearest neighbor reference fingerprint points, and takes the weighted centroid of the points as estimated coordinates of unknown points. By adopting the fingerprint database construction mode, a high-density fingerprint database is built only by consuming a great deal of manpower and time cost (generally within 2 meters). On the basis of ensuring high-precision positioning of a mobile user, a short-time and low-density fingerprint point acquisition mode is used for establishing a fingerprint library, so that the method is a challenge.
Disclosure of Invention
The invention aims to solve the problem of higher library construction cost of an offline fingerprint library, and provides an indoor positioning method based on an iBeacon fingerprint library.
In order to solve the problems existing in the background technology, the invention provides an indoor positioning method based on an iBeacon fingerprint library, which comprises the following steps:
step 1: and laying iBeacon and calibrating the positions of the reference fingerprint points. The deployment height of the iBeacon is 2.6+/-0.1 meter, the deployment distance is 5-10 meters, and strong magnetism, strong electricity and barriers should be avoided as much as possible during deployment. The reference fingerprint points are sparsely marked in the indoor location area and uniformly marked with a density of 3 + -0.5 square meters, but the specific density should be determined in conjunction with the field case.
Step 2: fingerprint information of each reference fingerprint point is collected, and RSS preprocessing is completed by utilizing a GM (1, 1) model. The fingerprint information on each reference fingerprint point is acquired in a short-time acquisition mode of 2 seconds, and compared with the traditional acquisition mode, the sampling time is reduced. Traditional data preprocessing adopts Gaussian filtering, and requires more sampling samples and longer acquisition time. The GM (1, 1) model has the advantages of simple operation, small required data amount, and the like. The RSS collected in a short-time collection mode has the characteristics of small sample and less information, data preprocessing cannot be performed by adopting Gaussian filtering, and the purpose of smoothing noise is achieved by fitting the RSS through a GM (1, 1) model.
Step 3: reconstructing a high-density off-line fingerprint library. And (3) averaging the RSS obtained in the step (2), constructing an offline fingerprint library for the fingerprint points, and reconstructing the high-density offline fingerprint library by adopting an IDW interpolation method. When an offline fingerprint database is established, the distance between reference fingerprint points is an important factor affecting the positioning accuracy. The smaller the reference fingerprint point spacing, the higher the positioning accuracy and the higher the time cost. The off-line fingerprint library with smaller sampling density can be reconstructed into the fingerprint library with larger density by the IDW interpolation method, so that the working efficiency of fingerprint library construction can be improved, and the positioning precision requirement of a user can be met.
Step 4: on-line location matching is accomplished using WKNN. WKNN finds k fingerprint points closest to the Euclidean distance of the unknown point by calculating the Euclidean distance between the RSS and the fingerprint points acquired in real time, and takes the weighted centroid of the k fingerprint points as the coordinates of the unknown point by adopting the inverse weighting of the n th power of the Euclidean distance. WKNN is an improvement on the K-nearest neighbor method (KNearest Neighbor, KNN), which fails to consider an important factor that the distances between fingerprint points and unknown points are different, and affects the weights differently, and which considers this factor, thereby having higher positioning accuracy than KNN.
In step 1, in order to determine the optimal deployment pitch and height of the iBeacon, an iBeacon effective coverage experiment is specifically performed. And 5 iBeacon with the same model are respectively stuck to walls with the heights of 2 meters, 2.3 meters, 2.6 meters, 2.9 meters and 3.2 meters from the floor, and the RSS data are respectively acquired in three different time periods of 9:00-11:00 in the morning, 15:00-17:00 in the afternoon and 19:00-21:00 in the evening, and the positions (0 meters) facing the iBeacon are along the direction of the wall line until 30 meters are acquired. Wherein the broadcasting frequency of the iBeacon is set to 10 hz, and the sampling time of each location is 12 seconds. The experimental result shows that the signal loss rate is higher than 10 meters, and the signal quality is the best at the height of 2.6 meters. Considering that the iBeacon signal is easy to be interfered by strong magnetism, strong electricity and barriers, the deployment interval of the iBeacon is 5-10 meters, and the deployment height is 2.6+/-0.1 meters. The reference fingerprint points are uniformly distributed in the experimental field at a distribution density of 3+/-0.5 square meters, but the specific distribution density is determined by combining the field environment.
Further, in the step 2, the pretreatment is completed by using the GM (1, 1) model as follows:
step 2.1: ordering a group of RSS data from small to large to form an original array of RSS (0) ：
Step 2.2: for RSS (0) Data accumulation is carried out to obtain a new number sequence RSS (1) As shown in formula (1):
in the formula (1), the components are as follows,
step 2.3: calculating the immediate meanAs shown in formula (2):
step 2.4: and constructing a GM (1, 1) model, and further obtaining the RSS after fitting. The GM (1, 1) model calculation formula is shown as a formula (3).
In the formula (3), the amino acid sequence of the compound,for the gray derivatives, a and u are key coefficients to be obtained. Wherein a is a development coefficient, and u is an ash action amount. A and u can be obtained by the least square method. The unknown data can be easily obtained by the least square method, and the sum of squares of errors between the obtained data and the actual data is minimized. The least square method is represented by the formula (4).
[a,u] T ＝(B T B) -1 B T Y (4)
In the formula (4), the amino acid sequence of the compound,the response function calculation formula is shown in formula (5).
In the formula (5), the amino acid sequence of the compound,is->Estimated value of ∈10->Is->I.e., the fitted RSS.
Step 2.5, optimizing and verifying. And (3) checking the GM (1, 1) model by using a variance ratio C and a small error probability p, so as to determine whether to use the fitted RSS obtained in the step (2.4), wherein the variance ratio C and the small error probability p are calculated as shown in a formula (6).
In the formula (6), ε (0) As a series of the residual values,is the average value of the original number sequence and the residual number sequence, S 1 、S 2 Standard deviations of the original and residual sequences, respectively. When C is less than 0.35 and p is more than 0.95, adopting RSS after fitting; otherwise, discarding the fitted RSS, selecting the RSS of the original sequence (0) . The GM (1, 1) model can not be used immediately after being established, and the robustness and the accuracy of the model can be checked by a correlation checking methodThe difference ratio C and the small error probability p are tested, and the accuracy grade is highest when C is smaller than 0.35 and p is larger than 0.95.
Further, in the step 3, the specific process of reconstructing the high-density fingerprint library by using the IDW interpolation method is as follows.
Given the point to be inserted F 0 Coordinates (x) 0 ,y 0 ) Find 4 reference fingerprint points F nearest to the point to be inserted i (where i=1, 2,3, 4), then the point F is to be inserted 0 The attribute value of (2) can be obtained by the following formula.
In the above, x i 、y i Respectively represent neighboring fingerprint points F i Is defined by the abscissa of (2), R (F i ) For the neighboring fingerprint point F i Attribute value lambda of (a) i (i=1, 2,3, 4) is R (F i ) Weight of R * (F 0 ) The attribute value of the point to be inserted is obtained.
In step 4, the weighted centroids of the k fingerprint points are used as the coordinates of unknown points, and the calculation formula is shown in the formula (10):
in the formula (10), (x, y) iBeacon Representing the coordinates of unknown points, D i Representing the Euclidean distance of the RSS to the ith fingerprint point acquired in real time, (x) i ,y i ) Representing the coordinates of the ith fingerprint point.
Compared with the prior art, the invention has the beneficial effects that: according to the invention, the GM (1, 1) model is used in the pretreatment process of the sampling data, and the noise reduction treatment can be carried out on the sampling data under the condition of less sampling data. The invention adopts the IDW interpolation method to reconstruct the large-capacity off-line fingerprint library, and can still ensure higher positioning precision of the mobile user in the on-line stage when the acquisition density of off-line fingerprint points is lower. On the basis of ensuring high-precision positioning of a mobile user, a fingerprint library can be established in a short-time and low-density fingerprint point acquisition mode, so that the working efficiency is greatly improved, and the hardware cost is reduced.
Drawings
Fig. 1 is an algorithm flow chart of the indoor positioning method of the present invention.
FIG. 2 is a plan view of the building J6 of Shandong university of science and technology in example 1.
Fig. 3 is a plan view of the S2 floor of the university of eastern technology in example 2.
FIG. 4 shows the root mean square error of the positioning results of the present invention after two different methods of preprocessing.
Fig. 5 is a graph of the cumulative probability of error of the fingerprint library optimization algorithm of the gray model and inverse distance weighted interpolation of the present invention versus other fingerprint algorithms in example 1.
Fig. 6 is a graph of cumulative probability of error of the fingerprint library optimization algorithm of the gray model and inverse distance weighted interpolation of the present invention versus other fingerprint algorithms in example 2.
FIG. 7 is a graph comparing the positioning traces of the fingerprint library optimization algorithm of the gray model and inverse distance weighted interpolation of the present invention with other fingerprint algorithms in example 1.
FIG. 8 is a graph comparing the positioning traces of the fingerprint library optimization algorithm of the gray model and inverse distance weighted interpolation of the present invention with other fingerprint algorithms in example 2.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
In this embodiment, the building J6 of the university of eastern technology is used as an experimental area, and corresponding indoor positioning work is performed according to the workflow chart of fig. 1. The experimental area corridor area of the building J6 of Shandong university of science and technology is about 124 square meters, and 26 reference fingerprint points are collected at the building J6 of Shandong university of science and technology in combination with specific field conditions, and for details, see FIG. 2, in which a star shape represents the positions of the reference fingerprint points.
Step 1: and (5) installing iBeacon and calibrating the positions of the reference fingerprint points. The specific installation effect is shown in fig. 2, wherein the deployment height of the iBeacon is 2.6±0.1 meters, and the deployment interval is 5-10 meters. Sparse calibration of the reference fingerprint points is uniformly calibrated in an indoor positioning area at a density of 3+/-0.5 square meters.
Step 2: fingerprint information on each reference fingerprint point is collected and preprocessing is completed by utilizing a GM (1, 1) model.
In step 2, the pretreatment is completed by using the GM (1, 1) model as follows:
step 2.1 ordering a group of RSS data from small to large to form an original array RSS (0) ：
Step 2.2 pair RSS (0) Data accumulation is carried out to obtain a new number sequence RSS (1) As shown in formula (1):
in the formula (1), the components are as follows,
step 2.3 calculating the close proximity meanAs shown in formula (2):
and 2.4, constructing a GM (1, 1) model, and further obtaining the fitted RSS. The GM (1, 1) model calculation formula is shown as a formula (3).
In the formula (3), the amino acid sequence of the compound,for the gray derivatives, a and u are key coefficients to be obtained. Wherein a is a development coefficient, and u is an ash action amount. A and u can be obtained by the least square method. The least square method is represented by the formula (4).
[a,u] T ＝(B T B) -1 B T Y (4)
In the formula (4), the amino acid sequence of the compound,the response function calculation formula is shown in formula (5).
In the formula (5), the amino acid sequence of the compound,is->Estimated value of ∈10->Is->Is to be estimated, i.e. toAnd combining the RSSs.
Step 2.5, optimizing and verifying. And (3) checking the GM (1, 1) model by using a variance ratio C and a small error probability p, so as to determine whether to use the fitted RSS obtained in the step (2.4), wherein the variance ratio C and the small error probability p are calculated as shown in a formula (6).
In the formula (6), ε (0) As a series of the residual values,is the average value of the original number sequence and the residual number sequence, S 1 、S 2 Standard deviations of the original and residual sequences, respectively. When C is less than 0.35 and p is more than 0.95, adopting RSS after fitting; otherwise, discarding the RSS after fitting, selecting the RSS of the original sequence (0) 。
Step 3: reconstructing a high-density off-line fingerprint library. And (3) averaging the RSS obtained in the step (2), constructing an offline fingerprint library for the fingerprint points, and reconstructing the high-density offline fingerprint library by adopting an IDW interpolation method.
In step 3, the specific process of reconstructing the high-density fingerprint library by using the IDW interpolation method is as follows.
Given the point to be inserted F 0 Coordinates (x) 0 ,y 0 ) Find 4 reference fingerprint points F nearest to the point to be inserted i (where i=1, 2,3, 4), then the point F is to be inserted 0 The attribute value of (2) can be obtained by the following formula.
In the above, x i 、y i Respectively represent neighboring fingerprint points F i Is defined by the abscissa of (2), R (F i ) For the neighboring fingerprint point F i Attribute value lambda of (a) i (i=1, 2,3, 4) is the weight of the fingerprint point attribute value to the point to be inserted, R * (F 0 ) The obtained attribute value of the insertion point is obtained.
Step 4: on-line location matching is accomplished using WKNN. WKNN finds k fingerprint points closest to the Euclidean distance by calculating the Euclidean distance between the RSS and the fingerprint points acquired in real time, and takes the weighted centroids of the k fingerprint points as coordinates of unknown points by adopting the inverse weighting of the n th power of the Euclidean distance.
In step 4, the weighted centroids of the k fingerprint points are used as coordinates of unknown points, and the calculation formula is shown in formula (10).
In the formula (10), (x, y) iBeacon Representing the coordinates of unknown points, D i Representing the Euclidean distance of the RSS to the ith fingerprint point acquired in real time, (x) i ,y i ) Representing the coordinates of the ith fingerprint point.
Example 2
In this embodiment, building No. S2 of Shandong university of science and technology is used as the experimental area. The area of the corridor of the experimental area of the S2 building of Shandong university of science and technology is about 180 square meters, and 65 reference fingerprint points are collected at the J6 of Shandong university of science and technology in combination with specific field conditions, and for details, see FIG. 3, in which a star shape represents the positions of the reference fingerprint points. The specific implementation steps of this embodiment are as shown in embodiment 1, and will not be described here again.
In order to verify the effectiveness of preprocessing by adopting a GM (1, 1) model, the invention adopts the GM (1, 1) model to preprocess the original data and establishes a fingerprint library; in contrast, the original data is preprocessed by Gaussian filtering, and a fingerprint database is built. Test points were randomly selected and tested for positioning using WKNN. The root mean square error of the positioning results after pretreatment by two different methods is shown in fig. 4. Experimental results show that the positioning performance of the fingerprint positioning algorithm after the GM (1, 1) model is higher than that of the fingerprint positioning algorithm after the Gaussian filter is adopted.
In order to verify the influence of GM (1, 1) model and IDW interpolation on the performance of the indoor positioning method based on the iBeacon fingerprint library, three strategies are adopted for data calculation: after preprocessing original data, a GM (1, 1) model establishes a fingerprint library, and WKNN is adopted as a matching positioning algorithm; GM (1, 1) model-Ordinary Kriging (OK) interpolation to build fingerprint library, and adopting WKNN as matching positioning algorithm; and (3) establishing a fingerprint library by GM (1, 1) model-IDW interpolation, and adopting WKNN as a matching positioning algorithm.
In order to verify the performance of the present invention, the above three strategies are used for positioning test on two different experimental areas in embodiment 1 and embodiment 2, the cumulative probability distribution of positioning errors after positioning test is shown in fig. 5 and 6, and the corresponding positioning tracks are shown in fig. 7 and 8, so that the abscissa scale of fig. 7 and 8 has a larger difference in order to clearly represent the positioning tracks of the two different experimental areas. Experimental results show that the probability positioning error of 70% of the fingerprint library optimization algorithm of the GM (1, 1) model-IDW interpolation provided by the invention is within 2 meters, and compared with the fingerprint positioning algorithm which singly adopts the GM (1, 1) model, the average positioning error and the RMSE are respectively reduced by about 18.2% and 15.7%. The common kriging interpolation is a fingerprint library interpolation method which is commonly used at present, and although the method is almost the same as the GM (1, 1) model-OK interpolation positioning accuracy, the method has the obvious advantages of simple algorithm and easy implementation.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (4)
1. An indoor positioning method based on an iBeacon fingerprint library is characterized by comprising the following specific steps:
step 1: installing iBeacon and calibrating the positions of reference fingerprint points;
step 2: collecting fingerprint information of each reference fingerprint point and preprocessing data by utilizing a GM (1, 1) model;
step 3: reconstructing a high-density off-line fingerprint library; after the RSS obtained by fitting is averaged, fingerprint points are established and built into an offline fingerprint library, the high-density offline fingerprint library is reconstructed in an IDW interpolation mode, and 4 neighboring fingerprint points are selected by the insertion points for prediction according to the deployment mode of the collected fingerprint points;
step 4: using WKNN to complete on-line positioning matching; WKNN finds k fingerprint points with nearest Euclidean distance by calculating RSS and Euclidean distance of the fingerprint points collected in real time, and takes the weighted centroids of the k fingerprint points as coordinates of unknown points by adopting inverse weighting of the Euclidean distance to the power of n;
the pretreatment process by using the GM (1, 1) model in the step 2 comprises the following specific steps:
step 2.1, arranging a group of RSS data values from small to large to form an original array RSS (0) ：
Step 2.2 pair RSS (0) Data accumulation is carried out to obtain a new number sequence RSS (1) As shown in formula (1):
in the formula (1), the components are as follows,
step 2.3, calculating the immediate mean value as shown in formula (2):
step 2.4, building a GM (1, 1) fitting model, and further obtaining predicted RSS, wherein the fitting model is shown in a formula (3):
in the formula (3), the amino acid sequence of the compound,for the gray derivatives, a and u are key coefficients to be obtained; wherein a is a development coefficient, u is an ash action amount, a and u can be obtained by a least square method, and a calculation formula of the least square method is shown as a formula (4);
[a,u] T ＝(B T B) -1 B T Y(4)
in the formula (4), the amino acid sequence of the compound, the response function calculation formula is shown in the formula (5);
in the formula (5), the amino acid sequence of the compound,is->Estimated value of ∈10->Is->I.e., predicted RSS;
step 2.5, optimizing and verifying; using variance ratio C test and small error probability p test to obtain predicted sequence, RSS (0) As the original number sequence is set up,is a model predictive array, ε (0) The residual number columns are the average value and the variance of each number column as shown in formula (6);
in the formula (6), a variance ratio is definedProbability of small error->Usually, C is less than 0.35, p is more than 0.95, and the precision grade is highest;
the specific process of reconstructing the high-density fingerprint library by adopting the IDW interpolation method in the step 3 is as follows:
given the point to be inserted F 0 Coordinates (x) 0 ,y 0 ) Find 4 reference fingerprint points F nearest to the point to be inserted i (whereinI=1, 2,3, 4), then the point F is to be inserted 0 The calculation formula of the attribute value of (2) is shown in the formula (7);
in the above, x i 、y i Respectively represent neighboring fingerprint points F i Is defined by the abscissa of (2), R (F i ) For the neighboring fingerprint point F i Attribute value lambda of (a) i (i=1, 2,3, 4) is R (F i ) Weight of R * (F 0 ) The attribute value of the point to be inserted is obtained.
2. The indoor positioning method based on the iBeacon fingerprint library according to claim 1, wherein the deployment height of the iBeacon in the step 1 is 2.6+/-0.1 m, the deployment distance is 5-10 m, and strong magnetism, strong electricity and barriers should be avoided as much as possible during deployment; sparse calibration of reference fingerprint points is uniformly calibrated in an indoor positioning area at a density of 3+/-0.5 square meters, but the specific density is determined by combining the field conditions.
3. The indoor positioning method based on the iBeacon fingerprint library according to claim 1, wherein in the step 2, fingerprint information on each reference fingerprint point is collected in a short-time collection manner of 2 seconds.
4. The indoor positioning method based on the iBeacon fingerprint library according to claim 1, wherein in the step 4, the weighted centroids of k fingerprint points are used as coordinates of unknown points, and the calculation formula is shown as formula (10):
in the formula (10), (x, y) iBeacon Representing the coordinates of unknown points, D i Representing the Euclidean distance of the RSS to the ith fingerprint point acquired in real time, (x) i ,y i ) Representing the coordinates of the ith fingerprint point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241688.9A CN114449438B (en) | 2021-10-25 | 2021-10-25 | Indoor positioning method based on iBeacon fingerprint library |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111241688.9A CN114449438B (en) | 2021-10-25 | 2021-10-25 | Indoor positioning method based on iBeacon fingerprint library |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114449438A CN114449438A (en) | 2022-05-06 |
| CN114449438B true CN114449438B (en) | 2024-04-09 |
Family
ID=81362548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111241688.9A Active CN114449438B (en) | 2021-10-25 | 2021-10-25 | Indoor positioning method based on iBeacon fingerprint library |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114449438B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117890949B (en) * | 2024-03-14 | 2024-05-24 | 山东科技大学 | GNSS and RSSI fusion positioning method considering MAC address |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109951807A (en) * | 2019-02-27 | 2019-06-28 | 西北师范大学 | Fusion RSS and CSI indoor orientation method based on WiFi signal |
| CN110557716A (en) * | 2019-09-03 | 2019-12-10 | 华南师范大学 | Indoor positioning method based on lognormal model |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2015251350A1 (en) * | 2014-04-24 | 2016-11-10 | Beijing Didi Infinity Technology And Development Co., Ltd. | System and method for managing supply of service |
| US11039414B2 (en) * | 2017-11-21 | 2021-06-15 | International Business Machines Corporation | Fingerprint data pre-process method for improving localization model |
-
2021
- 2021-10-25 CN CN202111241688.9A patent/CN114449438B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109951807A (en) * | 2019-02-27 | 2019-06-28 | 西北师范大学 | Fusion RSS and CSI indoor orientation method based on WiFi signal |
| CN110557716A (en) * | 2019-09-03 | 2019-12-10 | 华南师范大学 | Indoor positioning method based on lognormal model |
Non-Patent Citations (2)
| Title |
|---|
| "基于GM(1，1)模型的室内定位指纹库误差修正方法";张娟娟;《杭州电子科技大学学报（自然科学版）》;正文第1-3节 * |
| "基于泛克里金插值的WSN位置指纹预处理";乐燕芬;《传感技术学报》;正文第1-4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114449438A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111061821B (en) | Low-voltage distribution network topology verification method and system based on improved k-value clustering algorithm | |
| CN102573049B (en) | Method and system for indoor positioning | |
| CN108307301B (en) | Indoor positioning method based on RSSI ranging and track similarity | |
| CN110166930A (en) | A kind of indoor orientation method and system based on WiFi signal | |
| CN104507050B (en) | Probabilistic type finger print matching method in a kind of WiFi indoor positionings | |
| CN105142216B (en) | Indoor and outdoor based on characteristic signal fingerprint base positions switching method | |
| CN105792356A (en) | Wifi-based location fingerprint positioning method | |
| CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
| CN104093205A (en) | Method for deploying anchor nodes of wireless positioning system based on received signal strength indication | |
| CN114449438B (en) | Indoor positioning method based on iBeacon fingerprint library | |
| CN110933604B (en) | KNN indoor positioning method based on position fingerprint time sequence characteristics | |
| CN112653991A (en) | WLAN indoor positioning method of TebNet neural network model based on deep learning | |
| Wang et al. | Research on APIT and Monte Carlo method of localization algorithm for wireless sensor networks | |
| CN101873605B (en) | Adaptive method for classifying communication environments in network planning | |
| CN114363808A (en) | Indoor positioning method based on RSSI ranging | |
| CN108917583A (en) | A kind of super high-rise building deformation monitoring new method for taking tropospheric delay influence into account | |
| CN111194000B (en) | Distance measurement method and system based on Bluetooth fusion hybrid filtering and neural network | |
| CN117200181A (en) | Photovoltaic power generation amount prediction method based on DBSCAN-EM-GMM and Web technology | |
| CN112284335B (en) | Pole tower settlement and inclination monitoring system and method based on Beidou positioning | |
| CN111880140A (en) | RSSI-based wireless sensor network arc triangle positioning method | |
| CN113271542B (en) | Indoor mobile terminal positioning method based on Bluetooth and visible light | |
| CN111314896B (en) | Secondary construction method of environment self-adaptive fingerprint database | |
| CN115470858A (en) | Power distribution area topology identification method based on DDTW distance and minimum maximum distance algorithm | |
| CN106021861B (en) | A kind of motivational techniques of intelligent perception system | |
| CN110779513B (en) | Indoor public service place positioning system |
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 |