CN108566675B - WiFi indoor positioning method based on multiple access point selection - Google Patents
WiFi indoor positioning method based on multiple access point selection Download PDFInfo
- Publication number
- CN108566675B CN108566675B CN201711262019.3A CN201711262019A CN108566675B CN 108566675 B CN108566675 B CN 108566675B CN 201711262019 A CN201711262019 A CN 201711262019A CN 108566675 B CN108566675 B CN 108566675B
- Authority
- CN
- China
- Prior art keywords
- access point
- positioning
- cluster
- access points
- access
- 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
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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a WiFi indoor positioning method based on multiple access point selection, which mainly solves the problem of inaccurate positioning result of the access point in the prior art, and adopts the technical scheme that: 1) collecting access point data; 2) according to the access point data, multiple access point selections are carried out, and an access point set with stable signals and strong resolving power is selected to form a position fingerprint database; 3) grouping the positions according to the fingerprints of the positions; 4) reselecting an access point for each position cluster, and selecting a characteristic access point set capable of better expressing the position cluster; 5) establishing a decision tree model for each position group; 6) determining the position grouping of the target position of the positioning sample by the given positioning sample; 7) and determining the specific position of the positioning sample by using the positioning model of the position grouping of the positioning sample. The invention can effectively overcome the influence of unstable access points in the environment on the positioning precision, and can be used in various complex positioning environments.
Description
Technical Field
The invention belongs to the technical field of communication, and particularly relates to a WiFi indoor positioning method which can be used for positioning indoor users, navigating indoor users and other position-based services.
Background
With the rapid development of mobile communication technology and mobile internet technology, mobile intelligent terminals have come into play and are rapidly popularized, and various services based on mobile internet are explosively increased. The location based service LBS has experienced rapid development in the last decade, and is widely applied to the lives of people, thereby greatly changing the life style of people and bringing convenience to the lives of people. And the positioning technology is an essential underlying support technology in LBS applications. In outdoor environments, the global positioning system GPS is currently the most sophisticated positioning system. However, in the indoor environment, due to the obstruction of the wall body, the indoor environment is complex and variable, the interference is numerous, and the GPS signal cannot be used for indoor positioning.
With the continued sophistication of the IEEE 802.11 protocol, WiFi has gained popularity. Although WiFi is not a positioning device, it is a preferred choice for indoor positioning because of its fast transmission speed, high coverage, free use in public places, no need of special equipment, and low deployment cost. In the WiFi positioning technology, the main research direction is currently positioning based on signal strength RSSI, wherein a WiFi indoor positioning method based on location fingerprint identification is a popular method.
The WiFi indoor positioning method based on position fingerprint identification is to abstract and formally describe scene features observed in an environment to be positioned and position the scene features by utilizing the relevance between signal strength RSSI and a physical position. The RSSI representation is different at different physical locations, i.e., the signal strength of the AP received at each point is different. The signal intensity of AP points arranged in a positioning environment is detected in advance at each sampling point, the signal intensity is extracted as a positioning characteristic value, the positioning characteristic value is trained into a mapping relation with a physical position, and a corresponding position fingerprint database is constructed. Then, by a specific matching method, the signal strength RSSI fingerprint data measured in real time at the point to be positioned is matched with the fingerprint data in the position fingerprint database, and the position of the user to be positioned is estimated by the coordinate positions corresponding to a plurality of fingerprints with larger similarity.
With the rapid proliferation of WiFi, wireless access points have also become ubiquitous. Thus hundreds of access points may be detected in a positioning environment while data acquisition is taking place. Among these aps are some non-ideal aps that are far from the positioning environment, have unstable signals, fluctuate widely, and carry much noise, and provide little valuable information for the positioning, or even may degrade the positioning accuracy. In addition, this can greatly increase the dimensionality of the fingerprint repository, increasing the positioning complexity when using all of the access points.
Disclosure of Invention
The invention aims to provide a WiFi indoor positioning method based on multiple access point selection, which is used for selecting a more stable access point set with strong resolution capability to represent a position fingerprint, reducing the calculation complexity, reducing the dimensionality of a fingerprint library, removing the influence of an access point with poor signal quality on a positioning result and improving the positioning precision.
The technical idea of the invention is as follows: selecting an access point set with stable signals and strong resolving power through multiple access point selection, establishing a position fingerprint library with lower dimensionality and more stability, clustering positions in a positioning environment through the position fingerprint library, and clustering positions with higher fingerprint similarity into the same position cluster. And selecting an access point set which can better represent the characteristics of each position cluster through reselecting the access points, and establishing a decision model with better positioning effect on the position clusters.
According to the above thought, the implementation steps of the invention include the following:
1) constructing an access point signal strength database:
dividing the positioning environment into a plurality of grids with the same size, and expressing the positions of the grids by the positions of the central points of the grids; carrying out data acquisition on each position, recording the signal intensity value of each access point detected by each position, and forming an access point signal intensity database for recording the sampling data of each position;
2) constructing a position fingerprint database:
2a) setting an initial time threshold m for covering at least each position by the access point and an initial time threshold n for covering at least the whole positioning space by the access point according to the coverage time distribution of each access point in the positioning environment, performing multiple selection on the access point according to the coverage time of the access point to each position in the database and the coverage time of the access point in the whole positioning environment, deleting the access points with the coverage time smaller than the two thresholds, and screening out preselected access points to form a preselected access point set;
2b) calculating the information gain of each access point in the preselected access point set, sequencing the access points according to the sequence of the information gain from large to small, and selecting the first k access points to form a final fingerprint access point set, wherein k is more than or equal to 10;
2c) screening the access point signal strength database obtained in the step 1) according to the fingerprint access point set, and only retaining access point data contained in the fingerprint access point set to obtain fingerprints of all positions to form a final position fingerprint database;
3) clustering environmental positions by using a k-means algorithm, reselecting an access point for each position cluster, and selecting a characteristic access point set capable of better representing the position cluster;
4) establishing a decision tree model for each group by using a C4.5 decision tree method to obtain a decision model with the fastest position unknown information reduction;
5) positioning stage
5a) Giving sample data needing positioning, calculating Euclidean distances between the fingerprints of the positioning samples and each position cluster, selecting the position cluster with the minimum Euclidean distance to the position cluster, and taking the cluster as the cluster where the target position is located;
5b) the positioning samples move down along the clustered decision tree model from the root node until moving to a leaf node of the decision tree, which is the position of the final positioning sample.
Compared with the prior art, the invention has the following advantages:
according to the invention, through multiple access point selection, an unsatisfactory access point and an access point with unstable signal can be deleted, and an access point set which is more stable and has strong resolution capability can be selected, so that the complexity of positioning calculation is reduced, the dimensionality of a fingerprint database is reduced, the positioning precision is improved, and the method can be applied to a more complicated positioning environment;
according to the invention, through reselecting the position clustering access points, a characteristic access point set which better represents the position clustering can be selected, so that a more reasonable positioning model can be established for each cluster, and the positioning accuracy is further improved.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention;
FIG. 2 is a schematic diagram of a positioning scenario in which the present invention is implemented;
FIG. 3 is a schematic diagram of a positioning result of the present invention under different positioning errors in a positioning scenario;
FIG. 4 is a comparison graph of the positioning result in the positioning scene of the present invention and the positioning method based on the information gain method, with the positioning error within 2 m;
FIG. 5 is a decision tree model for location clustering.
Detailed Description
Referring to fig. 1, the implementation steps of the invention are as follows:
Referring to fig. 2, the positioning scene of the example is a corridor in the area of 4 th floor I of the main building of the university of sienna electronic technology, and the area is 340m2；
The method comprises dividing the positioning environment into 177 square grids with side length of 0.8m, expressing the grid positions by the central point positions of the grids, numbering the positions, and using GjRepresents the jth position; and then, data acquisition is carried out on each position, and the RSSI value of each access point detected by each position is recorded to form an RSSI database for recording the sampling data of each position.
And 2, selecting the access point.
When the access point selection is carried out in the step, the method comprises the following two steps:
2a) the method is characterized in that the method carries out preliminary screening on detected access points based on the coverage time of the access points, deletes the access points with unstable signals, and uses the access points with relative stability to form a pre-access point set:
2a1) calculating the number of detected access points at each location that occur during the detection period, and reserving those access points that cover the location for at least 80% of the detection period, deleting other access points, and forming a primary set of preselected access points from the set of access points reserved for each location;
2a2) calculating the occurrence times of all positions of each access point in the primary preselected access point set in the positioning environment, and reserving access points which cover all the positions for at least 20% of the detection time period to form a final preselected access point set;
2b) calculating the information gain of access points in a preselected access point set based on an information gain method, sequencing the access points according to the descending order of the information gain, and selecting 15 access points with the maximum information gain to form the access point set, wherein the information gain calculation process of the access points is as follows:
2b1) calculating uncertainty h (g) of location information in a positioning environment:
where G denotes the position in the positioning environment, GiDenotes the ith position, P (G)i) Indicates position GiThe probability of occurrence, 177 is the number of positions in the positioning environment;
2b2) calculating uncertainty H (G | AP) of location information in a positioning environment under the condition of a known access pointi)：
Wherein, APiDenotes the ith access point, vjRepresenting APiN represents APiThe number of values of the signal strength H (G | AP)i＝vj) Is shown in the known APiHas a signal strength of vjThe calculation formula of the entropy of the information of the position in the positioning environment is the same as that of H (G);
2b3) calculating information entropy Gain (AP) of the access point according to the results of 2b1) and 2b2)i)：
Gain(APi)＝H(G)-H(G|APi)，
Wherein, Gain (AP)i) Indicated in the known access point APiThe larger the information gain, the larger the reduction of the position uncertainty information, and the stronger the resolution capability of the access point to the position.
And 3, constructing a position fingerprint database.
And (3) screening the access point signal strength database obtained in the step (1) according to the fingerprint access point set, namely only retaining the access point data contained in the fingerprint access point set to obtain the fingerprint of each position and form a final position fingerprint database.
And 4, grouping the positions.
In the step, the positions are grouped according to the fingerprints of all the positions by using a classical k-means grouping method, and the process is as follows:
4a) determining the number k of clusters, which is 5 in the present example under the positioning environment shown in fig. 2, optionally selecting 5 positions as the cluster centers of the 5 clusters, and taking the fingerprints of the positions as the cluster fingerprints;
4b) calculating Euclidean distances from all the positions to the 5 cluster centers, distributing the Euclidean distances to clusters with the minimum distances, and after all the positions are distributed, solving the mean value of all the cluster element fingerprints in the position clusters to serve as a new cluster center;
4c) and repeating the step 4b until the fingerprint at the center of the group does not change any more, namely finishing the position grouping.
And 5, reselecting the access point.
The method comprises the following steps of reselecting access points by using an information gain method, respectively calculating the resolving power of each access point in a preselected access point set to each group element, selecting a group of access point sets for each position group, and when reselecting the access point set of the group, only considering the resolving power of the access point to the position in the group and not considering the resolving power of the access point to other group elements to obtain an optimal access point set for each group;
re-screening the access point signal strength database obtained in the step 1 through an access point set with the optimal grouping to obtain new fingerprints of each position in the position grouping, wherein the fingerprints of each position before the access point is re-selected are composed of the access point set selected in the step 2, and the access point set selected in the step 2 is optimal for the whole positioning environment;
the purpose of this step is to select the access point that is optimal for each location cluster, i.e. locally optimal, because the set of access points that is optimal for the entire positioning environment is not necessarily the optimal set of access points for each location cluster, so the new location fingerprint better represents the properties of the respective location than the location fingerprint before the access point was reselected, i.e. the new location fingerprint may better represent the characteristics of the respective location.
And 6, establishing a positioning decision model.
The step is to establish a decision tree model for each position group based on a C4.5 algorithm, the algorithm selects an access point of each node of the decision tree based on the information gain rate of the access point, and establishes a decision model with the fastest position unknown information reduction, and the process is as follows:
6a) discretizing the signal intensity value of each access point, namely dividing the value range of the access point into a plurality of continuous value ranges, dividing the value range of the access point into two sections, calculating the corresponding information gain rate of each discretized access point, and selecting the access point with the largest information gain rate as a root node;
6b) each value range of the access point corresponds to one branch, and the value range is used as a judgment condition of the branch;
6c) and repeating the process, further determining the sub-nodes of the branch connecting points until the sub-nodes of the branches are leaf nodes finally, and finishing the establishment of the decision tree.
And 7, judging the position of the sample to be grouped.
According to the sample data needing positioning, calculating Euclidean distances between the data and each position cluster, in the present example, 5 Euclidean distances are obtained in the positioning environment shown in FIG. 2, the position cluster with the minimum Euclidean distance to the positioning sample is selected, and the position cluster is taken as the cluster where the target position is located, and the Euclidean distance is calculated as follows:
wherein D (T, C)j) Representing the Euclidean distance, C, of the location sample T from the jth position clusterjIs the cluster center of the jth position cluster，SSj(T) represents the signal strength of the ith access point in the positioning sample, SSj(Cj) Indicating the signal strength of the ith access point of the jth location cluster.
And 8, judging the specific position of the positioning sample.
The positioning sample moves downwards from a root node along a decision tree model of a cluster where the positioning sample is located, and the decision conditions of the branch of the decision tree are matched according to the characteristic access point value of the positioning sample, namely the positioning sample moves downwards along the branch meeting the decision conditions until the positioning sample moves to a leaf node, and the leaf node is the final position of the positioning sample;
for example, table 1 shows a positioning sample, fig. 5 shows a decision tree model of a cluster where the positioning sample is located, and a positioning process of the positioning sample using the decision tree model is as follows:
8a) the root node of the decision tree model is AP4, so that the decision condition of which branch the value of AP4 in the positioning sample meets is judged firstly, and obviously, the sample meets the decision condition of the rightmost branch of the AP4 node, so that the branch moves downwards along the rightmost branch of the AP 4;
8b) moving to a node AP1, wherein the value of the positioning sample AP1 is 63, and if the judgment condition of the rightmost branch of the node is met, moving downwards along the rightmost branch of the AP 1;
8c) when the AP1 moves downwards to move to the node AP6, the value of the positioning sample AP6 is 57, the judgment condition of the leftmost branch of the node is met, and then the AP 3578 moves downwards along the leftmost branch of the AP 6;
8d) when the AP6 moves to node G6, the node is a leaf node, i.e., the target position of the positioning sample is G6.
TABLE 1
| AP1 | AP2 | AP3 | | AP5 | AP6 | |
| 63 | 56 | 45 | 70 | 61 | 57 |
The advantages of the present invention can be further illustrated by the following simulation results:
Claims (7)
1. The WiFi indoor positioning method based on multiple access point selection comprises the following steps:
1) constructing an access point signal strength database:
dividing the positioning environment into a plurality of grids with the same size, and expressing the positions of the grids by the positions of the central points of the grids; carrying out data acquisition on each position, recording the signal intensity value of each access point detected by each position, and forming an access point signal intensity database for recording the sampling data of each position;
2) constructing a position fingerprint database:
2a) setting an initial time threshold m for covering at least each position by the access point and an initial time threshold n for covering at least the whole positioning space by the access point according to the coverage time distribution of each access point in the positioning environment, performing multiple selection on the access point according to the coverage time of the access point to each position in the database and the coverage time of the access point in the whole positioning environment, deleting the access points with the coverage time smaller than the two thresholds, and screening out preselected access points to form a preselected access point set;
2b) calculating the information gain of each access point in the preselected access point set, sequencing the access points according to the sequence of the information gain from large to small, and selecting the first k access points to form a final fingerprint access point set, wherein k is more than or equal to 10;
2c) screening the access point signal strength database obtained in the step 1) according to the fingerprint access point set, and only retaining access point data contained in the fingerprint access point set to obtain fingerprints of all positions to form a final position fingerprint database;
3) clustering environmental positions by using a k-means algorithm, reselecting an access point for each position cluster, and selecting a characteristic access point set capable of better representing the position cluster;
4) establishing a decision tree model for each group by using a C4.5 decision tree method to obtain a decision model with the fastest position unknown information reduction;
5) positioning stage
5a) Giving sample data needing positioning, calculating Euclidean distances between the fingerprints of the positioning samples and each position cluster, selecting the position cluster with the minimum Euclidean distance to the position cluster, and taking the cluster as the cluster where the target position is located;
5b) the positioning samples move down along the clustered decision tree model from the root node until moving to a leaf node of the decision tree, which is the position of the final positioning sample.
2. The method of claim 1, wherein the information gain for each access point in the set of preselected access points is calculated in step 2b) by:
2b1) calculating uncertainty h (g) of location information in a positioning environment:
where G denotes the position in the positioning environment, GiDenotes the ith position, P (G)i) Indicates position GiProbability of occurrence, m representing the number of locations in the positioning environment;
2b2) calculating uncertainty H (G | AP) of position information in positioning environment under condition of known access pointi)：
Wherein, APiDenotes the ith access point, vjRepresenting APiN represents APiNumber of values of signal strength, P (AP)i＝vj) Indicating the detection of an access point AP at a reference location jiHas a signal intensity of vjThe probability of (d);
H(G|APi＝vj) Is shown in the known APiHas a signal strength of vjThe calculation formula of the entropy of the information of the position in the positioning environment is the same as that of H (G);
2b3) calculating information entropy Gain (AP) of the access point according to the results of 2b1) and 2b2)i)：
Gain(APi)＝H(G)-H(G|APi)，
Wherein, Gain (AP)i) Representing known access points APiThe larger the information gain, the larger the decrement of the position uncertainty information, the stronger the resolution capability of the access point to the position。
3. The method of claim 1, wherein the environment locations are clustered using a k-means algorithm in step 3) by:
3a) determining the position clustering number k, optionally selecting k positions as cluster centers of the k clusters, and taking fingerprints of the positions as cluster fingerprints, wherein k is more than or equal to 2;
3b) calculating Euclidean distances from all the positions to the k group centers, distributing the Euclidean distances to the groups with the minimum distances, and after all the positions are distributed, solving the mean value of all the group element fingerprints in the position grouping to serve as a new group center;
3c) and repeating the step 3b) until the cluster center is not changed any more, namely finishing the position clustering.
4. The method of claim 1, wherein the step 3) of reselecting the access points for each location cluster is to use an information gain method to calculate the resolution of each access point in the preselected set of access points to each cluster element, to select one set of access points for each location cluster, and to reselect the clustered set of access points, wherein the optimal set of access points for each cluster is obtained by considering only the resolution of the access points to the locations in the cluster, and not considering the resolution of the access points to other cluster elements, and the reselected set of access points can better represent the characteristics of each location cluster.
5. The method of claim 1, wherein the decision tree model is built for each cluster in step 4) using a C4.5 decision tree method, by:
5a) discretizing the signal intensity value of each access point, namely dividing the value range of each access point into a plurality of continuous value ranges, calculating the information gain rate corresponding to each discretized access point, and selecting the access point with the largest information gain rate as a root node;
5b) each value range of the access point corresponds to one branch, and the value range is used as a judgment condition of the branch;
5c) and repeating the process, further determining the sub-nodes of the branch connecting points until the final sub-nodes of the branches are all leaf nodes, and finishing the establishment of the decision tree.
6. The method according to claim 1, wherein the euclidean distance between the positioning sample fingerprints to each position cluster is calculated in step 5a) according to the following formula:
wherein D (T, C)j) Representing the Euclidean distance, C, of the location sample T from the jth position clusterjIs the cluster center of the j-th position cluster, k represents the number of access points selected in step 2b), SSj(T) represents the signal strength of the ith access point in the positioning sample, SSj(Cj) Indicating the signal strength of the ith access point of the jth location cluster.
7. The method according to claim 1, wherein the positioning samples in step 5b) move downwards from the root node along the clustered decision tree model, and the moving direction is determined by judging which branch of the decision tree they satisfy according to the values of the feature access points of the positioning samples until moving to a leaf node, which is the final position of the positioning sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711262019.3A CN108566675B (en) | 2017-12-04 | 2017-12-04 | WiFi indoor positioning method based on multiple access point selection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711262019.3A CN108566675B (en) | 2017-12-04 | 2017-12-04 | WiFi indoor positioning method based on multiple access point selection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108566675A CN108566675A (en) | 2018-09-21 |
| CN108566675B true CN108566675B (en) | 2020-06-23 |
Family
ID=63530225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711262019.3A Active CN108566675B (en) | 2017-12-04 | 2017-12-04 | WiFi indoor positioning method based on multiple access point selection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108566675B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109963261B (en) * | 2019-03-15 | 2020-08-14 | 北京航空航天大学 | Wireless router screening method and device for WIFI indoor positioning |
| CN110213710A (en) * | 2019-04-19 | 2019-09-06 | 西安电子科技大学 | A kind of high-performance indoor orientation method, indoor locating system based on random forest |
| CN110611952B (en) * | 2019-09-20 | 2021-04-02 | 北京眸星科技有限公司 | Fingerprint matching and positioning method |
| CN110636445B (en) * | 2019-10-16 | 2022-09-16 | 腾讯科技（深圳）有限公司 | WIFI-based indoor positioning method, device, equipment and medium |
| CN113518308B (en) * | 2021-05-25 | 2022-03-25 | 江南大学 | Optimal AP screening method in indoor positioning |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7822426B1 (en) * | 2008-01-17 | 2010-10-26 | Where, Inc. | System and method for snapping a user location to a landmark of known location |
| CN102821465A (en) * | 2012-09-07 | 2012-12-12 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor positioning method based on subregion information entropy gain |
| US8639640B1 (en) * | 2011-06-10 | 2014-01-28 | Google Inc. | Prediction of indoor location using decision trees |
| CN106304331A (en) * | 2016-08-19 | 2017-01-04 | 青岛海尔智能技术研发有限公司 | A kind of WiFi fingerprint indoor orientation method |
-
2017
- 2017-12-04 CN CN201711262019.3A patent/CN108566675B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7822426B1 (en) * | 2008-01-17 | 2010-10-26 | Where, Inc. | System and method for snapping a user location to a landmark of known location |
| US8639640B1 (en) * | 2011-06-10 | 2014-01-28 | Google Inc. | Prediction of indoor location using decision trees |
| CN102821465A (en) * | 2012-09-07 | 2012-12-12 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor positioning method based on subregion information entropy gain |
| CN106304331A (en) * | 2016-08-19 | 2017-01-04 | 青岛海尔智能技术研发有限公司 | A kind of WiFi fingerprint indoor orientation method |
Non-Patent Citations (1)
| Title |
|---|
| Power-efficient access-point selection for indoor location estimation;Yiqiang Chen;《IEEE Transactions on Knowledge and Data Engineering》;20060530;第4.1-4.2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108566675A (en) | 2018-09-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108566675B (en) | WiFi indoor positioning method based on multiple access point selection | |
| CN110012428B (en) | Indoor positioning method based on WiFi | |
| CN107948930B (en) | Indoor positioning optimization method based on position fingerprint algorithm | |
| CN105223546B (en) | Indoor orientation method based on received signal strength and reference point locations double focusing class | |
| CN106851573B (en) | Log path loss model-based joint weighting K nearest neighbor indoor positioning method | |
| CN104703143B (en) | A kind of indoor orientation method based on WIFI signal intensity | |
| CN103945533B (en) | Wireless real time position localization methods based on big data | |
| CN103916820B (en) | Wireless indoor location method based on access point stability | |
| CN107241700B (en) | Indoor positioning method based on CSI space-frequency characteristic and reference point position clustering algorithm | |
| CN110602651B (en) | Positioning method based on WIFI position fingerprint and positioning system of robot | |
| CN103634901B (en) | Novel location fingerprint based on Density Estimator gathers extracting method | |
| CN108919177B (en) | Positioning map construction method based on virtual information source estimation and track correction | |
| CN107182036A (en) | The adaptive location fingerprint positioning method merged based on multidimensional characteristic | |
| CN109348416B (en) | Fingerprint indoor positioning method based on binary k-means | |
| CN102695272B (en) | Matching location method and mobile terminal | |
| CN104185275A (en) | Indoor positioning method based on WLAN | |
| CN107087256A (en) | A kind of fingerprint cluster method and device based on WiFi indoor positionings | |
| CN112801268B (en) | Positioning method based on graph convolution and multilayer perceptron hybrid network | |
| CN109041206A (en) | A kind of indoor positioning floor method of discrimination based on improvement fuzzy kernel clustering | |
| CN107302794A (en) | The method of running fix and navigation is used as by the use of WIFI signal | |
| CN108966131A (en) | Fusion floor estimating method based on indoor positioning | |
| KR102304466B1 (en) | Method and system for building indoor positioning database and positioning indoor with indoor positioning database | |
| CN108521631B (en) | Mobile AP (access point) identification method for indoor positioning | |
| CN109541537B (en) | Universal indoor positioning method based on ranging | |
| Liu et al. | An indoor WLAN location algorithm based on fingerprint database processing |
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 |