CN111405461A - Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number - Google Patents
Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number Download PDFInfo
- Publication number
- CN111405461A CN111405461A CN202010181859.2A CN202010181859A CN111405461A CN 111405461 A CN111405461 A CN 111405461A CN 202010181859 A CN202010181859 A CN 202010181859A CN 111405461 A CN111405461 A CN 111405461A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- positioning
- training
- fingerprint information
- model
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—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
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 wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples, which comprises the steps of arranging a positioning environment taking UWB wireless communication equipment as an anchor node indoors, taking TOA as a component element of a fingerprint, and then positioning a positioning target in a self-adaptive manner through training and testing processes of a machine learning model; in the training stage, equally spaced fingerprint sampling is carried out in a positioning space, and collected fingerprint information is combined into a fingerprint data set; selecting partial fingerprint information from the fingerprint data set as a training set, enabling the position information and the fingerprint characteristic information to be mapped, and testing the positioning accuracy under the number of the fingerprints by using a testing set; the number of the trained fingerprints is increased gradually, and a test set is used for testing the change of the positioning precision; when the change rate of the positioning precision is lower than the threshold set by the invention, the most reasonable number of fingerprints is found out for positioning, and the reliable positioning precision and the higher operation efficiency are considered.
Description
Technical Field
The invention relates to the technical field of wireless communication, in particular to a wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples.
Background
With the development of mobile communication technology, people's demand for positioning is increasing day by day, and the location information service is receiving great attention. As indicated in the white paper book for indoor and outdoor high-precision positioning and navigation, in the current society, the time of people staying indoors every day exceeds 80% of the time of a day, and the indoor environment comprises places such as family houses, companies, supermarkets, markets, parking lots, underground mines, tunnels and the like. This has resulted in outdoor positioning not being sufficient to meet people's living requirements and positioning and tracking of people in indoor environments has become of paramount importance.
However, the widely used Global Positioning System (GPS) does not work well in indoor environments. The main reason is that the number of building layers and the density of buildings are increasing along with the increase of population, and the economy is increasing, so that the signal strength of GPS signals passing through the buildings is greatly reduced, the signals are easy to interfere in the process of propagation, and even cannot be normally received, and therefore, it is crucial to select an effective and high-precision positioning technology to replace the GPS in an indoor environment. Therefore, how to realize accurate positioning of the target indoors is a current hotspot problem in meeting the requirement of people on indoor positioning.
Existing technologies for indoor positioning, such as Wi-Fi technology, bluetooth technology, Zigbee technology, and the like. However, due to the characteristics of the positioning technologies, the positioning accuracy of the positioning technologies is not high, the positioning accuracy of the bluetooth technology can only reach about 2.5m, and the positioning accuracy of the Wi-Fi technology can reach about 1 m. In addition, the Wi-Fi and the Bluetooth have relatively weak anti-interference capability and are difficult to be applied to complicated and variable indoor environments, such as shopping malls with large pedestrian volume. Therefore, indoor positioning technologies with high positioning accuracy, strong anti-interference capability, low power consumption and low cost, such as ultra-wideband technology, are widely researched and rapidly developed.
The Ultra Wide Band (UWB) technology is very suitable for indoor positioning, and the indoor positioning method based on the UWB technology not only can achieve the positioning accuracy of centimeter level, but also can obtain the positioning result in a short time. The ultra-wideband (UWB) initial specifications were developed by the Federal Communications Commission (FCC) in 2002 and formally released its limits in the civilian field. Therefore, the ultra-wideband technology is used as indoor positioning and has a wide development prospect.
However, complex indoor environments cause non-line-of-sight (N L OS) and multipath signal propagation, resulting in various signal losses, resulting in inaccurate distance estimation.
The indoor positioning method based on the fingerprint uses a feature vector composed of a plurality of groups of features to represent the attribute of a specific position, the relevance between fingerprint information and the corresponding position is mined through a machine learning algorithm, in an indoor positioning system, a positioning target can continuously acquire the feature information from each anchor node, and the feature vector can be composed to be put into an algorithm model, so that the position of the positioning target is used as the target for training. Because the number of the trained fingerprints can be adjusted, if the number of the selected fingerprints is less, the positioning precision is lower; on the contrary, if the number of the selected fingerprints is too large, the acquisition is dense, and the acquisition task is complicated, so that the calculation efficiency is reduced. Therefore, an optimal fingerprint number is formulated for the system according to the training condition of the machine learning algorithm, and the positioning precision and the calculation efficiency can be considered at the same time.
The invention mainly researches a wireless indoor high-precision positioning method for optimizing the number of equally-spaced fingerprint samples, and an optimal fingerprint number is formulated for a system according to the training condition of a machine learning algorithm, so that the positioning precision and the calculation efficiency can be considered at the same time.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the problem that a large amount of data needs to be collected in fingerprint positioning, the invention provides a wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples.
The technical scheme is as follows: in order to achieve the purpose, the invention adopts the technical scheme that:
a wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples comprises the following steps:
step 1, building a wireless communication indoor positioning environment, arranging a positioning environment with UWB wireless communication equipment as an anchor node indoors, taking TOA as a constituent element of a fingerprint, collecting fingerprint information at equal intervals, constructing a fingerprint set, and initializing the number of the fingerprint information; in addition, fingerprint information is collected through random motion in a positioning environment, and a test set is constructed.
Step 2, selecting a machine learning model and training the machine learning model by taking the fingerprint information and the corresponding position coordinates as a training set;
step 3, testing the trained machine learning model in the step 2 in the test set by using the test set constructed in the step 1 to obtain the positioning precision of the model in the training set;
step 4, increasing the number of the fingerprint information, repeating the step 2 to the step 3, and obtaining the positioning precision obtained in the step 3 under the condition of different numbers of the fingerprint information until all the information in the fingerprint set is used;
and 6, completing the construction of an indoor positioning system after the optimal fingerprint sampling number is obtained in the step 5, and detecting the specific position of the target.
Further, the machine learning model in the step 2 is respectively simulated by adopting a KNN algorithm model and a random forest model, and the results are compared to obtain the optimal positioning precision; wherein
The KNN model input and output in the training process comprise the following processing processes:
inputting: the training set is denoted as D { (x)1,y1),(x2,y2),...，(xN,yN)}
Wherein
For fingerprint information in fingerprint collections, yi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: coordinate y to which fingerprint x belongs
According to the given distance measurement, k points nearest to x are found in the training set D, and the area of x covering the k points is marked as Nk(x)
In Nk(x) In which the coordinate y of x is determined according to a classification decision rule
In the above formula, I is an indicator function, i.e. when yi＝ciIf I is 1, otherwise, I is 0;
the input and output of the random forest model in the training process comprise the following processing processes:
step S1, the random forest uses CART decision tree as weak learning device;
step S2, the establishment of the decision tree is improved; the random forest randomly selects a part of sample characteristics on the nodes, and then selects an optimal characteristic from the randomly selected sample characteristics to divide left and right subtrees of the decision tree;
inputting: training set D { (x)1,y1),(x2,y2),...，(xN,yN) The iteration times of the weak classifier are T; wherein therein
For fingerprint information in fingerprint collections, yi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: final Strong classifier f (x)
(1) For T1, 2,3,. T;
sampling the training set for the t time, and acquiring m times in total to obtain a sampling set Dt containing m samples;
training a tth decision tree model Gt (x) by using a sampling set Dt, selecting a part of sample characteristics from all sample characteristics on a node when the node of the decision tree model is trained, and selecting an optimal characteristic from the randomly selected part of sample characteristics to divide left and right subtrees of the decision tree;
(2) in the regression prediction, the value obtained by arithmetically averaging the regression results obtained by the T weak learners is the final model coordinate output.
Has the advantages that: the system has the following advantages:
through arranging the positioning environment taking UWB wireless communication equipment as an anchor node indoors, the positioning target can sense the arrival time characteristic information of peripheral nodes, the TOA is taken as a component element of a fingerprint, and the positioning target can be positioned in a self-adaptive mode through the training and testing process of a machine learning model. In the training stage, the invention samples fingerprints at equal intervals in the positioning space, and the acquired fingerprint information is combined into a fingerprint data set. The method selects partial fingerprint information from the fingerprint data set, trains a machine learning model to enable position information and fingerprint characteristic information to be mapped, tests the positioning accuracy under the number of fingerprints by using the test set, gradually increases the number of the trained fingerprints, and tests the change of the positioning accuracy by using the test set; when the change rate of the positioning precision is lower than the threshold set by the invention, the most reasonable number of fingerprints is found out for positioning, and the reliable positioning precision and the higher operation efficiency are considered; and finally, in a system testing stage, because the optimal number of the fingerprint information is obtained, the indoor training model is built by using the optimal number of the fingerprint information, and the specific indoor position of the positioning target is detected. The invention can select the optimal number of the fingerprint information in the positioning process, thereby improving the efficiency of fingerprint information acquisition and providing more accurate position information.
Drawings
FIG. 1 is a schematic diagram of a UWB based wireless communication positioning system architecture;
FIG. 2 is a schematic illustration of equally spaced fingerprint samples in two dimensions;
FIG. 3 is a diagram of a fingerprint vector structure;
FIG. 4 is a fingerprint positioning algorithm flow;
FIG. 5 is a random forest algorithm model;
fig. 6 is a flowchart of an implementation of a wireless indoor positioning research method for optimizing the number of equally spaced fingerprint samples.
Detailed Description
As shown in fig. 1, a positioning environment using a UWB wireless communication device as an anchor node includes an anchor node (i.e., a broadcast node), a positioning node, and a server and a control terminal on an upper layer. According to a short-distance wireless communication protocol, the anchor node can continuously send characteristic information to the positioning node, and the positioning node analyzes the information to analyze the identifier and the characteristic information of the anchor node. The algorithm used by the invention is completed in the upper-layer server, the collected information is constructed into fingerprint data, the training process is completed by using a machine learning model, the optimal number of fingerprints is searched, and the optimization of the positioning precision and the calculation efficiency is realized.
The invention provides a wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples, which is an indoor positioning method based on UWB wireless communication equipment, and the specific implementation method is as follows:
step 1, building a wireless communication indoor positioning environment, arranging a positioning environment with UWB wireless communication equipment as an anchor node indoors, collecting fingerprint information at equal intervals by taking TOA (time of arrival) as a constituent element of a fingerprint, constructing a fingerprint set, and initializing the number of the fingerprint information; in addition, fingerprint information is collected through random motion in a positioning environment, and a test set is constructed.
The specification of the positioning space used by the invention is 480 × 460(cm), sampling is carried out according to rectangular tracks when fingerprint information is collected, in each rectangular track, the interval of each fingerprint point is set to be 10cm, and the interval of two adjacent rectangular tracks is 20cm, as shown in fig. 2.
Fig. 3 shows a fingerprint information structure used in the present invention, each fingerprint includes four elements, which are TOA information of a positioning node to 4 anchor nodes. This is because for the positioning node, we set that information of 4 anchor nodes will be received simultaneously within the elapsed time interval τ. Since the information of these anchor nodes is sent to the server by the positioning node in a random order, the server needs to sort the feature information from 4 anchor nodes in the time interval τ, which constitutes the form of fig. 3.
And 2, selecting a machine learning model and training the machine learning model by taking the fingerprint information and the corresponding position coordinates as a training set. The used machine learning algorithm is a KNN algorithm model and a random forest algorithm model, and the positioning accuracy under the condition of different fingerprint sampling numbers is respectively tested.
For the KNN algorithm model, the input and output of the training process comprise the following processing processes:
inputting: the training set is denoted as D { (x)1,y1),(x2,y2),...，(xN,yN)}
Wherein
For fingerprint information in fingerprint collections, yi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: coordinate y to which fingerprint x belongs
According to the given distance measurement, k points nearest to x are found in the training set D, and the area of x covering the k points is marked as Nk(x)
In Nk(x) In which the coordinate y of x is determined according to a classification decision rule
In the above formula, I is an indicator function, i.e. when yi＝ciWhen I is 1, otherwise, I is 0.
For the random forest algorithm model, the input and output in the training process comprise the following processing processes:
step S1, the random forest uses CART decision tree as weak learning device;
step S2, the establishment of the decision tree is improved; the random forest randomly selects a part of sample characteristics on the nodes, and then selects an optimal characteristic from the randomly selected sample characteristics to divide left and right subtrees of the decision tree;
inputting: training set D { (x)1,y1),(x2,y2),...，(xN,yN) The iteration times of the weak classifier are T; wherein therein
For fingerprint information in fingerprint collections, yi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: final Strong classifier f (x)
(1) For T1, 2,3,. T;
sampling the training set for the t time, and acquiring m times in total to obtain a sampling set Dt containing m samples;
training a tth decision tree model Gt (x) by using a sampling set Dt, selecting a part of sample characteristics from all sample characteristics on a node when the node of the decision tree model is trained, and selecting an optimal characteristic from the randomly selected part of sample characteristics to divide left and right subtrees of the decision tree;
(2) in the regression prediction, the value obtained by arithmetically averaging the regression results obtained by the T weak learners is the final model coordinate output.
And 3, testing the trained machine learning model in the step 2 in the test set by using the test set constructed in the step 1, and acquiring the positioning precision of the model in the training set.
Step 4, increasing the number of the fingerprint information, in the training environment of the invention, the number of the fingerprint information increased each time is 600, repeating the steps 2-3, and recording the positioning precision obtained in the step 3; and repeating the step 4 for a plurality of times until the data in the fingerprint database are all used, and obtaining the positioning accuracy of different numbers of fingerprints.
And 5, fitting a curve of the number of the fingerprint information relative to the positioning accuracy according to the positioning accuracy result obtained in the step 4, and selecting the number of the fingerprints with the change rate reaching a set threshold value as an optimal result according to the curve.
When the threshold is set, the judgment condition is determined according to the actual situation based on the performance of the machine learning model and the positioning space, and a threshold capable of realizing higher positioning accuracy and higher calculation efficiency is selected by combining the performance of the KNN and the random forest algorithm and the change of the positioning accuracy of the positioning space, wherein the threshold is preferably 2 cm.
And 6, completing the construction of an indoor positioning system after the optimal fingerprint sampling number is obtained in the step 5, and detecting the specific position of the target.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention and these are intended to be within the scope of the invention.
Claims (2)
1. A wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples is characterized by comprising the following steps:
step 1, building a wireless communication indoor positioning environment, arranging a positioning environment with UWB wireless communication equipment as an anchor node indoors, taking TOA as a constituent element of a fingerprint, collecting fingerprint information at equal intervals, constructing a fingerprint set, and initializing the number of the fingerprint information; in addition, fingerprint information is collected through random motion in a positioning environment, and a test set is constructed.
Step 2, selecting a machine learning model and training the machine learning model by taking the fingerprint information and the corresponding position coordinates as a training set;
step 3, testing the trained machine learning model in the step 2 in the test set by using the test set constructed in the step 1 to obtain the positioning precision of the model in the training set;
step 4, increasing the number of the fingerprint information, repeating the step 2 to the step 3, and obtaining the positioning precision obtained in the step 3 under the condition of different numbers of the fingerprint information until all the information in the fingerprint set is used;
step 5, fitting a curve of the number of the fingerprint information relative to the positioning accuracy according to the positioning accuracy result obtained in the step 4, and selecting the number of the fingerprints with the change rate reaching a set threshold value as an optimal result according to the curve;
and 6, completing the construction of an indoor positioning system after the optimal fingerprint sampling number is obtained in the step 5, and detecting the specific position of the target.
2. The wireless indoor positioning method for optimizing the number of equally spaced fingerprint samples according to claim 1, wherein the machine learning model in the step 2 is simulated by a KNN algorithm model and a random forest model respectively, and the results are compared to obtain the optimal positioning accuracy; wherein
The KNN model input and output in the training process comprise the following processing processes:
inputting: the training set is denoted as D { (x)1,y1),(x2,y2),...，(xN,yN)}
Wherein
For fingerprint information in fingerprint collections, yi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: coordinate y to which fingerprint x belongs
According to the given distance measurement, k points nearest to x are found in the training set D, and the area of x covering the k points is marked as Nk(x)
In Nk(x) In which the coordinate y of x is determined according to a classification decision rule
In the above formula, I is an indicator function, i.e. when yi＝ciIf I is 1, otherwise, I is 0;
the input and output of the random forest model in the training process comprise the following processing processes:
step S1, the random forest uses CART decision tree as weak learning device;
step S2, the establishment of the decision tree is improved; the random forest randomly selects a part of sample characteristics on the nodes, and then selects an optimal characteristic from the randomly selected sample characteristics to divide left and right subtrees of the decision tree;
inputting: training set D { (x)1,y1),(x2,y2),...，(xN,yN) The iteration times of the weak classifier are T; wherein therein
Fingerprint letter for fingerprint concentrationY ofi∈ Y is the virtual point coordinate corresponding to the fingerprint information, i is 1,2, 3.
And (3) outputting: final Strong classifier f (x)
(1) For T1, 2,3,. T;
sampling the training set for the t time, and acquiring m times in total to obtain a sampling set Dt containing m samples;
training a tth decision tree model Gt (x) by using a sampling set Dt, selecting a part of sample characteristics from all sample characteristics on a node when the node of the decision tree model is trained, and selecting an optimal characteristic from the randomly selected part of sample characteristics to divide left and right subtrees of the decision tree;
(2) in the regression prediction, the value obtained by arithmetically averaging the regression results obtained by the T weak learners is the final model coordinate output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010181859.2A CN111405461B (en) | 2020-03-16 | 2020-03-16 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010181859.2A CN111405461B (en) | 2020-03-16 | 2020-03-16 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111405461A true CN111405461A (en) | 2020-07-10 |
| CN111405461B CN111405461B (en) | 2021-10-08 |
Family
ID=71428931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010181859.2A Active CN111405461B (en) | 2020-03-16 | 2020-03-16 | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111405461B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112243193A (en) * | 2020-09-29 | 2021-01-19 | 成都长虹网络科技有限责任公司 | Indoor positioning method and device, computer equipment and readable storage medium |
| CN113709659A (en) * | 2021-07-26 | 2021-11-26 | 南京邮电大学 | Self-adaptive indoor positioning method based on region division |
| CN114205741A (en) * | 2021-12-13 | 2022-03-18 | 安徽理工大学 | UWB-based TOA and position fingerprint combined indoor positioning method |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101883424A (en) * | 2010-04-23 | 2010-11-10 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor KNN (K-Nearest Neighbor) positioning method based on near-neighbor point number optimization |
| US20170115368A1 (en) * | 2015-10-23 | 2017-04-27 | Siemens Healthcare Gmbh | Iterative Magnetic Resonance Fingerprinting Reconstruction |
| CN106793072A (en) * | 2016-12-08 | 2017-05-31 | 重庆大学 | A kind of indoor locating system fast construction method |
| CN106851571A (en) * | 2017-01-20 | 2017-06-13 | 华南理工大学 | WiFi localization methods in a kind of quick KNN rooms based on decision tree |
| CN107071743A (en) * | 2017-03-20 | 2017-08-18 | 华南理工大学 | WiFi localization methods in a kind of quick KNN rooms based on random forest |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
| CN108519579A (en) * | 2018-03-29 | 2018-09-11 | 吴帮 | The WiFi fingerprint location technologies of preferred AP are analyzed based on interval overlap degree |
| CN109168177A (en) * | 2018-09-19 | 2019-01-08 | 广州丰石科技有限公司 | Based on the soft longitude and latitude earth-filling method for accepting and believing order |
| CN109922432A (en) * | 2019-03-28 | 2019-06-21 | 南京邮电大学 | Pass through the object localization method of optimization fingerprint elements number under wireless communications environment |
| 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 |
-
2020
- 2020-03-16 CN CN202010181859.2A patent/CN111405461B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101883424A (en) * | 2010-04-23 | 2010-11-10 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor KNN (K-Nearest Neighbor) positioning method based on near-neighbor point number optimization |
| US20170115368A1 (en) * | 2015-10-23 | 2017-04-27 | Siemens Healthcare Gmbh | Iterative Magnetic Resonance Fingerprinting Reconstruction |
| CN106793072A (en) * | 2016-12-08 | 2017-05-31 | 重庆大学 | A kind of indoor locating system fast construction method |
| CN106851571A (en) * | 2017-01-20 | 2017-06-13 | 华南理工大学 | WiFi localization methods in a kind of quick KNN rooms based on decision tree |
| CN107071743A (en) * | 2017-03-20 | 2017-08-18 | 华南理工大学 | WiFi localization methods in a kind of quick KNN rooms based on random forest |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
| CN108519579A (en) * | 2018-03-29 | 2018-09-11 | 吴帮 | The WiFi fingerprint location technologies of preferred AP are analyzed based on interval overlap degree |
| CN109168177A (en) * | 2018-09-19 | 2019-01-08 | 广州丰石科技有限公司 | Based on the soft longitude and latitude earth-filling method for accepting and believing order |
| CN109922432A (en) * | 2019-03-28 | 2019-06-21 | 南京邮电大学 | Pass through the object localization method of optimization fingerprint elements number under wireless communications environment |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| AHMED H. SALAMAH: "《An enhanced WiFi indoor localization system based on machine learning》", 《 2016 INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN)》 * |
| 彭大芹: "《面向NB-IoT终端的指纹匹配定位改进算法》", 《计算机工程》 * |
| 杜钟祥: "《基于UWB的指纹定位算法研究》", 《中国新通信》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112243193A (en) * | 2020-09-29 | 2021-01-19 | 成都长虹网络科技有限责任公司 | Indoor positioning method and device, computer equipment and readable storage medium |
| CN112243193B (en) * | 2020-09-29 | 2022-08-12 | 成都长虹网络科技有限责任公司 | Indoor positioning method and device, computer equipment and readable storage medium |
| CN113709659A (en) * | 2021-07-26 | 2021-11-26 | 南京邮电大学 | Self-adaptive indoor positioning method based on region division |
| CN113709659B (en) * | 2021-07-26 | 2022-11-04 | 南京邮电大学 | Self-adaptive indoor positioning method based on region division |
| CN114205741A (en) * | 2021-12-13 | 2022-03-18 | 安徽理工大学 | UWB-based TOA and position fingerprint combined indoor positioning method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111405461B (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110012428B (en) | Indoor positioning method based on WiFi | |
| Yang et al. | Locating in fingerprint space: Wireless indoor localization with little human intervention | |
| CN111405461B (en) | Wireless indoor positioning method for optimizing equal-interval fingerprint sampling number | |
| KR102116824B1 (en) | Positioning system based on deep learnin and construction method thereof | |
| Rong et al. | Du-parking: Spatio-temporal big data tells you realtime parking availability | |
| CN108696932A (en) | It is a kind of using CSI multipaths and the outdoor fingerprint positioning method of machine learning | |
| Zhang et al. | A comprehensive study of bluetooth fingerprinting-based algorithms for localization | |
| CN106248107B (en) | A kind of track deduction calibration method and device based on indoor earth magnetism path matching | |
| CN105307121B (en) | A kind of information processing method and device | |
| CN108709557B (en) | Indoor map generation method based on multi-user track fitting | |
| CN105263113A (en) | Wi-Fi location fingerprint map building method and system based on crowd-sourcing | |
| Bhattacharya et al. | Automatically recognizing places of interest from unreliable GPS data using spatio-temporal density estimation and line intersections | |
| CN105243844A (en) | Road state identification method based on mobile phone signal | |
| CN103957505A (en) | Behavior trace detection analysis and service providing system and method based APs | |
| CN103167606B (en) | Based on the WLAN indoor orientation method of rarefaction representation | |
| CN104540221A (en) | WLAN indoor positioning method based on semi-supervised SDE algorithm | |
| CN104038901A (en) | Indoor positioning method for reducing fingerprint data acquisition workload | |
| CN110213710A (en) | A kind of high-performance indoor orientation method, indoor locating system based on random forest | |
| CN109151750A (en) | A kind of LTE indoor positioning floor method of discrimination based on Recognition with Recurrent Neural Network model | |
| CN102711245B (en) | Two-stage matching and positioning method in WLAN (Wireless Local Area Network) area in indoor environment | |
| Zhang et al. | Indoor 2.5 D positioning of WiFi based on SVM | |
| Xiang et al. | Enhance RSS-based indoor localization accuracy by leveraging environmental physical features | |
| Li et al. | Location estimation in large indoor multi-floor buildings using hybrid networks | |
| CN113596989A (en) | Indoor positioning method and system for intelligent workshop | |
| Dong et al. | Implementation of indoor fingerprint positioning based on ZigBee |
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 |