CN105120479B - The signal intensity difference modification method of terminal room Wi-Fi signal - Google Patents
The signal intensity difference modification method of terminal room Wi-Fi signal Download PDFInfo
- Publication number
- CN105120479B CN105120479B CN201510435830.1A CN201510435830A CN105120479B CN 105120479 B CN105120479 B CN 105120479B CN 201510435830 A CN201510435830 A CN 201510435830A CN 105120479 B CN105120479 B CN 105120479B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- offline
- terminal
- signal
- signal strength
- 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.)
- Expired - Fee Related
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Collating Specific Patterns (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
A kind of signal intensity difference modification method of the terminal room Wi-Fi signal of wireless communication technology field, offline fingerprint database space is mapped to according to initial transfer function observation fingerprint collected to online terminal, then fingerprint matching is carried out with the finger print information in offline database to obtain matching fingerprint, it recycles observation fingerprint and matches the parameter that fingerprint calculates the signal strength transfer function of updated Wi-Fi signal, after computing repeatedly until meeting the condition of convergence, obtain final transfer function and its parameter, finally observation fingerprint is mapped and the matching fingerprint in offline fingerprint database and final position result is calculated.The present invention is modified the signal intensity difference of Wi-Fi signal, and opposite existing method increases the fingerprint quantity of recurrence and handled abnormal signal intensity, then realizes fingerprint matching with optimization KNN algorithm, realizes being obviously improved for positioning accuracy.
Description
Technical field
The present invention relates to a kind of technology of wireless communication field, it is specifically a kind of based on EM (expectation maximization,
Expectation Maximization) algorithm different terminals between Wi-Fi signal signal intensity difference modification method.
Background technique
With the rapid development of wireless communication and network technology, wireless technology has been deep into every aspect, has for example cured
The fields such as treatment, industry, logistics, traffic, public safety and other closely bound up aspects of living with people.Just because of present nothing
Line information resources extensively and can be quite widely-available for users, so the indoor positioning technologies based on wireless system have also obtained quickly
Development, and Wi-Fi fingerprint positioning method is one of the indoor orientation method of current mainstream.This positioning system is generally divided into offline
Training stage and tuning on-line stage.Off-line training step needs to establish the Wi-Fi field strength fingerprint database of the interior space, online
Positioning stage is then matched according to currently detected fingerprint with the fingerprint in database, and positioning result is obtained.
Traditional Wi-Fi fingerprint positioning method has ignored the otherness of online terminal and offline terminal.Actually distinct end
There may be very big differences for the signal strength of Wi-Fi signal between end.When online terminal and offline terminal are different terminals, this
The signal intensity difference of Wi-Fi signal will cause the decline of positioning accuracy between kind different terminals, in some instances it may even be possible to and it is degradation, because
This, the difference problem of the signal strength of Wi-Fi signal must be accounted between different terminals.
By the retrieval discovery to existing technical literature, the Mobile of A.W.Tsui, Y.H.Chuang et al. in 2009
Paper " the Unsupervised learning for solving delivered in Networks and Applications meeting
It proposes and is solved in Wi-Fi positioning in RSS hardware variance problem in Wi-Fi localization "
The unsupervised learning method of RSS hardware differences problem, this method are considered in the same collected RSS of position different terminals
The signal strength of Wi-Fi signal between fingerprint for different terminal types, proposes a kind of non-there are linear mapping relations
Supervised learning method, by the transfer function of the signal strength of Wi-Fi signal between party's calligraphy learning acquisition different terminals, thus real
Mapping between the fingerprint now detected, reduce different terminals between Wi-Fi signal signal strength difference.But this method exists
Both sides is insufficient: 1) not carrying out specially treated for collecting the abnormal signal strength component of fingerprint, lead to positioning accurate
It spends lower；2) new transfer function is only calculated according to an observation fingerprint every time, cannot accurately obtains transfer function.
After searching and discovering the prior art, Chinese patent literature CN104540219A, open (bulletin) day
2015.04.22, a kind of Wi-Fi fingerprint indoor orientation method of low complex degree is disclosed, by utilizing end in environment indoors
The signal strength RSSI and magnetometer direction for terminating the Wi-Fi signal of the multiple AP received determine terminal location.Refer in foundation
In the line database stage, fingerprint base is established by sample mean.In real-time positioning stage, according to terminal direction and previous moment
Position obtains fingerprint base subset for calculating position, to reduce the computation complexity of matching algorithm.But the technology is at different ends
End the signal strength that same position collects Wi-Fi signal have differences and the difference caused by Wi-Fi fingerprint location system
The reduction of positioning accuracy.
Chinese patent literature CN102932738A, discloses a kind of improved base at open (bulletin) day 2013.02.13
In the indoor fingerprint positioning method of sub-clustering neural network.Its technical solution is off-line phase, is believed with the fingerprint acquired at reference point
Breath building fingerprint database；Classified using clustering algorithm to the fingerprint in fingerprint database；Recycle artificial neural network
Model is trained the fingerprint of each reference point with location information, obtains optimal network model.On-line stage, by the reality of acquisition
When finger print information and fingerprint database in class center carry out class matching, determine Primary Location region；And by Primary Location region
In include real time fingerprint information neural network model as a reference point input terminal, estimate to obtain final exact position
Meter.But when the terminal kinds difference that on-line stage and off-line phase use, the difference in signal strength of Wi-Fi signal between different terminals
The different decline that will cause positioning accuracy leads to the location estimation inaccuracy of the technology.
Summary of the invention
The present invention In view of the above shortcomings of the prior art, proposes a kind of difference in signal strength of terminal room Wi-Fi signal
Different modification method is modified using signal intensity difference value of the EM algorithm framework to Wi-Fi signal, increases the fingerprint of recurrence
Quantity, and abnormal signal intensity is handled, then fingerprint is realized with optimization K-Nearest-Neighbor (KNN) algorithm
Matching, so that positioning accuracy be made to significantly improve.
The present invention is achieved by the following technical solutions:
The present invention relates to a kind of signal intensity difference modification methods of terminal room Wi-Fi signal, according to initial transfer function
Observation fingerprint collected to online terminal maps to offline fingerprint database space, then believes with the fingerprint in offline database
Breath carries out fingerprint matching and obtains matching fingerprint, recycles observation fingerprint and matches the letter that fingerprint calculates updated Wi-Fi signal
The parameter of number Intensity Transfer function obtains final transfer function and its parameter, most after computing repeatedly until meeting the condition of convergence
Observation fingerprint is mapped afterwards and the matching fingerprint in offline fingerprint database and final position result is calculated.
The method specifically includes the following steps:
Step 1, using two different terminal devices as offline terminal, adopted in needing the interior space that positions respectively
Collect the finger print information of each position, while its corresponding spatial coordinate location demarcated to the collected every group of fingerprint of offline terminal,
And generate corresponding offline fingerprint database.
The offline terminal refers to: the terminal that off-line phase uses, can be different from online terminal type.
Step 2, the signal strength transfer function according to the Wi-Fi signal between different terminal equipment, online terminal is adopted
The observation fingerprint collected is mapped to offline fingerprint database space and carries out fingerprint matching with the finger print information in offline database,
To obtain the matching finger print information and corresponding position coordinate of observation fingerprint.
The finger print information refers to: multiple AP are come from each position in space indoors detected by offline terminal
The set for the signal strength vector that the signal strength of the Wi-Fi signal of (wireless access point) is constituted.
The online terminal refers to: terminal used in the tuning on-line stage, usually different types of with offline terminal
Terminal.
The observation fingerprint refers to: the space indoors detected by online terminal (terminal that on-line stage uses)
The vector that the signal strength of Wi-Fi signal from multiple AP at a certain position is constituted.
The spatial coordinate location is collected by discrete way or continuation mode, in which: discrete acquisitions refer to
The fingerprint of a period of time is acquired in several fixed points in space and demarcates position coordinates；Continuous acquisition refers to terminal in space
At the uniform velocity mobile sampling, and in manually recorded current route starting point position coordinates, to calculate each company according to timestamp
The position coordinates of the continuous fingerprint collected.
The signal strength transfer function of the Wi-Fi signal refers to: Ftrain=a × Ftrack+ b, in which: FtrainIt represents
The finger print information in offline fingerprint database that terminal device acquires when off-line training, FtrackTerminal acquires when representing tuning on-line
Fingerprint database in fingerprint, a and b are then two parameters of the linear function.
The signal strength transfer function model of the Wi-Fi signal, determination obtains initial parameter in the following manner:
EM positioning correction algorithm can be modified different initial parameters, and finally convergence obtains maximum likelihood parameter Estimation.General feelings
Under condition, initial parameter a is chosen as 1, and initial parameter b is chosen as 0.
The fingerprint matching optimizes it based on K-Nearest-Neighbor (KNN) algorithm, specifically
Are as follows: K fingerprint nearest at a distance from observation fingerprint in offline fingerprint database is found out, the calibration of the K fingerprint is then calculated
The center of position, finally using with the center apart from nearest fingerprint as matching fingerprint.Due to most in K fingerprint
The scaling position of number fingerprint is all close with physical location, and it is biggish inclined which can effectively avoid positioning result from occurring
Difference, therefore positioning accuracy can be improved.
The distance, preferably Euclidean distance, it may be assumed that for possessing the interior space of n AP, terminal acquires in space
Meet P=(x to two fingerprints1,x2,...,xn) and Q=(y1,y2,...,yn), in which: xn,ynCounterpart terminal samples to arrive
From the signal strength of n-th of AP (wireless access point), (xn,yn) then it is known as signal strength point pair, the Euclidean distance between two fingerprints
It is expressed as
The purpose of matching algorithm is found out in offline fingerprint database with fingerprint to be matched apart from nearest fingerprint and its fixed
Cursor position, and distance also represents similarity maximum recently.It is right in EM algorithm that calculating matching fingerprint and its scaling position are equivalent to
The calculating of implicit variable desired value.Particularly, it needs to reject during fingerprint matching in fingerprint not in [- 90dB, -30dB] model
Interior abnormal signal strength component is enclosed, these abnormal signal intensity can increase position error.
Step 3 observes the signal strength component in the matching fingerprint in obtained offline database in fingerprint with corresponding
Signal strength component different signal strength points pair is constituted according to different AP (wireless access point), then pass through linear regression
Processing obtains the estimation parameter of the signal strength transfer function of updated Wi-Fi signal until convergence.
The linear regression processing refers to: to observe fingerprint as X-axis, the matching fingerprint in offline database is as Y
Axis observes fingerprint from Corresponding matching fingerprint in offline database and constitutes different signal strength points pair by different AP, then right
The signal strength point of multiple groups fingerprint is to linear regression, new estimation of the parameter of obtained function as signal strength transfer function
Parameter.This process of linear regression is equivalent to the process of implicit variable expectation maximization in EM algorithm.
Particularly, abnormal is judged as the signal strength component outside [- 90dB, -30dB] range, and in linear regression
These abnormal components are not considered, to avoid the reduction of positioning accuracy.
The convergence refers to: after observation fingerprint is mapped by the signal strength transfer function with new estimation parameter
Matched with offline database average signal strength difference between fingerprint change continue preset time period after then recognize when being less than convergence threshold
For algorithmic statement, otherwise returns to step 2 and handle again.
Step 4 is mapped to offline fingerprint for fingerprint is observed using the signal strength transfer function of updated Wi-Fi signal
Finger print information in database space, with offline database carries out fingerprint matching, so that the final position for obtaining observation fingerprint is sat
Mark.
Technical effect
Compared with prior art, technical effect of the invention includes:
1) abnormal signal intensity is handled in the algorithm, positioning accuracy is made to get a promotion.
2) parameter of linear regression adjustment transfer function is carried out using multiple finger print informations every time, so that is be calculated turns
It is more acurrate to move function.
3) using optimization after K-Nearest-Neighbor (KNN) algorithm be used as matching algorithm, avoid positioning result and
Physical location substantial deviation, improves positioning accuracy.
Detailed description of the invention
Fig. 1 is work flow diagram of the invention；
Fig. 2 is the target area fingerprint discrete acquisitions route map in the embodiment of the present invention；
Target area fingerprint continuous acquisition route map in Fig. 3 the embodiment of the present invention；
Fig. 4 is that EM positioning correction algorithm uses the first six kind different terminals combined signal strength point pair in the embodiment of the present invention
Distribution schematic diagram, in figure: (a) for millet as online terminal Huawei as offline terminal, (b) be millet as online terminal three
Star as offline terminal, (c) for Samsung as online terminal Huawei as offline terminal, (d) be Samsung it is small as online terminal
Meter Zuo Wei offline terminal, (e) for Huawei as online terminal millet as offline terminal, (f) be Huawei as online terminal three
Star is as offline terminal.
Fig. 5 is that EM positions six kinds of different terminals combined signal strength points pair after correction algorithm use in the embodiment of the present invention
Distribution schematic diagram, in figure: (a) for millet as online terminal Huawei as offline terminal, (b) be millet as online terminal three
Star as offline terminal, (c) for Samsung as online terminal Huawei as offline terminal, (d) be Samsung it is small as online terminal
Meter Zuo Wei offline terminal, (e) for Huawei as online terminal millet as offline terminal, (f) be Huawei as online terminal three
Star is as offline terminal.
Fig. 6 is the positioning accuracy comparison diagram of the embodiment of the present invention and art methods.
Specific embodiment
It elaborates below to the embodiment of the present invention, the present embodiment carries out under the premise of the technical scheme of the present invention
Implement, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to following implementation
Example.
Embodiment 1
In the present embodiment, target area structure is as shown in Figures 2 and 3, is covered in region by 12 access points.Continuous fingerprint
Terminal user uniform motion and acquires the signal strength from each AP, discrete finger back and forth between selected route in real time when sampling
Terminal acquires the signal strength of same time respectively on 30 selected positions when line acquires.Respectively using this method with it is existing
Conventional fingerprint localization method and the unsupervised learning method that is not optimised, finally obtain six kinds of different terminals combination shown in fig. 6
Positioning accuracy comparison diagram.
As shown in Figure 1, the present embodiment includes the following steps:
Step 1: the finger print information of each position is acquired in needing the interior space positioned with offline terminal, and to every
Group fingerprint demarcates position coordinates, finally obtains offline fingerprint database.In this example, three kinds of Huawei, Samsung, millet different terminals
Fingerprint quantity is respectively 2399,1192 and 1823 in the offline fingerprint base finally constructed.
Step 2: using another different terminals as tuning on-line terminal, observation fingerprint is collected in space.This
In example, observation fingerprint is the fingerprint in the offline fingerprint base being had been built up using online terminal.
Step 3: it determines the model of the signal strength transfer function of Wi-Fi signal between different terminals, and gives one group of transfer
The initial parameter of function.Function model is shifted in this example is set to Ftrain=a × Ftrack+ b, given initial parameter, which takes, is set to a
=1, b=0.
Step 4: the parameter a, b obtained according to back determines transfer function mapping observation fingerprint, then with off-line data
Fingerprint in library carries out matching primitives, to obtain the matching fingerprint and its corresponding position coordinate of observation fingerprint.It is adopted in this example
Matching process is K-Nearest-Neighbor (KNN) algorithm of optimization.
Step 5 calculates new transfer function parameters using the matching fingerprint that observation fingerprint and step 4 obtain.This example
In, by the signal strength of the matching fingerprint in obtained offline database from the signal strength of corresponding observation fingerprint according to different AP
Different signal strength points pair is constituted, new transfer letter then is obtained to linear regression to the signal strength point of 5 groups of fingerprints every time
Number parameter Estimation.
Step 6 repeats step 4 and step 5 until algorithmic statement, the parameter Estimation of last Output transfer function.This reality
In example, continuous 100 resampled fingers are both less than if changing after observation fingerprint mapping with the average signal strength difference for matching fingerprint
0.5dB, then it is assumed that algorithmic statement.
Step 7, using the transfer function mapping observation fingerprint value obtained for the last time, the KNN algorithm of optimizing application is carried out
Position calculates.
As shown in table 1, comparison is promoted for the positioning accuracy of the present embodiment method:
Table 1
As shown in table 2, for positioning accuracy promotes comparison when continuous fingerprint collecting in the embodiment of the present invention:
Table 2
Claims (1)
1. a kind of signal intensity difference modification method of terminal room Wi-Fi signal, which is characterized in that according to initial transfer function pair
The online collected observation fingerprint of terminal maps to offline fingerprint database space, then with the finger print information in offline database
It carries out fingerprint matching and obtains matching fingerprint, recycle observation fingerprint and match the signal that fingerprint calculates updated Wi-Fi signal
The parameter of Intensity Transfer function obtains final transfer function and its parameter, finally after computing repeatedly until meeting the condition of convergence
Observation fingerprint is mapped and the matching fingerprint in offline fingerprint database and final position result is calculated；
The method specifically includes the following steps:
Step 1, using two different terminal devices as offline terminal, acquisition is each in needing the interior space that positions respectively
The finger print information of a position, while its corresponding spatial coordinate location is demarcated to the collected every group of fingerprint of offline terminal, and raw
At corresponding offline fingerprint database；
The offline terminal refers to: the terminal that off-line phase uses, with different from online terminal type；
Step 2, the signal strength transfer function according to the Wi-Fi signal between different terminal equipment, online terminal is collected
Observation fingerprint be mapped to offline fingerprint database space and in offline database finger print information carry out fingerprint matching, thus
Obtain the matching finger print information and corresponding position coordinate of observation fingerprint；
The finger print information refers to: wireless from multiple AP at each position in space indoors detected by offline terminal
The set for the signal strength vector that the signal strength of the Wi-Fi signal of access point is constituted；
The online terminal refers to: the tuning on-line stage is used with the different types of terminal of offline terminal；
The observation fingerprint refers to: from multiple AP's at a certain position in space indoors detected by online terminal
The vector that the signal strength of Wi-Fi signal is constituted；
The spatial coordinate location is collected by discrete way or continuation mode, in which: discrete acquisitions are referred in sky
The fingerprint of a period of time is acquired in interior several fixed points and demarcates position coordinates；Continuous acquisition refers to terminal in space at the uniform velocity
Mobile sampling, and in manually recorded current route starting point position coordinates, continuously adopted to calculate each according to timestamp
Collect the position coordinates of obtained fingerprint；
The signal strength transfer function of the Wi-Fi signal refers to: Ftrain=a × Ftrack+ b, in which: FtrainIt represents offline
Finger print information when training in the offline fingerprint database of terminal device acquisition, FtrackThe finger that terminal acquires when representing tuning on-line
Fingerprint in line database, a and b are then two parameters of the linear function；
The signal strength transfer function model of the Wi-Fi signal, determination obtains initial parameter in the following manner: EM is fixed
Position correction algorithm can be modified different initial parameters, and finally convergence obtains maximum likelihood parameter Estimation；
The initial parameter a is selected as 1, and initial parameter b is selected as 0；
The fingerprint matching optimizes it based on K-Nearest-Neighbor (KNN) algorithm, specifically:
K fingerprint nearest at a distance from observation fingerprint in offline fingerprint database is found out, the scaling position of the K fingerprint is then calculated
Center, finally using with the center apart from nearest fingerprint as matching fingerprint；Refer to due to most of in K fingerprint
The scaling position of line is all close with physical location, which can effectively avoid positioning result from biggish deviation occur, because
This is to improve positioning accuracy；
The distance is Euclidean distance, it may be assumed that for possessing the interior space of n AP, terminal collects two fingers in space
Line meets P=(x1,x2,...,xn) and Q=(y1,y2,...,yn), in which: xn,ynCounterpart terminal samples to obtain from n-th of AP
The signal strength of (wireless access point), (xn,yn) then it is known as signal strength point pair, the Euclidean distance between two fingerprints is expressed as
Step 3, by the letter in the signal strength component and corresponding observation fingerprint in the matching fingerprint in obtained offline database
Number strength component constitutes different signal strength points pair according to different AP (wireless access point), then passes through linear regression processing
Until convergence, obtains the estimation parameter of the signal strength transfer function of updated Wi-Fi signal；
The linear regression processing refers to: to observe fingerprint as X-axis, the matching fingerprint in offline database is seen as Y-axis
It surveys fingerprint and constitutes different signal strength points pair by different AP from Corresponding matching fingerprint in offline database, then multiple groups are referred to
The signal strength point of line is to linear regression, new estimation parameter of the parameter of obtained function as signal strength transfer function；
This process of linear regression is equivalent to the process of implicit variable expectation maximization in EM algorithm；For [- 90dB, -30dB]
Signal strength component outside range is judged as abnormal, and does not consider these abnormal components in linear regression, to avoid positioning accurate
The reduction of degree；
The convergence refers to: after observing fingerprint and being mapped by the signal strength transfer function with new estimation parameter and from
Then think to calculate when average signal strength difference changes after lasting preset time period less than convergence threshold between matching fingerprint in line database
Method convergence, otherwise returns to step 2 and handles again；
Step 4 is mapped to offline finger print data for fingerprint is observed using the signal strength transfer function of updated Wi-Fi signal
Library space carries out fingerprint matching with the finger print information in offline database, to obtain the final position coordinate of observation fingerprint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510435830.1A CN105120479B (en) | 2015-07-22 | 2015-07-22 | The signal intensity difference modification method of terminal room Wi-Fi signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510435830.1A CN105120479B (en) | 2015-07-22 | 2015-07-22 | The signal intensity difference modification method of terminal room Wi-Fi signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105120479A CN105120479A (en) | 2015-12-02 |
| CN105120479B true CN105120479B (en) | 2019-04-26 |
Family
ID=54668312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510435830.1A Expired - Fee Related CN105120479B (en) | 2015-07-22 | 2015-07-22 | The signal intensity difference modification method of terminal room Wi-Fi signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105120479B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105516931A (en) * | 2016-02-29 | 2016-04-20 | 重庆邮电大学 | Indoor differential positioning method on basis of double-frequency WLAN (wireless local area network) access points |
| CN106792559A (en) * | 2016-12-28 | 2017-05-31 | 北京航空航天大学 | The automatic update method of fingerprint base in a kind of WiFi indoor locating systems |
| CN109143156B (en) * | 2017-06-15 | 2020-10-30 | 中国移动通信集团浙江有限公司 | Calibration method and device for positioning fingerprint database |
| CN108566677B (en) * | 2018-03-20 | 2020-01-17 | 北京邮电大学 | Fingerprint positioning method and device |
| CN110858972B (en) * | 2018-08-24 | 2022-08-05 | 中移（杭州）信息技术有限公司 | Method and device for acquiring WIFI signal intensity distribution in space |
| CN109143161B (en) * | 2018-09-30 | 2023-01-10 | 电子科技大学 | High-precision indoor positioning method based on mixed fingerprint quality evaluation model |
| CN111654808B (en) * | 2019-03-04 | 2022-11-29 | 深圳光启空间技术有限公司 | Method and system for updating fingerprint database and wifi positioning method and system |
| CN114979955B (en) * | 2022-05-26 | 2024-04-16 | 中国联合网络通信集团有限公司 | Floor positioning method and device, electronic equipment and storage medium |
-
2015
- 2015-07-22 CN CN201510435830.1A patent/CN105120479B/en not_active Expired - Fee Related
Non-Patent Citations (4)
| Title |
|---|
| Characterization of Smart Phone Received Signal Strength Indication for WLAN Indoor Positioning Accuracy Improvement;Jiayou Luo;《JOURNAL OF NETWORKS》;20140331;全文 |
| Device signal strength self-calibration using histograms;Christos Laoudias;《2012 international conference on Indoor Positioning and Indoor Navigation》;20121115;全文 |
| Received Signal Strength Calibration for Handset Localization in WLAN;Diego Felix;《IEEE ICC2012》;20121115;全文 |
| Unsupervised Learning for Solving RSS Hardware Variance Problem in WiFi Localization;Arvin Wen Tsui;《Mobile Networks and Applications》;20090116;说明书第1-6节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105120479A (en) | 2015-12-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105120479B (en) | The signal intensity difference modification method of terminal room Wi-Fi signal | |
| CN105044662B (en) | A kind of fingerprint cluster multi-point joint indoor orientation method based on WIFI signal intensity | |
| CN105242239B (en) | A kind of indoor subregion localization method based on the sub-clustering of mass-rent fingerprint and matching | |
| CN108536851B (en) | User identity recognition method based on moving track similarity comparison | |
| CN107333238B (en) | Indoor fingerprint rapid positioning method based on support vector regression | |
| CN105704652B (en) | Fingerprint base acquisition and optimization method in a kind of positioning of WLAN/ bluetooth | |
| CN112881979B (en) | Initial state self-adaptive fusion positioning method based on EKF filtering | |
| CN104602342B (en) | A kind of high efficiency indoor localization method based on iBeacon equipment | |
| CN107064913A (en) | A kind of wireless location method and system based on deep learning | |
| CN107703480A (en) | Mixed kernel function indoor orientation method based on machine learning | |
| CN105911518A (en) | Robot positioning method | |
| CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
| CN109275095A (en) | A kind of indoor locating system based on bluetooth, positioning device and localization method | |
| CN102932738A (en) | Improved positioning method of indoor fingerprint based on clustering neural network | |
| CN104754735B (en) | Localization method based on location fingerprint storehouse | |
| WO2014106363A1 (en) | Mobile device positioning system and method | |
| CN110082716B (en) | Indoor positioning system and positioning method for complex environment of hospital | |
| CN110536245A (en) | A kind of indoor wireless positioning method and system based on deep learning | |
| CN106658704A (en) | Positioning method and system of starting point of indoor positioning | |
| CN109327797A (en) | Mobile robot indoor locating system based on WiFi network signal | |
| CN106646339A (en) | Online matching and positioning method in wireless position fingerprint indoor positioning | |
| CN114449452A (en) | Indoor positioning algorithm for heterogeneous equipment | |
| CN108834047B (en) | AP selection indoor positioning method of path loss model | |
| Abdou et al. | An efficient indoor localization system based on Affinity Propagation and Support Vector Regression | |
| Xu et al. | Neural network-based accuracy enhancement method for WLAN indoor positioning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190426 Termination date: 20210722 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |