CN109672973A - A kind of indoor positioning blending algorithm based on most strong AP method - Google Patents
A kind of indoor positioning blending algorithm based on most strong AP method Download PDFInfo
- Publication number
- CN109672973A CN109672973A CN201811109415.7A CN201811109415A CN109672973A CN 109672973 A CN109672973 A CN 109672973A CN 201811109415 A CN201811109415 A CN 201811109415A CN 109672973 A CN109672973 A CN 109672973A
- Authority
- CN
- China
- Prior art keywords
- region
- algorithm
- point
- fingerprint
- strong
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000002156 mixing Methods 0.000 title claims description 21
- 238000012545 processing Methods 0.000 claims abstract description 5
- 230000004807 localization Effects 0.000 claims description 14
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 230000004927 fusion Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- 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
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The present invention discloses a kind of indoor positioning algorithms based on most strong AP method, the specific algorithm combined using bayesian algorithm (Bayes) and weighted nearest neighbor algorithm (WKNN) realizes indoor positioning, for improving positioning accuracy, position error is reduced.It realizes that process is as follows, off-line phase: one, reasonable grid dividing is carried out to the region that needs position and records corresponding position coordinate；Two, in each net region multi collect signal strength indication and carry out data processing；Three, offline fingerprint base build after by different zone signal intensities and the AP regularity of distribution difference, divided corresponding region in advance.On-line stage: one, all fingerprints in the signal strength indication measured online first with point to be determined and offline fingerprint base are carried out apart from calculating, the point to be determined is first navigated into corresponding region by most strong AP method ballot, i.e., offline fingerprint base is updated in the region all fingerprints for including；Two, the posterior probability of online data and all fingerprints is calculated by bayesian algorithm, acquires S fingerprint point of maximum probability；Three, by WKNN algorithm, online data and S fingerprint point are sought into Euclidean distance, finally calculates positioning coordinate apart from the smallest fingerprint point with K (K < S) is a, acquire the position of point to be determined.
Description
Technical field
The present invention relates to a kind of indoor positioning blending algorithm based on most strong AP method is related to, it is based particularly on most strong AP method
The indoor positioning blending algorithm that is combined with WKNN of Bayes, which, which passes through, combines bayesian algorithm and WKNN algorithm to carry out
Positioning.Belong to field of locating technology.
Background technique
Currently, being based on communication technology of satellite GPS (Global Positioning System, global positioning system), GNSS
The position service systems such as (Global Navigation Satellite System, Global Navigation Satellite System) and Beidou are extensive
Using solving the problems, such as outdoor positioning, however as the explosive growth that Internet of Things and mobile Internet are applied, largely
Using the demand increased to indoor location service (Indoor Location Based Services, ILBS), pass through interior
Positioning system accurately obtains the location information of user, excavates the behavior of user, the needs of recommended user.
Commonly the Distance positioning mode based on signal measurement technique can be divided into based on arrival time (TOA) measurement, be based on
Reaching time-difference (TDOA) is measured, is measured based on angle of arrival (AOA) and measure four kinds based on received signal strength (RSSI) and determined
Position mode etc..Due to the complexity of indoor radio propagation effect, the diversity and wireless facilities of short-distance wireless communication signal
The randomness of deployment, so that calculating that the method positioning accuracy of distance is too low based on time, angle etc., it is difficult to practical.And it is based on
The Indoor Position Techniques Based on Location Fingerprint of received signal strength indicator (RSSI) becomes research hotspot.
With the widespread deployment of indoor WiFi network, the advantages that transmission rate is high, at low cost, broad covered area, Yi Jilian
Insertion includes sensor, smart phone, the equipment such as household electrical appliance, so that being provided using existing WiFi to the receiving module of valence extensively
Location fingerprint positioning is realized in source, has very big application market and commercial promise.WiFi localization method based on signal strength is again
It is divided into signal propagation model method and fingerprint technique, at present more is fingerprint technique.Fingerprint technique is divided into off-line phase and online rank
Section, off-line phase acquisition data simultaneously establish offline fingerprint base, and on-line stage is by location algorithm online data and offline fingerprint
Library is matched, and positioning result is obtained by calculation.
Summary of the invention
The present invention is to improve the position error of existing traditional location algorithm, provides a kind of indoor positioning based on most strong AP method
Blending algorithm can obtain lower position error and higher locating accuracy in the environment of teaching building.
In order to solve the above technical problems, the scheme that the present invention uses is as follows:
Step 1: localization region is carried out reasonable grid dividing according to the provincial characteristics of localization region, and record grid
The position coordinates of central point；
Step 2: the central point in all net regions, continuous acquisition multiple signal intensity data take after removing exceptional value
Mean value and standard deviation, and a fingerprint is formed with the coordinate of the point, test is completed to establish offline fingerprint base；
Step 3: observing all data of offline fingerprint base, the regularity of distribution of different AP is corresponded to according to the signal of difference,
Overall region is divided into several lesser regions；
Step 4: voting to obtain the region for meeting the regularity of distribution according to most strong AP method after obtaining online data；
Step 5: online data continues the calculating for carrying out posterior probability with all fingerprints in zonule, before obtaining after S
Test the fingerprint point of maximum probability；
Step 6: calculating Euclidean distance using online data and S fingerprint, obtain being used in combination apart from the smallest K fingerprint point
The weighted mean of K fingerprint point coordinate is as positioning result.
Carrying out localization region ballot using most strong AP method, detailed process is as follows:
Step 1: having multiple fingerprint points in each region, therefore each after offline fingerprint base is divided into multiple regions in advance
AP has maximum signal strength and the smallest signal strength, existing a signal strength range in the area；
Step 2: being separately employed in line number after obtaining online data and going to carry out region according to the signal strength at different AP
Match, if the signal strength under some AP, in the value range of some region AP, which adds 1, traverses institute
There is AP to vote；
Step 3: having traversed the highest region of votes after all AP is matching area, if there is multiple regions votes
It is identical, then continue to vote, until votes highest zone is unique.
Positioned that detailed process is as follows using blending algorithm:
Step 1: the fingerprint of preceding S maximum posterior probability is sought, wherein data distribution is assumed to become Gaussian Profile, because
And formula is as follows, wherein R is online data, and u is mean value, and σ is standard deviation:
Step 2: seeking last positioning result after known S fingerprint point with WKNN algorithm, seeking the formula of Euclidean distance such as
Under, wherein R is online data, and fp is fingerprint, and d is Euclidean distance:
Step 3: finding out corresponding weight with following equation after acquiring Euclidean distance:
Step 4: K the smallest Euclidean distances and corresponding coordinate, weight before taking, are weighted averaging and are positioned
As a result.
The beneficial effects of the present invention are:
The region for vote in using most strong AP method Primary Location, reduces the calculation amount of location algorithm；
Continue to solve posterior probability in zonule using bayesian algorithm, choose the fingerprint of maximum S posterior probability,
Update fingerprint base is S fingerprint, continues to zoom out localization region, reduces calculation amount；
The positioning result for finally solving in the fingerprint base of S fingerprint to the end using WKNN algorithm, positioning result are aobvious
Show that the indoor positioning blending algorithm based on most strong AP method has lower positioning to miss than bayesian algorithm and WKNN algorithm is used alone
Difference, higher locating accuracy.
Detailed description of the invention
Fig. 1 is the overview flow chart of the indoor positioning blending algorithm based on most strong AP method.
Fig. 2 is the average localization error of bayesian algorithm, WKNN algorithm, indoor positioning blending algorithm based on most strong AP method
Comparison (three kinds of algorithm average localization error comparisons).
Fig. 3 bayesian algorithm, WKNN algorithm, three kinds of algorithm locating accuracy comparisons of indoor positioning based on most strong AP method
(three kinds of algorithm locating accuracy comparisons).
Specific embodiment
The present invention is described further with specific embodiment with reference to the accompanying drawings of the specification.
Bayesian algorithm average localization error is 2.5889m in attached drawing 2, and WKNN algorithm average localization error is
2.6820m, the indoor positioning blending algorithm average localization error based on most strong AP method are 2.3559m.It can be seen that based on most strong
The indoor positioning blending algorithm of AP method average localization error on the basis of bayesian algorithm and WKNN algorithm is all reduced.
The locating accuracy of bayesian algorithm is that the locating accuracy of 32.35%, WKNN algorithm is in attached drawing 3
26.47%, the locating accuracy of the indoor positioning blending algorithm based on most strong AP method is 35%.So the room based on most strong AP method
The locating accuracy of interior positioning blending algorithm is all higher than bayesian algorithm and WKNN algorithm, and locating accuracy is position error herein
Points to be positioned within 0.6m are divided by all points to be positioned.
It is higher to solve position error existing for existing algorithm, the problems such as locating accuracy is low, the technology that the present invention uses
Scheme is: the present invention realizes that process is as follows, off-line phase: one, reasonable grid dividing is carried out to the region that needs position and is remembered
Picture recording answers position coordinates；Two, in each net region multi collect signal strength indication and carry out data processing；Three, offline fingerprint
Library build after by different zone signal intensities and the AP regularity of distribution difference, divided corresponding region in advance.On-line stage:
One, the signal strength indication measured online first with point to be determined lead to apart from calculating with all fingerprints in offline fingerprint base
It crosses most strong AP method ballot and the point to be determined is first navigated into corresponding region, i.e., offline fingerprint base is updated to the institute for including in the region
There is fingerprint；Two, the posterior probability of online data and all fingerprints is calculated by bayesian algorithm, acquires S finger of maximum probability
Line point；Three, by WKNN algorithm, online data and S fingerprint point are sought into Euclidean distance, it is finally a apart from the smallest with K (K < S)
Fingerprint point calculates positioning coordinate, acquires the position of point to be determined.
A kind of indoor positioning blending algorithm based on most strong AP method, includes the following steps:
Fig. 1 is the overview flow chart of the indoor positioning blending algorithm based on most strong AP method of the method for the present invention, the process packet
Include off-line training step and tuning on-line stage.Off-line phase mainly constructs offline fingerprint base, comprising:
Step 1: by the region classifying rationally for entirely needing to position at grid, and indicate the coordinate of grid element center point；
Step 2: using same procedure, identical equipment acquisition multiple signal intensity data at each grid element center point；
Step 3: the data to acquisition are handled, exceptional value is first removed, then seeks mean value and standard deviation, in conjunction with grid
The coordinate of point establishes complete offline fingerprint base as fingerprint；
Step 4: observing all data of offline fingerprint base, the regularity of distribution of different AP is corresponded to according to the signal of difference,
Overall region is divided into several lesser regions.
On-line stage mainly passes through location algorithm and is matched, and obtains positioning result, comprising:
Step 1: voting to obtain the region for meeting the regularity of distribution according to most strong AP method after obtaining online data；
Carrying out localization region ballot using most strong AP method, detailed process is as follows:
(a): after offline fingerprint base is divided into multiple regions in advance, there is multiple fingerprint points, therefore each AP in each region
There are maximum signal strength and the smallest signal strength in the area；
(b): after obtaining online data, it is separately employed in line number and goes to carry out Region Matching according to the signal strength at different AP,
If the signal strength under some AP, in the value range of some region AP, which adds 1, all AP are traversed
It votes；
(c): the highest region of votes is matching area after having traversed all AP, if there is multiple regions votes phase
Together, then continue to vote, until votes highest zone is unique.
Step 2: online data continues the calculating for carrying out posterior probability with all fingerprints in zonule, before obtaining after S
Test the fingerprint point of maximum probability；
The fingerprint point of S maximum a posteriori probability before asking, wherein data distribution is assumed to become Gaussian Profile, thus formula is such as
Under, wherein R is online data, and u is mean value, and σ is standard deviation:
Step 3: calculate Euclidean distance using online data and S fingerprint, obtain it is a apart from the smallest K, and with K point
The weighted mean of coordinate is as positioning result.
(a): after known S fingerprint point, last positioning result is sought with WKNN algorithm, asks the formula of Euclidean distance as follows,
Wherein R is online data, and fp is fingerprint, and d is Euclidean distance::
(b): after acquiring Euclidean distance, corresponding weight is found out with following equation:
(c): K the smallest Euclidean distances and corresponding coordinate, weight before taking are weighted averaging and obtain positioning knot
Fruit.
Finally the position coordinates of counted point to be determined are
Claims (5)
1. a kind of indoor positioning blending algorithm based on most strong AP method, which is characterized in that positioning blending algorithm is based on using pattra leaves
For the algorithm that this algorithm (Bayes) and weighted nearest neighbor algorithm (WKNN) combine to realize indoor positioning, process is as follows,
Off-line phase: () carries out reasonable grid dividing to the region that needs position and records corresponding position coordinate；(2) each net
Lattice region multi collect signal strength indication simultaneously carries out data processing；(3) by different regional signals after offline fingerprint base is built
The difference of intensity and the AP regularity of distribution, has divided corresponding region in advance；
On-line stage: (4), all fingerprints in the signal strength indication measured online first with point to be determined and offline fingerprint base into
Row distance calculates, and the point to be determined is first navigated to corresponding region by most strong AP method ballot, i.e., offline fingerprint base is updated to this
All fingerprints for including in region；(5), the posterior probability that online data and all fingerprints are calculated by bayesian algorithm, is acquired
S fingerprint point of maximum probability；Three, by WKNN algorithm, online data and S fingerprint point are sought into Euclidean distance, finally use K (K
< S) it is a calculate positioning coordinate apart from the smallest fingerprint point, acquire the position of point to be determined.
2. the indoor positioning blending algorithm according to claim 1 based on most strong AP method, which is characterized in that positioning fusion is calculated
Specific step is as follows for method:
Step 1: acquiring multiple data in each grid by realizing that reasonable grid type is divided to localization region and carrying out
Average value processing is taken, and records the number and coordinate of grid；
Step 2: after the acquisition of the data of all mesh points is finished forming offline fingerprint base, it is corresponding not according to the signal of difference
With the regularity of distribution of AP, overall region is divided into several lesser regions；
Step 3: it to be carried out to the calculating of Euclidean distance with fingerprints all in offline fingerprint base, according to most after obtaining online data
Strong AP method votes to obtain the region for meeting the regularity of distribution；
Step 4: online data continues the calculating for carrying out posterior probability with all fingerprints in zonule, S posteriority is general before obtaining
The maximum fingerprint point of rate；
Step 5: carrying out the calculating of Euclidean distance with S fingerprint using online data, obtain apart from the smallest K, and with K
The weighted mean of point coordinate is as positioning result.
3. the indoor positioning blending algorithm described in claim 1 based on most strong AP method, which is characterized in that for localization region into
Row mesh point divides, and measures the signal strength data of each mesh point central point and coordinate and records processing, establishes fingerprint base.
4. the indoor positioning blending algorithm described in claim 1 based on most strong AP method, which is characterized in that utilize the number of acquisition
According to region being divided into multiple regions according to the regularity of distribution that data correspond to each AP in advance, and most strong AP method is utilized to carry out area
The matching in domain, the specific steps are as follows:
Step 1: having multiple fingerprint points in each region, therefore each AP exists after offline fingerprint base is divided into multiple regions in advance
There are maximum signal strength and the smallest signal strength in the region；
Step 2: being separately employed in line number after obtaining online data and going to carry out Region Matching according to the signal strength at different AP, such as
Signal strength under some AP of fruit is in the value range of some region AP, then the region votes add 1, traverse all AP into
Row ballot；
Step 3: having traversed the highest region of votes after all AP is matching area, if there is multiple regions votes identical,
Then continue to vote, until votes highest zone is unique.
5. the indoor positioning blending algorithm according to claim 1 based on most strong AP method, which is characterized in that in conjunction with Bayes
Algorithm and WKNN algorithm first find out the maximum S fingerprint point of posterior probability in limited area, then are found out with WKNN algorithm undetermined
The position in site, the specific steps are as follows:
Step 1: S maximum posterior probability before asking, wherein data distribution is assumed to become Gaussian Profile, thus formula is as follows:
Step 2: seeking last positioning result after known S fingerprint point with WKNN algorithm, seeking the formula of Euclidean distance, seek weight
Formula, ask the formula of positioning result as follows:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811109415.7A CN109672973B (en) | 2018-09-21 | 2018-09-21 | Indoor positioning fusion method based on strongest AP |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811109415.7A CN109672973B (en) | 2018-09-21 | 2018-09-21 | Indoor positioning fusion method based on strongest AP |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109672973A true CN109672973A (en) | 2019-04-23 |
| CN109672973B CN109672973B (en) | 2021-02-19 |
Family
ID=66141593
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811109415.7A Expired - Fee Related CN109672973B (en) | 2018-09-21 | 2018-09-21 | Indoor positioning fusion method based on strongest AP |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109672973B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035384A (en) * | 2019-05-09 | 2019-07-19 | 桂林电子科技大学 | A kind of indoor orientation method merging multiple sensor signals filtering optimization |
| CN110430528A (en) * | 2019-07-23 | 2019-11-08 | 云南大学 | A kind of calibration-free indoor orientation method based on depth characteristic study |
| CN110543896A (en) * | 2019-08-16 | 2019-12-06 | 成都电科慧安科技有限公司 | heterogeneous crowdsourcing fingerprint labeling method based on semi-supervised naive Bayes |
| CN111065158A (en) * | 2019-12-25 | 2020-04-24 | 大连理工大学 | Fingerprint positioning method based on fusion of angle and intensity of cellular network signal |
| CN111372212A (en) * | 2020-03-17 | 2020-07-03 | 杭州十域科技有限公司 | Fingerprint matching method with low algorithm complexity |
| CN111818446A (en) * | 2020-06-02 | 2020-10-23 | 南京邮电大学 | Indoor positioning optimization method and system based on position fingerprints |
| CN113490272A (en) * | 2021-09-08 | 2021-10-08 | 中铁工程服务有限公司 | UWB positioning-based safe hoisting early warning method, system and medium |
| CN113747355A (en) * | 2021-09-03 | 2021-12-03 | 中国华能集团清洁能源技术研究院有限公司 | WiFi positioning method, device, equipment and medium in power plant |
| CN113852911A (en) * | 2021-09-26 | 2021-12-28 | 桂林电子科技大学 | Fingerprint library and PDR calculation-based fusion positioning method and fingerprint library updating method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101895867A (en) * | 2010-06-25 | 2010-11-24 | 哈尔滨工业大学 | Sliding time window based WLAN (Wireless Local Area Network) indoor WKNN (Weighted K Nearest Neighbors) tracking method |
| US20150334677A1 (en) * | 2014-05-16 | 2015-11-19 | Qualcomm Incorporated, Inc. | Leveraging wireless communication traffic opportunistically |
| CN106793075A (en) * | 2016-12-21 | 2017-05-31 | 武汉大学 | A kind of WiFi indoor orientation methods based on domain cluster |
| CN107949052A (en) * | 2017-10-09 | 2018-04-20 | 北京航空航天大学 | WKNN indoor orientation methods based on space characteristics subregion and preceding point constraint |
| 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 |
-
2018
- 2018-09-21 CN CN201811109415.7A patent/CN109672973B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101895867A (en) * | 2010-06-25 | 2010-11-24 | 哈尔滨工业大学 | Sliding time window based WLAN (Wireless Local Area Network) indoor WKNN (Weighted K Nearest Neighbors) tracking method |
| US20150334677A1 (en) * | 2014-05-16 | 2015-11-19 | Qualcomm Incorporated, Inc. | Leveraging wireless communication traffic opportunistically |
| CN106793075A (en) * | 2016-12-21 | 2017-05-31 | 武汉大学 | A kind of WiFi indoor orientation methods based on domain cluster |
| CN107949052A (en) * | 2017-10-09 | 2018-04-20 | 北京航空航天大学 | WKNN indoor orientation methods based on space characteristics subregion and preceding point constraint |
| 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 |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110035384A (en) * | 2019-05-09 | 2019-07-19 | 桂林电子科技大学 | A kind of indoor orientation method merging multiple sensor signals filtering optimization |
| CN110430528A (en) * | 2019-07-23 | 2019-11-08 | 云南大学 | A kind of calibration-free indoor orientation method based on depth characteristic study |
| CN110543896A (en) * | 2019-08-16 | 2019-12-06 | 成都电科慧安科技有限公司 | heterogeneous crowdsourcing fingerprint labeling method based on semi-supervised naive Bayes |
| CN110543896B (en) * | 2019-08-16 | 2023-04-07 | 成都电科慧安科技有限公司 | Heterogeneous crowdsourcing fingerprint labeling method based on semi-supervised naive Bayes |
| CN111065158B (en) * | 2019-12-25 | 2021-01-05 | 大连理工大学 | Fingerprint positioning method based on fusion of angle and intensity of cellular network signal |
| CN111065158A (en) * | 2019-12-25 | 2020-04-24 | 大连理工大学 | Fingerprint positioning method based on fusion of angle and intensity of cellular network signal |
| CN111372212A (en) * | 2020-03-17 | 2020-07-03 | 杭州十域科技有限公司 | Fingerprint matching method with low algorithm complexity |
| CN111818446A (en) * | 2020-06-02 | 2020-10-23 | 南京邮电大学 | Indoor positioning optimization method and system based on position fingerprints |
| CN111818446B (en) * | 2020-06-02 | 2022-06-24 | 南京邮电大学 | Indoor positioning optimization method and system based on position fingerprints |
| CN113747355A (en) * | 2021-09-03 | 2021-12-03 | 中国华能集团清洁能源技术研究院有限公司 | WiFi positioning method, device, equipment and medium in power plant |
| CN113490272A (en) * | 2021-09-08 | 2021-10-08 | 中铁工程服务有限公司 | UWB positioning-based safe hoisting early warning method, system and medium |
| CN113490272B (en) * | 2021-09-08 | 2021-12-28 | 中铁工程服务有限公司 | UWB positioning-based safe hoisting early warning method, system and medium |
| CN113852911A (en) * | 2021-09-26 | 2021-12-28 | 桂林电子科技大学 | Fingerprint library and PDR calculation-based fusion positioning method and fingerprint library updating method |
| CN113852911B (en) * | 2021-09-26 | 2024-05-07 | 桂林电子科技大学 | Fusion positioning method based on fingerprint library and PDR calculation and fingerprint library updating method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109672973B (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109672973A (en) | A kind of indoor positioning blending algorithm based on most strong AP method | |
| CN103747524B (en) | A kind of Android terminal indoor orientation method based on cloud platform | |
| CN105704652B (en) | Fingerprint base acquisition and optimization method in a kind of positioning of WLAN/ bluetooth | |
| CN103945332B (en) | A kind of received signal strength and multi-path information united NNs indoor orientation method | |
| KR102116824B1 (en) | Positioning system based on deep learnin and construction method thereof | |
| CN105792356A (en) | Wifi-based location fingerprint positioning method | |
| CN108919177B (en) | Positioning map construction method based on virtual information source estimation and track correction | |
| Prieto et al. | Performance evaluation of 3D-LOCUS advanced acoustic LPS | |
| CN104507050B (en) | Probabilistic type finger print matching method in a kind of WiFi indoor positionings | |
| CN103997717B (en) | A kind of real-time indoor locating system and method | |
| CN106093852A (en) | A kind of method improving WiFi fingerprint location precision and efficiency | |
| CN108375754B (en) | Node positioning method based on initial state and moving state of mobile node in WSN (Wireless sensor network) | |
| CN109275095A (en) | A kind of indoor locating system based on bluetooth, positioning device and localization method | |
| CN104053129A (en) | Wireless sensor network indoor positioning method and device based on sparse RF fingerprint interpolations | |
| CN102802260A (en) | WLAN indoor positioning method based on matrix correlation | |
| CN109511085B (en) | UWB fingerprint positioning method based on MeanShift and weighted k nearest neighbor algorithm | |
| CN103402258A (en) | Wi-Fi (Wireless Fidelity)-based indoor positioning system and method | |
| CN102209382A (en) | Wireless sensor network node positioning method based on received signal strength indicator (RSSI) | |
| CN105717483B (en) | A kind of location determining method and device based on multi-source positioning method | |
| CN103618997B (en) | Indoor positioning method and device based on signal intensity probability | |
| CN104754735B (en) | Localization method based on location fingerprint storehouse | |
| CN106851571A (en) | WiFi localization methods in a kind of quick KNN rooms based on decision tree | |
| CN103905992A (en) | Indoor positioning method based on wireless sensor networks of fingerprint data | |
| CN110933599A (en) | Self-adaptive positioning method fusing UWB and WIFI fingerprints | |
| CN110351660B (en) | Bluetooth indoor positioning method based on double-step fingerprint matching architecture |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210219 |