CN106792559A - The automatic update method of fingerprint base in a kind of WiFi indoor locating systems - Google Patents
The automatic update method of fingerprint base in a kind of WiFi indoor locating systems Download PDFInfo
- Publication number
- CN106792559A CN106792559A CN201611231542.5A CN201611231542A CN106792559A CN 106792559 A CN106792559 A CN 106792559A CN 201611231542 A CN201611231542 A CN 201611231542A CN 106792559 A CN106792559 A CN 106792559A
- Authority
- CN
- China
- Prior art keywords
- fingerprint base
- signal intensity
- rssi
- fingerprint
- scope
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/02—Hierarchically pre-organised networks, e.g. paging networks, cellular networks, WLAN [Wireless Local Area Network] or WLL [Wireless Local Loop]
- H04W84/10—Small scale networks; Flat hierarchical networks
- H04W84/12—WLAN [Wireless Local Area Networks]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of automatic update method of fingerprint base in WiFi indoor locating systems, belong to WiFi indoor positionings field.The specific steps of method include:The AP with data back function is laid, initial signal characteristics table is built, inactive state identification is carried out to scope, reject the signal difference opposite sex of scope and standard device, built part and update fingerprint base, structure is remaining to update fingerprint base, and synthesis updates fingerprint base.The method greatlys save manpower, the financial resources cost for updating fingerprint base, realizes the light load of mobile terminal, when indoor environment changes, renewal fingerprint base that can be automatic accurate.
Description
Technical field
The invention belongs to WiFi indoor positionings field, more specifically to fingerprint in a kind of WiFi indoor locating systems
The automatic update method in storehouse.
Background technology
In the last few years, location Based service (LBS) was provided and gave people increasing facility, related location technology
Rapidly developed.GPS (GNSS) can provide the positioning clothes of rice dimension accuracy in free environments
Business, but indoors in environment, because building is blocked to signal, GNSS can not be used for carrying out indoor positioning.Therefore,
The location technology based on signals such as WiFi, RFID, sound waves is developed in environment indoors.
With the popularization of Wi-Fi hotspot and widely using for smart mobile phone, WiFi indoor locating systems are subject to more and more
Concern.In WiFi indoor locating systems, fingerprint location method higher is determined due to that can be provided compared to other localization methods
Position precision, thus be widely used.Fingerprint location method is divided into two stages:Off-lined signal acquisition phase and tuning on-line rank
Section.Off-lined signal acquisition phase, is built by gathering the signal intensity of surrounding wireless aps at the reference point in positioning region
One reference point locations coordinate fingerprint base corresponding with surrounding AP signal intensities.Tuning on-line stage, mobile device can be gathered
The real-time signal intensity of surrounding AP, is matched real-time signal strength with fingerprint base by matching algorithm, finds similarity
Highest fingerprint, and using the position corresponding to the fingerprint as mobile device positioning result.
In fingerprint location scheme, the accuracy of fingerprint base directly affects positioning precision.Because wireless signal is easily received
To the influence of the environmental factors such as article movement, the opening and closing of door, temperature, humidity, wireless signal located space distribution with when
Between passage can change.The change of this signal, can cause the fingerprint base of original collection can not accurately react current
Signal characteristic, so as to influence the positioning precision of fingerprint location method.Accordingly, it would be desirable to regularly update fingerprint base so that fingerprint base
The feature of current demand signal can accurately be characterized.
Updating for fingerprint base can be using the scheme for manually resurveying fingerprint, but this scheme can expend a large amount of manpowers
Financial resources.Another scheme is that fingerprint is corrected by user feedback, but or this scheme needs the active feedback of user,
The resource of a large amount of mobile devices is taken, is not easy to promote.
The content of the invention
The technical problem to be solved in the present invention:Overcome the deficiencies in the prior art, there is provided in a kind of WiFi indoor locating systems
The automatic update method of fingerprint base, automatically moves the renewal fingerprint base of the light load in end, to solve fingerprint base caused by environmental change
Problem of Failure, while manpower, the financial resources saved needed for fingerprint base updates, and to the occupancy of mobile device system resource.
Technical solution of the invention:The automatic update method of fingerprint base in a kind of WiFi indoor locating systems, in order to
The fingerprint base of WiFi indoor locating systems is automatically updated, the change of environment is adapted it to, the present invention is known by signature analysis
The motion state of other scope, the data that the signal intensity of scope inactive state fingerprint as a reference point updates are come
Source;By building the equation of linear regression between scope and standard device signal intensity, between the different mobile devices of rejecting
The otherness of signal intensity;By extracting the multicollinearity relation between original fingerprint base reference point, realize fingerprint base more
New method;Fingerprint base updates operation to be carried out in background server completely, realizes the light load of mobile terminal.
It is as follows that the present invention implements step:
Step one:The AP with data back function is laid in area to be targeted;The AP with data back function
Refer to the signal intensity for having and being able to record that around wireless device is received, and the signal intensity is periodically returned into fingerprint
Storehouse updates the AP of server capability;It is the computer equipment for automatically updating fingerprint base, fortune that the fingerprint base updates server
The related algorithm that fingerprint base of going updates;
Step 2:By area to be targeted rasterizing, choose reference point and record the position coordinates of reference point, at reference point
Use standard device HcThe signal intensity RSSI and mac address information of collection surrounding AP, build initial signal characteristics table Sc;It is described
Standard device HcIt refer to the equipment for building fingerprint base, test position fix result, it is possible to use the smart mobile phone of disposable type;Institute
State initial signal characteristics table ScIncluding in a period of time, the signal intensity of the surrounding AP that standard device is collected at reference point is arranged
Table;
Step 3:The scan data bag that fingerprint base updates server, the sight that identification remains static are returned to using AP
Measurement equipment, and preserve the signal intensity S that scope remains statico;The scope refer in area to be targeted,
It is likely to be at the arbitrarily mobile device with WiFi module such as mobile phone, removable computer, PDA of optional position;
Wherein, the step of scope that identification remains static, is as follows:
(1) signal intensity of same AP in sweep time section is filtered using Kalman filter;
The state equation of Kalman filter is the signal intensity that X (k)=X (k-1)+W (k) is used for predicting subsequent time,
The observational equation of Kalman filter is Z (k)=X (k)+V (k), and wherein X (k) is the predicted value of k time-ofday signals intensity, Z (k)
It is the measured value of k time-ofday signals intensity, W (k) and V (k) represents the noise of prediction and measurement respectively, it is assumed that be white Gaussian noise;
(2) the start/stop time T for being used for marking scope to remain static is setstart,Tend;
(3) filtered RSSI sequences, each RSSI of sequence analysis, if current RSSI and RSSI sequences before are used
AverageLess than the threshold value of setting, threshold value is 2db to difference, then scope remains static;Otherwise at scope
In motion state;
(4) inactive state duration T is calculatedlast=Tend-TstartIf, Tlast>=30s, then preserve this it is static when
Between scan data S in sectiono, operation is updated for carrying out follow-up fingerprint base;
(5) (2) (3) (4) step is repeated, is finished until the signal in section of whole sweep time is all processed.
Step 4:The signal intensity S that scope in step 3 is remained staticoWith the position coordinates of reference point
Match somebody with somebody, the equation of linear regression set up between scope and standard device signal intensity, using the equation reject scope with
Otherness between standard device signal intensity, the signal intensity of scope after being corrected;
Comprise the following steps that:
(1) agreement footmark c represents standard device, and footmark o represents scope;
(2) the signal intensity S of calculating observation equipment inactive stateoWith initial signal characteristics table SS in step 2cMiddle record
The correlation between signal intensity at all reference pointsWherein k represents AP's
Number,It is the signal intensity of i-th AP that scope is received,Be corresponding A P in initial signal characteristics table signal it is strong
Degree, μ (So) represent the average that the signal intensity of i-th AP that scope is received is sampled, μ (Sc) represent initial signal characteristics table
The average of the signal intensity sampling of middle corresponding A P;;
(3) position of the maximum reference points of correlation r is chosen from step (1), by the letter in the position initial signal table
Number intensity is put together with the signal intensity of scope inactive state, constitutes sampled data to p=(RSSIo,RSSIc);
(4) repeat step (1), step (2), until the signal intensity of all inactive states is obtained for calculating, obtain by
Sampled data P={ the p that scope is constituted with standard device signal intensity sampled data to p1,p2,…,pn, wherein n is represented
The number of inactive state;
(5) using the sampled data P in step (3), equation of linear regression is solved:RSSIc=b+a*RSSIo+ ε, wherein
RSSIoRepresent the signal intensity of scope, RSSIcThe signal intensity of standard device is represented, a is the slope of regression straight line, and b is
Square is cut, ε is the random noise of Gaussian distributed;
(6) in recording step (4) equation of linear regression parameter a and b, using the equation of linear regression, by scope
Signal intensity RSSIOBring formula RSSI intom=b+a*RSSIo, try to achieve the signal intensity RSSI of scope after amendmentm。
Step 5:The signal intensity RSSI of scope after being corrected in step 4mPosition coordinates with reference point is closed
Together, the renewal fingerprint at reference point is obtained, adds part to update fingerprint base F in the renewal fingerprintp;The part updates fingerprint
Storehouse refers to, the fingerprint base of composition that all renewal fingerprints are put together;
Step 6:Step 3, step 4, step 5 are continuously carried out, such as 24 points of timing daily checks that part updates fingerprint
Storehouse FpIf, FpThe number of middle reference point accounts for the ratio of general reference points number more than 30%, and reference point number compare it is previous
Its no increase, then by FpWith initial signal characteristics table Sc, fingerprint base F is updated using PLS generation is remainingr;Institute
Stating the remaining fingerprint base that updates refers to, the fingerprint base being made up of the fingerprint of reference point not in part updates fingerprint base;
Wherein, fingerprint base F is updated using PLS generation is remainingrStep is as follows:
(1) part is updated into fingerprint base FpIn the reference point number that includes be designated as n1, by not in part updates fingerprint base
Reference point number is designated as n2, for not in FpIn a reference point Li, from initial signal characteristics table ScMiddle extraction sample data
(RSSIi,RSSIc), wherein RSSIiRepresent ScMiddle LiThe signal intensity at place, RSSIcRepresent ScIn with FpAt corresponding reference point
Signal intensity, wherein
(2) sample data (RSSI in step (1) is usedi,RSSIc) PLS equation is solved, by RSSIi
As X, RSSIcFormula Y=XB=XPR is brought into as YT, try to achieve regression coefficient B=PRT, wherein P is the axial direction after X standardization
Moment matrix, R is regression coefficient matrixes of the X to the regression equation of Y after X and Y is standardized;
(3) part is updated into fingerprint base FpIn with RSSIcSignal intensity RSSI at corresponding all reference pointsoAs X
Bring the regression equation tried to achieve in step (2) into, obtain reference point LiThe signal intensity at placeWith LiCoordinate constitute L togetheri
The fingerprint at place, remaining renewal fingerprint base F is added by the fingerprintr;
(4) repeat step (1), step (2), step (3), until by all not in FpIn reference point at fingerprint all add
Enter to residue and update fingerprint base Fr。
Step 7:Part is updated into fingerprint base FpFingerprint base F is updated with residuerIt is combined, constitutes and update fingerprint base Fn。
Present invention advantage compared with prior art is:
(1) fingerprint base is automatically updated by system, reduces manpower, the financial resources of the consuming of artificial regeneration fingerprint base;
(2) it is all to update operation in background server execution, realize the light load of mobile terminal;
(3) by identification equipment inactive state, removal equipment otherness, using many between reference point in original fingerprint base
The methods such as weight co-linear relationship, reconstruct complete, accurate fingerprint base.
Brief description of the drawings
Fig. 1 is fingerprint base automatic update method flow chart;
Fig. 2 is WiFi fingerprint base automatic update system schematic diagrames.
Specific embodiment
As a example by as shown in Figure 1, 2, illustrate of the invention to realize step:
Step one:The AP with data back function is laid in area to be targeted, it is ensured that every 30 meters of at least 1 AP,
Enable that all AP cover whole positioning region;
Step 2:By positioning region rasterizing, choose reference point and record the position coordinates of reference point, make at reference point
Use standard device HcThe information such as the signal intensity RSSI and MAC Address of collection surrounding AP, build initial signal characteristics table Sc;
Wherein, described initial signal characteristics table ScIncluding (3 minutes) in a period of time, standard setting equipment is in reference point
The signal strength list of the surrounding AP that place collects:
Reference point is numbered | Sweep time | The MAC Address of AP | Signal intensity |
1 | T1 | MAC1 | RSSI1 |
1 | T2 | MAC2 | RSSI2 |
2 | T1 | MAC1 | RSSI3 |
… | … | … | … |
Step 3:The scan data bag that fingerprint base updates server, the sight that identification remains static are returned to using AP
Measurement equipment, and preserve the signal intensity S that scope remains statico;
Wherein, described " scan data bag " includes scope scanning to the signal strength list of surrounding AP:
Mobile device MAC Address | Sweep time | The MAC Address of AP | Signal intensity |
MOB_MAC1 | T1 | MAC1 | RSSI1 |
MOB_MAC1 | T2 | MAC2 | RSSI2 |
MOB_MAC1 | T3 | MAC3 | RSSI3 |
… | … | … | … |
Wherein, described identification remains static mobile device is comprised the following steps that:
(1) signal intensity of same AP in sweep time section is filtered using Kalman filter;Kalman filtering
The state equation of device is the signal intensity that X (k)=X (k-1)+W (k) is used for predicting subsequent time, the observation of Kalman filter
Equation is Z (k)=X (k)+V (k), and wherein X (k) is the predicted value of k time-ofday signals intensity, and Z (k) is the survey of k time-ofday signals intensity
Value, W (k) and V (k) represent the noise of prediction and measurement respectively, it is assumed that be white Gaussian noise;The covariance matrix Q of W (k) is
Null matrix, the covariance matrix R of V (k) is null matrix;The covariance of state variable is P (k | k-1)=P (k-1 | k-1)+Q;Filter
Two initial values of ripple device:X (0) takes first RSSI in sweep time section, and P (0) takes 1;
(2) the start/stop time T for being used for marking scope to remain static is setstart,Tend;
(3) filtered RSSI sequences, each RSSI of sequence analysis, if current RSSI and RSSI sequences before are used
AverageDifference is less than 2db, then scope remains static;Otherwise scope is kept in motion;
(4) inactive state duration T is calculatedlast=Tend-TstartIf, Tlast>=30s, then preserve this it is static when
Between scan data S in sectiono, operation is updated for carrying out follow-up fingerprint base;
(5) (2) (3) (4) step is repeated, is finished until the signal in section of whole sweep time is all processed.
Step 4:The signal intensity S that scope in step 3 is remained staticoWith the position coordinates of reference point
Match somebody with somebody, the equation of linear regression set up between scope and standard device signal intensity, using the equation reject scope with
Otherness between standard device signal intensity, the signal intensity of scope after being corrected;
Comprise the following steps that:
(1) agreement footmark c represents standard device, and footmark o represents scope;
(2) the signal intensity S of calculating observation equipment inactive stateoWith initial signal characteristics table S in step 2cMiddle record
The correlation between signal intensity at all reference pointsWherein k represents AP's
Number,It is the signal intensity of i-th AP that scope is received,Be corresponding A P in initial signal characteristics table signal it is strong
Degree, μ (So) represent the average that the signal intensity of i-th AP that scope is received is sampled, μ (Sc) represent initial signal characteristics table
The average of the signal intensity sampling of middle corresponding A P;;
(3) position of the maximum reference points of correlation r is chosen from step (1), by the letter in the position initial signal table
Number intensity is put together with the signal intensity of scope inactive state, constitutes sampled data to p=(RSSIo,RSSIc);
(4) repeat step (1), step (2), until the signal intensity of all inactive states is obtained for calculating, obtain by
Sampled data P={ the p that scope is constituted with standard device signal intensity sampled data to p1,p2,…,pn, wherein n is represented
The number of inactive state;
(5) using the sampled data P in step (3), equation of linear regression is solved:RSSIc=b+a*RSSIo+ ε, wherein
RSSIoRepresent the signal intensity of scope, RSSIcThe signal intensity of standard device is represented, a is the slope of regression straight line, and b is
Square is cut, ε is the random noise of Gaussian distributed;
(6) in recording step (4) equation of linear regression parameter a and b, using the equation of linear regression, by scope
Signal intensity RSSIoBring formula RSSI intom=b+a*RSSIo, try to achieve the signal intensity RSSI of scope after amendmentm。
Step 5:The signal intensity RSSI of scope after being corrected in step 4mPosition coordinates with reference point is closed
Together, the renewal fingerprint at reference point is obtained, adds part to update fingerprint base F in the renewal fingerprintp;The part updates fingerprint
Storehouse refers to, the fingerprint base of composition that all renewal fingerprints are put together;
Step 6:Step 3, step 4, step 5 are continuously carried out, check that part updates fingerprint base F at daily 24 pointspIf,
FpThe number of middle reference point accounts for the ratio of general reference points number more than 30%, and the number of reference point is compared the previous day and do not increased
Plus, then by FpWith initial signal characteristics table Sc, fingerprint base F is updated using PLS generation is remainingr;The residue is more
New fingerprint base refers to, the fingerprint base being made up of the fingerprint of reference point not in part updates fingerprint base;
Wherein, fingerprint base F is updated using PLS generation is remainingrStep is as follows:
(1) part is updated into fingerprint base FpIn the reference point number that includes be designated as n1, by not in part updates fingerprint base
Reference point number is designated as n2, for not in FpIn a reference point Li, from initial signal characteristics table ScMiddle extraction sample data
(RSSIi,RSSIc), wherein RSSIiRepresent ScMiddle LiThe signal intensity at place, RSSIcRepresent ScIn with FpAt corresponding reference point
Signal intensity, wherein
(2) sample data (RSSI in step (1) is usedi,RSSIc) PLS equation is solved, by RSSIi
As X, RSSIcFormula Y=XB=XPR is brought into as YT, try to achieve regression coefficient B=PRT, wherein P is the axial direction after X standardization
Moment matrix, R is regression coefficient matrixes of the X to the regression equation of Y after X and Y is standardized;
(3) part is updated into fingerprint base FpIn with RSSIcSignal intensity RSSI at corresponding all reference pointsoAs X
Bring the regression equation tried to achieve in step (2) into, obtain reference point LiThe signal intensity at placeWith LiCoordinate constitute L togetheri
The fingerprint at place, remaining renewal fingerprint base F is added by the fingerprintr;
(4) repeat step (1), step (2), step (3), until by all not in FpIn reference point at fingerprint all add
Enter to residue and update fingerprint base Fr。
Step 7:Part is updated into fingerprint base FpFingerprint base F is updated with residuerIt is combined, constitutes and update fingerprint base Fn。
In a word, the present invention lays the AP with data back function, builds initial signal characteristics table, and scope is carried out
Inactive state recognizes that reject the signal difference opposite sex of scope and standard device, structure part updates fingerprint base, and structure is remaining more
New fingerprint base, synthesis updates fingerprint base.The method greatlys save manpower, the financial resources cost for updating fingerprint base, realizes movement
The light load at end, when indoor environment changes, renewal fingerprint base that can be automatic accurate.
Above example is provided just for the sake of the description purpose of the present invention, and is not intended to limit the scope of the present invention.This
The scope of invention is defined by the following claims.The various equivalents that do not depart from spirit and principles of the present invention and make and repair
Change, all should cover within the scope of the present invention.
Claims (4)
1. in a kind of WiFi indoor locating systems fingerprint base automatic update method, it is characterised in that comprise the following steps:
Step one:The AP with data back function is laid in area to be targeted;The AP with data back function refers to
With the signal intensity for being able to record that around wireless device is received, and the signal intensity is periodically returned into fingerprint base more
The AP of new demand servicing device function;It is the computer equipment for automatically updating fingerprint base that the fingerprint base updates server, is run
The related algorithm that fingerprint base updates;
Step 2:By area to be targeted rasterizing, choose reference point and record the position coordinates of reference point, used at reference point
The signal intensity RSSI and mac address information of standard device collection surrounding AP, build initial signal characteristics table;The standard device
It refer to the equipment for building fingerprint base, test position fix result, it is possible to use the smart mobile phone of disposable type;The initial signal
Mark sheet includes that a period of time is interior, the signal strength list of the surrounding AP that standard device is collected at reference point;
Step 3:The scan data bag that fingerprint base updates server is returned to using AP, the observation that identification remains static sets
It is standby, and preserve the signal intensity that scope remains static;The scope refers in area to be targeted, at possibility
In any mobile device with WiFi module of optional position, including mobile phone, removable computer, PDA;
Step 4:The signal intensity that scope in step 3 is remained static is matched with the position coordinates of reference point, is built
Vertical equation of linear regression between scope and standard device signal intensity, rejects scope and is set with standard using the equation
Otherness between standby signal intensity, the signal intensity of scope after being corrected;
Step 5:The signal intensity of scope is combined with the position coordinates of reference point after being corrected in step 4, obtains
Renewal fingerprint at reference point, adds part to update fingerprint base in the renewal fingerprint;The part updates fingerprint base, by institute
Have and update fingerprint and put together the fingerprint base of composition;
Step 6:Step 3, step 4, step 5 are continuously carried out, daily regular check part updates fingerprint base, such as fruit part more
The number of reference point accounts for the threshold value of the ratio more than setting of general reference points number in new fingerprint base, and the number of reference point is compared
The previous day does not increase, then update fingerprint base and initial signal characteristics table by part, is generated using PLS remaining
Update fingerprint base;The remaining fingerprint base that updates refers to be made up of the fingerprint of reference point not in part updates fingerprint base
Fingerprint base;
Step 7:Part is updated into fingerprint base and the remaining fingerprint base that updates is combined, constituted and update fingerprint base.
2. in a kind of WiFi indoor locating systems according to claim 1 fingerprint base automatic update method, its feature exists
In:In the step 3, identification remain static scope the step of it is as follows:
(1) signal intensity of same AP in sweep time section is filtered using Kalman filter;
(2) the start/stop time T for being used for marking scope to remain static is setstart,Tend;
(3) filtered RSSI sequences, each RSSI of sequence analysis are used, if current RSSI is equal with RSSI sequences before
ValueDifference remains static less than the threshold value for setting, then scope;Otherwise scope is kept in motion;
(4) inactive state duration T is calculatedlast=Tend-TstartIf, TlastMore than given threshold value, then this is preserved quiet
Only the scan data in the time period, operation is updated for carrying out follow-up fingerprint base;
(5) (2) (3) (4) step is repeated, is finished until the signal in section of whole sweep time is all processed.
3. in a kind of WiFi indoor locating systems according to claim 1 fingerprint base automatic update method, its feature exists
In:The step 4, step is as follows:
(1) all references recorded in initial signal characteristics table in the signal intensity of calculating observation equipment inactive state and step 2
The correlation between signal intensity at point;
(2) position of the reference point of correlation maximum is chosen from step (1), by the signal intensity of the position in initial signal table
Signal intensity with scope inactive state is put together, constitutes sampled data pair;
(3) repeat step (1), step (2), until the signal intensity of all inactive states is obtained for calculating, obtain by observing
Equipment and standard device signal intensity sampled data are to the sampled data that constitutes;
(4) using the sampled data in step (3), equation of linear regression is solved:RSSIc=b+a*RSSIo+ ε, wherein RSSIoTable
Show the signal intensity of scope, RSSIcThe signal intensity of standard device is represented, a is the slope of regression straight line, and b is to cut square, ε
It is the random noise of Gaussian distributed;
(5) in recording step (4) equation of linear regression parameter a and b, observe and setting after trying to achieve amendment using the equation of linear regression
Standby signal intensity.
4. in a kind of WiFi indoor locating systems according to claim 1 fingerprint base automatic update method, its feature exists
In:It is as follows using the remaining renewal fingerprint base step of PLS generation in the step 6:
(1) for reference point L not in part updates fingerprint basei, the letter at the reference point is extracted from initial signal characteristics table
Number intensity RSSIi;The signal corresponding with all reference points in part renewal fingerprint base is extracted from initial signal characteristics table strong
Degree RSSIc;
(2) sample data (RSSI in step (1) is usedi,RSSIc) PLS equation is solved, by RSSIiAs
X, RSSIcFormula Y=XB=XPR is brought into as YT, try to achieve regression coefficient B=PRT, wherein P is the axial vector square after X standardization
Battle array, R is regression coefficient matrixes of the X to the regression equation of Y after X and Y is standardized;
(3) will part update fingerprint base in RSSIcSignal intensity RSSI at corresponding all reference pointsoStep is brought into as X
Suddenly the regression equation tried to achieve in (2), obtains reference point LiThe signal intensity at placeWith LiCoordinate constitute L togetheriThe finger at place
Line, remaining renewal fingerprint base is added by the fingerprint;
(4) repeat step (1), step (2), step (3), until by all reference points not in part updates fingerprint base
Fingerprint is all added to remaining renewal fingerprint base.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611231542.5A CN106792559A (en) | 2016-12-28 | 2016-12-28 | The automatic update method of fingerprint base in a kind of WiFi indoor locating systems |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611231542.5A CN106792559A (en) | 2016-12-28 | 2016-12-28 | The automatic update method of fingerprint base in a kind of WiFi indoor locating systems |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106792559A true CN106792559A (en) | 2017-05-31 |
Family
ID=58921088
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611231542.5A Pending CN106792559A (en) | 2016-12-28 | 2016-12-28 | The automatic update method of fingerprint base in a kind of WiFi indoor locating systems |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106792559A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009485A (en) * | 2017-11-28 | 2018-05-08 | 元力云网络有限公司 | Wireless fingerprint storehouse update method based on crowdsourcing data |
CN110099442A (en) * | 2019-05-05 | 2019-08-06 | 北京三快在线科技有限公司 | The change in location of the network equipment determines method, apparatus, computer equipment and medium |
US10660062B1 (en) | 2019-03-14 | 2020-05-19 | International Business Machines Corporation | Indoor positioning |
CN111654843A (en) * | 2019-03-04 | 2020-09-11 | 深圳光启空间技术有限公司 | Method and system for automatically updating fingerprint database and wifi positioning method and system |
CN112740759A (en) * | 2018-09-28 | 2021-04-30 | 谷歌有限责任公司 | Method and apparatus for proactive handover between available networks |
CN112804642A (en) * | 2021-04-08 | 2021-05-14 | 上海迹寻科技有限公司 | Fingerprint data updating judgment method and device for target area |
CN112860718A (en) * | 2021-02-03 | 2021-05-28 | 腾讯科技(深圳)有限公司 | Subway station fingerprint database updating method and device, computer equipment and storage medium |
CN112887911A (en) * | 2021-01-19 | 2021-06-01 | 湖南大学 | Indoor positioning method based on WIFI and vision fusion |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945428A (en) * | 2013-01-21 | 2014-07-23 | 华为技术有限公司 | Radio frequency fingerprint database updating method, device and system |
CN104853317A (en) * | 2014-11-24 | 2015-08-19 | 北京航空航天大学 | WiFi indoor positioning fingerprint database construction and update method |
CN104869536A (en) * | 2014-12-25 | 2015-08-26 | 清华大学 | Method of automatically updating wireless indoor positioning fingerprint map and device |
CN105120479A (en) * | 2015-07-22 | 2015-12-02 | 上海交通大学 | Signal strength difference correction method of Wi-Fi signals between terminals |
US20160094951A1 (en) * | 2014-09-26 | 2016-03-31 | Shao-Wen Yang | Wi-fi fingerprint location database creation and update from crowd sourced data |
US20160150029A1 (en) * | 2014-11-26 | 2016-05-26 | Avaya Inc. | Service discovery using a location database |
CN105813192A (en) * | 2014-12-29 | 2016-07-27 | 上海奕通信息科技有限公司 | Combined fingerprint feature-based WiFi fingerprint positioning method |
CN106211313A (en) * | 2015-04-30 | 2016-12-07 | 西门子公司 | Location fingerprint update method and device for wireless location |
-
2016
- 2016-12-28 CN CN201611231542.5A patent/CN106792559A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945428A (en) * | 2013-01-21 | 2014-07-23 | 华为技术有限公司 | Radio frequency fingerprint database updating method, device and system |
US20160094951A1 (en) * | 2014-09-26 | 2016-03-31 | Shao-Wen Yang | Wi-fi fingerprint location database creation and update from crowd sourced data |
CN104853317A (en) * | 2014-11-24 | 2015-08-19 | 北京航空航天大学 | WiFi indoor positioning fingerprint database construction and update method |
US20160150029A1 (en) * | 2014-11-26 | 2016-05-26 | Avaya Inc. | Service discovery using a location database |
CN104869536A (en) * | 2014-12-25 | 2015-08-26 | 清华大学 | Method of automatically updating wireless indoor positioning fingerprint map and device |
CN105813192A (en) * | 2014-12-29 | 2016-07-27 | 上海奕通信息科技有限公司 | Combined fingerprint feature-based WiFi fingerprint positioning method |
CN106211313A (en) * | 2015-04-30 | 2016-12-07 | 西门子公司 | Location fingerprint update method and device for wireless location |
CN105120479A (en) * | 2015-07-22 | 2015-12-02 | 上海交通大学 | Signal strength difference correction method of Wi-Fi signals between terminals |
Non-Patent Citations (1)
Title |
---|
崔丽珍: "基于改进卡尔曼滤波算法的煤矿井下跟踪方法", 《煤矿安全》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009485A (en) * | 2017-11-28 | 2018-05-08 | 元力云网络有限公司 | Wireless fingerprint storehouse update method based on crowdsourcing data |
CN112740759A (en) * | 2018-09-28 | 2021-04-30 | 谷歌有限责任公司 | Method and apparatus for proactive handover between available networks |
CN111654843A (en) * | 2019-03-04 | 2020-09-11 | 深圳光启空间技术有限公司 | Method and system for automatically updating fingerprint database and wifi positioning method and system |
CN111654843B (en) * | 2019-03-04 | 2024-04-30 | 深圳光启空间技术有限公司 | Method and system for automatically updating fingerprint database, wifi positioning method and system |
US10660062B1 (en) | 2019-03-14 | 2020-05-19 | International Business Machines Corporation | Indoor positioning |
CN110099442A (en) * | 2019-05-05 | 2019-08-06 | 北京三快在线科技有限公司 | The change in location of the network equipment determines method, apparatus, computer equipment and medium |
CN110099442B (en) * | 2019-05-05 | 2020-10-23 | 北京三快在线科技有限公司 | Method and device for determining position change of network equipment, computer equipment and medium |
CN112887911A (en) * | 2021-01-19 | 2021-06-01 | 湖南大学 | Indoor positioning method based on WIFI and vision fusion |
CN112860718A (en) * | 2021-02-03 | 2021-05-28 | 腾讯科技(深圳)有限公司 | Subway station fingerprint database updating method and device, computer equipment and storage medium |
CN112860718B (en) * | 2021-02-03 | 2022-07-08 | 腾讯科技(深圳)有限公司 | Subway station fingerprint database updating method and device, computer equipment and storage medium |
CN112804642A (en) * | 2021-04-08 | 2021-05-14 | 上海迹寻科技有限公司 | Fingerprint data updating judgment method and device for target area |
CN112804642B (en) * | 2021-04-08 | 2022-03-04 | 上海迹寻科技有限公司 | Fingerprint data updating judgment method and device for target area |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106792559A (en) | The automatic update method of fingerprint base in a kind of WiFi indoor locating systems | |
CN105101408B (en) | Indoor orientation method based on distributed AP selection strategy | |
CN106646338B (en) | A kind of quickly accurate indoor orientation method | |
CN103582119B (en) | The finger print data base construction method of WiFi indoor locating system | |
CN104883734B (en) | A kind of indoor Passive Location based on geographical fingerprint | |
CN105657823B (en) | WIFI indoor weighted K nearest neighbor positioning algorithm based on kernel function main feature extraction | |
CN107703480B (en) | Mixed kernel function indoor positioning method based on machine learning | |
CN105934684B (en) | The method and apparatus calibrated automatically for striding equipment | |
CN108769907B (en) | Indoor positioning method based on deep learning and integrating WiFi and iBeacon | |
CN104394588B (en) | Indoor orientation method based on Wi Fi fingerprints and Multidimensional Scaling | |
CN111586605B (en) | KNN indoor target positioning method based on adjacent weighted self-adaptive k value | |
CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
CN111726765B (en) | WIFI indoor positioning method and system for large-scale complex scene | |
CN107037399A (en) | A kind of Wi Fi indoor orientation methods based on deep learning | |
Zhang et al. | Device-free wireless localization and activity recognition with deep learning | |
CN108225332B (en) | Indoor positioning fingerprint map dimension reduction method based on supervision | |
Li et al. | Location estimation in large indoor multi-floor buildings using hybrid networks | |
Gu et al. | HED: Handling environmental dynamics in indoor WiFi fingerprint localization | |
CN110366109B (en) | Positioning method and system for indoor target | |
CN109302674B (en) | WiFi indoor positioning method based on multiple filtering | |
Chen et al. | A wifi indoor localization method based on dilated cnn and support vector regression | |
Wei et al. | Handling device heterogeneity in Wi-Fi based indoor positioning systems | |
Zhang et al. | Dual-band wi-fi based indoor localization via stacked denosing autoencoder | |
Aguilar-Garcia et al. | Enhancing localization accuracy with multi-antenna UHF RFID fingerprinting | |
CN106792560B (en) | Target identification method based on wireless reception of signals intensity |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170531 |
|
WD01 | Invention patent application deemed withdrawn after publication |