CN105933975A - WiFi fingerprint-based accuracy improved indoor positioning method - Google Patents
WiFi fingerprint-based accuracy improved indoor positioning method Download PDFInfo
- Publication number
- CN105933975A CN105933975A CN201610220583.8A CN201610220583A CN105933975A CN 105933975 A CN105933975 A CN 105933975A CN 201610220583 A CN201610220583 A CN 201610220583A CN 105933975 A CN105933975 A CN 105933975A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- wifi
- rss
- point
- sampled point
- 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
-
- 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
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a WiFi fingerprint-based accuracy improved indoor positioning method. The method includes a sampling stage and a positioning stage. In the sampling phase, Collection and Gauss filter at different directions are combined, so that an FODG (fusion of different direction collection and gauss Filter) sampling method is designed; WiFi signals are collected in different directions (east, south, west and north); some signals of which the signal intensity larges deviates from a signal intensity mean value are filtered out through Gauss filter; and average filtering is performed on the signals, and the filtered signals are stored into a fingerprint database. In the positioning phase, an AWKNN matching method is designed, namely, when Euclidean distances are calculated, different weights are assigned to access points (AP) with different signal intensities; and in a coordinate matching link, different weights are assigned to K neighbor sampling points according to the lengths of the Euclidean distances. Compared with a traditional WiFi fingerprint positioning method, the positioning method of the invention according to which FODG sampling and AWKNN matching are combined can improve positioning accuracy.
Description
Technical field
The present invention relates to the indoor orientation method that a kind of precision based on WiFi fingerprint is improved, belong to indoor positioning technologies neck
Territory.
Background technology
Along with the fast development of information technology, indoor positioning technologies based on terminal can provide the user information retrieval clothes
Business, indoor navigation service, community friend-making service etc., therefore have become as current hot research field.Existing WiFi fingerprint
Positioning mode orientation range is wide, low cost, use flexibly, without additional hardware support, the most become the focus of research.
But, still there are the following problems for existing WiFi fingerprint location method: first, in sample phase, on each sampled point
Needing to gather signal pretreatment, the processing mode of existing one direction collection and mean filter is the most not ideal enough, causes fingerprint
Data base is not accurate enough, the most just makes later stage positioning precision not ideal enough;Second, at positioning stage, more existing matching process are such as
KNN imparts K the identical weights of neighbour's reference point, causes matching precision not ideal enough.
And the present invention can solve problem above well.
Summary of the invention
Present invention aim at providing the indoor orientation method that a kind of precision based on WiFi fingerprint is improved, the method is divided
For sampling and two stages of location.In sample phase, different directions acquisition method and gaussian filtering are merged, it is proposed that adopting of improvement
Sample method FODG (Fusion of Different direction collection and Gauss Filter), i.e. from
Four, east, south, west, north different directions gathers WiFi signal, then filters some and signal intensity mean bias with gaussian filtering
Bigger signal, then mean filter is stored in fingerprint database.At positioning stage, AP weighted euclidean distance and WKNN method are merged,
Propose the matching method AWKNN (AP weighted and distanced weighted KNN) of improvement, i.e. calculating
During Euclidean distance, compose the AP that different weights have unlike signal intensity to each, then propose distance weighted KNN (WKNN)
Carry out coordinate matching, finally draw tested point position coordinates.
The present invention solves its technical problem and is adopted the technical scheme that: the room that a kind of precision based on WiFi fingerprint is improved
Inner position method, the FODG method that the method sample phase uses, has merged different discovery acquisition method and gaussian filtering method, had both considered
To mobile phone be pointed in different directions time signal intensity diversity, filtered again some with signal intensity mean bias bigger little generally
Rate signal, the fingerprint database set up hence with FODG method is relatively more accurate.
Method flow:
Step 1: sample phase;
Step 1-1: utilize mobile phone terminal to gather the WiFi signal of east, south, west, north four direction on each sampled point,
Some groups of signals are gathered on each direction;
Step 1-2: these WiFi signal are carried out gaussian filtering, filters some letters bigger with signal intensity mean bias
Number;
Step 1-3: utilize mean filter to obtain the WiFi signal strength mean value of each sampled point;
Step 1-4: the WiFi signal average of each sampled point and corresponding sampling point position information are stored in data base;
Step 2: positioning stage;
Step 2-1: mobile phone receives real-time WiFi fingerprint in site undetermined;
Step 2-2: traveled through with data base by real-time WiFi fingerprint, calculates the Euclidean distance of AP weighting;
Step 2-3: the Euclidean distance weighted by AP, by sorting from small to large, is chosen before Euclidean distance is less in data base
K fingerprint sampled point;
Step 2-4: this K fingerprint sampled point is carried out WKNN coupling;
Step 2-5: draw the position coordinates of tested point.
Further, in step 1-2 of the present invention, WiFi signal intensity Normal Distribution, i.e. RSS~N (μ, σ2), thenObey standard normal distribution, i.e.Wherein μ is average, and σ is standard deviation,
Taking probability of happening data within 90%, query criteria gaussian distribution table can obtainI.e. through Gauss
After filtering, the span that the RSS of mobile terminal WiFi retains is (μ-1.65 σ, μ+1.65 σ).
Further, in step 1-3 of the present invention, to the WiFi signal mean filter after gaussian filtering, i.e. take these letters
Number average.
Further, in step 2-2 of the present invention, the Euclidean distance of AP weighting is,
wjRepresent the weighted value giving jth AP focus.Assume to acquire altogether the WiFi fingerprint of m sampled point in sample phase, note
Make { F1, F2..., Fm},Fi=(rssi1,rssi2...,rssij...rssin), wherein FiRepresent the fingerprint of ith sample point,
rssijRepresent the signal intensity of the jth AP focus received at ith sample point, it is assumed that altogether can receive at each sampled point
Signal to n AP focus.At positioning stage, the signal intensity array of real-time tested point is s=(RSS1,
RSS2...RSSj...RSSn),RSSjRepresent the signal intensity of the jth AP focus received at tested point.
Further, in step 2-4 of the present invention, WKNN algorithm is after have chosen K neighbour's sampled point, to each sampled point
Position coordinates be multiplied by weights, calculate the sampling point position coordinate after this K weighting and (namely weighting be averaging), make
For the elements of a fix, i.e.In formula, (x y) is determining of drawing of system
Position coordinate, (xi,yi) it is the position coordinates of ith sample point, wiFor weight coefficient, diAdopt with i-th for tested point real time fingerprint
The Euclidean distance of sampling point fingerprint.
Beneficial effect:
1, the FODG method that sample phase of the present invention uses, has merged different discovery acquisition method and gaussian filtering method, had both considered
To mobile phone be pointed in different directions time signal intensity diversity, filtered again some with signal intensity mean bias bigger little generally
Rate signal, the fingerprint database set up hence with FODG method is relatively more accurate.
2, the AWKNN method that positioning stage of the present invention uses, has merged Euclidean distance and the WKNN method of AP weighting, had both considered
Tradition KNN method gives each AP drawback of identical weights when calculating Euclidean distance, it is also contemplated that give K when coordinate matching
The weights of neighbour's sampled point should be different, and the elements of a fix hence with AWKNN method coupling are more accurate.
Accompanying drawing explanation
Fig. 1 is the WiFi fingerprint location method schematic diagram of the present invention.
Fig. 2 is the system schematic of the present invention.
Detailed description of the invention
Below in conjunction with Figure of description, the invention is described in further detail.
As it is shown in figure 1, the present invention is divided into sample phase and positioning stage.
Sample phase is in advance by a number of sampled point of grid arrangement in area to be targeted, utilizes mobile device often
The WiFi signal intensity from different AP focuses that individual sampled point collection receives, the physical location together with this sampled point is deposited
Enter data base, finally set up the fingerprint database that a WiFi signal intensity maps with physical location.Assume in sample phase one
Acquire the WiFi fingerprint of m sampled point altogether, be denoted as { F1, F2..., Fm},Fi=(rssi1,rssi2...,
rssij...rssin), wherein FiRepresent the fingerprint of ith sample point, rssijRepresent the jth received at ith sample point
The signal intensity of AP focus, it is assumed that altogether can receive the signal of n AP focus at each sampled point.
At positioning stage, after the mobile terminal device that user holds detects the WiFi signal of tested point, with sample phase
WiFi fingerprint in the fingerprint database created mates, and according to certain matching algorithm, finds out and wherein receives with tested point
The maximum reference point of WiFi signal intensity fingerprint similarity, using this fingerprint reference point position as the estimation of tested point position
Value.Assuming at positioning stage, the signal intensity array of real-time tested point is s=(RSS1, RSS2...RSSj...RSSn),RSSjTable
Show the signal intensity of the jth AP focus received at tested point.
As in figure 2 it is shown, in sample phase, first arrange some sampled points in experimental situation in advance, utilize mobile phone terminal
Each sampled point gathers the WiFi signal of east, south, west, north four direction, each direction gathers some groups of signals;Then
These WiFi signal are carried out gaussian filtering, filters some signals bigger with signal intensity mean bias, take probability of happening and exist
Data within 90%, i.e. after gaussian filtering, the span that the signal intensity RSS of mobile terminal WiFi retains be (μ-
1.65 σ, μ+1.65 σ);Recycling mean filter obtains the WiFi signal strength mean value of each sampled point, by each sampled point
WiFi signal average and corresponding sampling point position information are stored in data base, so far complete sample phase work.
At positioning stage, mobile phone receives real-time WiFi fingerprint in site undetermined, by real-time WiFi fingerprint with data base time
Go through, calculate the Euclidean distance of AP weighting Then
The Euclidean distance weighted by AP, by sorting from small to large, chooses front K fingerprint sampled point corresponding in data base;Finally to this K
Individual fingerprint sampled point carries out the WKNN coupling of Euclidean distance weighting, i.e. the position coordinates to this K sampled point is multiplied by weights,
I.e. weighting is averaging, and finally draws the elements of a fix, i.e.In formula,
(x y) is the elements of a fix that draw of system, (xi,yi) it is the position coordinates of ith sample point, wiFor weight coefficient, diFor to be measured
Point real time fingerprint and the Euclidean distance of ith sample point fingerprint.
Claims (5)
1. the indoor orientation method that a precision based on WiFi fingerprint is improved, it is characterised in that described method includes walking as follows
Rapid:
Step 1: sample phase;
Step 1-1: utilize mobile phone terminal to gather the WiFi signal of east, south, west, north four direction on each sampled point, each
Some groups of signals are gathered on direction;
Step 1-2: these WiFi signal are carried out gaussian filtering, filters some signals bigger with signal intensity mean bias;
Step 1-3: utilize mean filter to obtain the WiFi signal strength mean value of each sampled point;
Step 1-4: the WiFi signal average of each sampled point and corresponding sampling point position information are stored in data base;
Step 2: positioning stage;
Step 2-1: mobile phone receives real-time WiFi fingerprint in site undetermined;
Step 2-2: traveled through with data base by real-time WiFi fingerprint, calculates the Euclidean distance of AP weighting;
Step 2-3: the Euclidean distance weighted by AP, by sorting from small to large, chooses the less front K of Euclidean distance in data base
Fingerprint sampled point;
Step 2-4: this K fingerprint sampled point is carried out WKNN coupling;
Step 2-5: draw the position coordinates of tested point.
The indoor orientation method that a kind of precision based on WiFi fingerprint the most according to claim 1 is improved, it is characterised in that
In described step 1-2, WiFi signal intensity Normal Distribution, i.e. RSS~N (μ, σ2), soObedience standard normal is divided
Cloth, i.e.Wherein μ is average, and σ is standard deviation,Take and send out
Raw probability data within 90%, query criteria gaussian distribution table can obtainI.e. pass through
After gaussian filtering, the span that the RSS of mobile terminal WiFi retains is (μ-1.65 σ, μ+1.65 σ).
The indoor orientation method that a kind of precision based on WiFi fingerprint the most according to claim 1 is improved, it is characterised in that
In described step 1-3, to the WiFi signal mean filter after gaussian filtering, i.e. take the average of these signals.
The indoor orientation method that a kind of precision based on WiFi fingerprint the most according to claim 1 is improved, it is characterised in that
In described step 2-2, the Euclidean distance of AP weighting is,wjRepresent
Give the weighted value of jth AP focus, it is assumed that acquire altogether the WiFi fingerprint of m sampled point in sample phase, be denoted as { F1,
F2..., Fm},Fi=(rssi1,rssi2…,rssij…rssin), wherein FiRepresent the fingerprint of ith sample point, rssijRepresent
The signal intensity of the jth AP focus that ith sample point receives, it is assumed that altogether can receive n AP heat at each sampled point
The signal of point, at positioning stage, the signal intensity array of real-time tested point is s=(RSS1, RSS2…RSSj...RSSn),RSSj
Represent the signal intensity of the jth AP focus received at tested point.
The indoor orientation method that a kind of precision based on WiFi fingerprint the most according to claim 1 is improved, it is characterised in that
In described step 2-4, the position coordinates of each sampled point, after have chosen K neighbour's sampled point, is multiplied by one by WKNN algorithm
Weights, calculate the sum of the sampling point position coordinate after this K weighting, i.e. weighting and are averaging, as the elements of a fix, i.e.In formula, (x y) is the elements of a fix that draw of system, (xi,yi)
For the position coordinates of ith sample point, wiFor weight coefficient, diEuropean for tested point real time fingerprint and ith sample point fingerprint
Distance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610220583.8A CN105933975A (en) | 2016-04-11 | 2016-04-11 | WiFi fingerprint-based accuracy improved indoor positioning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610220583.8A CN105933975A (en) | 2016-04-11 | 2016-04-11 | WiFi fingerprint-based accuracy improved indoor positioning method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105933975A true CN105933975A (en) | 2016-09-07 |
Family
ID=56840168
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610220583.8A Pending CN105933975A (en) | 2016-04-11 | 2016-04-11 | WiFi fingerprint-based accuracy improved indoor positioning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105933975A (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106646366A (en) * | 2016-12-05 | 2017-05-10 | 深圳市国华光电科技有限公司 | Visible light positioning method and system based on particle filter algorithm and intelligent equipment |
CN106646339A (en) * | 2017-01-06 | 2017-05-10 | 重庆邮电大学 | Online matching and positioning method in wireless position fingerprint indoor positioning |
CN106792554A (en) * | 2016-11-23 | 2017-05-31 | 长安大学 | A kind of localization method based on Dual Matching fingerprint location technology |
CN107222851A (en) * | 2017-04-07 | 2017-09-29 | 南京邮电大学 | A kind of method of utilization difference secret protection Wifi Fingerprint indoor locating system privacies |
CN107843260A (en) * | 2017-10-27 | 2018-03-27 | 上海工程技术大学 | A kind of low-altitude unmanned vehicle positioning navigation method based on electromagnetism finger print information |
CN108632763A (en) * | 2018-03-07 | 2018-10-09 | 电子科技大学 | A kind of indoor positioning weighting k nearest neighbor method based on WiFi fingerprints |
CN108761435A (en) * | 2018-04-25 | 2018-11-06 | 西安交通大学 | A kind of fingerprint optimization method based on normal distribution signal |
CN108989976A (en) * | 2018-06-04 | 2018-12-11 | 华中师范大学 | Fingerprint positioning method and system in a kind of wisdom classroom |
CN109239659A (en) * | 2018-08-31 | 2019-01-18 | 平安科技(深圳)有限公司 | Indoor navigation method, device, computer equipment and storage medium |
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 |
CN110087188A (en) * | 2019-04-25 | 2019-08-02 | 中山大学 | The virtual finger print data base construction method of indoor positioning based on RFID label tag |
CN110231592A (en) * | 2019-04-11 | 2019-09-13 | 深圳市城市交通规划设计研究中心有限公司 | Indoor orientation method, device, computer readable storage medium and terminal device |
CN110602651A (en) * | 2019-09-20 | 2019-12-20 | 北京智芯微电子科技有限公司 | Positioning method based on WIFI position fingerprint and positioning system of robot |
CN112394321A (en) * | 2021-01-21 | 2021-02-23 | 上海磐启微电子有限公司 | Multi-base-station real-time positioning method and system based on Bluetooth signals |
CN112399366A (en) * | 2020-05-27 | 2021-02-23 | 南京邮电大学 | Indoor positioning method based on Hankel matrix and WKNN variance extraction |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102802260A (en) * | 2012-08-15 | 2012-11-28 | 哈尔滨工业大学 | WLAN indoor positioning method based on matrix correlation |
CN103679118A (en) * | 2012-09-07 | 2014-03-26 | 汉王科技股份有限公司 | Human face in-vivo detection method and system |
CN104780606A (en) * | 2015-03-30 | 2015-07-15 | 南京邮电大学 | Indoor positioning system and method based on WLAN (wireless local area network) |
GB2530106A (en) * | 2014-09-11 | 2016-03-16 | Tracy Buckland | Vital Pad + |
CN105472733A (en) * | 2015-11-17 | 2016-04-06 | 华南理工大学 | Indoor positioning method based on AP selection |
-
2016
- 2016-04-11 CN CN201610220583.8A patent/CN105933975A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102802260A (en) * | 2012-08-15 | 2012-11-28 | 哈尔滨工业大学 | WLAN indoor positioning method based on matrix correlation |
CN103679118A (en) * | 2012-09-07 | 2014-03-26 | 汉王科技股份有限公司 | Human face in-vivo detection method and system |
GB2530106A (en) * | 2014-09-11 | 2016-03-16 | Tracy Buckland | Vital Pad + |
CN104780606A (en) * | 2015-03-30 | 2015-07-15 | 南京邮电大学 | Indoor positioning system and method based on WLAN (wireless local area network) |
CN105472733A (en) * | 2015-11-17 | 2016-04-06 | 华南理工大学 | Indoor positioning method based on AP selection |
Non-Patent Citations (2)
Title |
---|
刘志达: "智能手机室内定位技术的研究与实现", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
刘腾飞: "wifi网络下的室内定位算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106792554A (en) * | 2016-11-23 | 2017-05-31 | 长安大学 | A kind of localization method based on Dual Matching fingerprint location technology |
CN106646366A (en) * | 2016-12-05 | 2017-05-10 | 深圳市国华光电科技有限公司 | Visible light positioning method and system based on particle filter algorithm and intelligent equipment |
CN106646339A (en) * | 2017-01-06 | 2017-05-10 | 重庆邮电大学 | Online matching and positioning method in wireless position fingerprint indoor positioning |
CN107222851B (en) * | 2017-04-07 | 2020-04-14 | 南京邮电大学 | Method for protecting privacy of Wifi finger rprint indoor positioning system by using differential privacy |
CN107222851A (en) * | 2017-04-07 | 2017-09-29 | 南京邮电大学 | A kind of method of utilization difference secret protection Wifi Fingerprint indoor locating system privacies |
CN107843260A (en) * | 2017-10-27 | 2018-03-27 | 上海工程技术大学 | A kind of low-altitude unmanned vehicle positioning navigation method based on electromagnetism finger print information |
CN108632763A (en) * | 2018-03-07 | 2018-10-09 | 电子科技大学 | A kind of indoor positioning weighting k nearest neighbor method based on WiFi fingerprints |
CN108761435A (en) * | 2018-04-25 | 2018-11-06 | 西安交通大学 | A kind of fingerprint optimization method based on normal distribution signal |
CN108989976A (en) * | 2018-06-04 | 2018-12-11 | 华中师范大学 | Fingerprint positioning method and system in a kind of wisdom classroom |
CN108989976B (en) * | 2018-06-04 | 2020-09-11 | 华中师范大学 | Fingerprint positioning method and system in intelligent classroom |
CN109239659A (en) * | 2018-08-31 | 2019-01-18 | 平安科技(深圳)有限公司 | Indoor navigation method, device, computer equipment and storage medium |
CN109239659B (en) * | 2018-08-31 | 2023-12-15 | 平安科技(深圳)有限公司 | Indoor navigation method, device, computer equipment and storage medium |
CN110231592A (en) * | 2019-04-11 | 2019-09-13 | 深圳市城市交通规划设计研究中心有限公司 | Indoor orientation method, device, computer readable storage medium and terminal device |
CN110087188A (en) * | 2019-04-25 | 2019-08-02 | 中山大学 | The virtual finger print data base construction method of indoor positioning based on RFID label tag |
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 |
CN110602651A (en) * | 2019-09-20 | 2019-12-20 | 北京智芯微电子科技有限公司 | Positioning method based on WIFI position fingerprint and positioning system of robot |
CN110602651B (en) * | 2019-09-20 | 2022-02-01 | 北京智芯微电子科技有限公司 | Positioning method based on WIFI position fingerprint and positioning system of robot |
CN112399366A (en) * | 2020-05-27 | 2021-02-23 | 南京邮电大学 | Indoor positioning method based on Hankel matrix and WKNN variance extraction |
CN112394321A (en) * | 2021-01-21 | 2021-02-23 | 上海磐启微电子有限公司 | Multi-base-station real-time positioning method and system based on Bluetooth signals |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105933975A (en) | WiFi fingerprint-based accuracy improved indoor positioning method | |
CN106131959B (en) | A kind of dual-positioning method divided based on Wi-Fi signal space | |
CN103796305B (en) | Indoor positioning method based on Wi-Fi position fingerprint | |
CN106093852A (en) | A kind of method improving WiFi fingerprint location precision and efficiency | |
CN103905992B (en) | Indoor positioning method based on wireless sensor networks of fingerprint data | |
CN103455811B (en) | Indoor wireless locating fingerprint collection method and system | |
CN106658704A (en) | Positioning method and system of starting point of indoor positioning | |
CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
CN107182036A (en) | The adaptive location fingerprint positioning method merged based on multidimensional characteristic | |
CN105813194A (en) | Indoor positioning method based on fingerprint database secondary correction | |
CN103916820A (en) | Wireless indoor locating method based on access point stability degree | |
CN109640269A (en) | Fingerprint positioning method based on CSI Yu Time Domain Fusion algorithm | |
CN102695272B (en) | Matching location method and mobile terminal | |
CN107677989B (en) | A kind of indoor location localization method carrying out RSSI removal noise based on RSSI maximum value | |
CN104754735B (en) | Localization method based on location fingerprint storehouse | |
CN106646339A (en) | Online matching and positioning method in wireless position fingerprint indoor positioning | |
CN110213710A (en) | A kind of high-performance indoor orientation method, indoor locating system based on random forest | |
CN108966131A (en) | Fusion floor estimating method based on indoor positioning | |
CN105208651A (en) | Wi-Fi position fingerprint non-monitoring training method based on map structure | |
CN109348416A (en) | Fingerprint indoor orientation method based on two points of k mean values | |
CN104333906A (en) | Positioning system and method based on indoor wireless signal | |
CN108566620B (en) | Indoor positioning method based on WIFI | |
CN106793085A (en) | Fingerprint positioning method based on normality assumption inspection | |
Zhong et al. | WiFi indoor localization based on K-means | |
CN106954190A (en) | A kind of WIFI indoor orientation methods based on index mapping domain |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160907 |
|
RJ01 | Rejection of invention patent application after publication |