CN110300372A - A kind of WIFI indoor orientation method based on location fingerprint - Google Patents
A kind of WIFI indoor orientation method based on location fingerprint Download PDFInfo
- Publication number
- CN110300372A CN110300372A CN201910624811.1A CN201910624811A CN110300372A CN 110300372 A CN110300372 A CN 110300372A CN 201910624811 A CN201910624811 A CN 201910624811A CN 110300372 A CN110300372 A CN 110300372A
- Authority
- CN
- China
- Prior art keywords
- wifi
- algorithm
- location fingerprint
- initial
- rssi
- 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
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/318—Received signal strength
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- 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
Abstract
The invention discloses a kind of WIFI indoor orientation method based on location fingerprint, steps of the method are: (1) experimental situation is built, WIFI location fingerprint library is established;(2) position location WIFI fingerprint base is established;(3) using improvedK- means clustering algorithm calculates initial cluster center;(4) optimal initial cluster center is calculated;(5) it determinesKThe optimum clustering number of-means clustering algorithmK;(6) it combines WKNN algorithm to calculate target position and exports target position.The present invention reduces positioning stage calculation amount while improving positioning accuracy, has the characteristics that positioning accuracy is high, noise resisting ability is strong, stability is good, time complexity is low, realizes requirement of real time under the premise of guaranteeing positioning accuracy.
Description
Technical field
The present invention relates to indoor positioning technologies fields, and in particular to a kind of indoor positioning side WIFI based on location fingerprint
Method.
Background technique
With the fast development of computer network and mobile intelligent terminal technology, based on indoor location service (LBS) by
Extensive concern.Indoor positioning technologies based on WIFI have the advantages that simple, low cost, high-precision, robustness, scalability,
As a kind of indoor positioning solution and be widely used.But due to the complexity of indoor environment, RSSI shows height
The precision of the complexity and variability of degree, WIFI indoor positioning is highly susceptible to the influence of environmental factor.Typical other interiors
Localization method has bluetooth, infrared ray, ultra wide band, earth magnetism, RFID, ZigBe and ultrasonic wave etc..But infrared ray, ultra wide band, RFID,
The indoor positioning technologies such as ZigBee and ultrasonic wave need additional reception and transmitting equipment, and these increased use costs, and
Reduce the convenience of positioning.Indoor positioning technologies based on bluetooth are highly-safe, at low cost, low in energy consumption, equipment volume is small, mesh
The preceding all included bluetooth module of major part mobile phone terminal, is easy universal on a large scale and deployment and implements, but the technology be easy by
The disadvantages of interference of external noise signals, signal stabilization is poor, and communication range is smaller.Currently used WIFI location technology,
Simple location requirement can be substantially met, for complicated, changeable indoor environment, WIFI location technology is easily affected by environment, leads
Cause positioning accuracy not high.
Summary of the invention
In view of the above-mentioned deficiencies in the prior art, it is an object of the present invention to and provide it is fixed in a kind of room WIFI based on location fingerprint
Position method, this method reduce positioning stage calculation amount while improving positioning accuracy, have positioning accuracy height, noise resisting ability
By force, the feature that stability is good, time complexity is low realizes requirement of real time under the premise of guaranteeing positioning accuracy.
Realizing the technical solution of the object of the invention is:
A kind of WIFI indoor orientation method based on location fingerprint, includes the following steps:
(1) experimental situation is built, establishes WIFI location fingerprint library, detailed process is as follows:
Offline positioning stage, experiment scene are arranged in rectangular room area, at four of the rectangular chamber inner region
Corner and the midpoint of two long sides are evenly arranged six WIFI signal AP, and the sampling interval of reference point RP is set as 2 meters, use
Android mobile phone terminal is established in the received signal strength index RSSI of the collected AP of each RP point based on the initial of RSSI
Location fingerprint database;
(2) position location WIFI fingerprint base is established, detailed process is as follows:
Initial position fingerprint database satisfaction based on RSSI is just distributed very much, by Gaussian filter algorithm to based on RSSI's
Initial position fingerprint database is pre-processed, and a large amount of redundancy can be effectively filtered out, and reduces ambient noise factor in fingerprint
Acquisition phase is interfered caused by RSSI, is obtained one group than more gentle RSSI fingerprint base numerical value, is established WIFI using the numerical value
Position location fingerprint base;
(3) improved K-means clustering algorithm calculates initial cluster center, and detailed process is as follows:
Clustering processing is carried out to the position location WIFI fingerprint base using improved K-means clustering algorithm, fingerprint can be reduced
The calculation amount of matching algorithm, location algorithm falls into locally optimal solution when avoiding positioning in real time;Improved K-means clustering algorithm is adopted
With the clustering criteria function of ε of optimization, the expression formula of function of ε isM is the total number of data object, and K is subset
Number, σiFor the standard deviation of i-th of subclass, miThe number of data object in i-th of subclass is represented, and uses cluster centre
Searching algorithm obtains preferably initial cluster center;
(4) optimal initial cluster center is calculated
J sub-sampling is taken to the center of initially birdsing of the same feather flock together that step (3) obtain, the sample set size extracted every time should be able to be packed into
Main memory, the sum of sample set of J extraction are equal to raw data set, K-means are respectively adopted for the sample data extracted every time
Clustering algorithm is clustered, corresponding to generate a group cluster center respectively, at J group cluster center, then again J sub-sampling operates symbiosis
The comparison of clustering criteria functional value is carried out to J group cluster center, functional value the smallest group cluster center is optimal initial clustering
Center;
(5) the optimum clustering number K of K-means clustering algorithm is determined, detailed process is as follows:
It improves K-means algorithm and sets initial clustering number as k ' (k ' > K), biggish k ' value can expand searching for solution space
Rope range avoids the occurrence of the phenomenon that certain Near The Extreme Points are without initial value, using the initial cluster center searched, uses K- again
Means clustering algorithm clusters raw data set and exports a cluster centre of k ', then between more each cluster centre
Until the number of distance, the closest subclass in agglomerative clustering center, the subclass after merging is reduced to specified K value;
(6) it combines WKNN algorithm to calculate target position and exports target position, detailed process is as follows:
Weighting coefficient is respectively allocated to corresponding reference point RP using Orientation and Matching Algorithm WKNN by the tuning on-line stage
Coordinate is set, has the characteristics that positioning result is stable, the weight coefficient ω of WKNNiFor distinguishing different fingerprints in position matching
Significance level, the position coordinates specific formula for calculation of reference point are as follows:
Wherein xi、yiFor reference point coordinate, K is the K fingerprint reference point closest with node to be measured, ωiIt is close for i-th
The weight of adjoint point, it is ensured that the RSSI measured in real time smaller reference point locations coordinate its weight is bigger, can be in certain journey
The precision of positioning system is improved on degree.
The utility model has the advantages that a kind of WIFI indoor orientation method based on location fingerprint provided by the invention, this method are improving
Positioning stage calculation amount is reduced while positioning accuracy, with the spy that positioning accuracy is high, software operand is low, anti-noise ability is strong
Point realizes requirement of real time under the premise of guaranteeing positioning accuracy.
Detailed description of the invention
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is that schematic diagram is arranged in laboratory experiment environment of the invention;
Fig. 3 is the location fingerprint system schematic of the invention based on WIFI.
Specific embodiment
A specific embodiment of the invention is further described with reference to the accompanying drawing, but is not to limit of the invention
It is fixed.
As shown in Figure 1, a kind of WIFI indoor orientation method based on location fingerprint, includes the following steps:
A kind of WIFI indoor orientation method based on location fingerprint, includes the following steps:
(1) experimental situation is built, establishes WIFI location fingerprint library, detailed process is as follows:
Offline positioning stage, rectangular room area of the experiment scene setting at 12 × 8 square metres, in the rectangular chamber
Four corners of inner region and the midpoint of two long sides are evenly arranged six WIFI signal AP, and the sampling interval of reference point RP sets
2 meters are set to, using Android mobile phone terminal in the received signal strength index RSSI of the collected AP of each RP point, establishes base
In the initial position fingerprint database of RSSI.
(2) Gaussian filter algorithm is combined, establishes the position location WIFI fingerprint base, detailed process is as follows:
Initial position fingerprint database satisfaction based on RSSI is just distributed very much, by Gaussian filter algorithm to based on RSSI's
Initial position fingerprint database is pre-processed, and a large amount of redundancy can be effectively filtered out, and reduces ambient noise factor in fingerprint
Acquisition phase is interfered caused by RSSI, is obtained one group than more gentle RSSI fingerprint base numerical value, is established WIFI using the numerical value
Position location fingerprint base;
If RSSI meets the Gaussian Profile that mean value is μ, standard deviation is σ, for RSSIiI-th of fingerprint signal intensity value, then
Shown in the following formula of the density function of RSSI:
Wherein
M represents the quantity of RSSI in above-mentioned formula, and σ is bigger, and the smooth degree of gaussian filtering is better, selects density function f
(x) it is greater than the value of 0.6 (empirical value), shown in following formula:
0.6≤f(x)≤1
0.15σ+μ≤x≤3.09σ+μ
Meet RSSI in above-mentioned formula all to retain, geometrical mean is asked to it, the fingerprint base RSSI needed for you can get it,
Location fingerprint library is as shown in Figure 3;
(3) mapping relations between fingerprint signal and position are established using improved K-means clustering algorithm, calculated initial
Cluster centre, detailed process is as follows:
Clustering processing is carried out to the position location WIFI fingerprint base using improved K-means clustering algorithm, fingerprint can be reduced
The calculation amount of matching algorithm, location algorithm falls into locally optimal solution when avoiding positioning in real time;Improved K-means clustering algorithm is adopted
With the clustering criteria function of ε of optimization, the expression formula of function of ε isM is the total number of data object, and K is subset
Number, σiFor the standard deviation of i-th of subclass, miThe number of data object in i-th of subclass is represented, and uses cluster centre
Searching algorithm obtains preferably initial cluster center.
(4) mapping relations between fingerprint signal and position are established using improved K-means clustering algorithm, calculated optimal
Initial cluster center, detailed process is as follows:
J sub-sampling is taken to the center of initially birdsing of the same feather flock together that step (3) obtain, the sample set size extracted every time should be able to be packed into
Main memory, the sum of sample set of J extraction are equal to raw data set, K-means are respectively adopted for the sample data extracted every time
Clustering algorithm is clustered, corresponding to generate a group cluster center respectively, at J group cluster center, then again J sub-sampling operates symbiosis
The comparison of clustering criteria functional value is carried out to J group cluster center, functional value the smallest group cluster center is optimal initial clustering
Center.
(5) mapping relations between fingerprint signal and position are established using improved K-means clustering algorithm, determines K-
The optimum clustering number K of means clustering algorithm, detailed process is as follows:
It improves K-means algorithm and sets initial clustering number as k ' (k ' > K), biggish k ' value can expand searching for solution space
Rope range avoids the occurrence of the phenomenon that certain Near The Extreme Points are without initial value.Using the initial cluster center searched, K- is used again
Means clustering algorithm clusters raw data set and exports a cluster centre of k ', then between more each cluster centre
Distance.Until the number of the closest subclass in agglomerative clustering center, the subclass after merging is reduced to specified K value.
(6) it combines WKNN algorithm to calculate target position and exports target position, detailed process is as follows:
Weighting coefficient is respectively allocated to corresponding reference point RP using Orientation and Matching Algorithm WKNN by the tuning on-line stage
Coordinate is set, has the characteristics that positioning result is stable, specific calculating is as follows:
Wherein, RSSIijIt is j-th of element in ith cluster, RSSIiIt is the RSSI mean value of ith cluster.N is cluster
The number of middle element, diTo cluster i (RSSIi) in RSSI value standard deviation, σiShow more greatly to cluster i (RSSIi) in it is most of
RSSI value and its mean value (RSSIi) between differ greatly, it is on the contrary then difference is smaller, RiThe RSSI of cluster i is characterized for coefficient of dispersion
It is worth standard deviation sigmaiDiscretization degree between the RSSI mean value of cluster i;The weight coefficient ω of WKNNiFor distinguishing different fingerprints
Significance level in position matching, the position coordinates specific formula for calculation of reference point are as follows:
Wherein xi、yiFor reference point coordinate, K is the K fingerprint reference point closest with node to be measured, ωiIt is close for i-th
The weight of adjoint point, it is ensured that the RSSI measured in real time smaller reference point locations coordinate its weight is bigger, can be in certain journey
The precision of positioning system is improved on degree.
Claims (7)
1. a kind of WIFI indoor orientation method based on location fingerprint, which comprises the steps of:
(1) experimental situation is built, WIFI location fingerprint library is established;
(2) position location WIFI fingerprint base is established;
(3) initial cluster center is calculated using improved K-means clustering algorithm;
(4) optimal initial cluster center is calculated;
(5) the optimum clustering number K of K-means clustering algorithm is determined;
(6) it combines WKNN algorithm to calculate target position and exports target position.
2. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (1) detailed process is as follows:
Offline positioning stage, experiment scene are arranged in rectangular room area, in four corners of the rectangular chamber inner region
And the midpoint of two long sides is evenly arranged six WIFI signal AP, the sampling interval of reference point RP is set as 2 meters, uses
Android mobile phone terminal is established in the received signal strength index RSSI of the collected AP of each RP point based on the initial of RSSI
Location fingerprint database.
3. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (2) detailed process is as follows:
Initial position fingerprint database satisfaction based on RSSI is just distributed very much, by Gaussian filter algorithm to based on the initial of RSSI
Location fingerprint database is pre-processed, and is obtained one group than more gentle RSSI fingerprint base numerical value, is established WIFI using the numerical value
Position location fingerprint base.
4. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (3) detailed process is as follows:
Clustering processing is carried out to the position location WIFI fingerprint base using improved K-means clustering algorithm, improved K-means is poly-
Class algorithm uses the clustering criteria function of ε of optimization, and the expression formula of function of ε isM is the total number of data object,
K is the number of subset, σiFor the standard deviation of i-th of subclass, miThe number of data object in i-th of subclass is represented, and uses cluster
The searching algorithm at center obtains preferably initial cluster center.
5. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (4) detailed process is as follows:
J sub-sampling is taken to the center of initially birdsing of the same feather flock together that step (3) obtain, the sample set size extracted every time should be able to be packed into master
It deposits, the sum of sample set of J extraction is equal to raw data set, and it is poly- that K-means is respectively adopted for the sample data extracted every time
Class algorithm is clustered, corresponding to generate a group cluster center respectively, and the operation symbiosis of J sub-sampling is then right again at J group cluster center
J group cluster center carries out the comparison of clustering criteria functional value, and functional value the smallest group cluster center is in optimal initial clustering
The heart.
6. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (5) detailed process is as follows:
It improves K-means algorithm and sets initial clustering number as k ' (k ' > K), biggish k ' value can expand the search model of solution space
It encloses, avoids the occurrence of the phenomenon that certain Near The Extreme Points are without initial value, using the initial cluster center searched, use K- again
Means clustering algorithm clusters raw data set and exports a cluster centre of k ', then between more each cluster centre
Until the number of distance, the closest subclass in agglomerative clustering center, the subclass after merging is reduced to specified K value.
7. a kind of WIFI indoor orientation method based on location fingerprint according to claim 1, which is characterized in that the step
Suddenly (5) detailed process is as follows:
Weighting coefficient is respectively allocated to the position corresponding reference point RP using Orientation and Matching Algorithm WKNN and sat by the tuning on-line stage
Mark, has the characteristics that positioning result is stable, the weight coefficient ω of WKNNiIt is important in position matching for distinguishing different fingerprints
Degree, the position coordinates specific formula for calculation of reference point are as follows:
Wherein xi、yiFor reference point coordinate, K is the K fingerprint reference point closest with node to be measured, ωiFor i-th of Neighbor Points
Weight, it is ensured that the RSSI measured in real time smaller reference point locations coordinate its weight is bigger, can be to a certain extent
Improve the precision of positioning system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624811.1A CN110300372A (en) | 2019-07-11 | 2019-07-11 | A kind of WIFI indoor orientation method based on location fingerprint |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910624811.1A CN110300372A (en) | 2019-07-11 | 2019-07-11 | A kind of WIFI indoor orientation method based on location fingerprint |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110300372A true CN110300372A (en) | 2019-10-01 |
Family
ID=68030930
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910624811.1A Pending CN110300372A (en) | 2019-07-11 | 2019-07-11 | A kind of WIFI indoor orientation method based on location fingerprint |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110300372A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110958583A (en) * | 2019-10-31 | 2020-04-03 | 西南科技大学 | Indoor positioning method based on position and strength dual clustering |
CN112714493A (en) * | 2020-12-29 | 2021-04-27 | 北京工业大学 | Object position positioning method and positioning system |
CN112887904A (en) * | 2021-01-27 | 2021-06-01 | 电子科技大学 | WiFi positioning method suitable for intelligent stadium |
CN112966567A (en) * | 2021-02-05 | 2021-06-15 | 深圳市品致信息科技有限公司 | Coordinate positioning method, system, storage medium and terminal based on PCA (principal component analysis), clustering and K nearest neighbor |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090247185A1 (en) * | 2008-03-31 | 2009-10-01 | Kutiel Gilad | Cluster-based fingerprinting algorithms |
CN102821465A (en) * | 2012-09-07 | 2012-12-12 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor positioning method based on subregion information entropy gain |
CN104853434A (en) * | 2015-01-13 | 2015-08-19 | 中山大学 | Indoor positioning method based on SVM and K mean value clustering algorithm |
CN107517446A (en) * | 2017-09-28 | 2017-12-26 | 知谷(上海)网络科技有限公司 | Indoor orientation method and device based on Wi Fi focuses |
CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
CN109362036A (en) * | 2018-10-17 | 2019-02-19 | 桂林电子科技大学 | A kind of multi-modal indoor orientation method combined based on image with WIFI |
CN109511085A (en) * | 2018-10-29 | 2019-03-22 | 中国矿业大学 | A kind of UWB fingerprint positioning method based on MeanShift and weighting k nearest neighbor algorithm |
-
2019
- 2019-07-11 CN CN201910624811.1A patent/CN110300372A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090247185A1 (en) * | 2008-03-31 | 2009-10-01 | Kutiel Gilad | Cluster-based fingerprinting algorithms |
CN102821465A (en) * | 2012-09-07 | 2012-12-12 | 哈尔滨工业大学 | WLAN (Wireless Local Area Network) indoor positioning method based on subregion information entropy gain |
CN104853434A (en) * | 2015-01-13 | 2015-08-19 | 中山大学 | Indoor positioning method based on SVM and K mean value clustering algorithm |
CN107517446A (en) * | 2017-09-28 | 2017-12-26 | 知谷(上海)网络科技有限公司 | Indoor orientation method and device based on Wi Fi focuses |
CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
CN109362036A (en) * | 2018-10-17 | 2019-02-19 | 桂林电子科技大学 | A kind of multi-modal indoor orientation method combined based on image with WIFI |
CN109511085A (en) * | 2018-10-29 | 2019-03-22 | 中国矿业大学 | A kind of UWB fingerprint positioning method based on MeanShift and weighting k nearest neighbor algorithm |
Non-Patent Citations (1)
Title |
---|
张雪凤等: "基于聚类准则函数的改进K-means算法", 《计算机工程与应用》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110958583A (en) * | 2019-10-31 | 2020-04-03 | 西南科技大学 | Indoor positioning method based on position and strength dual clustering |
CN110958583B (en) * | 2019-10-31 | 2021-02-09 | 西南科技大学 | Indoor positioning method based on position and strength dual clustering |
CN112714493A (en) * | 2020-12-29 | 2021-04-27 | 北京工业大学 | Object position positioning method and positioning system |
CN112714493B (en) * | 2020-12-29 | 2023-03-24 | 北京工业大学 | Object position positioning method and positioning system |
CN112887904A (en) * | 2021-01-27 | 2021-06-01 | 电子科技大学 | WiFi positioning method suitable for intelligent stadium |
CN112966567A (en) * | 2021-02-05 | 2021-06-15 | 深圳市品致信息科技有限公司 | Coordinate positioning method, system, storage medium and terminal based on PCA (principal component analysis), clustering and K nearest neighbor |
CN112966567B (en) * | 2021-02-05 | 2021-12-10 | 深圳市品致信息科技有限公司 | Coordinate positioning method and system based on PCA (principal component analysis), clustering and K nearest neighbor |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110300372A (en) | A kind of WIFI indoor orientation method based on location fingerprint | |
CN108989976B (en) | Fingerprint positioning method and system in intelligent classroom | |
Peng et al. | An iterative weighted KNN (IW-KNN) based indoor localization method in bluetooth low energy (BLE) environment | |
CN104936148B (en) | A kind of WIFI indoor orientation methods based on fuzzy KNN | |
Zhang et al. | DeepPositioning: Intelligent fusion of pervasive magnetic field and WiFi fingerprinting for smartphone indoor localization via deep learning | |
CN113064117B (en) | Radiation source positioning method and device based on deep learning | |
CN108594170B (en) | WIFI indoor positioning method based on convolutional neural network identification technology | |
CN103476118A (en) | WLAN indoor location fingerprint positioning method used for real-time monitoring | |
CN109275095A (en) | A kind of indoor locating system based on bluetooth, positioning device and localization method | |
CN110536256B (en) | Indoor positioning method based on double-layer grids | |
Huang et al. | An accurate and efficient device-free localization approach based on sparse coding in subspace | |
Lei et al. | Fingerprint-based device-free localization in changing environments using enhanced channel selection and logistic regression | |
Peng et al. | Deep convolutional neural network for passive RFID tag localization via joint RSSI and PDOA fingerprint features | |
CN110536245A (en) | A kind of indoor wireless positioning method and system based on deep learning | |
CN103220777A (en) | Mobile device positioning system | |
Li et al. | Smartphone-based indoor localization with integrated fingerprint signal | |
CN111901749A (en) | High-precision three-dimensional indoor positioning method based on multi-source fusion | |
CN108225332B (en) | Indoor positioning fingerprint map dimension reduction method based on supervision | |
Zhong et al. | WiFi indoor localization based on K-means | |
CN106686722A (en) | Large-scale indoor environment positioning micro base station based on CSS (cascading style sheets) technology and operating method thereof | |
CN113596989A (en) | Indoor positioning method and system for intelligent workshop | |
Yang et al. | An indoor RFID location algorithm based on support vector regression and particle swarm optimization | |
Chen et al. | A wifi indoor localization method based on dilated cnn and support vector regression | |
CN109541537B (en) | Universal indoor positioning method based on ranging | |
Liu et al. | CTSLoc: An indoor localization method based on CNN by using time-series RSSI |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |