CN112261578B - Indoor fingerprint positioning method based on mode filtering - Google Patents
Indoor fingerprint positioning method based on mode filtering Download PDFInfo
- Publication number
- CN112261578B CN112261578B CN202011132650.3A CN202011132650A CN112261578B CN 112261578 B CN112261578 B CN 112261578B CN 202011132650 A CN202011132650 A CN 202011132650A CN 112261578 B CN112261578 B CN 112261578B
- Authority
- CN
- China
- Prior art keywords
- rssi
- data
- filtering
- fingerprint
- indoor
- 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses an indoor fingerprint positioning method based on mode filtering, which comprises the following steps of S1-S6; the invention fully utilizes the distribution characteristics of RSSI data, improves the quality of the fingerprint database relative to the average filtering and ensures the operation efficiency; compared with a single filtering method, the invention provides a novel RSSI data processing method, applies the mode to the filtering method for the first time, and provides a new idea for subsequent research; compared with the prior art, the method can avoid the RSSI ranging problem based on the Received Signal Strength (RSSI) position fingerprint positioning algorithm, and can construct a high-quality fingerprint database through filtering processing. Aiming at the problems of long operation time of Gaussian filtering, large positioning error of mean filtering and the like, the operation efficiency is superior to that of Gaussian filtering, and meanwhile, compared with mean filtering, mode filtering improves the positioning precision by about 0.15m, the maximum positioning error is limited within 2m under the condition of 95%, and the quality of a fingerprint database can be effectively improved.
Description
Technical Field
The invention belongs to the technical field of position fingerprint positioning with low indoor space complexity, and particularly relates to an indoor fingerprint positioning method based on modal filtering.
Background
With the rapid development of Wireless Local Area Network (WLAN) technology and the wide deployment of WLAN in the world, a location positioning technology based on WLAN coverage becomes a hot spot for location service research in indoor environment. The position service based on the wireless local area network has the characteristics of simple realization, wide coverage range, high application integration level and the like, and can realize higher positioning precision; the location positioning technique using the wireless lan includes a variety of methods, among which there are mainly the strongest base station method, time of arrival (TOA) of a signal, angle of arrival (AOA) of a signal, time difference of arrival (TDOA) of a signal, and signal strength measurement. The indoor positioning based on the signal intensity also comprises a transmission loss method and a fingerprint positioning method, and the transmission loss method causes the problem of positioning accuracy due to the multipath effect generated by the through-wall of WLAN air signals and other reasons; the fingerprint positioning method can directly utilize the existing WLAN wireless environment, and can realize positioning without changing hardware equipment to carry out time synchronization and angle measurement, so that the environmental adaptability is strong, the cost is low, and the method becomes a hotspot of the research of domestic and foreign communication industries; meanwhile, the RSSI (Received Signal Strength Indicator) based position fingerprint positioning algorithm can avoid the RSSI ranging problem, and a high-quality fingerprint database can be constructed through filtering processing.
The so-called fingerprint positioning method comprises two stages of off-line detection and on-line positioning. The off-line detection is to plan and set a plurality of sampling points in a certain range, and store the information of the sampling points and the sampled signal strength into a database, which is a position fingerprint database. In the on-line positioning stage, the strength of the acquired signals is compared with the fingerprints stored in the database so as to determine the position. Various algorithms for determining the position are proposed at present, mainly a data correlation method is adopted, but the existing fingerprint positioning method has the defects that the number of sampling points participating in the calculation of the data correlation method is large, the calculation workload is large, and high positioning precision cannot be realized;
therefore, it is necessary to provide an indoor fingerprint positioning method based on mode filtering, which comprehensively considers the operation efficiency and the positioning accuracy.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and the invention fully utilizes the distribution characteristics of RSSI data, improves the quality of a fingerprint database relative to average filtering, and ensures the operation efficiency; compared with a single filtering method, the invention provides a novel RSSI data processing method, applies the mode to the filtering method for the first time, and provides a new idea for subsequent research; the invention can avoid RSSI ranging problem based on the Received Signal Strength (RSSI) position fingerprint positioning algorithm, and can construct a high-quality fingerprint database through filtering processing. Aiming at the problems that the Gaussian filtering operation time is long and the average filtering positioning error is large, a mode filtering method is provided based on the characteristic that partial RSSI repeatedly appears by analyzing the distribution rule of the RSSI, the mode in the current data is selected successively, and the characteristic RSSI is extracted by averaging until the ratio of the accumulated frequency sum of the selected mode to the total data amount is greater than 95%, so that the indoor fingerprint positioning method based on the mode filtering is provided.
In order to achieve the purpose, the invention provides the following technical scheme:
the indoor fingerprint positioning method based on mode filtering comprises the following steps:
s1, according to indoor wireless signal propagation characteristics, RSSI is removed by using a box plot method i An abnormal data value in the sequence;
s2, counting the total amount of RSSI data, establishing statistics of frequency numbers and mode numbers of each group, and initializing an optimal data ratio Z;
s3, selecting the RSSI with high frequency by using the optimal data ratio Z to carry out mean filtering to calculate the characteristic value of the RSSI group;
s4, constructing a fingerprint database based on the RSSI characteristic values and the position coordinates of the corresponding reference points;
s5, selecting an optimal data ratio Z by using an exhaustion method;
s6, solving the position of the indoor undetermined point based on the optimal fingerprint database through a WKNN (Weighted K-Nearest Neighbor) algorithm.
Preferably, the step S1 includes the steps of:
s1.1, forming a sequence by RSSI data collected from various known reference points indoors;
s1.2, carrying out abnormal value detection on each group of data through a boxplot: if an abnormal value exists, replacing the abnormal value by a front and back mean value; otherwise, the next step is performed.
Preferably, the step S2 is: and creating statistics for each reference point to receive RSSI data of each indoor wireless signal transmitting station, recording the total amount of each group of RSSI data as N, and initializing a data ratio Z =0.6.
Preferably, the step S3 includes the steps of:
s3.1, recording current RSSI sequence mode RSSI i And frequency m thereof, K = K +1, P = P + m, the data ratio Z = P/N is calculated;
s3.2, removing the RSSI in the current sequence i Forming a new RSSI sequence;
s3.3, judging whether the mode filtering search Z is less than P/N and meets the stop condition: if yes, continuing to perform step S2; otherwise, returning to the step S3.2;
and S3.4, calculating the arithmetic mean value of the RSSI with the frequency arranged at the first K of the array as the characteristic value of the group of RSSI.
Preferably, the step S4 is: calculating characteristic values of all known indoor reference points by using a mode filtering method based on the initial data ratio Z to form fingerprint data; obtaining position coordinates (X, Y) of all indoor reference points by a measuring method; combining the fingerprint data and the position coordinates together to construct a fingerprint database.
Preferably, the step S5 includes the steps of:
s5.1, selecting 0.05 as an exhaustion step length, and enabling Z = Z +0.05;
s5.2, resetting the frequency number accumulation statistic P, selecting the mode number accumulation K and the total RSSI data quantity N, and enabling P =0, K =0 and N to be the number of the current RSSI array;
s5.3, repeating the step S4, and establishing a fingerprint database based on the current Z value;
s5.4, calculating the error in the current positioning through a WKNN algorithm;
s5.5, judging whether the exhaustive list Z =1 and meeting the stopping condition: if yes, continuing to step S5.6; otherwise, returning to the step S5.1;
and S5.6, comparing the total positioning errors of the fingerprint databases corresponding to the Z values under different Z values, and selecting the Z corresponding to the fingerprint database with the minimum error as the optimal data ratio.
Preferably, the step S6 is: collecting the point data at an indoor undetermined point through receiving equipment, and calculating fingerprint data of the point based on the optimal data Z value determined by an exhaustion method; and searching and comparing the fingerprint data of the point with a fingerprint database, and selecting K adjacent points to perform weighted average calculation on coordinates (X, Y) of the undetermined point.
The invention has the technical effects and advantages that: the invention fully utilizes the distribution characteristics of RSSI data, improves the quality of a fingerprint database relative to average filtering and ensures the operation efficiency;
compared with a single filtering method, the invention provides a novel RSSI data processing method, applies the mode to the filtering method for the first time, and provides a new idea for subsequent research;
compared with the prior art, the indoor fingerprint positioning method based on the mode filtering can avoid the RSSI ranging problem based on the Received Signal Strength (RSSI) position fingerprint positioning algorithm, and can construct a high-quality fingerprint database through filtering processing. Aiming at the problems of long Gaussian filter operation time, large mean filter positioning error and the like, the RSSI distribution rule is analyzed, a mode filtering method is provided based on the repeated appearance characteristic of partial RSSIs, the mode in the current data is selected successively, and the average is taken until the ratio of the cumulative frequency sum of the selected mode to the total data amount is larger than 95% to extract the characteristic RSSI. Experiments show that the fingerprint database constructed based on the mode filtering is similar to the Gaussian filtering positioning precision under 73% of conditions, but the operation efficiency is superior to that of Gaussian filtering. Meanwhile, compared with mean value filtering, mode filtering improves the positioning precision by about 0.15m, limits the maximum positioning error within 2m under the condition of 95%, and can effectively improve the quality of the fingerprint database.
Drawings
FIG. 1 is a schematic box plot diagram illustrating the elimination of outliers in initial data using RSSI in accordance with an embodiment of the present invention;
FIG. 2 is a graph of RSSI data distribution characteristics used in the practice of the present invention;
FIG. 3 is a schematic diagram of a boxplot for outlier detection for a set of RSSI data in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a modal filtering process in accordance with an embodiment of the present invention;
FIG. 5 is a graph illustrating an exhaustive selection of optimal data to Z values in mode filtering in accordance with an embodiment of the present invention;
fig. 6 is a schematic diagram of an indoor fingerprint positioning method based on mode filtering according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The technical solution of the present invention is further described below with reference to the accompanying drawings 1-6 and the detailed description: the specific embodiment discloses an indoor fingerprint positioning method based on mode filtering, which comprises the following steps:
s1, according to indoor wireless signal propagation characteristics, RSSI is removed by using a box plot method i The abnormal data value in the sequence specifically comprises the following steps:
s1.1, forming a sequence by RSSI data collected at each known reference point indoors;
s1.2, carrying out abnormal value detection on each group of data through a boxplot: if an abnormal value exists, replacing the abnormal value by a front and back mean value; otherwise, the next step is performed.
The boxplot is a statistical graph showing a set of data dispersion data, and as shown in fig. 1, an outlier exclusion rule is formulated by two upper and lower quartiles in a set of data, and an outlier is detected as shown in fig. 3 without prior knowledge of data distribution.
The specific implementation mode of the invention is based on a certain indoor positioning laboratory of Nanjing university of industry, and MOL iBeacon equipment of a homing company is used as base station equipment, and nova3i of a Huacheng smart phone is used as receiving equipment to acquire RSSI data. And arranging 80 known reference points in the chamber, and testing 17 known points.
And (3) carrying out data abnormal value elimination on the acquired RSSI data through the boxplot in the step S1.
S2, initializing an optimal data ratio Z =0.6, establishing each group of frequency accumulation amount and mode statistic for each group of RSSI data, and recording the total quantity N of the group of RSSI data; the same data ratio Z is adopted for each group of data when carrying out mode filtering;
s3, selecting the RSSI with larger frequency by using the optimal data ratio Z to carry out mean filtering to calculate the set of RSSI characteristic values, and specifically comprising the following steps of:
s3.1, recording current RSSI sequence mode RSSI i And frequency m thereof, K = K +1, P = P + m, the data ratio Z = P/N is calculated;
s3.2, eliminating RSSI in the current sequence i Forming a new RSSI sequence;
s3.3, judging whether the mode filtering search Z is less than P/N and meets the stop condition: if yes, continuing to step S2; otherwise, returning to the step S3.2;
s3.4, calculating an arithmetic mean value of the RSSI with the selected frequency arranged in the front K groups of the array as the characteristic value of the group of RSSI;
s4, calculating characteristic values of all known indoor reference points by using a mode filtering method based on the initial data ratio Z to form fingerprint data; obtaining position coordinates (X, Y) of all indoor reference points by a measuring method; combining the fingerprint data and the position coordinates together to construct a fingerprint database, which is as follows:
and S5, selecting the optimal data ratio Z by using an exhaustion method. The method specifically comprises the following steps:
s5.1, selecting 0.05 as an exhaustion step length, and enabling Z = Z +0.05;
s5.2, resetting the frequency accumulation statistic P, selecting the mode number accumulation K and the total RSSI data quantity N, and enabling P =0, K =0 and N to be the number of the current RSSI arrays;
s5.3, repeating the step S4, and establishing a fingerprint database based on the current Z value;
s5.4, calculating the error in the current positioning through a WKNN algorithm;
s5.5, judging whether the exhaustive list Z =1 and meeting the stopping condition: if yes, continuing to step S5.6; otherwise, returning to the step S5.1;
s5.6, comparing the total positioning errors of the fingerprint databases corresponding to the Z values under different Z values, and selecting the Z value corresponding to the minimum error as the optimal data ratio.
The invention fully utilizes the distribution characteristics of RSSI data, improves the quality of a fingerprint database relative to average filtering, and ensures the operation efficiency; compared with a single filtering method, the invention provides a novel RSSI data processing method, applies the mode to the filtering method for the first time, and provides a new idea for subsequent research;
s6, collecting the point data at the indoor undetermined point through receiving equipment, and calculating fingerprint data of the point based on the optimal data Z value determined by an exhaustion method; and (3) searching and comparing the point fingerprint data with a fingerprint database, selecting K adjacent points according to the formula (a), calculating a weight value according to the formula (b), and calculating coordinates (X, Y) of the undetermined point according to the formula (c).
Mode filtering, median filtering and Gaussian filtering are selected to compare and analyze the positioning result precision and the operation efficiency, and indoor fingerprint RSSI data are collected through the specific implementation mode of the invention to verify the uniqueness of the mode filtering.
TABLE 1 comparison table of positioning effect of different filtering methods
In comparison with the results in table 1, gaussian, median and mode filters increased processing time relative to mean, but mode filters increased minimally by only 15%, whereas gaussian increased by about 150% and median increased by about 260%. Meanwhile, compared with the mean value filtering, the mode filtering effectively reduces the root mean square error by about 0.15m, is similar to the median filtering, and has higher efficiency than the median filtering.
Through the above analysis, it was found that:
1) Mode filtering utilizes the distribution characteristics of RSSI fingerprint data, proposes that mode is applied to characteristic value extraction, and provides a new idea for follow-up research;
2) Compared with the average filtering, the mode filtering positioning precision is improved by about 0.15m, and the operation time is only increased by 15%. Meanwhile, mode filtering can control the maximum error within 2m under 95% of conditions.
In conclusion, the method makes full use of the distribution characteristics of the RSSI data, improves the quality of the fingerprint database compared with the average filtering, and ensures the operation efficiency;
compared with a single filtering method, the invention provides a novel RSSI data processing method, applies the mode to the filtering method for the first time, and provides a new idea for subsequent research;
compared with the prior art, the indoor fingerprint positioning method based on the mode filtering can avoid the RSSI ranging problem based on the Received Signal Strength (RSSI) position fingerprint positioning algorithm, and can construct a high-quality fingerprint database through filtering processing. Aiming at the problems that the Gaussian filtering operation time is long and the mean filtering positioning error is large, the RSSI distribution rule is analyzed, a mode filtering method is provided based on the characteristic that partial RSSI repeatedly appears, the mode in the current data is selected successively, and the characteristic RSSI is extracted by averaging until the ratio of the accumulated frequency sum of the selected mode to the total data amount is larger than 95%.
Experiments show that the fingerprint database constructed based on the mode filtering is similar to the Gaussian filtering positioning precision under 73% of conditions, but the operation efficiency is superior to that of Gaussian filtering. Meanwhile, compared with mean value filtering, mode filtering improves the positioning precision by about 0.15m, limits the maximum positioning error within 2m under the condition of 95%, and can effectively improve the quality of the fingerprint database.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still make modifications to the technical solutions described in the foregoing embodiments, or make equivalent substitutions and improvements to part of the technical features of the foregoing embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. The indoor fingerprint positioning method based on the mode filtering is characterized by comprising the following steps: the method comprises the following steps:
s1, according to indoor wireless signal propagation characteristics, RSSI is removed by using a box plot method i An abnormal data value in the sequence;
s2, counting the total amount of RSSI data, establishing statistics of frequency numbers and mode numbers of each group, and initializing an optimal data ratio Z;
s3, selecting the RSSI with high frequency by using the optimal data ratio Z to carry out mean filtering to calculate the characteristic value of the RSSI group;
s4, constructing a fingerprint database based on the RSSI characteristic value and the position coordinates of the corresponding reference point;
s5, selecting an optimal data ratio Z by using an exhaustion method;
s6, resolving the position of the indoor undetermined point based on the optimal fingerprint database through a WKNN (WeightedK-nearest neighbor) algorithm;
the step S1 includes the steps of:
s1.1, forming a sequence by RSSI data collected from various known reference points indoors;
s1.2, abnormal value detection is carried out on each group of data through a box plot: if an abnormal value exists, replacing the abnormal value by the average value before and after the abnormal value; otherwise, the next step is carried out;
the step S2 is as follows: receiving RSSI data of each indoor wireless signal transmitting station for each reference point to create statistics, recording the total amount of each group of RSSI data as N, and initializing a data ratio Z =0.6;
the step S3 includes the steps of:
s3.1, recording current RSSI sequence mode RSSI i And frequency m thereof, let K = K +1, P = P + m, the data ratio Z = P/N is calculated;
s3.2, removing the RSSI in the current sequence i Forming a new RSSI sequence;
s3.3, judging whether the mode filtering search Z is less than P/N and meets the stop condition: if yes, continuing to step S2; otherwise, returning to the step S3.2;
s3.4, calculating an arithmetic mean value of the RSSI with the selected frequency arranged in the front K groups of the array as the characteristic value of the group of RSSI;
the step S5 includes the steps of:
s5.1, selecting 0.05 as an exhaustion step length, and enabling Z = Z +0.05;
s5.2, resetting the frequency number accumulation statistic P, selecting the mode number accumulation K and the total RSSI data quantity N, and enabling P =0, K =0 and N to be the number of the current RSSI array;
s5.3, repeating the step S4, and establishing a fingerprint database based on the current Z value;
s5.4, calculating the error in the current positioning through a WKNN algorithm;
s5.5, judging whether the exhaustion Z =1 and meeting the stop condition: if yes, continuing to step S5.6; otherwise, returning to the step S5.1;
and S5.6, comparing the total positioning errors of the fingerprint databases corresponding to the Z values under different Z values, and selecting the Z corresponding to the fingerprint database with the minimum error as the optimal data ratio.
2. The mode filtering based indoor fingerprint positioning method of claim 1, wherein: the step S4 is as follows: calculating characteristic values of all known indoor reference points by using a mode filtering method based on the initial data ratio Z to form fingerprint data; obtaining position coordinates (X, Y) of all indoor reference points by a measuring method; combining the fingerprint data and the position coordinates together to construct a fingerprint database.
3. The mode filtering based indoor fingerprint positioning method of claim 1, wherein: the step S6 is as follows: collecting selected point data at an indoor undetermined point through receiving equipment, and calculating selected point fingerprint data based on an optimal data Z value determined by an exhaustion method; and searching and comparing the selected point fingerprint data with a fingerprint database, and selecting K adjacent points to perform weighted average calculation on coordinates (X, Y) of the undetermined point.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011132650.3A CN112261578B (en) | 2020-10-21 | 2020-10-21 | Indoor fingerprint positioning method based on mode filtering |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011132650.3A CN112261578B (en) | 2020-10-21 | 2020-10-21 | Indoor fingerprint positioning method based on mode filtering |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112261578A CN112261578A (en) | 2021-01-22 |
CN112261578B true CN112261578B (en) | 2023-04-14 |
Family
ID=74264382
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011132650.3A Active CN112261578B (en) | 2020-10-21 | 2020-10-21 | Indoor fingerprint positioning method based on mode filtering |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112261578B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113438731B (en) * | 2021-06-11 | 2022-08-05 | 武汉大学 | Positioning method and system based on signal quality control and characteristic fingerprint enhancement |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106454747B (en) * | 2016-08-31 | 2020-07-10 | 重庆市志愿服务工作指导中心 | Wireless positioning method of mobile phone terminal |
CN107071902A (en) * | 2017-05-11 | 2017-08-18 | 桂林电子科技大学 | One kind is based on mixed filtering and Power Exponent Mapping WIFI indoor orientation methods |
CN107979810A (en) * | 2017-11-03 | 2018-05-01 | 上海斐讯数据通信技术有限公司 | Indoor orientation method, server and system |
CN107948930B (en) * | 2017-12-31 | 2020-07-17 | 电子科技大学 | Indoor positioning optimization method based on position fingerprint algorithm |
CN108989976B (en) * | 2018-06-04 | 2020-09-11 | 华中师范大学 | Fingerprint positioning method and system in intelligent classroom |
CN109640260B (en) * | 2018-12-13 | 2020-10-27 | 闽南师范大学 | Indoor Wi-Fi positioning method |
-
2020
- 2020-10-21 CN CN202011132650.3A patent/CN112261578B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112261578A (en) | 2021-01-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106793082B (en) | Mobile equipment positioning method in WLAN/Bluetooth heterogeneous network environment | |
CN104883734B (en) | A kind of indoor Passive Location based on geographical fingerprint | |
KR100987615B1 (en) | Iterative method for jointly estimating time-of-arrival of received signals and terminal location | |
CN109672973B (en) | Indoor positioning fusion method based on strongest AP | |
CN108540929B (en) | Indoor fingerprint positioning method based on RSSI signal strength sequencing | |
CN103916820B (en) | Wireless indoor location method based on access point stability | |
CN108650628B (en) | Indoor positioning method combining distance measurement and fingerprint based on Wi-Fi network | |
CN102480678B (en) | Fingerprint positioning method and system | |
CN106851571B (en) | Decision tree-based rapid KNN indoor WiFi positioning method | |
CN108966121B (en) | Fingerprint database updating method suitable for fingerprint positioning algorithm | |
CN107807346A (en) | Adaptive WKNN outdoor positionings method based on OTT Yu MR data | |
CN109348416B (en) | Fingerprint indoor positioning method based on binary k-means | |
CN110351660B (en) | Bluetooth indoor positioning method based on double-step fingerprint matching architecture | |
CN103987118B (en) | Access point k means clustering methods based on received signal strength signal ZCA albefactions | |
CN109511085A (en) | A kind of UWB fingerprint positioning method based on MeanShift and weighting k nearest neighbor algorithm | |
CN112714493B (en) | Object position positioning method and positioning system | |
CN107861098B (en) | Intelligent court positioning system and method | |
CN112261578B (en) | Indoor fingerprint positioning method based on mode filtering | |
CN107290714B (en) | Positioning method based on multi-identification fingerprint positioning | |
CN109302674B (en) | WiFi indoor positioning method based on multiple filtering | |
Liu et al. | A real-time algorithm for fingerprint localization based on clustering and spatial diversity | |
CN108521631B (en) | Mobile AP (access point) identification method for indoor positioning | |
Li et al. | WiFi indoor location method based on RSSI | |
CN112083375A (en) | Cooperative positioning algorithm based on position fingerprints and Taylor | |
CN108445443B (en) | KNN-based fingerprint point clustering method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |