CN114928882A - WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization - Google Patents
WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization Download PDFInfo
- Publication number
- CN114928882A CN114928882A CN202210434881.2A CN202210434881A CN114928882A CN 114928882 A CN114928882 A CN 114928882A CN 202210434881 A CN202210434881 A CN 202210434881A CN 114928882 A CN114928882 A CN 114928882A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- adaptive
- fingerprints
- probability
- particle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 239000002245 particle Substances 0.000 title claims abstract description 66
- 238000005457 optimization Methods 0.000 title claims abstract description 26
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 11
- 230000006870 function Effects 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims abstract description 4
- 238000005259 measurement Methods 0.000 claims abstract 3
- 239000013598 vector Substances 0.000 claims description 20
- 239000000126 substance Substances 0.000 claims description 6
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011524 similarity measure Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 241000764238 Isis Species 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- 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]
-
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Computational Mathematics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization, which comprises similarity measurement and optimal position prediction calculation: 1) calculating the correlation and cosine distance between the inquiry fingerprint and the training fingerprint by using a double-panel uniformity model; 2) establishing a fitness function of the positioning model; 3) and calculating parameters of the optimal adaptive value by adopting a self-adaptive Bayes comprehensive learning particle swarm optimization algorithm and obtaining an optimal predicted position. The method can efficiently and accurately carry out indoor positioning, measures the similarity of the positioned fingerprints by adopting a double-panel fingerprint uniformity model, measures the matching degree between the fingerprints by utilizing the correlation, introduces cosine distance to reflect the difference of the fingerprints in the direction, and improves the diversity and the robustness of a positioning module; parameter optimization is carried out by adopting a self-adaptive Bayes comprehensive learning particle swarm optimization algorithm, a self-adaptive mechanism adopts interval division to select the comprehensive learning probability level of particles, and the performance of the particle swarm optimization algorithm is improved. The system has more robustness and can improve the positioning precision.
Description
Technical Field
The invention relates to the field of indoor positioning technology and optimization algorithm, in particular to a WLAN fingerprint positioning method based on adaptive Bayesian comprehensive learning particle swarm optimization.
Background
With the increasing demand of indoor positioning systems in modern society, while many technologies (such as ultra wide band UWB, inertial sensor IMU, Bluetooth, geomagnetic sensor, laser, etc.) are researched and developed, WiFi-based indoor positioning technologies are gaining attention in academic research and engineering applications due to the advantages of wide signal range, low deployment cost, no need of additional hardware deployment, no influence from non-line-of-sight, etc. The location fingerprint positioning method is one of WiFi indoor positioning methods, where a WiFi signal is usually used to represent location information, and the signal strength RSS, the signal-to-noise ratio, and the channel state information are mainly studied and used as a location identification fingerprint.
The accuracy and stability of positioning are the indexes most concerned or only concerned by the positioning service terminal user, however, since the wireless signal is easily influenced by external factors in a complex and changeable indoor environment, the signal reception strength RSS has sensitive and changeable characteristics, and the RSS-based fingerprint is not significant in terms of spatial recognition rate and temporal stability.
With the research of more and more machine learning algorithms, methods based on Particle Filters (PF), Support Vector Machines (SVM), Neural Networks (NN), classification algorithms, etc. are introduced to indoor positioning, and many positioning models are widely proposed and improve indoor positioning based on WiFi fingerprints to some extent. The limited precision and unstable performance of the existing algorithm become the restriction factors for popularizing the WiFi indoor positioning technology, the robustness of positioning models of many systems is insufficient, and the average error is usually larger in practice.
The PSO algorithm optimized by the particle swarm is used as a biological evolution algorithm, and has better performance on the aspect of optimization. On the basis of the PSO algorithm, many scholars research the influence of different parameter configurations, particle learning strategies and the like on the PSO algorithm. In the comprehensive learning particle swarm optimization method (BCLPSO) based on the Bayes iteration method, the positions of particles with the maximum posterior probability based on the Bayes formula are used as learning samples, so that the particles can be effectively prevented from being trapped in local optimization and missing potential global optimal solutions, and the method has better applicability in the indoor positioning technology based on WiFi fingerprints.
Disclosure of Invention
The invention aims to provide a WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization aiming at the defects of the prior art. The method measures the matching degree between fingerprints by utilizing the correlation, introduces the cosine distance to reflect the difference of the fingerprints in the direction, and improves the diversity and the robustness of a positioning module; parameter optimization is carried out by adopting a self-adaptive Bayes comprehensive learning particle swarm optimization algorithm, so that the system has higher robustness and the positioning accuracy can be improved.
In order to achieve the purpose, the technical scheme provided by the invention comprises the following steps:
the WLAN fingerprint positioning method based on the adaptive Bayes comprehensive learning particle swarm optimization comprises the steps of measuring fingerprint similarity by adopting a double-panel uniformity model, optimizing positioning parameters and predicting positions by adopting an adaptive Bayes comprehensive learning particle swarm optimization algorithm, and specifically comprises the following steps:
suppose there are M signal access points AP in the indoor environment and N physical locations are chosen uniformly as reference points RP. Is provided with
And
representing the set of APs and RPs, respectively. Is provided with
Denotes the position coordinates, s, of the ith (i ═ 1,2, …, N) RP ij Indicating the RSS of the jth AP at that location. StatorDefine the ith RP position corresponding to a fingerprint (RSS vector) of
In summary, the training fingerprint set of reference point RP in the positioning context can be expressed as:
is provided with
Representing RSS vectors collected by the mobile device during the online phase for mobile device positioning. If there are multiple users to perform location queries, the fingerprint set is represented as:
where Γ is the number of query fingerprints. If the jth AP can not be detected in the positioning, the positioning is s ij The assignment is made with a very small value.
1. Fingerprint similarity measure
The similarity of different fingerprints is measured by a double-panel fingerprint uniformity chart representation method.
1) For the first panel, the correlation is used to evaluate the similarity of different fingerprints. For fingerprints
Calculating the correlation between the two:
cor(u,v)＝1-r(u,v) (10)
wherein the content of the first and second substances,
and
are respectively as
The average value and the standard deviation of (a),
and
are respectively as
Mean and standard deviation of (d).
H and are selected according to equation (1)
The fingerprint with the highest correlation, expressed as:
wherein the content of the first and second substances,
represents the q-th similar fingerprint,
and
the training fingerprints in (2) constitute the edges of the first panel.
2) For the second panel, for fingerprints
Calculating the cosine distance between the two (reflecting the fingerprint vector in the square)Divergence in directivity):
similarly, the second panel is divided into h
Is expressed as:
wherein, the first and the second end of the pipe are connected with each other,
representing the qth' th similar fingerprint in the second panel,
and
the training fingerprints in (1) constitute the edges of the second panel graph.
3) For on-panel fingerprint
The corresponding position coefficient is determined according to the similarity and is expressed as
Then, calculating by utilizing softmax function
All fingerprint coefficients in (c) are such that their cumulative amount equals 1. Integrating the results of the two panels to obtain
Represents the optimal predicted position of:
2. calculating the optimal predicted position by adopting an adaptive Bayes comprehensive learning particle swarm optimization algorithm
1) First, a particle group (ps particles) is initialized, and each particle position vector can be expressed as a particle position vector X having d-3 dimensions using equation (6) as a fitness function n ＝(x n ,y n ,h n ) N is 1,2, 3. An initial fitness value for each particle is calculated and each particle is randomly assigned a level of integrated learning (CL) probability.
2) The comprehensive learning probability is determined by dividing the posterior probability interval in a self-adaptive manner: in iterative calculation, the posterior probability p of the particles of the t iteration is calculated by using Bayes theorem t A 1 is to p t Dividing the data into L intervals, wherein the subintervals are defined as:
wherein
Is the L th iteration of the t th i A sub-interval;
and
the maximum and minimum of the a posteriori probability vectors, respectively. Δ p t Is the deviation interval of the posterior probability;
and
respectively, the lower and upper bounds of the sub-interval.
Is the CL probability of the η th subinterval.
The posterior probabilities of all particles are divided into sub-intervals S according to equation (7) I The CL probability of each bin is the median of the bins. When the CL probability of one particle needs to be updated, the self-adaptive mechanism selects the CL probability level of the particle by adopting interval division, realizes the self-adaptation of the comprehensive learning CL probability and determines a particle learning sample.
3) And finally, updating the speed, the position, the adaptive value and the like of the particles to complete iteration, and stopping iteration if the iteration time T reaches the set maximum iteration time T. And (5) taking the final optimal position of the particle swarm as the optimal solution of the formula (6), and taking the corresponding (x, y) as the optimal prediction position for positioning.
Drawings
FIG. 1 is a schematic diagram of a positioning model and algorithm of the present invention;
FIG. 2 is a schematic diagram of a test environment in an embodiment of the invention;
Detailed Description
The present invention will now be described in more detail with reference to the following examples and the accompanying drawings, wherein the examples are given by way of illustration only, and not by way of limitation. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Example (b):
the WLAN fingerprint positioning method based on the adaptive Bayes comprehensive learning particle swarm optimization comprises the steps of measuring fingerprint similarity by adopting a double-panel uniformity model, optimizing positioning parameters and predicting positions by adopting an adaptive Bayes comprehensive learning particle swarm optimization algorithm, and specifically comprises the following steps:
assume that there are M signal access points AP in the indoor environment and N physical locations are chosen uniformly as the reference point RP. Is provided with
And
representing the set of APs and RPs, respectively. Is provided with
Denotes the position coordinates, s, of the ith (i: 1,2, …, N) RP ij Indicating the RSS of the jth AP at that location. Define the ith RP position corresponding to a fingerprint (RSS vector) of
In summary, the training fingerprint set of the reference point RP in the positioning environment can be represented as:
is provided with
Representing RSS vectors collected by the mobile device during the online phase for mobile device location. If there are multiple users to perform location queries, the fingerprint set is represented as:
where Γ is the number of query fingerprints. If the jth AP can not be detected in the positioning, the result is s ij The assignment is made with a very small value.
To verify the effectiveness and robustness of the algorithm, we performed experiments in a real indoor scenario. In the environment, 11 APs are deployed, N53 reference points are selected in the whole area, RSS data is collected and processed into 53 sets of fingerprint vectors to form a training fingerprint set in an offline stage, and RSS data is collected in 136 different positions of Γ 136 and processed into 136 sets of fingerprint vectors to form an online stage query (test) fingerprint set, as shown by open square dots and solid dots in fig. 2.
1. Fingerprint similarity measure
The similarity of different fingerprints is measured by a double-panel fingerprint uniformity chart representation method.
1) For the first panel, the correlation is used to evaluate the similarity of different fingerprints. For fingerprints
Calculating the correlation between the two:
cor(u,v)＝1-r(u,v) (19)
wherein the content of the first and second substances,
and
are respectively as
The average value and the standard deviation of (a),
and
are respectively as
Mean and standard deviation of (d).
H and are selected according to equation (1)
The fingerprint with the highest correlation, expressed as:
wherein, the first and the second end of the pipe are connected with each other,
represents the q-th similar fingerprint of the user,
and
the training fingerprints in (1) constitute the edges of the first panel graph.
2) For the second panel, for fingerprints
The cosine distance between the two is calculated (reflecting the divergence of the fingerprint vector in terms of directionality):
similarly, the number of h on the second panel is
Is expressed as:
wherein the content of the first and second substances,
representing the qth' th similar fingerprint in the second panel,
and
the training fingerprints in (1) constitute the edges of the second panel graph.
3) For on-panel fingerprint
The corresponding position coefficient is determined according to the similarity and is expressed as
Then, calculating by utilizing softmax function
All fingerprint coefficients in (c) are such that their cumulative amount equals 1. The result of integrating the two panels is obtained
Represents the optimal predicted position of:
2. calculating the optimal predicted position by adopting the adaptive Bayes comprehensive learning particle swarm optimization algorithm
1) First, initializing a particle group (ps particles), and using equation (6) as a fitness function, each particle position vector can be expressed as a particle position vector X having d ═ 3 dimensions n ＝(x n ,y n ,h n ) N is 1,2, 3. Calculating initial adaptive value of each particle, and randomly assigning each particleOne level of integrated learning (CL) probability.
2) The comprehensive learning probability is determined by dividing the posterior probability interval in a self-adaptive manner: in iterative calculation, the posterior probability p of the particles of the t iteration is calculated by using Bayes theorem t Let p be t Dividing the data into L intervals, and defining the subintervals as:
wherein
Is the Lth of the t-th iteration i A sub-interval;
and
the maximum and minimum of the a posteriori probability vectors, respectively. Δ p t Is the deviation interval of the posterior probability;
and
respectively, the lower and upper bounds of the subintervals.
Is the CL probability of the η th subinterval.
Specifically, L may be taken to be 3 in an implementation to reduce computational complexity.
The posterior probabilities of all particles are divided into sub-intervals S according to equation (7) I The CL probability of each interval is the median of the interval. When the CL probability of one particle needs to be updated, the self-adaptive mechanism selects the CL probability level of the particle by adopting interval division, realizes the self-adaptation of the comprehensive learning CL probability and determines a particle learning sample.
3) And finally, updating the speed, the position, the adaptive value and the like of the particles to complete iteration, and stopping iteration if the iteration time T reaches the set maximum iteration time T. And (5) taking the final optimal position of the particle swarm as the optimal solution of the formula (6), and taking the corresponding (x, y) as the optimal prediction position for positioning.
Claims (2)
1. The WLAN fingerprint positioning method based on the adaptive Bayes comprehensive learning particle swarm optimization is characterized by comprising the steps of establishing a double-panel uniformity measurement model to calculate similarity among fingerprints and calculating an optimal prediction position by the adaptive Bayes comprehensive learning particle swarm optimization algorithm, calculating the similarity part among the fingerprints in the double-panel uniformity measurement model, respectively measuring the similarity of the fingerprints by adopting correlation and cosine distance, and combining the correlation and the cosine distance to calculate the optimal prediction position in the claim 2, wherein the method specifically comprises the following steps:
assuming that there are M signal access points AP in an indoor environment, and uniformly selecting N physical locations as reference points RP; is provided with
And
respectively representing a set of APs and RPs; is provided with
Denotes the position coordinates, s, of the ith (i ═ 1,2, …, N) RP ij Represents the RSS of the jth AP at that location; define the ith RP position corresponding to a fingerprint (RSS vector) of
In summary, the training fingerprint set of the reference point RP in the positioning environment can be represented as:
let S query ＝[s query1 ,s query2 ,…,s queryM ] T Representing RSS vectors collected by the mobile device during the online phase for mobile device positioning; if there are multiple users to perform location queries, the fingerprint set is represented as:
wherein Γ is the number of query fingerprints; if the jth AP can not be detected in the positioning, the result is s ij Assigning a very small value;
1) for the first panel, the correlation is used to evaluate the similarity of different fingerprints; for fingerprints
Calculating the correlation between the two:
cor(u,v)＝1-r(u,v) (1)
wherein the content of the first and second substances,
and
are respectively as
The average value and the standard deviation of (a),
and
are respectively as
Mean and standard deviation of (a);
h and are selected according to equation (1)
The fingerprint with the highest correlation, is represented as:
wherein, the first and the second end of the pipe are connected with each other,
represents the q-th similar fingerprint,
and with
The training fingerprints in (1) constitute edges of the first panel graph;
2) for the second panel, for fingerprints
The cosine distance between the two is calculated (reflecting the divergence of the fingerprint vector in terms of directionality):
similarly, the second panel is divided into h
Is expressed as:
wherein the content of the first and second substances,
representing the qth' th similar fingerprint in the second panel,
and
the training fingerprints in (2) constitute edges of the second panel graph;
3) for on-panel fingerprint pattern
The corresponding position coefficient is determined according to the similarity and is expressed as
Then, calculating by utilizing softmax function
All fingerprint coefficients in (1), so that their cumulative amount equals 1; integrating the results of the two panels to obtain
Represents the optimal predicted position of:
2. the WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization is characterized in that an optimal prediction position is calculated by an adaptive Bayes comprehensive learning particle swarm optimization algorithm, the position prediction expression in the claim 1 is used as a fitness function, in the improved Bayes comprehensive learning particle swarm optimization algorithm, the posterior probability of particles is divided into regions, the comprehensive learning probability is determined in a self-adaptive manner, and the optimal prediction position is calculated in an iterative manner, wherein the method specifically comprises the following steps:
1) first, a particle group (ps particles) is initialized, and each particle position vector can be expressed as a particle position vector X having d-3 dimensions using equation (6) as a fitness function n ＝(x n ,y n ,h n ) N is 1,2, 3.. ps; calculating an initial adaptive value of each particle, and randomly assigning a level of a Comprehensive Learning (CL) probability to each particle;
2) the comprehensive learning probability is determined by dividing the posterior probability interval in a self-adaptive manner: in iterative calculation, the posterior probability p of the particles of the t iteration is calculated by using Bayes theorem t A 1 is to p t Dividing the data into L intervals, wherein the subintervals are defined as:
wherein
Is the L th iteration of the t th i A sub-interval;
and
the maximum value and the minimum value of the posterior probability vector are respectively; Δ p of t Is the deviation interval of the posterior probability;
and
the lower and upper bounds of the subintervals, respectively;
is the CL probability of the η sub-interval;
the posterior probabilities of all particles are divided into sub-intervals S according to equation (7) I The CL probability of each interval is the median of the interval; when the CL probability of one particle needs to be updated, the adaptive mechanism adopts interval division to select the CL probability level of the particle, so that the adaptive of the comprehensive learning CL probability is realized, and a particle learning sample is determined;
3) finally, updating the speed, the position, the adaptive value and the like of the particles to complete iteration, and stopping iteration if the iteration time T reaches the set maximum iteration time T; and (5) taking the final optimal position of the particle swarm as the optimal solution of the formula (6), and taking the corresponding (x, y) as the optimal prediction position for positioning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210434881.2A CN114928882B (en) | 2022-04-24 | WLAN fingerprint positioning method based on self-adaptive Bayes comprehensive learning particle swarm optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210434881.2A CN114928882B (en) | 2022-04-24 | WLAN fingerprint positioning method based on self-adaptive Bayes comprehensive learning particle swarm optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114928882A true CN114928882A (en) | 2022-08-19 |
| CN114928882B CN114928882B (en) | 2024-06-28 |
Family
ID=
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110116565A (en) * | 2010-04-19 | 2011-10-26 | 목포대학교산학협력단 | Method determining indoor location using bayesian algorithm |
| EP2570772A1 (en) * | 2011-09-16 | 2013-03-20 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method for localisation and mapping of pedestrians or robots using wireless access points |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| CN112887902A (en) * | 2021-01-22 | 2021-06-01 | 湖南大学 | Indoor positioning method of WiFi fingerprint based on Gaussian clustering and hybrid measurement |
| CN112911705A (en) * | 2021-02-02 | 2021-06-04 | 湖南大学 | Bayesian iteration improved particle swarm optimization algorithm-based indoor positioning method |
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110116565A (en) * | 2010-04-19 | 2011-10-26 | 목포대학교산학협력단 | Method determining indoor location using bayesian algorithm |
| EP2570772A1 (en) * | 2011-09-16 | 2013-03-20 | Deutsches Zentrum für Luft- und Raumfahrt e.V. | Method for localisation and mapping of pedestrians or robots using wireless access points |
| CN109298389A (en) * | 2018-08-29 | 2019-02-01 | 东南大学 | Indoor pedestrian based on multiparticle group optimization combines position and orientation estimation method |
| CN112887902A (en) * | 2021-01-22 | 2021-06-01 | 湖南大学 | Indoor positioning method of WiFi fingerprint based on Gaussian clustering and hybrid measurement |
| CN112911705A (en) * | 2021-02-02 | 2021-06-04 | 湖南大学 | Bayesian iteration improved particle swarm optimization algorithm-based indoor positioning method |
Non-Patent Citations (4)
| Title |
|---|
| WEI SUN: "Design of Indoor Localization Algorithm Based on WiFi Fingerprints", 《2021 CHINA AUTOMATION CONGRESS (CAC)》, 14 March 2022 (2022-03-14) * |
| 沈栋林;杨明;: "一种顾及用户朝向的PSO-LSSVM指纹定位算法", 石家庄铁道大学学报(自然科学版), no. 01, 25 March 2020 (2020-03-25) * |
| 潘滟;谢胜曙;张群;: "基于BP神经网络指纹识别的算法", 邵阳学院学报(自然科学版), no. 01, 30 March 2007 (2007-03-30) * |
| 赵妍;乐燕芬;施伟斌;: "基于微粒群优化LSSVM的室内指纹定位算法", 软件导刊, no. 04, 4 January 2019 (2019-01-04) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Campos et al. | Wi-Fi multi-floor indoor positioning considering architectural aspects and controlled computational complexity | |
| Zheng et al. | Exploiting fingerprint correlation for fingerprint-based indoor localization: A deep learning-based approach | |
| Bae et al. | Large-scale indoor positioning using geomagnetic field with deep neural networks | |
| Li et al. | SmartLoc: Smart wireless indoor localization empowered by machine learning | |
| CN112887902B (en) | Indoor positioning method of WiFi fingerprint based on Gaussian clustering and hybrid measurement | |
| CN112135248B (en) | WIFI fingerprint positioning method based on K-means optimal estimation | |
| CN114449452B (en) | Wi-Fi indoor positioning method based on CNN-RNN | |
| CN111122989B (en) | K-clustering intelligent selection microwave signal multipath interference suppression method | |
| Buczak et al. | Genetic algorithm convergence study for sensor network optimization | |
| Xingli et al. | Indoor positioning technology based on deep neural networks | |
| Yan et al. | A noise reduction fingerprint feature for indoor localization | |
| CN111757257B (en) | Dynamic fuzzy matching indoor positioning method for overcoming equipment difference | |
| Alfakih et al. | An enhanced indoor positioning method based on Wi-fi RSS fingerprinting | |
| CN109803234B (en) | Unsupervised fusion positioning method based on weight importance constraint | |
| CN114928882A (en) | WLAN fingerprint positioning method based on adaptive Bayes comprehensive learning particle swarm optimization | |
| Guo et al. | A hybrid indoor positioning algorithm for cellular and Wi-Fi networks | |
| US20230353980A1 (en) | Determination and tracking of trajectories of moving objects in wireless applications | |
| CN114928882B (en) | WLAN fingerprint positioning method based on self-adaptive Bayes comprehensive learning particle swarm optimization | |
| KR20120048375A (en) | Knn/pcm hybrid mehod using gath-geva method for indoor location determination in waln | |
| Nie et al. | Joint access point fuzzy rough set reduction and multisource information fusion for indoor Wi-Fi positioning | |
| CN113923589A (en) | Non-contact multi-target positioning method | |
| Luckner et al. | Selection of signal sources influence at indoor positioning system | |
| Qian et al. | Convolutional mixture density recurrent neural network for predicting user location with WiFi fingerprints | |
| CN112437485A (en) | Positioning method and device of fingerprint space interpolation method based on neural network | |
| Liu et al. | Hierarchical fingerprinting and feature extraction for indoor localization |
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 |