CN108489495A - A kind of RFID tag indoor orientation method and equipment based on SVR and PSO - Google Patents
A kind of RFID tag indoor orientation method and equipment based on SVR and PSO Download PDFInfo
- Publication number
- CN108489495A CN108489495A CN201810267979.7A CN201810267979A CN108489495A CN 108489495 A CN108489495 A CN 108489495A CN 201810267979 A CN201810267979 A CN 201810267979A CN 108489495 A CN108489495 A CN 108489495A
- Authority
- CN
- China
- Prior art keywords
- label
- reader
- rssi
- svr
- pso
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/06—Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
- G06K7/10009—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation sensing by radiation using wavelengths larger than 0.1 mm, e.g. radio-waves or microwaves
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Toxicology (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electromagnetism (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Automation & Control Theory (AREA)
- Radar Systems Or Details Thereof (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a kind of RFID tag indoor orientation methods and equipment based on SVR and PSO, belong to Internet of Things technical field of RFID, this method includes：The distance matrix of the RSSI matrixes of reference label and reference label is trained by non-linear SVR, builds the Nonlinear Mapping relationship of RSSI and distance, it follows that the distance matrix of label and reader to be positioned.According to the distance matrix of label to be positioned and the position coordinates of reader, the Nonlinear System of Equations for calculating label position to be positioned is constructed；Convert Solving Nonlinear Systems of Equations problem to the optimization problem of object function, the optimal solution for seeking object function by iteration using PSO optimization methods is the position coordinates of label to be positioned.The present invention makes full use of the RSSI of reference label and the location information of reader, and the positioning accuracy of label is effectively improved by SVR and PSO optimization methods.
Description
Technical field
The present invention relates to a kind of radio frequency identifications being based on support vector regression (SVR) and particle group optimizing (PSO)
(RFID) label indoor orientation method and equipment belong to Internet of Things technical field of RFID.
Background technology
Radio frequency identification is a kind of automatic identification technology of wireless communication, it completes Item Information using radio frequency signal
The advantages that acquisition and transmission have non line of sight, non-contact, at low cost, strong environmental adaptability, the weight greatly of 21 century ten of being known as
Want one of technology.With the arriving in 5G epoch, a core support technology of the RFID technique as Internet of Things, it passes through reader
Communication between electronic tag can carry out information data collection to object, accurately and effectively data are provided for upper layer application
It supports.With the continuous improvement of its performance and in logistics, the application fields such as materials supply chain are popularized, and Radio Frequency Identification Technology is
Through penetrating into the various aspects of people's daily life, wherein RFID location technologies due to its cost it is relatively low, response speed is very fast etc.
Feature provides solution for the location aware and tracking of indoor occupant and article.
Most common technology is GPS positioning and BEI-DOU position system by satellite positioning in outdoor positioning at present, it
Positioning accuracy it is higher, but indoor positioning is not suitable for, first, since there is indoor spaces stronger closure, signal to pass through and build
Decay seriously after building object, so that it cannot positioning, second is that since indoor environment is more complicated than outdoor environment very much, position error is big,
It cannot be satisfied demand of the people to Indoor Location Information.More commonly used technology is infrared ray positioning in positioning indoors at present,
ZigBee is positioned, Wi-Fi positioning, RFID positioning etc..Infrared ray positioning accuracy is high, but infrared ray propagation distance is remote, can only regard
Away from propagate and equipment costliness be its practical application bring limitation；ZigBee positions small power consumption, at low cost, but propagation distance
Short, transmission rate is not high；Wi-Fi positioning accuracies are high, at low cost, but it is limited in scope, easily by other signal interferences；RFID is fixed
Position technology is a kind of bidirectional data exchange using between reader and electronic tag, is identified and positions to object to be measured,
This technical costs is low, strong environmental adaptability, can reach higher positioning accuracy in a short period of time, therefore RFID is positioned
Technology is got growing concern for.
Frequency recognition positiming method can be divided into location algorithm and non-ranging algorithm.The essence of location algorithm is to measure label
Orientation or distance between reader are positioned, and the distance measuring method that each algorithm uses is different, for example TOA, TDOA are roots
According to time of arrival (toa) ranging；AOA is according to direction of arrival ranging；RSSI is according to signal receiving strength ranging etc..It is non-
Ranging localization algorithm is based on scene analysis method.LANDMARK algorithms are fixed in the rooms RFID based on scene analysis of comparative maturity
Position method.This method introduces reference label, reduces the quantity of reader, significantly reduces the cost of system, but fixed
The density of position precision and reference label is closely related, and the bigger position error of density is smaller, but when density is excessive, between label
The interference that will produce signal again causes the information collected inaccurate, and positioning accuracy is not high.
Invention content
Inventive problem：In view of the above shortcomings of the prior art, the object of the present invention is to provide a kind of based on SVR's and PSO
RFID tag indoor orientation method and equipment, this method is returned using Nonlinear Support Vector Machines to be calculated label to be positioned and reads
Device distance, and position error is reduced using particle group optimizing, it is effectively improved positioning accuracy.
Technical solution：To achieve the above object, the technical solution adopted by the present invention is：
A kind of RFID tag indoor orientation method based on SVR and PSO, this method comprises the following steps：
(1) it is established with reference to mark according to the signal strength values RSSI for being evenly distributed on indoor reference label that reader obtains
The RSSI matrixes of label；The distance matrix of reference label is established according to the distance between reference label and reader；
(2) using the RSSI matrixes of reference label as the input value of sample, using the distance matrix of reference label as sample
Desired output, the two is trained by non-linear SVR, obtains decision function, builds RSSI and the non-linear of distance reflects
Penetrate relationship；
(3) signal strength values of the label to be positioned obtained according to reader establish the RSSI matrixes of label to be positioned, will
Input of the RSSI matrixes of label to be positioned as decision function is closed according to the Nonlinear Mapping of RSSI and distance in step (2)
System, obtains the distance matrix of label and reader to be positioned；
(4) it according to the distance matrix of label to be positioned and the position coordinates of reader, constructs and calculates label to be positioned
The Nonlinear System of Equations of position；
(5) Solving Nonlinear Systems of Equations problem is converted to the optimization problem of object function, is passed through using PSO optimization methods
Iteration seeks the optimal solution of object function, calculates and the fitness value of more all particles, most according to global optimum and individual
The figure of merit draws close the position seat that the optimal solution obtained from is label to be positioned to change the position and speed of particle to optimal solution
Mark.
In preferred embodiments, the non-linear SVR steps in step (2) include：
(2.1) it is SVR kernel functions, setting kernel functional parameter, precision ε and punishment parameter C to choose gaussian radial basis function；
(2.2) object function Solve problems are constructed
Solution can obtain Lagrange multiplier vectorsWherein, K () is Gauss diameter
To base kernel function, rimIt is the RSSI, r of m-th of reference label that i-th of reader obtainsinIt is the n-th of i-th of reader acquisition
The RSSI of a reference label, dinIt is i-th of reader at a distance from n-th of reference label, N is the number of reference label；
(2.3) it chooses and is located in open interval (0, C)Component, according to KKT conditions solve offset constantIf chosen
BeThenIf what is chosen isThenSolution obtains
(2.4) decision function is obtainedThe mark to be positioned that i-th of reader obtains
The RSSI of label is r, and the distance between the reader and label to be positioned for being estimated according to decision function are d, to set up
Nonlinear Mapping relationship between input signal strength r and output distance d.
In preferred embodiments, the Nonlinear System of Equations in step (4) is：Tag coordinate to be positioned be Z=(x,
Y), the position coordinates of the distance between label to be positioned and reader for being estimated according to step (3) and reader can be with structure
The Nonlinear System of Equations of calculating label position to be positioned is built out, it is as follows：
Wherein, dtarget-iIt is the distance between the label and i-th of reader to be positioned predicted according to step (3)；
In preferred embodiments, the object function in step (5) is
In preferred embodiments, the step of PSO optimization object functions in step (5) include：
(5.1) P particle of generation in plain region is being searched, and is initializing the initial position and initial velocity of P particle, s
The position coordinates of a particle in space are Zs=(xs,ys), search speed Vs=(vsx,vsy), wherein s=1,2,3 ..., P；
(5.2) according to fitness function Meter
Calculate the fitness function value of each particle；
(5.3) to the individual optimal value P of populationbestWith global optimum GbestUpdate：According to object function, for s
The individual optimal value that a particle is searched in k search process is Pbest-s k, then the K+1 times search individual optimal value
For：
The global optimum of all particles is：Gbest k=min (Pbest-1 k,Pbest-2 k,…,Pbest-P k)；
(5.4) each particle updates the position and speed of oneself according to its individual optimal value and global optimum：In kth time
The speed and location update formula of particle s are as follows when search：
W is inertia weight in formula, is used for the ability of searching optimum and local search ability of equilibrium particle；c1,c2For study because
Son controls population to the individual optimal and close degree of global optimum respectively；r1,r2For the random number between [0,1]；
(5.5) reach iterations or computational accuracy then stops search, output result is that the position of label to be positioned is sat
Otherwise mark returns to (5.3) and continues search for.
A kind of computer equipment that another aspect of the present invention provides, including memory, processor and storage are on a memory
And the computer program that can be run on a processor, the computer program realize when being loaded on processor it is described based on
The RFID tag indoor orientation method of SVR and PSO.
Advantageous effect：Compared with the prior art, the advantages of the present invention are as follows：Use RFID tag room according to the present invention
Interior localization method builds the Nonlinear Mapping relationship of the signal strength values and distance of label using non-linear SVR methods, effectively
The precision for improving RSSI rangings estimates label to be positioned at a distance from reader further according to the RSSI of label to be positioned, uses
Particle group optimizing method seeks the optimal location of label to be positioned by iteration, and the search of PSO optimization algorithms is efficient, realizes simply,
Largely reduce position error.Compared with prior art, the method for the present invention realize in less reference label and
In the case of reader quantity, the RSSI of reference label and the location information of reader are made full use of, improves RSSI ranging essences
It spends, and improves the positioning accuracy of label by PSO optimization methods.
Description of the drawings
Fig. 1 is the system model figure of tag location method in the embodiment of the present invention；
Fig. 2 is the flow schematic overview of tag location method in the embodiment of the present invention；
Fig. 3 is the SVR flow diagrams of tag location method in the embodiment of the present invention；
Fig. 4 is the PSO flow diagrams of tag location method in the embodiment of the present invention；
Fig. 5 is the simulation result Error Graph of tag location method in the embodiment of the present invention.
Specific implementation mode
Below in conjunction with the drawings and specific embodiments, present invention is further described in detail.
As shown in Figure 1, being the system model figure that tag location method is implemented, specific requirement is as follows：It is put in area to be targeted
M reader and equally distributed N number of reference label are set, a reading is placed in the every nook and cranny usually in area to be targeted
Device, and place a reference label every two meters；And a certain number of labels to be positioned are generated at random and are scattered in area to be targeted.
The reading range of reader can cover entire area to be targeted, and the wherein position coordinates of reader are (Xi,Yi),i∈(1,M)；
The position coordinates of reference label are (Sj,Tj),j∈(1,N)；
As shown in Fig. 2, a kind of RFID tag indoor orientation method based on SVR and PSO disclosed by the embodiments of the present invention, main
Include the following steps：
(1) it is established with reference to mark according to the signal strength values RSSI for being evenly distributed on indoor reference label that reader obtains
The RSSI matrixes of label；The distance matrix of reference label is established according to the distance between reference label and reader；
(2) using the RSSI matrixes of reference label as the input value of sample, using the distance matrix of reference label as sample
Desired output, the two is trained by non-linear SVR, obtains decision function, builds RSSI and the non-linear of distance reflects
Penetrate relationship；
Non-linear SVR specific steps wherein in step (2) are as shown in figure 3, include：
(2.1) it is SVR kernel functions, Selecting All Parameters δ=20, precision ε=0.5, punishment ginseng to choose gaussian radial basis function
Number C=15；
(2.2) object function Solve problems are constructed
Solution can obtain Lagrange multiplier vectorsWherein, K () is Gauss diameter
To base kernel function, rimIt is the RSSI, r of m-th of reference label that i-th of reader obtainsinIt is the n-th of i-th of reader acquisition
The RSSI of a reference label, dinIt is i-th of reader at a distance from n-th of reference label, N is the number of reference label；
(2.3) it chooses and is located in open interval (0, C)Component, according to KKT conditions solve offset constantIf chosen
BeThenIf what is chosen isThenSolution obtains
(2.4) decision function is obtainedThe mark to be positioned that i-th of reader obtains
The RSSI of label is r, and the distance between the reader and label to be positioned for being estimated according to decision function are d, to set up
Nonlinear Mapping relationship between input signal strength r and output distance d.
(3) signal strength values of the label to be positioned obtained according to reader establish the RSSI matrixes of label to be positioned, will
Input of the RSSI matrixes of label to be positioned as decision function is closed according to the Nonlinear Mapping of RSSI and distance in step (2)
System, obtains the distance matrix of label and reader to be positioned；
The RSSI for some label to be positioned that i-th of reader obtains is rtarget-i, as the input of decision function,
Then the distance between the label and i-th of reader to be positioned
(4) it according to the distance matrix of label to be positioned and the position coordinates of reader, constructs and calculates label to be positioned
The Nonlinear System of Equations of position；
Remember that the tag coordinate to be positioned is Z=(x, y), the label to be positioned estimated according to step (3) and reader it
Between distance and the position coordinates of reader can construct the Nonlinear System of Equations for calculating label position to be positioned, it is as follows：
(5) Solving Nonlinear Systems of Equations problem is converted to the optimization problem of object function, is passed through using PSO optimization methods
Iteration seeks the optimal solution of object function, calculates and the fitness value of more all particles, most according to global optimum and individual
The figure of merit draws close the position seat that the optimal solution obtained from is label to be positioned to change the position and speed of particle to optimal solution
Mark.
Convert solution Nonlinear System of Equations problem to the optimization problem of object function, then object function isMethod using population PSO optimizations seeks this
The optimal solution of object function.As shown in figure 4, PSO optimizations detailed process is as follows：
(5.1) P particle of generation in plain region is being searched, and is initializing the initial position and initial velocity of P particle, s
The position coordinates of a particle in space are Zs=(xs,ys), search speed Vs=(vsx,vsy), wherein s=1,2,3 ..., P；
(5.2) according to fitness function Meter
Calculate the fitness function value of each particle；
(5.3) to the individual optimal value P of populationbestWith global optimum GbestUpdate：According to object function, for s
The individual optimal value that a particle is searched in k search process is Pbest-s k, then the K+1 times search individual optimal value
For：
The global optimum of all particles is：Gbest k=min (Pbest-1 k,Pbest-2 k,…,Pbest-P k)；
(5.4) each particle updates the position and speed of oneself according to its individual optimal value and global optimum：In kth time
The speed and location update formula of particle s are as follows when search：
W is inertia weight in formula, is used for the ability of searching optimum and local search ability of equilibrium particle, advantageous if smaller
In the local search ability for improving algorithm, be conducive to the ability of searching optimum for improving algorithm if larger.Therefore it uses and linearly passs
Subtract strategyQ is iteration total degree；Wherein wmax=0.9, wmin=0.4.
c1,c2For Studying factors, population is controlled respectively to the individual optimal and close degree of global optimum, this embodiment party
C is set in case1=c2=2；r1,r2For the random number between [0,1].
(5.5) reach iterations or computational accuracy then stops search, output result is that the position of label to be positioned is sat
Otherwise mark returns to (5.3) and continues search for.
The case where for multiple labels to be positioned, repetition step (3) to step (5) are undetermined up to entire area to be targeted
Position label, which positions, to be terminated.
As shown in figure 5, giving the simulation result of the RFID tag indoor orientation method based on SVR and PSO in this example
Error Graph.Experimental situation is configured to：Each of in this experiment, area to be targeted is the room area of 8m*8m, in this region
Place a reader, that is, M=4 in corner；4*4 reference label i.e. N=16 is uniformly placed in whole region；It is random to generate 10
A label to be positioned is scattered in each place in the region.The iteration total degree Q of PSO optimizations is set as 100.It can be seen by Fig. 5
Go out, under the conditions of same experiment simulation, RFID tag positions in the present invention error significantly lower than classical LANDMARC and
The position error of VIRE methods.From the foregoing, it will be observed that the indoor positioning of the tag location method and the prior art in the embodiment of the present invention
Algorithm, which is compared, has higher positioning accuracy, and the result that it is positioned for the label of different zones is more stable, there is no
Certain zone location error is larger and situation that other zone location errors are smaller.
Based on the same technical idea, the embodiment of the present invention additionally provides a kind of computer equipment, which can
With including memory, processor and storage on a memory and the computer program that can run on a processor, the computer
Program realizes the above-mentioned RFID tag indoor orientation method based on SVR and PSO when being loaded on processor.
The foregoing is merely the better embodiment of the present invention, protection scope of the present invention is not with the above embodiment
Limit, as long as those of ordinary skill in the art should all be included in power according to equivalent modification or variation made by disclosed content
In protection domain described in sharp claim.
Claims (6)
1. a kind of RFID tag indoor orientation method based on SVR and PSO, it is characterised in that：This method comprises the following steps：
(1) reference label is established according to the signal strength values RSSI for being evenly distributed on indoor reference label that reader obtains
RSSI matrixes；The distance matrix of reference label is established according to the distance between reference label and reader；
(2) using the RSSI matrixes of reference label as the input value of sample, using the distance matrix of reference label as the phase of sample
Value to be output, the two are trained by non-linear SVR, obtain decision function, and the Nonlinear Mapping for building RSSI and distance is closed
System；
(3) signal strength values of the label to be positioned obtained according to reader establish the RSSI matrixes of label to be positioned, will be undetermined
Input of the RSSI matrixes of position label as decision function is obtained according to the Nonlinear Mapping relationship of RSSI and distance in step (2)
To the distance matrix of label to be positioned and reader；
(4) it according to the distance matrix of label to be positioned and the position coordinates of reader, constructs and calculates label position to be positioned
Nonlinear System of Equations；
(5) Solving Nonlinear Systems of Equations problem is converted to the optimization problem of object function, passes through iteration using PSO optimization methods
The fitness value for seeking the optimal solution of object function, calculating and more all particles, according to global optimum and individual optimal value
Position and speed to change particle draws close the position coordinates that the optimal solution obtained from is label to be positioned to optimal solution.
2. a kind of RFID tag indoor orientation method based on SVR and PSO according to claim 1, it is characterised in that：Institute
Stating non-linear SVR steps in step (2) includes：
(2.1) it is SVR kernel functions, setting kernel functional parameter, precision ε and punishment parameter C to choose gaussian radial basis function；
(2.2) object function Solve problems are constructed
Solution can obtain Lagrange multiplier vectorsWherein, K () is gaussian radial basis function core
Function, rimIt is the RSSI, r of m-th of reference label that i-th of reader obtainsinIt is n-th of reference that i-th of reader obtains
The RSSI of label, dinIt is i-th of reader at a distance from n-th of reference label, N is the number of reference label；
(2.3) it chooses and is located in open interval (0, C)Component, according to KKT conditions solve offset constantIf what is chosen isThenIf what is chosen isThenSolution obtains
(2.4) decision function is obtainedThe label to be positioned that i-th of reader obtains
RSSI is r, and the distance between the reader and label to be positioned for being estimated according to decision function are d, to set up input
Nonlinear Mapping relationship between signal strength r and output distance d.
3. a kind of RFID tag indoor orientation method based on SVR and PSO according to claim 1, it is characterised in that：Institute
The Nonlinear System of Equations stated in step (4) is：
Wherein, dtarget-iIt is the distance between the label and i-th of reader to be positioned predicted according to step (3), (x, y)
For tag coordinate to be positioned, (Xi,Yi) be reader position coordinates, i ∈ (1, M)；M is the number of reader.
4. a kind of RFID tag indoor orientation method based on SVR and PSO according to claim 3, it is characterised in that：Institute
The object function stated in step (5) is：
5. a kind of RFID tag indoor orientation method based on SVR and PSO according to claim 4, it is characterised in that：Institute
The step of stating the PSO optimization object functions in step (5) include：
(5.1) P particle of generation in plain region is being searched, and is initializing the initial position and initial velocity of P particle, s-th
The position coordinates of son in space are Zs=(xs,ys), search speed Vs=(vsx,vsy), wherein s=1,2,3 ..., P；
(5.2) according to fitness function It calculates each
The fitness function value of a particle；
(5.3) to the individual optimal value P of populationbestWith global optimum GbestUpdate：According to object function, for s-th
The individual optimal value that son is searched in k search process is Pbest-s k, then the K+1 times search individual optimal value be：
The global optimum of all particles is：Gbest k=min (Pbest-1 k,Pbest-2 k,…,Pbest-P k)；
(5.4) each particle updates the position and speed of oneself according to its individual optimal value and global optimum：In kth time search
When particle s speed and location update formula it is as follows：
W is inertia weight in formula, is used for the ability of searching optimum and local search ability of equilibrium particle；c1,c2For Studying factors,
Control population is to the individual optimal and close degree of global optimum respectively；r1,r2For the random number between [0,1]；
(5.5) reach iterations or computational accuracy then stops search, output result is the position coordinates of label to be positioned, no
(5.3) are then returned to continue search for.
6. a kind of computer equipment, including memory, processor and storage are on a memory and the meter that can run on a processor
Calculation machine program, which is characterized in that the computer program is realized when being loaded on processor according to any one of claim 1-5 institutes
The RFID tag indoor orientation method based on SVR and PSO stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267979.7A CN108489495A (en) | 2018-03-29 | 2018-03-29 | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267979.7A CN108489495A (en) | 2018-03-29 | 2018-03-29 | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108489495A true CN108489495A (en) | 2018-09-04 |
Family
ID=63317162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810267979.7A Pending CN108489495A (en) | 2018-03-29 | 2018-03-29 | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108489495A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109255182A (en) * | 2018-09-09 | 2019-01-22 | 浙江工业大学 | A kind of hard brittle material technology-parameter predictive model and its Multipurpose Optimal Method |
| CN109447133A (en) * | 2018-10-11 | 2019-03-08 | 东南大学 | A kind of elimination method of the location information outlier based on SVR algorithm |
| CN109541533A (en) * | 2018-11-26 | 2019-03-29 | 东南大学 | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering |
| CN110232428A (en) * | 2018-03-05 | 2019-09-13 | 中华映管股份有限公司 | Binary positions label generating method |
| CN110348258A (en) * | 2019-07-12 | 2019-10-18 | 西安电子科技大学 | A kind of RFID answer signal frame synchronization system and method based on machine learning |
| CN110888109A (en) * | 2019-11-22 | 2020-03-17 | 天津大学 | RFID label positioning method based on generalized multidimensional scale |
| CN113343728A (en) * | 2021-05-19 | 2021-09-03 | 天津大学 | RFID positioning method based on nonlinear optimization method |
| CN113794983A (en) * | 2021-08-27 | 2021-12-14 | 北京理工大学 | Multi-target indoor positioning method based on nonlinear geometric constraint optimization |
| CN114372543A (en) * | 2022-01-11 | 2022-04-19 | 重庆邮电大学 | RFID (radio frequency identification device) indoor multi-target 3D (three-dimensional) positioning system and method based on carrier phase |
| CN116299184A (en) * | 2023-05-24 | 2023-06-23 | 至控(湖州)智能系统有限公司 | Positioning method and system based on nonlinear optimization |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103124396A (en) * | 2013-01-24 | 2013-05-29 | 河南科技大学 | Method for positioning mobile node of wireless sensor network based on crossed particle swarm |
| CN104023394A (en) * | 2014-06-17 | 2014-09-03 | 河海大学 | WSN positioning method based on self-adaptation inertia weight |
| CN104459089A (en) * | 2014-12-12 | 2015-03-25 | 东北大学 | Soft measurement method of freeness of high-consistency pulp grinding system |
| CN106022511A (en) * | 2016-05-11 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Information predicting method and device |
| CN106792540A (en) * | 2016-12-29 | 2017-05-31 | 上海应用技术大学 | A kind of improvement DV Hop localization methods based on route matching |
| CN107734479A (en) * | 2017-09-11 | 2018-02-23 | 广东广业开元科技有限公司 | A kind of fire fighter's localization method, system and device based on wireless sensor technology |
-
2018
- 2018-03-29 CN CN201810267979.7A patent/CN108489495A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103124396A (en) * | 2013-01-24 | 2013-05-29 | 河南科技大学 | Method for positioning mobile node of wireless sensor network based on crossed particle swarm |
| CN104023394A (en) * | 2014-06-17 | 2014-09-03 | 河海大学 | WSN positioning method based on self-adaptation inertia weight |
| CN104459089A (en) * | 2014-12-12 | 2015-03-25 | 东北大学 | Soft measurement method of freeness of high-consistency pulp grinding system |
| CN106022511A (en) * | 2016-05-11 | 2016-10-12 | 北京京东尚科信息技术有限公司 | Information predicting method and device |
| CN106792540A (en) * | 2016-12-29 | 2017-05-31 | 上海应用技术大学 | A kind of improvement DV Hop localization methods based on route matching |
| CN107734479A (en) * | 2017-09-11 | 2018-02-23 | 广东广业开元科技有限公司 | A kind of fire fighter's localization method, system and device based on wireless sensor technology |
Non-Patent Citations (2)
| Title |
|---|
| 尹强 等: "基于支持向量回归机的RFID室内定位研究", 《计算机工程与科学》 * |
| 王娜娜 等: "基于RSSI实时精确定位系统设计与实现", 《传感技术学报》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110232428A (en) * | 2018-03-05 | 2019-09-13 | 中华映管股份有限公司 | Binary positions label generating method |
| CN109255182A (en) * | 2018-09-09 | 2019-01-22 | 浙江工业大学 | A kind of hard brittle material technology-parameter predictive model and its Multipurpose Optimal Method |
| CN109447133B (en) * | 2018-10-11 | 2021-09-24 | 东南大学 | SVR algorithm-based method for eliminating position information outliers |
| CN109447133A (en) * | 2018-10-11 | 2019-03-08 | 东南大学 | A kind of elimination method of the location information outlier based on SVR algorithm |
| CN109541533A (en) * | 2018-11-26 | 2019-03-29 | 东南大学 | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering |
| CN110348258A (en) * | 2019-07-12 | 2019-10-18 | 西安电子科技大学 | A kind of RFID answer signal frame synchronization system and method based on machine learning |
| CN110348258B (en) * | 2019-07-12 | 2020-11-24 | 西安电子科技大学 | RFID response signal frame synchronization system and method based on machine learning |
| CN110888109A (en) * | 2019-11-22 | 2020-03-17 | 天津大学 | RFID label positioning method based on generalized multidimensional scale |
| CN110888109B (en) * | 2019-11-22 | 2022-02-22 | 天津大学 | RFID label positioning method based on generalized multidimensional scale |
| CN113343728A (en) * | 2021-05-19 | 2021-09-03 | 天津大学 | RFID positioning method based on nonlinear optimization method |
| CN113794983A (en) * | 2021-08-27 | 2021-12-14 | 北京理工大学 | Multi-target indoor positioning method based on nonlinear geometric constraint optimization |
| CN113794983B (en) * | 2021-08-27 | 2022-08-12 | 北京理工大学 | Multi-target indoor positioning method based on nonlinear geometric constraint optimization |
| CN114372543A (en) * | 2022-01-11 | 2022-04-19 | 重庆邮电大学 | RFID (radio frequency identification device) indoor multi-target 3D (three-dimensional) positioning system and method based on carrier phase |
| CN114372543B (en) * | 2022-01-11 | 2023-12-19 | 东莞市宇讯电子科技有限公司 | RFID indoor multi-target 3D positioning system and method based on carrier phase |
| CN116299184A (en) * | 2023-05-24 | 2023-06-23 | 至控(湖州)智能系统有限公司 | Positioning method and system based on nonlinear optimization |
| CN116299184B (en) * | 2023-05-24 | 2023-09-01 | 至控(湖州)智能系统有限公司 | Positioning method and system based on nonlinear optimization |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108489495A (en) | A kind of RFID tag indoor orientation method and equipment based on SVR and PSO | |
| Li et al. | Deep reinforcement learning (DRL): Another perspective for unsupervised wireless localization | |
| CN108696932B (en) | Outdoor fingerprint positioning method using CSI multipath and machine learning | |
| Shao et al. | Indoor positioning based on fingerprint-image and deep learning | |
| Chung et al. | Indoor location sensing using geo-magnetism | |
| CN109541533A (en) | A kind of RFID label tag indoor tracking method and equipment based on Unscented kalman filtering | |
| CN106525031B (en) | A kind of combined indoor orientation method | |
| CN108871332A (en) | A kind of RFID indoor locating system and method based on XGBoost | |
| CN108716918A (en) | A kind of RSSI indoor positioning algorithms based on Grid Clustering | |
| Tomažič et al. | Confidence-interval-fuzzy-model-based indoor localization | |
| CN106559750B (en) | Passive type localization method in multiple target room based on passive ultra-high frequency RFID | |
| CN106488548A (en) | A kind of determination method and device of indoor multipath error | |
| Zou et al. | An integrative weighted path loss and extreme learning machine approach to RFID based indoor positioning | |
| CN108919177A (en) | A kind of positioning map construction method based on virtual information source estimation and trajectory corrector | |
| Ashraf et al. | A comprehensive analysis of magnetic field based indoor positioning with smartphones: Opportunities, challenges and practical limitations | |
| CN105044659B (en) | Indoor positioning device and method based on ambient light spectrum fingerprint | |
| CN109239661A (en) | A kind of RFID indoor locating system and algorithm based on depth Q network | |
| CN108871318A (en) | A kind of rotary magnetic beacon intelligence fast search number localization method | |
| Song et al. | An improved RSSI of geomagnetic field-based indoor positioning method involving efficient database generation by building materials | |
| Wang et al. | An implementation of positioning system in indoor environment based on active RFID | |
| Li et al. | RBF neural network based RFID indoor localization method using artificial immune system | |
| Cherntanomwong et al. | Soft-clustering Technique for Fingerprint-based Localization. | |
| Kerdjidj et al. | Uncovering the potential of indoor localization: Role of deep and transfer learning | |
| Sharp et al. | Indoor wifi positioning | |
| Farid et al. | A WLAN fingerprinting based indoor localization technique via artificial neural network |
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: 20180904 |