CN105307264A - Mobile node positioning method for wireless sensor network - Google Patents
Mobile node positioning method for wireless sensor network Download PDFInfo
- Publication number
- CN105307264A CN105307264A CN201510445657.3A CN201510445657A CN105307264A CN 105307264 A CN105307264 A CN 105307264A CN 201510445657 A CN201510445657 A CN 201510445657A CN 105307264 A CN105307264 A CN 105307264A
- Authority
- CN
- China
- Prior art keywords
- mobile node
- node
- wireless sensor
- sensor network
- positioning method
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor 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 relates to a mobile node positioning method for a wireless sensor network. The mobile node positioning method comprises the following steps: arranging anchor nodes on the boundary of a three-dimensional area, randomly selecting one anchor node to serve as a sink node, and communicating by the sink node through the wireless sensor network to collect the position information of each anchor node; selecting a grid vertex beyond the boundary of the three-dimensional area, obtaining a distance vector between the grid vertex and each anchor node, establishing a mathematical model between the distance vector and the three-dimensional area excluding a coordinate of the grid vertex beyond the boundary; and substituting the distance vector from a mobile node to each anchor node into an expression of the mathematical model to figure out a position coordinate of the mobile node. The mathematical model established by the mobile node positioning method provided by the invention simplifies the calculation complexity and can accurately position the position coordinate of the mobile node.
Description
Technical field
The present invention relates to a kind of mobile node positioning method of wireless sensor network, belong to the field that wireless network positions of mobile nodes is estimated.
Background technology
At present, wireless sensor network has a extensive future, and is widely used in multiple fields such as environmental monitoring, urban transportation, military affairs, medical treatment and nursing.Wherein, positioning service is in occupation of consequence in wireless sensor network, and it is prerequisite and the basis that wireless sensor network carries out the application such as target following, target identification, monitoring.Such as, the methods such as the reckoning in mobile robot, target identification and rout marking allocation are all realize on the positioning service basis of wireless sensor network.
Utilize wireless sensor network to locate the method for mobile node in prior art, mainly through dividing virtual grid to wireless sensor network signal region of acceptance, utilizing grid vertex as parameter, solving the position coordinates of mobile node.
As Chinese patent literature publication No. CN103118333A based in the mobile node of wireless sensor network localization method of similarity, described method is by gathering the RSSI value of mobile node and anchor node, be converted to corresponding distance vector, by estimating this distance vector and the grid vertex similarity degree to the distance vector of anchor node, using the position coordinates of the barycenter of mesh vertex coordinates the highest for similarity degree as mobile node.The RSSI value obtained in described method is the signal message of network power, can be subject to the impact of surrounding enviroment factor in gatherer process, and easily doping is entered the accuracy reduction that partial noise causes mobile node locate.
Summary of the invention
The object of the invention is to overcome the deficiencies in the prior art, propose a kind of mobile node positioning method of wireless sensor network, solve computational process complexity, mobile node locates not accurate enough problem.
The present invention is achieved by following scheme:
Based on a mobile node location algorithm for wireless sensor network, step is as follows:
Step 1, anchor node is arranged on the border that size is a × b × c 3 D stereo region, and the scope of mobile node location is described 3 D stereo region;
Step 2, random selecting anchor node is as aggregation node in the entire network, and aggregation node collects the positional information of each anchor node, to described 3 D stereo regional space with
virtual grid divide, wherein, N ∈ Z
+;
Step 3, chooses the grid vertex of described 3 D stereo region except zone boundary, obtains the distance vector V that it arrives each anchor node;
Step 4, sets up the Mathematical Modeling between distance vector V and the 3 D stereo region mesh vertex coordinates except zone boundary;
Step 5, substitutes into each anchor node distance vector D the coordinate that Mathematical Modeling asks for mobile node by mobile node, realizes locating the position of mobile node.
Further, in the Mathematical Modeling described in step 2, utilize core principle component analysis that distance vector V is converted into characteristic vector.
Further, described characteristic vector is as the input amendment of Mathematical Modeling, the grid vertex position coordinate of described 3 D stereo region except zone boundary as the output sample of Mathematical Modeling, by population and BP neural net combination algorithm to described input amendment and output sample founding mathematical models.
Further, the particle rapidity in described population and BP neural net combination algorithm and the renewal expression formula of position are:
v
id(t+1)＝w·v
id(t)+c
1rand()(P
id(t)-x
id(t))+c
2rand()(P
gd(t)-x
id(t))(1)
x
id(t+1)＝x
id(t)+v
id(t+1)(2)
Wherein, v
id(t+1) speed of i-th particle in t+1 iteration in d dimension is represented; P
idt () represents the individual optimal solution of the i-th particle in t iteration; P
gdt () represents the optimal solution of whole population in t iteration; x
id(t+1) position of i-th particle d dimension in t+1 iteration is represented; c
1, c
2for acceleration constant; Rand () is the random number of 0 ~ 1; W is inertia weight; w
maxfor inertia weight maximum; w
minfor inertia weight minimum value; T is current iteration number of times; M is maximum iteration time.
The present invention's beneficial effect compared to the prior art:
The localization method of the mobile node of wireless network sensor in the past, utilize the RSSI value gathering anchor node and mobile node, the power of network signal is utilized to be converted into the distance vector of anchor node and mobile node, this method is very easily subject to the impact of surrounding enviroment, and prior art is the coordinate according to grid vertex quantity survey (surveying) mobile node, if the virtual grid quantity divided is inadequate, the problem that the mobile node of location is not accurate enough will be caused.The present invention is by extracting the distance vector of grid vertex and anchor node as characteristic vector, utilize and set up the complete of characteristic vector and node location coordinate and accurate Mathematical Modeling, realize the coordinate position of disposable acquisition mobile node, analyze by experiment and show that the present invention can position the position coordinates of mobile node accurately.
Present invention utilizes core principle component analysis method and be converted to characteristic vector to by distance vector, and based on the algorithm founding mathematical models that population and BP neural net combine, outside the accuracy ensureing mobile node location, also reduce the complexity of calculating.
Accompanying drawing explanation
Fig. 1 is flow chart schematic diagram of the present invention;
Fig. 2 is virtual grid partitioning model figure in embodiment;
Fig. 3 is the evolution curve based on fitness value in population-neural network algorithm in embodiment;
Fig. 4 is the position error curve of mobile node in algorithms of different in embodiment.
Embodiment
Below in conjunction with accompanying drawing, the present invention will be further described in detail.
Step (one), suppose one group of wireless sensor node S={S
i| i=1 ..., M} is deployed in three-dimensional cubic body region, and 3 D stereo area size is a × b × c.Each node is isomorphism node, and its communication radius is R, and radius R is greater than the diagonal L in region.Be that the origin of coordinates sets up coordinate system with top left corner apex, front n node S
i(x
i, y
i, z
i) (1≤i≤n) obtain self-position in advance, be called anchor node, anchor node is arranged on 3 D stereo zone boundary.S
i(x
i, y
i, z
i) (n<i≤M) need to determine that the node of position is called mobile node, wherein S by anchor node and localization method
1for coordinate origin.
Step (two), in the entire network random selecting anchor node are as aggregation node, each anchor node uploads the packet comprising own node ID, position to aggregation node, after aggregation node collects the packet of each anchor node, set up network topological diagram and data link table.According to the anchor node distributed intelligence in digital chained list, aggregation node by cubical area with
virtual grid divide, wherein N ∈ Z
+.The grid vertex K of mark except zone boundary
jcoordinate, wherein, j=1,2 ..., (N-1)
3, if Fig. 2 is virtual grid partitioning model.
Step (three), aggregation node collect the distance vector D=[d of mobile node to each anchor node
i1, d
i2, d
i3..., d
in].
Described distance vector V is transformed into feature space from data space by step (four), application core principle component analysis method, obtains the nonlinear characteristic of this distance vector V.
By distance vector D=[d
i1, d
i2, d
i3..., d
in] be set to N number of sample point that q ties up the input space, pass through nonlinear transformation
d is mapped to high-dimensional feature space, namely
: D → F (D),
for sample point corresponding in feature space F.At the sample covariance matrix of feature space be:
Then
characteristic value and the relational expression of characteristic vector be:
Wherein, λ, ν representing matrix respectively
characteristic value and characteristic of correspondence vector, because covariance matrix is real symmetric, thus can find r normal orthogonal characteristic vector, namely there is r untrivialo solution in formula (4).Owing to converting the unknown, matrix
cannot obtain, thus cannot direct solution characteristic vector.According to theory of reproducing kernel space, characteristic vector ν can be generated by the sample in the F of space, Ji Keyou
linear combination represent, wherein,
(3) and (5) formula is substituted into
in, order matrix
can obtain:
Ka＝nλa(6)
Wherein, matrix K is nuclear matrix, and through type (6) can try to achieve the characteristic value of sample in feature space and characteristic vector.
Step (five), using the Non-linear Principal Component feature of above-mentioned gained as input amendment, the position of 3 D stereo region grid vertex except zone boundary is as output sample, utilize population and BP neural net combination algorithm to set up Mathematical Modeling between input amendment and output sample, concrete steps are as follows.
1) input number of nodes setting BP neural net is r, output node number is s, node in hidden layer p, and initialization weights and threshold is the random number between [0,1].Use x
i=(x
i1, x
i2..., x
id) represent a particle, wherein, d is all weights and threshold summations in BP network, as shown in the formula expression:
d＝r×p+p+p×s+s(7)
2) to maximum and the minimum value of inertia weight w, and acceleration constant c
1and c
2carry out initialization, provide population scale R and maximum iteration time M.
3) calculate the real output value of each particle according to BP neural net forward direction, solve the fitness of its mean square error as each particle.
4) best position, the position P that the fitness value comparing each particle lives through with it
idfitness value, the speed of each particle and position are upgraded, as shown in the formula expression:
v
id(t+1)＝w·v
id(t)+c
1rand()(P
id(t)-x
id(t))+c
2rand()(P
gd(t)-x
id(t))(8)
x
id(t+1)＝x
id(t)+v
id(t+1)(9)
Wherein, v
id(t+1) speed of i-th particle in t+1 iteration in d dimension is represented; P
idt () represents the individual optimal solution of the i-th particle in t iteration; P
gdt () represents the optimal solution of whole population in t iteration; x
id(t+1) position of i-th particle d dimension in t+1 iteration is represented; c
1, c
2for acceleration constant; Rand () is the random number of 0 ~ 1; W is inertia weight; w
maxfor inertia weight maximum; w
minfor inertia weight minimum value; T is current iteration number of times; M is maximum iteration time.
5) if above-mentioned calculating meets convergence criterion or reaches maximum iteration time, then particle cluster algorithm is exited, tentative 6) step, otherwise turn back to 3) step.
6) utilize BP neural network algorithm to proceed training, if training result is better than particle cluster algorithm, export the result of BP neural computing, otherwise export the neural computing result of particle cluster algorithm.
Step (six), aggregation node collect the distance vector V=[v of the grid vertex of 3 D stereo except zone boundary to anchor node
i1, v
i2, v
i3..., v
in] as input amendment, substitute into the coordinate obtaining mobile node in above-mentioned Mathematical Modeling, thus obtain the position of mobile node.
MATLAB emulation experiment:
If three-dimensional cubic body region is 50m × 50m × 25m, 3 D stereo zone boundary is chosen 16 nodes as anchor node, in three-dimensional localization region, random selecting 10 points position test as mobile node.The propagation path loss model of wireless signal adopts log-distance path loss model model, the transmit signal strength P of unknown node and anchor node
tfor 30dBm, reference distance d
0for 20m, transmitter antenna gain (dBi) G
twith receiving antenna gain G
rfor 1dBi, path loss index n is 2.Cubical area divides with the virtual grid of 5m × 5m × 2.5m by aggregation node, then the grid vertex number except zone boundary is 729, and it is 16 to the dimension of distance vector between each anchor node.
Core principle component analysis method is utilized to carry out feature extraction to all distance vectors and sort to characteristic value.Result of calculation is as shown in table 1, the accumulation contribution rate of front 4 principal components reaches 97.76%, determine that required principal component number is 4 according to accumulation contribution rate, show core principle component analysis method dimensionality reduction successful, extract corresponding principal component, calculate the characteristic vector of its projection on feature space as sample.
Table 1KPCA analysis result
Then, characteristic vector extraction obtained is as input amendment, and except zone boundary, the position coordinates of grid vertex is as output sample, sets up the Algorithm for Training data set of population and the combination of BP neural net.According to training dataset feature, according to Kolmogrov theorem, choose that BP network input number of nodes is r=4, output node number is s=3, node in hidden layer is p=10.Wherein, the transfer function of hidden neuron adopts S type tan tansig, and the neuronic transfer function of output layer then adopts logsig, and the iterations of BP network is 100, and learning rate is 0.1, and training error target is 0.00001.Setting population scale R=50, acceleration constant c
1and c
2be all 1.4944, inertia weight maximum w
max=1, inertia weight minimum value w
min=-1, maximum iteration time M=50, population scale R=30, convergence precision ε=10
-6.The training process of population and BP neural net combination algorithm and traditional BP neural net is contrasted, fitness value change as shown in Figure 3, show that the fitness value of population and BP neural net combination algorithm declines rapidly from Fig. 3, namely adaptive optimal control angle value is reached through 25 evolution, illustrate that particle cluster algorithm has good effect of optimization, best weight value and the threshold value of BP neural net can be searched out with less cost.
Choose 10 groups of mobile node samples as test sample book, the Mathematical Modeling of above-mentioned foundation is tested, by comparing with traditional BP neural net and SVM SVMs, as shown in Figure 4, the position error of the mobile node obtained based on population and BP neural network algorithm is significantly less than and adopts additive method to obtain.Demonstrate the present invention is directed to mobile node can realize accurately position location.
The basic scheme that above-described embodiment reflects is:
By obtaining grid vertex except zone boundary to the distance vector of anchor node, setting up the Mathematical Modeling between this distance vector and described mesh vertex coordinates, solving the position coordinates of mobile node based on described Mathematical Modeling.
According to above technical scheme, the kernel function adopting core principle component analysis method to adopt in embodiment step (four) is k (x, x ')=[(x, x ')+1]
2, also can adopt other forms of kernel function in practical application, as: rbf core, sigmoid kernel function etc.
In the present embodiment when setting up the Mathematical Modeling between distance vector and coordinate, the mode that the population of main utilization and BP neural net combine, can select other algorithms to carry out location, position according to the demand of mobile node positioning precision for different experiments object.
Under the thinking of basic scheme of the present invention; the mode easily expected to those skilled in the art is adopted to convert the technological means in above-described embodiment, replace, revise; and the effect played goal of the invention that is substantially identical with the relevant art means in the present invention, that realize is also substantially identical, the technical scheme formed so still falls within the scope of protection of the present invention.
Claims (4)
1. based on a mobile node positioning method for wireless sensor network, it is characterized in that, step is as follows:
Step 1, anchor node is arranged on the border that size is a × b × c 3 D stereo region, and the scope of mobile node location is described 3 D stereo region;
Step 2, random selecting anchor node is as aggregation node in the entire network, and aggregation node collects the positional information of each anchor node, to described 3 D stereo regional space with
virtual grid divide, wherein, N ∈ Z
+;
Step 3, chooses the grid vertex of described 3 D stereo region except zone boundary, obtains the distance vector V that it arrives each anchor node;
Step 4, sets up the Mathematical Modeling between distance vector V and the 3 D stereo region mesh vertex coordinates except zone boundary;
Step 5, substitutes into each anchor node distance vector D the coordinate that Mathematical Modeling asks for mobile node by mobile node, realizes locating the position of mobile node.
2. a kind of mobile node positioning method based on wireless sensor network according to claim 1, is characterized in that in the Mathematical Modeling described in step 2, utilizes core principle component analysis that distance vector V is converted into characteristic vector.
3. a kind of mobile node positioning method based on wireless sensor network according to claim 2, it is characterized in that the input amendment of described characteristic vector as Mathematical Modeling, the grid vertex position coordinate of described 3 D stereo region except zone boundary as the output sample of Mathematical Modeling, by population and BP neural net combination algorithm to described input amendment and output sample founding mathematical models.
4. a kind of mobile node positioning method based on wireless sensor network according to claim 3, is characterized in that the renewal expression formula of particle rapidity in described population and BP neural net combination algorithm and position is:
v
id(t+1)＝w·v
id(t)+c
1rand()(P
id(t)-x
id(t))+c
2rand()(P
gd(t)-x
id(t))(1)
x
id(t+1)＝x
id(t)+v
id(t+1)(2)
Wherein, v
id(t+1) speed of i-th particle in t+1 iteration in d dimension is represented; P
idt () represents the individual optimal solution of the i-th particle in t iteration; P
gdt () represents the optimal solution of whole population in t iteration; x
id(t+1) position of i-th particle d dimension in t+1 iteration is represented; c
1, c
2for acceleration constant; Rand () is the random number of 0 ~ 1; W is inertia weight; w
maxfor inertia weight maximum; w
minfor inertia weight minimum value; T is current iteration number of times; M is maximum iteration time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510445657.3A CN105307264B (en) | 2015-07-27 | 2015-07-27 | A kind of mobile node positioning method of wireless sensor network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510445657.3A CN105307264B (en) | 2015-07-27 | 2015-07-27 | A kind of mobile node positioning method of wireless sensor network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105307264A true CN105307264A (en) | 2016-02-03 |
| CN105307264B CN105307264B (en) | 2019-01-08 |
Family
ID=55203881
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510445657.3A Expired - Fee Related CN105307264B (en) | 2015-07-27 | 2015-07-27 | A kind of mobile node positioning method of wireless sensor network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105307264B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106912105A (en) * | 2017-03-08 | 2017-06-30 | 哈尔滨理工大学 | 3-D positioning method based on PSO_BP neutral nets |
| CN107343052A (en) * | 2017-07-25 | 2017-11-10 | 苏州大学 | The physical distribution monitoring system that a kind of WSN is combined with RFID |
| CN107992648A (en) * | 2017-11-15 | 2018-05-04 | 南京航空航天大学 | A kind of Adaptive radial basis function neural network carries out aeroengine thrust algorithm for estimating |
| CN108990833A (en) * | 2018-09-11 | 2018-12-14 | 河南科技大学 | A kind of animal movement behavior method of discrimination and device based on location information |
| CN109327797A (en) * | 2018-10-15 | 2019-02-12 | 山东科技大学 | Mobile robot indoor locating system based on WiFi network signal |
| CN109600706A (en) * | 2017-09-29 | 2019-04-09 | 北京布科思科技有限公司 | Detect and calculate the method and system of uwb anchor point coordinate |
| CN109618284A (en) * | 2019-02-20 | 2019-04-12 | 清华珠三角研究院 | Three-dimensional base station positioning method and device |
| CN109814066A (en) * | 2019-01-24 | 2019-05-28 | 西安电子科技大学 | RSSI indoor positioning distance measuring method, indoor positioning platform based on neural network learning |
| CN110726970A (en) * | 2018-07-17 | 2020-01-24 | Tcl集团股份有限公司 | Target positioning method and terminal equipment |
| CN113253204A (en) * | 2021-03-08 | 2021-08-13 | 同济大学 | Positioning method, system and device based on pyroelectric infrared sensor |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130084886A1 (en) * | 2011-10-03 | 2013-04-04 | Cellular Specialties, Inc. | Pilot beacon system for indoor positioning |
| CN103118333A (en) * | 2013-01-25 | 2013-05-22 | 河南科技大学 | Similarity based wireless sensor network mobile node positioning method |
| 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 |
| CN104202816A (en) * | 2014-08-22 | 2014-12-10 | 西北大学 | Large scale three dimension (3D) wireless sensor network node location method based on convex partition |
| CN104301996A (en) * | 2014-04-15 | 2015-01-21 | 河南科技大学 | Wireless sensor network positioning method |
| CN104363654A (en) * | 2014-11-04 | 2015-02-18 | 浙江师范大学 | Wireless sensor network three-dimensional node positioning method based on tunneling method |
-
2015
- 2015-07-27 CN CN201510445657.3A patent/CN105307264B/en not_active Expired - Fee Related
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130084886A1 (en) * | 2011-10-03 | 2013-04-04 | Cellular Specialties, Inc. | Pilot beacon system for indoor positioning |
| 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 |
| CN103118333A (en) * | 2013-01-25 | 2013-05-22 | 河南科技大学 | Similarity based wireless sensor network mobile node positioning method |
| CN104301996A (en) * | 2014-04-15 | 2015-01-21 | 河南科技大学 | Wireless sensor network positioning method |
| CN104202816A (en) * | 2014-08-22 | 2014-12-10 | 西北大学 | Large scale three dimension (3D) wireless sensor network node location method based on convex partition |
| CN104363654A (en) * | 2014-11-04 | 2015-02-18 | 浙江师范大学 | Wireless sensor network three-dimensional node positioning method based on tunneling method |
Non-Patent Citations (1)
| Title |
|---|
| 王俊等: "无线传感器网络三维定位交叉粒子群算法", 《农业自动化与环境控制》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106912105A (en) * | 2017-03-08 | 2017-06-30 | 哈尔滨理工大学 | 3-D positioning method based on PSO_BP neutral nets |
| CN106912105B (en) * | 2017-03-08 | 2020-06-09 | 哈尔滨理工大学 | Three-dimensional positioning method based on PSO _ BP neural network |
| CN107343052B (en) * | 2017-07-25 | 2019-12-27 | 苏州大学 | Logistics monitoring system combining WSN and RFID |
| CN107343052A (en) * | 2017-07-25 | 2017-11-10 | 苏州大学 | The physical distribution monitoring system that a kind of WSN is combined with RFID |
| CN109600706A (en) * | 2017-09-29 | 2019-04-09 | 北京布科思科技有限公司 | Detect and calculate the method and system of uwb anchor point coordinate |
| CN107992648A (en) * | 2017-11-15 | 2018-05-04 | 南京航空航天大学 | A kind of Adaptive radial basis function neural network carries out aeroengine thrust algorithm for estimating |
| CN107992648B (en) * | 2017-11-15 | 2021-04-20 | 南京航空航天大学 | Adaptive RBF neural network algorithm for estimating thrust of aircraft engine |
| CN110726970A (en) * | 2018-07-17 | 2020-01-24 | Tcl集团股份有限公司 | Target positioning method and terminal equipment |
| CN108990833A (en) * | 2018-09-11 | 2018-12-14 | 河南科技大学 | A kind of animal movement behavior method of discrimination and device based on location information |
| CN109327797B (en) * | 2018-10-15 | 2020-09-29 | 山东科技大学 | Indoor positioning system of mobile robot based on WiFi network signal |
| CN109327797A (en) * | 2018-10-15 | 2019-02-12 | 山东科技大学 | Mobile robot indoor locating system based on WiFi network signal |
| CN109814066A (en) * | 2019-01-24 | 2019-05-28 | 西安电子科技大学 | RSSI indoor positioning distance measuring method, indoor positioning platform based on neural network learning |
| CN109814066B (en) * | 2019-01-24 | 2023-08-18 | 西安电子科技大学 | RSSI indoor positioning distance measurement method and indoor positioning platform based on neural network learning |
| CN109618284A (en) * | 2019-02-20 | 2019-04-12 | 清华珠三角研究院 | Three-dimensional base station positioning method and device |
| CN113253204A (en) * | 2021-03-08 | 2021-08-13 | 同济大学 | Positioning method, system and device based on pyroelectric infrared sensor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105307264B (en) | 2019-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105307264A (en) | Mobile node positioning method for wireless sensor network | |
| CN103247041B (en) | A kind of dividing method of the cloud data of the many geometric properties based on local sampling | |
| CN103413151B (en) | Hyperspectral image classification method based on figure canonical low-rank representation Dimensionality Reduction | |
| CN103118333B (en) | Similarity based wireless sensor network mobile node positioning method | |
| CN110234085B (en) | Indoor position fingerprint map generation method and system based on anti-migration network | |
| CN108709557B (en) | Indoor map generation method based on multi-user track fitting | |
| CN104318622B (en) | Triangular mesh modeling method of indoor scene inhomogeneous three dimension point cloud data | |
| CN104375117B (en) | Object localization method and system | |
| Li et al. | Hybrid self-adaptive learning based particle swarm optimization and support vector regression model for grade estimation | |
| CN105512759A (en) | Urban CA model parameter optimization method based on biogeographic optimization algorithm | |
| CN103885030A (en) | Locating method of mobile node in wireless sensor network | |
| CN104535960B (en) | Indoor rapid positioning method based on RFID | |
| CN110110763A (en) | A kind of grating map fusion method based on maximum public subgraph | |
| CN106792540A (en) | A kind of improvement DV Hop localization methods based on route matching | |
| CN106886980A (en) | A kind of enhanced method of point cloud density based on three-dimensional laser radar target identification | |
| CN103517413A (en) | WSN node locating method based on heterogeneous double-population particle swarm optimization | |
| CN107979817A (en) | A kind of mobile terminal two dimension fingerprint positioning method | |
| CN105469445A (en) | Step size changeable map generation method | |
| CN109885082A (en) | The method that a kind of lower unmanned aerial vehicle flight path of task based access control driving is planned | |
| CN104050254B (en) | The method that feature database in 3D rooms is built using house data | |
| Qian et al. | Optimal recharge scheduler for drone-to-sensor wireless power transfer | |
| CN105513051B (en) | A kind of Processing Method of Point-clouds and equipment | |
| Ding et al. | OGI-SLAM2: A hybrid map SLAM framework grounded in inertial-based SLAM | |
| Li et al. | UAV trajectory optimization for spectrum cartography: a PPO approach | |
| Kim et al. | Formulating human mobility model in a form of continuous time Markov chain |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190108 Termination date: 20190727 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |