CN113866716A - RSSI (received Signal Strength indicator) -based weighted neighbor positioning method - Google Patents
RSSI (received Signal Strength indicator) -based weighted neighbor positioning method Download PDFInfo
- Publication number
- CN113866716A CN113866716A CN202111234353.4A CN202111234353A CN113866716A CN 113866716 A CN113866716 A CN 113866716A CN 202111234353 A CN202111234353 A CN 202111234353A CN 113866716 A CN113866716 A CN 113866716A
- Authority
- CN
- China
- Prior art keywords
- rssi
- positioning
- node
- data
- value
- 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
Images
Classifications
-
- 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
- G01S5/0252—Radio frequency fingerprinting
-
- 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
- G01S5/0278—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 involving statistical or probabilistic considerations
-
- 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
- G01S5/0295—Proximity-based methods, e.g. position inferred from reception of particular signals
-
- 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
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Probability & Statistics with Applications (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a neighbor positioning method based on RSSI weighting, which comprises the following steps: s1: deploying reference nodes in the test area, S2: collecting information of the reference node, S3: summarizing the information collected in the step S2 into a fingerprint database, and in the step S4: deploying an unknown node, and collecting information of the unknown node, and step S5: the data of S3 and S4 are integrated and processed to be used as a positioning data set, S6: converting all RSSI data in the fingerprint database into distances, and step S7: and (4) obtaining a derivative function value, wherein the derivative function value is collected into a positioning data set and used as a reference point weight material, S8: obtaining the positioning coordinates of the unknown node, S9: calculating the positioning error of the unknown node through the S8 and the collected coordinate value; the invention takes the propagation function of the signal strength as a research object, solves the problem of inaccurate positioning precision caused by nonlinear change of the RSSI value in the propagation process, reduces the positioning error and improves the positioning precision.
Description
Technical Field
The invention belongs to the technical field of network positioning, and particularly relates to a neighbor positioning method based on RSSI weighting.
Background
The self-propelled trolley conveying system is a common intelligent conveying device and is widely applied to the industries and fields of automobiles, engineering machinery, machine manufacturing, light industry, tobacco, chemical industry, automatic warehouses and the like. The traditional self-propelled trolley is controlled in a wired communication mode, data communication is carried out through a sliding contact line, the mode has the defects of limited information exchange amount, complex electrical installation, high failure rate and the like, and the increasing process and performance requirements cannot be met.
The digitization and the intellectualization of the workshop are the inevitable trend of the informatization development of the enterprise. At present, the problems that the production process is difficult to monitor comprehensively, and products and manufacturing resources are difficult to track and position accurately and the like generally exist in the production process. Due to the shielding of the building on the satellite signal, the GNSS is difficult to provide positioning service indoors, so that the indoor space becomes a blind area for positioning. With the deep development of the internet, technologies such as the internet of things and 5G are gradually mature, and the active sensing and all-round monitoring of manufacturing resources and execution states are realized through an indoor positioning technology, so that the intelligent scheduling and optimization decision of the manufacturing process and the resources is realized. It is seen that location based services will play an increasingly important role in the future.
In the prior art (Wangbaoyuan, Liu Ching, the Miu Bao, Jia Rui, Ganjing, Huangluo. improved weighted k neighbor algorithm [ J ] in WiFi fingerprint positioning, the university of Sian electronic technology, 2019,46(05): 41-47.) the problem of RSSI-d nonlinearity is improved to a certain extent by adopting the signal intensity mean value of fingerprint data and test data as the basis of weighted k neighbor algorithm weight distribution, but the number of nearest neighbor reference points is selected as a fixed value, the characteristics of each test point cannot be completely expressed in the calculation process, and the positioning accuracy also cannot reach a higher level.
In the prior art (rigorous new indoor positioning technology research [ D ] based on WiFi signal characteristics, the university of sienna electronic technology, 2020.), a matching algorithm based on a probability distribution interval is provided at the selection stage of adjacent fingerprints, and adjacent fingerprint points are selected according to the RSSI strength and the probability distribution interval, so that the positioning accuracy is effectively improved compared with the conventional matching fingerprint positioning algorithm, but the problem of RSSI-D nonlinearity exists, and the quality requirement of fingerprint data is high.
In the prior art (Wangzhuan, WiFi indoor positioning algorithm research [ D ] based on position fingerprints, Liaoning engineering technology university, 2019.), an intelligent algorithm is adopted in the construction stage of an offline fingerprint library, a dense fingerprint library is obtained after less fingerprint data are trained, and the weight is calculated by adopting an AP weighting method, so that the positioning precision is improved by more than 11%. But because a logarithmic decrement function model is also adopted in the training process, the problem of nonlinearity still exists in the weight distribution stage.
Disclosure of Invention
The invention provides a neighbor positioning method based on RSSI weighting, and aims to solve the problem of inaccurate positioning accuracy caused by nonlinear change of RSSI values in a propagation process.
In order to solve the technical problems, the technical scheme of the invention is as follows: a neighbor positioning method based on RSSI weighting comprises the following steps: step S1: the method comprises the steps that four anchor nodes are deployed at the boundary of a test area, one node is placed in the test area and serves as a reference node, the reference node periodically sends self position information to the four anchor nodes, and the four anchor nodes extract received information and then forward the information to a computer;
step S2: collecting information sent by a reference node on 165 test bits in a test area, wherein the information content is as follows: information source number, RSSI value and physical coordinate;
step S3: summarizing the information collected in the step S2 into a fingerprint database which is used as the basis of the online positioning stage;
step S4: an unknown node is deployed on a random test position in a test area, the unknown node sends information to four anchor nodes, the four anchor nodes extract the received information and transmit the information to a computer, the information is summarized into a test set, and the data content of the test set is as follows; information source number, RSSI value and real coordinate value of the unknown node;
step S5: integrating the data of the test set in the step S4 and the information source number and the RSSI value in the fingerprint database in the step S3 into a whole data set; processing data in the whole data set by using fuzzy C-means clustering, and extracting fingerprint data which belong to the same category as the data in the test set from the whole data set to be used as a positioning data set;
step S6: converting all RSSI data in the fingerprint database of step S3 into distances using the following formula; the formula is as follows:
(ii) a A is a signal value, A is a signal RSSI value at a position where the anchor node is 0.8-1.2 m away from a reference node, the unit of A is dB, d is the distance between the anchor node and the reference node, the unit of d is meter, and n is an environmental loss factor;
step S7: fitting the function value calculated in the step S6, calculating a derivative function value by using a derivative function algorithm, extracting the corresponding derivative function value, and summarizing the derivative function value into a positioning data set to be used as a reference point weight material;
step S8: obtaining the positioning coordinates (x, y) of the unknown node according to the data of the weighted material in the step S7 by using a WKNN positioning algorithm;
step S9: representing the positioning error of the unknown node through absolute distance, wherein (X, Y) is the calculated coordinate of the unknown node, and (X, Y) is the real coordinate of the unknown node; will absolute distance
As a standard for judging the positioning accuracy, the closer the value is to 0, the more ideal the positioning effect is; the positioning error formula is as follows:
further limiting the above technical solution, in step S1, the time for acquiring the information sent by the anchor node is 60S.
Further limiting the above technical solution, in step S2, the distance between adjacent test bits is 0.5 m.
To further limit the above technical solution, in step S5, the data in the whole data set are randomly scrambled for 3 times.
Further defined to the above technical solution, in the step S6, a is that the anchor node is 1m away from the reference node.
Further limiting the above technical solution, in step S7, the reference point weight W is calculated as follows: the value of the derivative function is K, the weight of the weighted K nearest neighbor algorithm is redistributed, and the distribution formula is as follows:
wherein
For the derivative values of the RSSI-d function corresponding to each fingerprint node in the set of location data,
and the Euclidean distance between the fingerprint RSSI data of the same type of fingerprint nodes and the RSSI value of the unknown node is obtained.
Further limiting the above technical solution, in step S8, the positioning coordinate calculation formula is:
(ii) a Calculating the calculated coordinates (x, y) of the unknown node using the weights, wherein (x)i,yi) The real coordinate values of the fingerprint nodes.
The invention has the beneficial effects that: in the ranging stage, the propagation function of the signal strength is taken as a research object, so that the problem of inaccurate positioning accuracy caused by nonlinear change of the RSSI value in the propagation process is solved; and the curve slope of the RSSI-d is introduced as the weight basis of the adjacent fingerprint nodes, and the reciprocal distance of the corresponding anchor node and the curve slope are used for calculating the weight, so that the anchor nodes with the same RSSI value have the weight distinguishing basis, the positioning error is reduced, and the positioning precision is improved.
Drawings
FIG. 1 is a flow chart of the present invention.
Fig. 2 is a deployment diagram of anchor nodes and reference nodes in the present invention.
FIG. 3 is a diagram of test bit deployment in the present invention.
Fig. 4 is a signal propagation curve in the present invention.
Fig. 5 is a formula for converting RSSI data to distance in the present invention.
Fig. 6 is a reference point weight formula in the present invention.
FIG. 7 is an unknown node coordinate formula in the present invention.
Fig. 8 is a positioning error equation in the present invention.
Detailed Description
As shown in fig. 1, a method for neighbor positioning based on RSSI weighting includes the following steps: step S1: as shown in fig. 2, four anchor nodes 2 are deployed at the boundary of a test area 1, a node is placed in the test area as a reference node 3, the reference node periodically sends self-position information to the four anchor nodes, and the four anchor nodes extract the received information and forward the information to a computer; in the acquisition process, the reference node periodically sends self messages at a time interval of 0.5s, and the acquisition time is set to be 60s, so that signal fluctuation caused by the test environment can be eliminated, and the accuracy of signals can be ensured;
step S2: as shown in fig. 3, information sent by the reference node on 165 test bits 4 in the test area is collected, and the information content is as follows: information source number, RSSI value and physical coordinate; because the accuracy of the rssi signal is low, if the distance between the test bits is too small, the distance difference can not be represented in the signal value, and in order to ensure the diversity of the fingerprint data points, the distance between adjacent test bits is set to be 0.5m in the test process;
step S3: summarizing the information collected in the step S2 into a fingerprint database which is used as the basis of the online positioning stage;
step S4: an unknown node is deployed on a random test position in a test area, the unknown node sends information to four anchor nodes, the four anchor nodes extract the received information and transmit the information to a computer, the information is summarized into a test set, and the data content of the test set is as follows; information source number, RSSI value and real coordinate value of the unknown node;
step S5: integrating the data of the test set in the step S4 and the information source number and the RSSI value in the fingerprint database in the step S3 into a whole data set; processing data in the whole data set by using fuzzy C-means clustering, and extracting fingerprint data which belong to the same category as the data in the test set from the whole data set to be used as a positioning data set;
the whole-body data set is randomly disordered for 3 times, and the original distribution rule of initial information is disturbed, so that the reliability of a clustering result is better, and because a clustering label is arranged in a clustering algorithm, the data in a disordered state can embody a more real clustering result;
clustering the summarized data by using a fuzzy C-means clustering algorithm to obtain the category and membership degree vector of each data vector; screening out vectors in all fingerprint databases with the same class as the data vectors of each test set according to the cluster class and the membership value, and summarizing the vectors into a positioning data set according to the class;
the clustering algorithm is a common data processing algorithm, wherein FCM clustering belongs to flexible clustering, and the proximity degree of data and classes can be displayed through membership degree vectors while representing the classification result of each data; the K value in the traditional WKNN algorithm is generally a fixed value and has certain limitation in the positioning solving process because the selection of the K value in the WKNN algorithm also has great influence on the positioning accuracy; when the fingerprint data of the same category is adopted for positioning, K of the later WKNN positioning algorithm can be converted into the number of the same type of data, so that the dynamic self-adaptive selection of the WKNN algorithm K is realized;
step S6: converting all RSSI data in the fingerprint database of step S3 into distances using the following formula; as shown in fig. 5, the formula is:
(ii) a A is a signal value, A is a signal RSSI value at a position 1m away from the anchor node and the reference node, the unit of A is dB (decibel), d is a distance between the anchor node and the reference node, the unit of d is meter, and n is an environmental loss factor; in the step, the value of d is calculated by RSSI and A value; when the length is 1 meter, the unknown number n is excluded according to the logarithmic relation lg (1) being 0, so that the value A is determined; due to different environments, rssi has larger difference, and 1 meter is taken to eliminate the influence of the environment on n, so that the accuracy of subsequent fitting is improved;
step S7: fitting the function value calculated in the step S6, calculating a derivative function value by using a derivative function algorithm, extracting the corresponding derivative function value, and summarizing the derivative function value into a positioning data set to be used as a reference point weight material; because a logarithmic distribution rule is presented between the signal strength value rssi and the distance value d, the influence of the nonlinearity is also a main problem of inaccurate positioning according to the rssi; the derivative function of the function has the same rule in distribution as the original function and can be used as the weight to reduce the influence of the nonlinearity;
in step S7, the reference point weight W is calculated as follows: the derivative function has a value of K, and the weights of the weighted K-nearest neighbor algorithm are redistributed, as shown in fig. 6, the distribution formula is:
wherein
For the derivative values of the RSSI-d function corresponding to each fingerprint node in the set of location data,
the Euclidean distance between the fingerprint RSSI data of the same type of fingerprint nodes and the RSSI value of the unknown node is calculated;
step S8: obtaining the positioning coordinates (x, y) of the unknown node according to the data of the weighted material in the step S7 by using a WKNN positioning algorithm; in step S8, as shown in fig. 7, the positioning coordinate calculation formula is:
(ii) a Calculating the calculated coordinates (x, y) of the unknown node using the weights, wherein (x)i,yi) The real coordinate value of the fingerprint node;
step S9: representing the positioning error of the unknown node through absolute distance, wherein (X, Y) is the calculated coordinate of the unknown node, and (X, Y) is the real coordinate of the unknown node; will absolute distance
As a standard for judging the positioning accuracy, the closer the value is to 0, the more ideal the positioning effect is; as shown in fig. 8, the positioning error formula is:
since the RSSI value of a wireless signal has a nonlinear characteristic in space propagation, there are cases where the RSSI difference is equal and the distance is different when RSSI data is generally used as a positioning basis. As shown in fig. 4, point B is used as an unknown node RSSI value point, point a is used as a reference node RSSI value, point C is used as a reference node RSSI value, and point a and point C participate in the positioning process of point B; rb-Ra|=|Rb-RcI, it is determined that the influence of A and C on B is the same, and in fact, from a distance perspective, there is db-da|<|db-dcThe situation of | therefore, it should actually be that the influence of the point a on the point B should be greater than the influence of the point C on the point B. Therefore, when the weighted neighbor positioning algorithm based on RSSI calculation is directly used, the positioning error is large due to the nonlinear influence of the RSSI in weight distribution. The method combines the curve characteristics of the RSSI-d, corrects the division of the weight by adopting the derivative function (slope), and effectively improves the positioning accuracy of the WKNN positioning algorithm.
Claims (7)
1. A neighbor positioning method based on RSSI weighting comprises the following steps: step S1: the method comprises the steps that four anchor nodes are deployed at the boundary of a test area, one node is placed in the test area and serves as a reference node, the reference node periodically sends self position information to the four anchor nodes, and the four anchor nodes extract received information and then forward the information to a computer;
step S2: collecting information sent by a reference node on 165 test bits in a test area, wherein the information content is as follows: information source number, RSSI value and physical coordinate;
step S3: summarizing the information collected in the step S2 into a fingerprint database which is used as the basis of the online positioning stage;
step S4: an unknown node is deployed on a random test position in a test area, the unknown node sends information to four anchor nodes, the four anchor nodes extract the received information and transmit the information to a computer, the information is summarized into a test set, and the data content of the test set is as follows; information source number, RSSI value and real coordinate value of the unknown node;
step S5: integrating the data of the test set in the step S4 and the information source number and the RSSI value in the fingerprint database in the step S3 into a whole data set; processing data in the whole data set by using fuzzy C-means clustering, and extracting fingerprint data which belong to the same category as the data in the test set from the whole data set to be used as a positioning data set;
step S6: converting all RSSI data in the fingerprint database of step S3 into distances using the following formula; the formula is as follows:
(ii) a A is a signal value, A is a signal RSSI value at a position where the anchor node is 0.8-1.2 m away from a reference node, the unit of A is dB, d is the distance between the anchor node and the reference node, the unit of d is meter, and n is an environmental loss factor;
step S7: fitting the function value calculated in the step S6, calculating a derivative function value by using a derivative function algorithm, extracting the corresponding derivative function value, and summarizing the derivative function value into a positioning data set to be used as a reference point weight material;
step S8: obtaining the positioning coordinates (x, y) of the unknown node according to the data of the weighted material in the step S7 by using a WKNN positioning algorithm;
step S9: representing the positioning error of the unknown node through absolute distance, wherein (X, Y) is the calculated coordinate of the unknown node, and (X, Y) is the real coordinate of the unknown node; will absolute distance
As a standard for judging the positioning accuracy, the closer the value is to 0, the more ideal the positioning effect is; error in positioningThe formula is as follows:
2. the RSSI-based weighted neighbor positioning method of claim 1, wherein: in step S1, the time for the collecting anchor node to send information is 60S.
3. The RSSI-based weighted neighbor positioning method according to claim 1 or 2, wherein: in step S2, the distance between adjacent test bits is 0.5 m.
4. The RSSI-based weighted neighbor positioning method of claim 3, wherein: in step S5, the data in the entire data set is randomly scrambled 3 times.
5. The RSSI-based weighted neighbor positioning method of claim 1, 2 or 4, wherein: in step S6, a is the distance between the anchor node and the reference node is 1 m.
6. The RSSI-based weighted neighbor positioning method of claim 5, wherein: in step S7, the reference point weight W is calculated as follows: the value of the derivative function is K, the weight of the weighted K nearest neighbor algorithm is redistributed, and the distribution formula is as follows:
wherein
For the derivative values of the RSSI-d function corresponding to each fingerprint node in the set of location data,
and the Euclidean distance between the fingerprint RSSI data of the same type of fingerprint nodes and the RSSI value of the unknown node is obtained.
7. The RSSI-based weighted neighbor positioning method of claim 1, 2, 4 or 6, wherein: in step S8, the positioning coordinate calculation formula is:
(ii) a Calculating the calculated coordinates (x, y) of the unknown node using the weights, wherein (x)i,yi) The real coordinate values of the fingerprint nodes.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111234353.4A CN113866716A (en) | 2021-10-22 | 2021-10-22 | RSSI (received Signal Strength indicator) -based weighted neighbor positioning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111234353.4A CN113866716A (en) | 2021-10-22 | 2021-10-22 | RSSI (received Signal Strength indicator) -based weighted neighbor positioning method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113866716A true CN113866716A (en) | 2021-12-31 |
Family
ID=78997221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111234353.4A Pending CN113866716A (en) | 2021-10-22 | 2021-10-22 | RSSI (received Signal Strength indicator) -based weighted neighbor positioning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113866716A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236247A (en) * | 2023-11-16 | 2023-12-15 | 零壹半导体技术(常州)有限公司 | Signal shielding wire generation method for chip test |
-
2021
- 2021-10-22 CN CN202111234353.4A patent/CN113866716A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117236247A (en) * | 2023-11-16 | 2023-12-15 | 零壹半导体技术(常州)有限公司 | Signal shielding wire generation method for chip test |
| CN117236247B (en) * | 2023-11-16 | 2024-01-23 | 零壹半导体技术(常州)有限公司 | Signal shielding wire generation method for chip test |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111654874B (en) | Wireless sensor network anomaly detection method | |
| CN113159714B (en) | Meteorological data correction method for power grid | |
| CN112135248B (en) | WIFI fingerprint positioning method based on K-means optimal estimation | |
| CN110430224B (en) | Communication network abnormal behavior detection method based on random block model | |
| CN110109055B (en) | Indoor positioning method based on RSSI ranging | |
| CN108307301A (en) | Indoor orientation method based on RSSI rangings and track similitude | |
| CN107861098B (en) | Intelligent court positioning system and method | |
| CN114189809A (en) | Indoor positioning method based on convolutional neural network and high-dimensional 5G observation characteristics | |
| CN106412841A (en) | Indoor location method based on DBSCAN algorithm | |
| CN113271539B (en) | Indoor target positioning method based on improved CNN model | |
| CN113866716A (en) | RSSI (received Signal Strength indicator) -based weighted neighbor positioning method | |
| CN107071894B (en) | Indoor positioning optimization algorithm based on WiFi | |
| CN112444778A (en) | Reference point weighted trilateral centroid positioning method based on DBSCAN | |
| CN118051800B (en) | Intelligent processing method for in-mine monitoring data based on cloud edge cooperation | |
| CN112100243B (en) | Abnormal aggregation detection method based on massive space-time data analysis | |
| CN112910699A (en) | Intelligent fault detection method and device for power internet of things | |
| CN117641240A (en) | Method and device for indoor positioning by utilizing neural network | |
| CN116362036B (en) | High-speed rail equipment fault early warning method and system | |
| Liu | Research on wsn node localization algorithm based on rssi iterative centroid estimation | |
| JP2017138708A (en) | Program, device, and method for detecting time series change point by scalar feature value | |
| CN116234005A (en) | Indoor positioning method for multiple buildings | |
| CN116828529B (en) | Intelligent community communication signal safety monitoring and early warning platform based on Internet of things | |
| CN116801192B (en) | Indoor electromagnetic fingerprint updating method and system by end cloud cooperation | |
| CN115297435B (en) | RSSI self-adaptive ranging model matching method | |
| CN117335912B (en) | Spectrum intelligent sensing method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |