CN116033345A - Indoor abnormal signal high-precision positioning method, system and device - Google Patents
Indoor abnormal signal high-precision positioning method, system and device Download PDFInfo
- Publication number
- CN116033345A CN116033345A CN202211664148.6A CN202211664148A CN116033345A CN 116033345 A CN116033345 A CN 116033345A CN 202211664148 A CN202211664148 A CN 202211664148A CN 116033345 A CN116033345 A CN 116033345A
- Authority
- CN
- China
- Prior art keywords
- signal
- grid
- region
- positioning
- acquired
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims description 14
- 239000000523 sample Substances 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000004807 localization Effects 0.000 claims description 4
- 238000005192 partition Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims description 4
- 101100272279 Beauveria bassiana Beas gene Proteins 0.000 claims description 3
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 4
- 238000013507 mapping Methods 0.000 abstract description 4
- 238000004891 communication Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention provides a high-precision positioning method, system and device for indoor abnormal signals, and belongs to the technical field of wireless signal positioning. The method comprises the following steps: the signal receiver is arranged in the space to be positioned, and the area and the grid division are carried out; setting fingerprint acquisition points, and acquiring signal intensity data of abnormal signals sent by the fingerprint acquisition points; preprocessing the acquired signal intensity data to generate corresponding acquired fingerprints; training a region positioning model and a grid positioning model by using the collected fingerprints; and acquiring signal intensity data acquired by the signal receiver in real time, predicting the position of a region to which the abnormal signal belongs by using a region positioning model, predicting the grid position of the abnormal signal by using a grid positioning model according to the predicted region position, and generating coordinates of the abnormal signal. The invention uses machine learning algorithm to construct fingerprint map database and algorithm model, and can inquire the actual position of the target signal by comparing the nonlinear mapping relation between the fingerprint and the coordinates.
Description
Technical Field
The invention relates to the technical field of wireless signal positioning, in particular to a method, a system and a device for positioning indoor abnormal signals with high precision.
Background
Along with the vigorous development of informatization technology, the information security problem is more serious, and in order to ensure that the indoor information security of a secret-related place is not threatened, the real-time monitoring and the accurate positioning of abnormal suspicious signals are required to be enhanced. Currently, the commonly used electromagnetic signal indoor positioning technology mainly comprises a signal arrival time method TOA (Time of Arrival), a signal arrival time difference method TDOA (Time Difference of Arrival), a signal arrival angle method AOA (Angle of Arrival), a signal receiving intensity method RSS (Received Strength of Signal), an RSS fingerprint positioning method combined with artificial intelligence and the like.
The TOA principle is to obtain the position of the to-be-positioned point by utilizing the time of the terminal sending message reaching the receiving node, and the time of the receiving node and the terminal are required to be strictly synchronized when the TOA algorithm is used for indoor positioning, otherwise, larger time error occurs, and the positioning precision is greatly influenced.
TDOA is a further improvement of the TOA positioning method, and the principle of the positioning method is that the time difference of the terminal sending signal reaching a plurality of receiving nodes is utilized to obtain the position of the to-be-positioned point, so that the time synchronization requirement of the receiving nodes and the terminal is reduced. Because the distances from each receiving node to the terminal are different, the time for the signal to reach the node is different, and the difference of distances between 2 or more receiving nodes and the terminal can be calculated by using the TDOA value, so that the position of the to-be-positioned point can be calculated. When the algorithm is used for indoor positioning, the response delay of the system is required to be small, a time error of 10ns generates a distance error of about 3m, and the algorithm is not applicable to smaller indoor environments.
AOA is to acquire distance by adding an antenna array or measuring the transmission angle of a wireless signal. According to the positioning method, a receiving node is used for transmitting wireless signals, and a receiving end can obtain the transmitting angle of the signals through an antenna array, so that the position of a to-be-positioned point is calculated. The positioning method has higher positioning precision in a non-interference positioning environment, but has high deployment cost in an indoor environment.
The traditional RSS collects the intensity of a received signal through a plurality of nodes, converts the power value of loss into distance by using an empirical or theoretical model of radio signal propagation, and estimates the position coordinates. Since most network devices now have the function of acquiring the received signal strength value, no additional hardware is required in the implementation process. However, the indoor environment is complex, the obstruction of the obstacle to the signal is serious, the stability of the signal received by the receiving node is poor, the channel model is correspondingly changed along with the change of the environment, and the accuracy of the finally estimated distance is reduced, so that the positioning accuracy of the method is not high under the condition of complex environment.
Disclosure of Invention
Aiming at the problems existing in the prior art, the invention aims to provide a method, a system and a device for positioning an indoor abnormal signal with high precision, wherein a fingerprint map database and an algorithm model are constructed by using a machine learning algorithm, and the actual position of a target signal can be inquired and obtained by comparing the nonlinear mapping relation between fingerprints and coordinates.
The invention aims to achieve the aim, and the aim is achieved by the following technical scheme:
a high-precision positioning method for indoor abnormal signals comprises the following steps:
s1: a signal receiver is arranged in the space to be positioned, the space to be positioned is divided into areas and grids, fingerprint acquisition points are arranged, and signal intensity data of abnormal signals sent by the fingerprint acquisition points are acquired;
s2: preprocessing the acquired signal intensity data to generate corresponding acquired fingerprints;
s3: training a region positioning model based on a naive Bayesian algorithm by using acquired fingerprints;
s4: training a grid positioning model based on a K-nearest neighbor algorithm by using collected fingerprints;
s5: and acquiring signal intensity data acquired by the signal receiver in real time, predicting the position of a region to which the abnormal signal belongs by using a region positioning model, predicting the grid position of the abnormal signal by using a grid positioning model according to the predicted region position, and generating coordinates of the abnormal signal.
Further, step S1 includes:
within a space to be located
The signal receivers divide the space to be positioned into a plurality of areas according to the effective receiving range of the signal receivers, each area is divided into a plurality of grids according to a square block of 1 meter multiplied by 1 meter, and the center of each grid is the fingerprint acquisition point.
Further, step S2 includes:
let it be assumed that co-partition
Each region is provided with,
Grid, signal source is at the first
The grid sends out signals, the first
The signal strength sequences received by the signal receivers are:
wherein ,
representation of
At the first time
Signal intensity collected at each grid;
by passing throughThe following pair of formulas
Normalizing and averaging to obtain:
Further, step S3 includes:
binding the collected fingerprint with the region id of the collected fingerprint to generate a data set, and learning joint probability distribution through the data set according to a naive Bayes algorithm
The joint probability distribution is converted into the product of the prior probability distribution and the conditional probability distribution according to the Bayesian theorem using the following formula:
wherein the area
Prior probability distribution for categories
By the formula
Counting how many samples are available under each category;
because the naive bayes algorithm assumes that all features are condition independent, the condition independent assumption is:
using maximum likelihood estimation, one can obtain:
i.e. given zone category
Under the condition of the first
The signal intensity received by each probe is a specific value
The probability of (2) being equal to the class
And the first
The signal intensity received by each probe is
Divided by the number of samples of (2)
All sample numbers;
obtaining
And (3) with
Then, training the regional classification model based on the naive Bayesian algorithm is completed.
Further, step S4 includes:
fingerprint collection and its belongingsThe method comprises the steps of binding grid ids to generate a data set, and dividing the data set into a training set and a testing set; setting the K value selection range to
Distance calculation method
, wherein 
When the method is used, the Euclidean distance is adopted;
when the Manhattan distance is adopted;
assume that the training set is:
the test set is:
wherein ,
representing the received signal strength of the K probes,
representing a grid id;
combining different K values with P values by means of exhaustive traversal, traversing all of the test sets
Will be
As an input example, find K instances in the training dataset that are nearest to the instance, subject to multiple compliance by a fewThe number principle is that the class of the instance is the class which is the majority in the K instances;
and calculating the classification accuracy of the test set, and obtaining a K value and a P value when the classification accuracy is highest, wherein grid positioning model training based on a K-nearest neighbor algorithm is completed.
Further, step S5 includes:
the signal strengths of the 5 moments received by the K signal receivers are:
for a pair of
Normalization and averaging are carried out to obtain:
will be
Inputting the posterior probability into a region classification model based on a naive Bayes algorithm, and finding the posterior probability by using a naive Bayes formula
Maximum category of (2)
As an output
I.e.
wherein ,
i.e. area id, according to which selection is madeCorresponding grid positioning model based on K-nearest neighbor algorithm, loading parameters K and P, and determining
The signal is input into a grid positioning model as an example of the signal, a corresponding grid id is output, and the coordinates of the grid corresponding to the grid id are the positions of the signal sources.
Correspondingly, the invention also discloses a high-precision positioning system for the indoor abnormal signal, which comprises the following steps:
the preparation unit is used for arranging a signal receiver in the space to be positioned, dividing the space to be positioned into areas and grids, setting fingerprint acquisition points, and acquiring signal intensity data of abnormal signals sent by the fingerprint acquisition points;
the data processing unit is used for preprocessing the acquired signal intensity data and generating corresponding acquired fingerprints;
a first model training unit for training a region localization model based on a naive Bayesian algorithm by using the acquired fingerprint;
the second model training unit is used for training a grid positioning model based on a K-nearest neighbor algorithm by using the acquired fingerprint;
the positioning unit is used for acquiring the signal intensity data acquired by the signal receiver in real time, predicting the position of the area to which the abnormal signal belongs by using the area positioning model, predicting the grid position of the abnormal signal by using the grid positioning model according to the predicted position of the area, and generating the coordinates of the abnormal signal.
Correspondingly, the invention also discloses a device for positioning the indoor abnormal signal with high precision, which comprises the following steps:
a memory for storing a computer program;
a processor for implementing the steps of the indoor abnormal signal high-precision positioning method according to any one of the above when executing the computer program.
Compared with the prior art, the invention has the beneficial effects that: the invention provides a high-precision positioning method, a system and a device for indoor abnormal signals, which are characterized in that a fingerprint map database and an algorithm model are constructed by using a machine learning algorithm, and the actual position of a target signal can be inquired and obtained by comparing the nonlinear mapping relation between fingerprints and coordinates, so that the defect that the traditional ranging and positioning algorithm is influenced by complex environments such as multipath effect and the like is overcome. The invention has low complexity, strong robustness and high precision, and is an important development direction of indoor positioning technology.
The invention adopts a two-step method to realize the high-precision positioning of the abnormal signal. Firstly, training a region positioning model through a naive Bayesian algorithm, positioning the region of an abnormal signal, and determining the region of the signal; and training a grid positioning model through a KNN algorithm, performing grid positioning on the abnormal signal, and determining grids to which the signal belongs, wherein the coordinates of the grid center point are the coordinates of the abnormal signal.
It can be seen that the present invention has outstanding substantial features and significant advances over the prior art, as well as the benefits of its implementation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method of an embodiment of the present invention.
Fig. 2 is a regional grid partition diagram of an embodiment of the present invention.
Fig. 3 is a diagram of a region-specific confusion matrix according to an embodiment of the present invention.
Fig. 4 is a diagram of a region 1 grid positioning confusion matrix in accordance with embodiments of the invention.
Fig. 5 is a diagram of a region 2 grid positioning confusion matrix in accordance with embodiments of the invention.
Fig. 6 is a diagram of a region 3 grid positioning confusion matrix in accordance with embodiments of the invention.
Fig. 7 is a diagram of a region 4 grid positioning confusion matrix in accordance with embodiments of the invention.
Fig. 8 is a system configuration diagram of an embodiment of the present invention.
Detailed Description
The following describes specific embodiments of the present invention with reference to the drawings.
The high-precision positioning method for the indoor abnormal signals shown in fig. 1 comprises the following steps:
s1: a signal receiver is deployed in the space to be positioned, the space to be positioned is divided into areas and grids, fingerprint acquisition points are arranged, and signal intensity data of abnormal signals sent by the fingerprint acquisition points are acquired.
Specifically, deployment within the space to be localized
The signal receivers divide the space to be positioned into a plurality of areas according to the effective receiving range of the signal receivers, each area is divided into a plurality of grids according to a square block of 1 meter multiplied by 1 meter, and the center of each grid is the fingerprint acquisition point.
S2: preprocessing the acquired signal intensity data to generate corresponding acquired fingerprints.
By way of example, assume that a co-partition
Each region is provided with,
Grid, signal source is at the first
The grid sends out signals, the first
The signal strength (Received Signal Strength Indication, RSSI) sequences received by the signal receivers are:
wherein ,
representation of
At the first time
Signal strength collected at each grid. For a pair of
Normalizing and averaging to obtain:
S3: a region localization model based on a naive bayes algorithm is trained using the captured fingerprints.
By way of example, a naive Bayesian algorithm learns joint probability distributions over a dataset by binding a captured fingerprint to its region id
The joint probability can be converted into the product of the prior probability distribution and the conditional probability distribution by the bayesian theorem:
wherein the area
Prior probability distribution for categories
By counting how many samples are under each category, namely:
because the naive bayes algorithm assumes that all features are conditional independent. The condition independent assumption is:
using maximum likelihood estimation, one can obtain:
i.e. given zone category
Under the condition of the first
The signal intensity received by each probe is a specific value
The probability of (2) being equal to the class
And the first
The signal intensity received by each probe is
Divided by the number of samples of (2)
All sample numbers. Obtaining
And (3) with
Then, the training of the regional positioning model based on the naive Bayesian algorithm is completed.
S4: a grid positioning model based on a K-nearest neighbor algorithm is trained by using acquired fingerprints.
As an example, a fingerprint collection is bound to its belonging grid id to generate a dataset, which is divided into a training set and a test set. The K-nearest neighbor algorithm does not have a training process, but the K value and the distance calculation method are two basic elements of the K-nearest neighbor algorithm, and are closely related to the classification performance of the K-nearest neighbor algorithm. The method aims at improving the classification accuracy of the K-nearest neighbor algorithm by training different K values and distance calculation methods.
First, the K value selection range is set to
. Distance calculating method
, wherein 
When the method is used, the Euclidean distance is adopted;
when using manhattan distance.
Assume that the training set is:
the test set is:
Combining different K values with P values by means of exhaustive traversal, traversing all of the test sets
Will be
As an input instance, K instances nearest to the instance are found in the training dataset, the class of which is the class of the majority of the K instances according to the minority compliance majority principle.
And calculating the classification accuracy of the test set, and obtaining a K value and a P value when the classification accuracy is highest, wherein grid positioning model training based on a K-nearest neighbor algorithm is completed.
S5: and acquiring signal intensity data acquired by the signal receiver in real time, predicting the position of a region to which the abnormal signal belongs by using a region positioning model, predicting the grid position of the abnormal signal by using a grid positioning model according to the predicted region position, and generating coordinates of the abnormal signal.
As an example, the signal strengths of the 5 moments received by the K signal receivers are:
for a pair of
Normalization and averaging are carried out to obtain:
will be
Inputting into a naive Bayes model, and finding posterior probability by using a naive Bayes formula
Maximum category of (2)
As an output
I.e.
Based on the high-precision positioning method for the indoor abnormal signals, in order to demonstrate the positioning precision of the method, the following experiment is carried out:
an office floor is selected as a region to be positioned, the region to be positioned is divided into four small regions, namely a region 1, a region 2, a region 3 and a region 4, the region 1 is divided into 6 grids, the region 2 is divided into 4 grids, the region 3 is divided into 6 grids, and the region 4 is divided into 5 grids. The specific meshing is shown in fig. 2.
Wherein, dark dot indicates signal receiver position, and this experiment adopts three signal receivers. The method of the invention locates signals in two steps, and the classification accuracy of the regional locating model is shown in figure 3.
In the figure, numbers in the horizontal and vertical axes corresponding to the grid indicate the number of correctly classified data, and if 36 indicates the number of correctly classified data in the region 1 is 36. The classification accuracy of each grid positioning model is shown in fig. 4-7.
Through the experiment, the grid positioning accuracy can reach 1.37m after the indoor abnormal signal high-accuracy positioning method provided by the invention is utilized. Therefore, the method and the device position the region to which the signal belongs first and then position the grid to which the signal belongs through a two-step method, so that the positioning error is effectively reduced.
Correspondingly, as shown in fig. 8, the invention also discloses a high-precision positioning system for indoor abnormal signals, which comprises: the system comprises a preparation unit, a data processing unit, a first model training unit, a second model training unit and a positioning unit.
The preparation unit is used for arranging the signal receiver in the space to be positioned, dividing the area and the grid of the space to be positioned, setting fingerprint acquisition points, and acquiring signal intensity data of abnormal signals sent by the fingerprint acquisition points.
And the data processing unit is used for preprocessing the acquired signal intensity data and generating corresponding acquired fingerprints.
And the first model training unit is used for training the region positioning model based on the naive Bayesian algorithm by using the acquired fingerprints.
And the second model training unit is used for training a grid positioning model based on a K-nearest neighbor algorithm by using the acquired fingerprint.
The positioning unit is used for acquiring the signal intensity data acquired by the signal receiver in real time, predicting the position of the area to which the abnormal signal belongs by using the area positioning model, predicting the grid position of the abnormal signal by using the grid positioning model according to the predicted position of the area, and generating the coordinates of the abnormal signal.
The embodiment provides a high-precision positioning system for indoor abnormal signals, which can construct a fingerprint map database and an algorithm model by using a machine learning algorithm, and can inquire the actual position of a target signal by comparing nonlinear mapping relations between fingerprints and coordinates, thereby solving the defect that the traditional ranging positioning algorithm is influenced by complex environments such as multipath effect and the like.
Correspondingly, the invention also discloses a high-precision positioning device for the indoor abnormal signals, which comprises a processor and a memory; the processor realizes the following steps when executing the indoor abnormal signal high-precision positioning program stored in the memory:
1. a signal receiver is deployed in the space to be positioned, the space to be positioned is divided into areas and grids, fingerprint acquisition points are arranged, and signal intensity data of abnormal signals sent by the fingerprint acquisition points are acquired.
2. Preprocessing the acquired signal intensity data to generate corresponding acquired fingerprints.
3. A region localization model based on a naive bayes algorithm is trained using the captured fingerprints.
4. A grid positioning model based on a K-nearest neighbor algorithm is trained by using acquired fingerprints.
5. And acquiring signal intensity data acquired by the signal receiver in real time, predicting the position of a region to which the abnormal signal belongs by using a region positioning model, predicting the grid position of the abnormal signal by using a grid positioning model according to the predicted region position, and generating coordinates of the abnormal signal.
Further, the high-precision positioning device for indoor abnormal signals in this embodiment may further include:
the input interface is used for acquiring an indoor abnormal signal high-precision positioning program imported from the outside, storing the acquired indoor abnormal signal high-precision positioning program into the memory, and acquiring various instructions and parameters transmitted by the external terminal equipment and transmitting the various instructions and parameters into the processor so that the processor can develop corresponding processing by utilizing the various instructions and parameters. In this embodiment, the input interface may specifically include, but is not limited to, a USB interface, a serial interface, a voice input interface, a fingerprint input interface, a hard disk reading interface, and the like.
And the output interface is used for outputting various data generated by the processor to the terminal equipment connected with the output interface so that other terminal equipment connected with the output interface can acquire various data generated by the processor. In this embodiment, the output interface may specifically include, but is not limited to, a USB interface, a serial interface, and the like.
And the communication unit is used for establishing remote communication connection between the indoor abnormal signal high-precision positioning device and the external server so that the indoor abnormal signal high-precision positioning device can mount the image file to the external server. In this embodiment, the communication unit may specifically include, but is not limited to, a remote communication unit based on a wireless communication technology or a wired communication technology.
And the keyboard is used for acquiring various parameter data or instructions input by a user by knocking the key cap in real time.
And the display is used for running the related information of the short-circuit positioning process of the power supply line of the server to display in real time.
A mouse may be used to assist a user in inputting data and to simplify user operations.
It will be apparent to those skilled in the art that the techniques of embodiments of the present invention may be implemented in software plus a necessary general purpose hardware platform. Based on such understanding, the technical solution in the embodiments of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium such as a U-disc, a mobile hard disc, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, etc. various media capable of storing program codes, including several instructions for causing a computer terminal (which may be a personal computer, a server, or a second terminal, a network terminal, etc.) to execute all or part of the steps of the method described in the embodiments of the present invention. The same or similar parts between the various embodiments in this specification are referred to each other. In particular, for the terminal embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and reference should be made to the description in the method embodiment for relevant points.
In the several embodiments provided by the present invention, it should be understood that the disclosed systems, and methods may be implemented in other ways. For example, the system embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, system or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional module in the embodiments of the present invention may be integrated in one processing unit, or each module may exist alone physically, or two or more modules may be integrated in one unit.
Similarly, each processing unit in the embodiments of the present invention may be integrated in one functional module, or each processing unit may exist physically, or two or more processing units may be integrated in one functional module.
The invention will be further described with reference to the accompanying drawings and specific embodiments. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention. Further, it will be understood that various changes or modifications may be made by those skilled in the art after reading the teachings of the invention, and such equivalents are intended to fall within the scope of the invention as defined herein.
Claims (8)
1. The high-precision positioning method for the indoor abnormal signals is characterized by comprising the following steps of:
s1: a signal receiver is arranged in the space to be positioned, the space to be positioned is divided into areas and grids, fingerprint acquisition points are arranged, and signal intensity data of abnormal signals sent by the fingerprint acquisition points are acquired;
s2: preprocessing the acquired signal intensity data to generate corresponding acquired fingerprints;
s3: training a region positioning model based on a naive Bayesian algorithm by using acquired fingerprints;
s4: training a grid positioning model based on a K-nearest neighbor algorithm by using collected fingerprints;
s5: and acquiring signal intensity data acquired by the signal receiver in real time, predicting the position of a region to which the abnormal signal belongs by using a region positioning model, predicting the grid position of the abnormal signal by using a grid positioning model according to the predicted region position, and generating coordinates of the abnormal signal.
2. The method for locating an indoor abnormal signal with high accuracy according to claim 1, wherein the step S1 comprises:
within a space to be located
The signal receivers divide the space to be positioned into a plurality of areas according to the effective receiving range of the signal receivers, each area is divided into a plurality of grids according to a square block of 1 meter multiplied by 1 meter, and the center of each grid is the fingerprint acquisition point.
3. The method for locating an indoor abnormal signal with high accuracy according to claim 2, wherein the step S2 comprises:
let it be assumed that co-partition
Each region is provided with,
Grid, signal source is at the first
The grid sends out signals, the first
The signal strength sequences received by the signal receivers are:
wherein ,
representation of
At the first time
Signal intensity collected at each grid;
by the following formula pair
Normalizing and averaging to obtain:
4. The method for locating an indoor abnormal signal with high accuracy according to claim 3, wherein the step S3 comprises:
binding the collected fingerprint with the region id of the collected fingerprint to generate a data set, and learning joint probability distribution through the data set according to a naive Bayes algorithm
The joint probability distribution is converted into the product of the prior probability distribution and the conditional probability distribution according to the Bayesian theorem using the following formula:
wherein the area
Prior probability distribution for categories
By the formula
Counting how many samples are available under each category;
because the naive bayes algorithm assumes that all features are condition independent, the condition independent assumption is:
using maximum likelihood estimation, one can obtain:
i.e. given zone category
Under the condition of the first
The signal intensity received by each probe is a specific value
The probability of (2) being equal to the class
And the first
The signal intensity received by each probe is
Divided by the number of samples of (2)
All sample numbers;
obtaining
And (3) with
Then, training the regional classification model based on the naive Bayesian algorithm is completed.
5. The method for locating an indoor abnormal signal with high accuracy according to claim 4, wherein said step S4 comprises:
binding the collected fingerprint with the grid id of the fingerprint to generate a data set, and dividing the data set into a training set and a testing set; setting the K value selection range to
Distance calculation method
, wherein 
When the method is used, the Euclidean distance is adopted;
when the Manhattan distance is adopted;
assume that the training set is:
the test set is:
wherein ,
representing the received signal strength of the K probes,
representing a grid id;
combining different K values with P values by means of exhaustive traversal, traversing all of the test sets
Will be
As an input example, finding K examples nearest to the example in the training data set, wherein the class of the example is the class of the majority in the K examples according to the minority compliance majority principle;
and calculating the classification accuracy of the test set, and obtaining a K value and a P value when the classification accuracy is highest, wherein grid positioning model training based on a K-nearest neighbor algorithm is completed.
6. The method for locating an indoor abnormal signal with high accuracy according to claim 5, wherein said step S5 comprises:
the signal strengths of the 5 moments received by the K signal receivers are:
for a pair of
Normalization and averaging are carried out to obtain:
will be
Inputting the posterior probability into a region classification model based on a naive Bayes algorithm, and finding the posterior probability by using a naive Bayes formula
Maximum category of (2)
As an output
I.e.
wherein ,
namely, the method is a region id, a corresponding grid positioning model based on a K-nearest neighbor algorithm is selected according to the region id, parameters K and P are loaded, and the method is characterized in that
The signal is input into a grid positioning model as an example of the signal, a corresponding grid id is output, and the coordinates of the grid corresponding to the grid id are the positions of the signal sources.
7. An indoor abnormal signal high-precision positioning system is characterized by comprising:
the preparation unit is used for arranging a signal receiver in the space to be positioned, dividing the space to be positioned into areas and grids, setting fingerprint acquisition points, and acquiring signal intensity data of abnormal signals sent by the fingerprint acquisition points;
the data processing unit is used for preprocessing the acquired signal intensity data and generating corresponding acquired fingerprints;
a first model training unit for training a region localization model based on a naive Bayesian algorithm by using the acquired fingerprint;
the second model training unit is used for training a grid positioning model based on a K-nearest neighbor algorithm by using the acquired fingerprint;
the positioning unit is used for acquiring the signal intensity data acquired by the signal receiver in real time, predicting the position of the area to which the abnormal signal belongs by using the area positioning model, predicting the grid position of the abnormal signal by using the grid positioning model according to the predicted position of the area, and generating the coordinates of the abnormal signal.
8. An indoor abnormal signal high-precision positioning device is characterized by comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method for locating an indoor abnormal signal with high accuracy according to any one of claims 1 to 6 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211664148.6A CN116033345A (en) | 2022-12-23 | 2022-12-23 | Indoor abnormal signal high-precision positioning method, system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211664148.6A CN116033345A (en) | 2022-12-23 | 2022-12-23 | Indoor abnormal signal high-precision positioning method, system and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116033345A true CN116033345A (en) | 2023-04-28 |
Family
ID=86079206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211664148.6A Pending CN116033345A (en) | 2022-12-23 | 2022-12-23 | Indoor abnormal signal high-precision positioning method, system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116033345A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118102443A (en) * | 2024-04-18 | 2024-05-28 | 青岛日日盛智能科技有限公司 | High-precision indoor positioning method and system |
-
2022
- 2022-12-23 CN CN202211664148.6A patent/CN116033345A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118102443A (en) * | 2024-04-18 | 2024-05-28 | 青岛日日盛智能科技有限公司 | High-precision indoor positioning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hsieh et al. | Deep learning-based indoor localization using received signal strength and channel state information | |
| Wang et al. | LiFS: Low human-effort, device-free localization with fine-grained subcarrier information | |
| Mirowski et al. | Probabilistic radio-frequency fingerprinting and localization on the run | |
| CN109068267B (en) | Indoor positioning method based on LoRa SX1280 | |
| CN112218330B (en) | Positioning method and communication device | |
| Aernouts et al. | TDAoA: A combination of TDoA and AoA localization with LoRaWAN | |
| CN108882149B (en) | NLOS compensation positioning method of distance correlation probability | |
| CN104540221A (en) | WLAN indoor positioning method based on semi-supervised SDE algorithm | |
| CN103618997A (en) | Indoor positioning method and device based on signal intensity probability | |
| CN116033345A (en) | Indoor abnormal signal high-precision positioning method, system and device | |
| Ni et al. | Fingerprint-MDS based algorithm for indoor wireless localization | |
| Lan et al. | Measurement-level target tracking fusion for over-the-horizon radar network using message passing | |
| CN108931789A (en) | Attack detection method, attack detectors, computer readable storage medium and terminal | |
| Lian et al. | Improved Indoor positioning algorithm using KPCA and ELM | |
| Islam et al. | LoRa-based outdoor localization and tracking using unsupervised symbolization | |
| CN107592654B (en) | Method for positioning field intensity of same-frequency multiple radiation sources based on compressed sensing | |
| Wang et al. | High-accuracy localization using single-anchor ultra-wide bandwidth systems | |
| Fahama et al. | An experimental comparison of RSSI-based indoor localization techniques using ZigBee technology | |
| CN109302706B (en) | Pseudo base station positioning method and device and computer readable storage medium | |
| CN104821854A (en) | Multidimensional spectrum sensing method for multiple main users based on random sets | |
| Alamleh et al. | A weighting system for building RSS maps by crowdsourcing data from smartphones | |
| CN111654808B (en) | Method and system for updating fingerprint database and wifi positioning method and system | |
| Longo et al. | Localization and Monitoring System based on BLE Fingerprint Method. | |
| CN114286306B (en) | Indoor signal positioning method, device, computer equipment and storage medium | |
| CN105553583B (en) | The indoor white frequency spectrum detecting method from training based on Bayes's compressed sensing |
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 |