CN113660600B - Indoor positioning system and data processing method - Google Patents
Indoor positioning system and data processing method Download PDFInfo
- Publication number
- CN113660600B CN113660600B CN202110703715.3A CN202110703715A CN113660600B CN 113660600 B CN113660600 B CN 113660600B CN 202110703715 A CN202110703715 A CN 202110703715A CN 113660600 B CN113660600 B CN 113660600B
- Authority
- CN
- China
- Prior art keywords
- layer
- positioning
- neural network
- artificial neural
- feature map
- 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.)
- Active
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 claims abstract description 43
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000011176 pooling Methods 0.000 claims description 21
- 238000012549 training Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000010586 diagram Methods 0.000 claims description 12
- 230000004913 activation Effects 0.000 claims description 10
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 14
- 238000004590 computer program Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 230000008901 benefit Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/023—Services making use of location information using mutual or relative location information between multiple location based services [LBS] targets or of distance thresholds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L51/00—User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
- H04L51/04—Real-time or near real-time messaging, e.g. instant messaging [IM]
- H04L51/046—Interoperability with other network applications or services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/72406—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality by software upgrading or downloading
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
-
- 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
Abstract
The invention discloses an indoor positioning system and a data processing method in the technical field of indoor positioning. An indoor positioning system, comprising: the base station is used for acquiring personnel position information, generating positioning data and then sending the positioning data to the mobile terminal; the server terminal is used for generating a gray scale map from the positioning data forwarded by the mobile terminal, inputting the gray scale map into the artificial neural network, and returning the positioning result to the mobile terminal after obtaining the positioning result; the positioning data includes UUID and received signal strength RSSI values. The ibeacon base station and the artificial neural network are adopted for indoor positioning, the cost and the positioning accuracy of an indoor positioning scheme are comprehensively evaluated, and the ibeacon base station is used and can be supported by a smart phone, so that the method has high practicability; an artificial neural network with higher convergence rate is used; the trained artificial neural network can be universally applied to various indoor places needing positioning; the deployment difficulty of the system is reduced, and higher positioning accuracy can be obtained through lower cost.
Description
Technical Field
The invention relates to an indoor positioning system and a data processing method, and belongs to the technical field of indoor positioning.
Background
The development scale of modern cities is larger and larger, large indoor public places are increased, indoor environments are larger and more complicated, human activities are more limited indoors, however, GPS satellite signals are easily shielded by modern buildings, so that the positioning performance of the GPS satellite signals in indoor closed environments is reduced sharply, and therefore the positioning technology cannot provide good positioning and navigation services in indoor environments. This makes indoor positioning research increasingly interesting as a new research direction. Indoor positioning technology has been widely used in many ways, including applications in recreational life, applications in smart medicine, applications in industrial production, and the like.
In order to perform positioning in a relatively closed indoor environment, improve the accuracy of a positioning technology, and reduce the system power consumption and the deployment cost, current research work includes WiFi positioning, infrared positioning, RFID positioning, UWB positioning, ibeacon positioning, and the like. The advantages and the disadvantages of various positioning technologies are evaluated from the aspects of cost, positioning precision, system complexity, coverage area, robustness and the like, in the aspect of implementation cost, the system implementation cost of UWB positioning and infrared positioning is higher, the system implementation cost is not suitable for commercial application, the Wi Fi positioning precision is lower, the RFID signal coverage area is limited, the BLE Bluetooth module is almost completely built in the existing mobile intelligent terminal, the iBeacon signal can be received without obstacles, and the positioning technology based on the iBeacon has the advantages of low power consumption, wide application, suitability for implementation of a smart phone and the like.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, provides an indoor positioning system and a data processing method, comprehensively evaluates the cost and positioning accuracy of an indoor positioning scheme, can be supported by both ibeacon base stations and smart phones, and has higher practicability.
In order to achieve the purpose, the invention adopts the following technical scheme:
in a first aspect, the present invention provides an indoor positioning system, including:
the base station is used for generating positioning data and then sending the positioning data to the mobile terminal;
the server terminal is used for generating a gray scale map from the positioning data forwarded by the mobile terminal, inputting the gray scale map into the artificial neural network, and returning the positioning result to the mobile terminal after obtaining the positioning result;
the positioning data includes UUID and received signal strength RSSI values.
Preferably, the artificial neural network comprises an input layer, a hidden layer and an output layer, and the number of nodes of the hidden layer is according to a formula
Calculating and determining, wherein h is the number of nodes of the hidden layer, m is the number of nodes of the input layer, and n is the number of nodes of the output layerAnd a is a tuning constant between 1 and 10.
Preferably, the hiding layer includes:
a convolution layer for extracting a feature map in a local region in the upper layer feature map using a convolution filter and a nonlinear activation function;
and the pooling layer is used for performing down-sampling on the feature map extracted from the local area in the feature map of the previous layer through pooling calculation.
In a second aspect, the present invention provides an indoor positioning data processing method, which is applied to the above indoor positioning system and executed by a server, and includes:
receiving positioning data sent by the mobile terminal;
preprocessing the positioning data;
generating a gray scale map by using the preprocessed data;
and judging whether the artificial neural network is in a training stage, if so, continuing to train the artificial neural network until the training is finished, and if so, inputting the gray scale map into the artificial neural network and outputting a positioning result.
Preferably, the positioning data preprocessing includes performing a mean filtering calculation on the received signal strength RSSI values, where the mean filtering calculation formula is:
in the formula: ISDZ(i) For inputting data, NISDAs data volume, lenswFor sliding window length, lensSliding the number of data strips backwards for the window.
Preferably, the generating the gray scale map by using the preprocessed data includes the following steps:
the preprocessed RSSI is expressed as
M is the mth acquisition point, where M =1,2, …, M, M is the total number of acquisition points located within the chamber, i isThe ith measurement fingerprint collected in the mth located collection point, i =1,2, …, N is the total number of sample collections, J represents the jth UUID, J =1,2, …, K is the total number of UUIDs;
order to
Maximum value of (1) is
Minimum value of
By the formula
Carrying out standardization to obtain 0-1 distribution of RSSI;
a 1 x n vector obtained for each fingerprint record is multiplied by 255 and the vector is then converted into a 24 x 24 matrix of pixel values required to generate a grey scale image.
Preferably, the training of the artificial neural network includes the following steps:
extracting data characteristics of the gray level graph by executing the convolution layer and the pooling layer, and then obtaining a training weight by using a BP algorithm;
calculating a loss function according to the training weight, and then comparing the loss function with a threshold value;
if the loss function is smaller than the threshold value, the training of the artificial neural network is completed; otherwise, the gray-scale image is passed through the convolution layer and the pooling layer again.
In a third aspect, the present invention provides an artificial neural network data processing method, which is applied to the indoor positioning system described above and executed by an artificial neural network, and includes:
manually marking the positioning data to be input;
extracting a feature map in a local area in the upper layer feature map by using a convolution filter and a nonlinear activation function;
preferably, down-sampling the feature map extracted from the local region in the feature map of the previous layer by pooling calculation, where the extracting the feature map specifically includes:
definition of
The ith characteristic diagram of the j layer of the artificial neural network is represented by the formula:
where σ is the activation function, bjIs the bias term of the j-th layer, SCMj-1Is connected to a set of j-level feature maps,
is the convolution kernel for generating the ith feature map of the jth layer from the mth feature map of the jth-1 layer.
Preferably, the pooling calculation formula is:
wherein beta isjIs the multiplicative bias for layer j, posing stands for pooling operation.
Compared with the prior art, the invention has the following beneficial effects:
the ibeacon base station and the artificial neural network are adopted for indoor positioning, the cost and the positioning accuracy of an indoor positioning scheme are comprehensively evaluated, and the ibeacon base station is used and can be supported by a smart phone, so that the method has high practicability; an artificial neural network with higher convergence rate is used; the trained artificial neural network can be universally applied to various indoor places needing positioning; the deployment difficulty of the system is reduced, and higher positioning accuracy can be obtained through lower cost.
Drawings
Fig. 1 is a general flowchart of an indoor positioning data processing method according to a second embodiment of the present invention;
fig. 2 is a flowchart of the cooperative positioning work of the mobile terminal and the server terminal according to the second embodiment of the present invention;
FIG. 3 is a schematic structural diagram of an artificial neural network model according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a mobile phone display of a positioning result according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The first embodiment is as follows:
referring to fig. 1-4, an embodiment of the present invention discloses an indoor positioning system, which includes:
the base station is used for generating positioning data and then sending the positioning data to the mobile terminal;
the server end is used for processing the positioning data forwarded by the mobile end to generate a gray scale image, inputting the gray scale image into the artificial neural network, and returning the positioning result to the mobile end after obtaining the positioning result; it is noted that the artificial neural network comprises an input layer, a hidden layer and an output layer, and the number of nodes of the hidden layer is according to a formula
Calculating and determining, wherein h is the number of nodes of the hidden layer, m is the number of nodes of the input layer, n is the number of nodes of the output layer, and a is an adjustment constant between 1 and 10, and the number of nodes of the hidden layer is not less than 15 in the embodiment; the hidden layer includes: a convolution layer for extracting a feature map in a local region in the upper layer feature map using a convolution filter and a nonlinear activation function; and the pooling layer is used for performing down-sampling on the feature map extracted from the local area in the feature map of the previous layer through pooling calculation.
The positioning data includes UUID and received signal strength RSSI values.
Example two:
referring to fig. 1-4, a second embodiment of the present invention discloses an indoor positioning data processing method, which includes the following steps:
step 1: in the embodiment, the ibeacon base station is arranged in an office room with the length of 12 meters, the width of 7.2 meters and the height of 3 meters, and is used for carrying out grid division on an area needing to be positioned; specifically in this example, step 1 is refined as: collecting positioning area type information including room length a, width b and height h; and determining the grid division number as m x n and establishing a coordinate system. The ibeacon base stations are deployed with the transverse interval of Lx, the longitudinal interval of Ly and the number of the base stations of N, and the three quantities are determined to ensure that any position of a positioning area can receive enough data;
step 2: acquiring a UUID and a received signal strength RSSI value sent by an ibeacon base station through a mobile phone terminal App and sending the UUID and the received signal strength RSSI value to a server on a local computer; specifically in this example, step 2 is refined as: the mobile phone terminal App is realized by using a WeChat applet, the WeChat applet can be used in a cross-platform mode at An Zhuoduan and an iOS end, and the installation-free advantage is achieved;
and step 3: preprocessing the received signal strength RSSI value obtained in the step 2 by using a mean value filtering algorithm; specifically in this example, step 3 is refined as: the mean filtering calculation formula is:
in the formula ISDZ(i) For inputting data, NISDAs data volume, lenswFor the sliding window length, the data of the window is averaged in the formula, and the step length is set to be LensEach time the window slides back LensThe bar data. LensThe length of (a) needs to be adjusted according to specific real-time requirements;
generating a gray scale map using the preprocessed data, comprising the steps of:
the preprocessed RSSI is expressed as
M is the mth acquisition point, where M =1,2, …, M is the total number of located acquisition points in the room, i is the ith measurement fingerprint acquired in the mth located acquisition point,i =1,2, …, N is the total number of sample acquisitions, J denotes the J-th UUID, J =1,2, …, K is the total number of UUIDs;
order to
Maximum value of
Minimum value of
By the formula
Carrying out standardization to obtain 0-1 distribution of RSSI;
a 1 x n vector obtained for each fingerprint record is multiplied by 255 and the vector is then converted into a 24 x 24 matrix of pixel values required to generate a grey scale image.
And 4, step 4: establishing a deep artificial neural network which takes a gray-scale image as input and a positioning coordinate as output, and receiving positioning data sent by the mobile terminal; preprocessing the positioning data; generating a gray scale map by using the preprocessed data; judging whether the artificial neural network is in a training stage, if so, continuing to train the artificial neural network until the training is finished, if so, inputting a gray scale map into the artificial neural network and outputting a positioning result, wherein the data acquired in the step 2 and the step 3 are used for training, the gray scale map generated after preprocessing positioning data sent by a base station is used for automatically extracting data characteristics through executing a convolution layer and a pooling layer, and a training weight is obtained by using a BP algorithm. When the loss function is smaller than the threshold value, completing the training of the artificial neural network;
the steps 1 to 4 are completed with an off-line training stage, and then the trained artificial neural network can be used for obtaining indoor positioning coordinates by inputting relevant data;
and 5: the UUID and the received signal strength RSSI acquired by the App at the mobile phone end in real time are sent to a local computer; specifically in this example, step 5 is subdivided into: the mobile phone terminal and a server end on the local computer are positioned in the same local area network, communication is realized through an HTTP protocol based on a TCP/IP protocol, and the mobile phone App sends the collected data to the local computer in real time;
and 6: and (5) taking the data obtained in the step (5) as the input of the artificial neural network to obtain a positioning result, and sending the positioning result to a mobile phone terminal for displaying to finish an indoor positioning process.
So far, an indoor positioning method based on ibeacon and an artificial neural network is completed from step 1 to step 6. The method is still effective when the office scene is changed into other scenes and only room type information, grid division size and base station deployment need to be changed. In addition, the artificial neural network used in the embodiment is changed into other similar algorithms, and the method is still effective, but the speed and the precision are different. Technical matters related to the above-described embodiments that are not related to the above-described embodiments can be achieved by taking or referring to the existing technologies.
Example three:
the third embodiment of the invention discloses an artificial neural network data processing method, and specifically in the third embodiment, artificial marking is performed before data input. The convolutional layer extracts the feature map in a local region in the previous layer feature map using a convolution filter and a nonlinear activation function. Definition of
The ith feature map of the j layer of the artificial neural network can be expressed as
Where σ is the activation function, bjIs the bias term of the j-th layer, SCMj-1Is connected to a set of j-level feature maps,
is the convolution kernel for generating the ith feature map of the jth layer from the mth feature map of the jth-1 layer. The pooling layer may reduce the resolution of the feature map by down-sampling the previous layer feature map. The pool process has the formula
Wherein beta isjIs the multiplicative bias for layer j, posing represents pooling operation.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (4)
1. A method for processing indoor positioning data is characterized in that the method is applied to an indoor positioning system,
the indoor positioning system comprises:
the base station is used for acquiring personnel position information, generating positioning data and then sending the positioning data to the mobile terminal;
the server terminal is used for generating a gray scale map from the positioning data forwarded by the mobile terminal, inputting the gray scale map into the artificial neural network, and returning the positioning result to the mobile terminal after obtaining the positioning result;
the positioning data comprises a UUID and a received signal strength RSSI value;
the artificial neural network comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the hidden layer is according to a formula
Calculating and determining, wherein h is the number of nodes of a hidden layer, m is the number of nodes of an input layer, n is the number of nodes of an output layer, and a is an adjusting constant between 1 and 10;
the hidden layer includes:
a convolution layer for extracting a feature map within a local region in the upper layer feature map using a convolution filter and a nonlinear activation function;
the pooling layer is used for performing down-sampling on the feature map extracted from the local area in the feature map of the previous layer through pooling calculation;
the method is executed by a server side and comprises the following steps:
receiving positioning data sent by the mobile terminal;
preprocessing the positioning data;
generating a gray scale map by using the preprocessed data;
judging whether the artificial neural network is in a training stage, if so, continuing to train the artificial neural network until the training is finished, and if so, inputting the gray scale map into the artificial neural network and outputting a positioning result;
the positioning data preprocessing comprises the step of performing mean filtering calculation on the RSSI value of the received signal, wherein the mean filtering calculation formula is as follows:
in the formula: ISDZ(i) For inputting data, NISDFor data volume, lenswFor sliding window length, lensSliding the number of data strips backwards for the window.
2. The indoor positioning data processing method as claimed in claim 1, wherein the generating a gray scale map by using the preprocessed data comprises the following steps:
the preprocessed RSSI is expressed as
M is the mth acquisition point, where M =1,2, …, M is the total number of acquisition points located indoors, i is the ith measurement fingerprint acquired in the mth location acquisition point, i =1,2, …, N is the total number of sample acquisitions, J represents the jth UUID, J =1,2, …, K is the total number of UUIDs;
order to
Maximum value of
Minimum value of
By the formula
Carrying out standardization to obtain 0-1 distribution of RSSI;
a 1 x n vector obtained for each fingerprint record is multiplied by 255 and the vector is then converted to a 24 x 24 matrix of pixel values required to generate a grayscale image.
3. The indoor positioning data processing method according to claim 1, wherein the training of the artificial neural network comprises the following steps:
extracting data characteristics of the gray level graph by executing the convolution layer and the pooling layer, and then obtaining a training weight by using a BP algorithm;
calculating a loss function according to the training weight, and then comparing the loss function with a threshold value;
if the loss function is smaller than the threshold value, the training of the artificial neural network is completed; otherwise, the gray-scale image is passed through the convolution layer and the pooling layer again.
4. An artificial neural network data processing method is characterized in that the method is applied to an indoor positioning system, and the indoor positioning system comprises the following steps:
the base station is used for collecting personnel position information, generating positioning data and then sending the positioning data to the mobile terminal;
the server terminal is used for generating a gray scale map from the positioning data forwarded by the mobile terminal, inputting the gray scale map into the artificial neural network, and returning the positioning result to the mobile terminal after obtaining the positioning result;
the positioning data comprises a UUID and a received signal strength RSSI value;
the artificial neural network comprises an input layer, a hidden layer and an output layer, wherein the number of nodes of the hidden layer is according to a formula
Calculating and determining, wherein h is the number of nodes of a hidden layer, m is the number of nodes of an input layer, n is the number of nodes of an output layer, and a is an adjusting constant between 1 and 10;
the hidden layer includes:
a convolution layer for extracting a feature map in a local region in the upper layer feature map using a convolution filter and a nonlinear activation function;
the pooling layer is used for performing down-sampling on the feature map extracted from the local area in the feature map of the previous layer through pooling calculation;
performed by an artificial neural network, comprising:
manually marking the positioning data to be input;
extracting a feature map in a local area in the upper layer feature map by using a convolution filter and a nonlinear activation function;
performing down-sampling on the feature map extracted from the local area in the feature map of the previous layer through pooling calculation;
the extracting the feature map specifically includes:
definition of
The ith characteristic diagram of the j layer of the artificial neural network is represented by the formula:
where σ is the activation function, bjIs the bias term of the j-th layer, SCMj-1Is connected to a set of j-level feature maps,
is a convolution kernel for generating the ith feature map of the jth layer from the mth feature map of the jth-1 layer;
the pooling calculation formula is as follows:
wherein beta isjIs the multiplicative bias for layer j, posing represents pooling operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703715.3A CN113660600B (en) | 2021-06-24 | 2021-06-24 | Indoor positioning system and data processing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110703715.3A CN113660600B (en) | 2021-06-24 | 2021-06-24 | Indoor positioning system and data processing method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113660600A CN113660600A (en) | 2021-11-16 |
| CN113660600B true CN113660600B (en) | 2022-11-01 |
Family
ID=78489016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110703715.3A Active CN113660600B (en) | 2021-06-24 | 2021-06-24 | Indoor positioning system and data processing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113660600B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108120436A (en) * | 2017-12-18 | 2018-06-05 | 北京工业大学 | Real scene navigation method in a kind of iBeacon auxiliary earth magnetism room |
| CN108769907A (en) * | 2018-06-04 | 2018-11-06 | 江南大学 | The indoor orientation method of fusion WiFi and iBeacon based on deep learning |
| CN109151716A (en) * | 2018-09-06 | 2019-01-04 | 杭州电子科技大学 | A kind of indoor orientation method of the preferred beaconing nodes based on iBeacon |
| CN110832860A (en) * | 2017-07-06 | 2020-02-21 | 三星电子株式会社 | Method for encoding/decoding image and apparatus therefor |
| CN111031485A (en) * | 2019-12-31 | 2020-04-17 | 吉林大学 | Bluetooth position service system combined with CNN and positioning method thereof |
-
2021
- 2021-06-24 CN CN202110703715.3A patent/CN113660600B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110832860A (en) * | 2017-07-06 | 2020-02-21 | 三星电子株式会社 | Method for encoding/decoding image and apparatus therefor |
| CN108120436A (en) * | 2017-12-18 | 2018-06-05 | 北京工业大学 | Real scene navigation method in a kind of iBeacon auxiliary earth magnetism room |
| CN108769907A (en) * | 2018-06-04 | 2018-11-06 | 江南大学 | The indoor orientation method of fusion WiFi and iBeacon based on deep learning |
| CN109151716A (en) * | 2018-09-06 | 2019-01-04 | 杭州电子科技大学 | A kind of indoor orientation method of the preferred beaconing nodes based on iBeacon |
| CN111031485A (en) * | 2019-12-31 | 2020-04-17 | 吉林大学 | Bluetooth position service system combined with CNN and positioning method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113660600A (en) | 2021-11-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107529222B (en) | WiFi indoor positioning system based on deep learning | |
| CN109743683B (en) | Method for determining position of mobile phone user by adopting deep learning fusion network model | |
| CN105911518A (en) | Robot positioning method | |
| CN110536245B (en) | Deep learning-based indoor wireless positioning method and system | |
| CN106454747B (en) | Wireless positioning method of mobile phone terminal | |
| CN105898713A (en) | WiFi fingerprint indoor positioning method based on weighted cosine similarity | |
| CN102932738A (en) | Improved positioning method of indoor fingerprint based on clustering neural network | |
| CN107182036A (en) | The adaptive location fingerprint positioning method merged based on multidimensional characteristic | |
| CN102959946A (en) | Augmenting image data based on related 3d point cloud data | |
| CN106092093A (en) | A kind of indoor orientation method based on earth magnetism fingerprint matching algorithm | |
| CN111698774B (en) | Indoor positioning method and device based on multi-source information fusion | |
| CN113108792A (en) | Wi-Fi fingerprint map reconstruction method and device, terminal equipment and medium | |
| CN115393712B (en) | SAR image road extraction method and system based on dynamic hybrid pooling strategy | |
| CN105792131A (en) | Positioning method and system | |
| CN113660600B (en) | Indoor positioning system and data processing method | |
| CN113271539A (en) | Indoor target positioning method based on improved CNN model | |
| CN108462992B (en) | Indoor positioning method based on super-resolution reconstruction Wi-Fi fingerprint map | |
| CN105956595A (en) | Image feature extraction method and system | |
| CN116310802A (en) | Method and device for monitoring change of residence based on multi-scale fusion model | |
| CN113534226B (en) | Indoor and outdoor seamless positioning algorithm based on smart phone scene recognition | |
| CN113532424B (en) | Integrated equipment for acquiring multidimensional information and cooperative measurement method | |
| CN113008226B (en) | Geomagnetic indoor positioning method based on gated cyclic neural network and particle filtering | |
| CN116188587A (en) | Positioning method and device and vehicle | |
| CN108195379A (en) | A kind of indoor navigation method based on WiFi received signal strength Grad | |
| CN111372211A (en) | Smart phone WiFi indoor positioning method based on ensemble learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240108 Address after: Room 401, 4th Floor, Building 6, No. 6 Fengxin Road, Yuhuatai District, Nanjing City, Jiangsu Province, 210012 Patentee after: Nanjing EasyVision Cuizhi Technology Co.,Ltd. Address before: 210003, 66 new model street, Gulou District, Jiangsu, Nanjing Patentee before: NANJING University OF POSTS AND TELECOMMUNICATIONS |