CN106507477A - A kind of outdoor positioning method and server based on humidity - Google Patents
A kind of outdoor positioning method and server based on humidity Download PDFInfo
- Publication number
- CN106507477A CN106507477A CN201611044942.5A CN201611044942A CN106507477A CN 106507477 A CN106507477 A CN 106507477A CN 201611044942 A CN201611044942 A CN 201611044942A CN 106507477 A CN106507477 A CN 106507477A
- Authority
- CN
- China
- Prior art keywords
- data
- training
- weather
- state
- humidity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
- H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment
-
- 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
- G01S5/0009—Transmission of position information to remote stations
-
- 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
- G01S5/14—Determining absolute distances from a plurality of spaced points of known location
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of outdoor positioning method based on humidity, methods described includes step：In S100, acquisition testing region, each WAP receives signal strength data and the outdoor environment data of the sent out signal of client to be detected；The outdoor environment data include weather mark and with the weather corresponding humidity data of mark；S200, respectively by the signal strength data and the outdoor environment data input training after location model input data layer；S300, based on training after the Internet of location model calculate the signal strength data and the outdoor environment data, and determine the position of client to be detected according to the output result of output layer.Location model in the present invention is trained to deep neural network by a large amount of training sample data using the deep neural network after training, lifts Position location accuracy and precision.
Description
Technical field
A kind of the present invention relates to wireless local area network technology field, more particularly to outdoor positioning method and service based on humidity
Device.
Background technology
Location technology worldwide mainly has GPS location, Wi-Fi positioning, bluetooth positioning etc., GPS location at present
Outdoor is mainly used in, Wi-Fi, bluetooth positioning can be not only used for interior, it can also be used to outdoor.As Wi-Fi positions relative maturity,
The particular content of the present invention is introduced with Wi-Fi location technologies as background below.With the popularization of wireless router, current big portion
Point public territory all has been carried out more than ten or even tens WiFi signals are covered, and these routers are being propagated to surrounding
While WiFi signal, its physical address and the information such as signal intensity is also ceaselessly sent, as long as in its signal cover,
Even if not knowing the password of Wi-Fi, these information can be similarly obtained.
General WiFi indoor positioning technologies are the WLAN (WLAN) based on IEEE802.11b/g agreements mostly
Signal intensity location technology.It is that letter is calculated according to the intensity of the signal for receiving based on the location technology ultimate principle of signal intensity
The distance between number receptor and signal source, are largely divided into two classes：Triangle intensity algorithm and location fingerprint recognizer.Its
Intermediate cam shape intensity arithmetic accuracy is low, it is difficult to meet indoor positioning requirement；And there is receiving device in general fingerprint recognizer
Different and cause to receive the defect that signal has error.
Content of the invention
For solving above-mentioned technical problem, the present invention provides a kind of outdoor positioning method and server based on humidity, passes through
The corresponding signal strength data of each WAP and outdoor environment data are gathered, is realized based on deep neural network
WiFi outdoor positionings.
The technical scheme that the present invention is provided is as follows：
The invention discloses a kind of outdoor positioning method based on humidity, methods described includes step：S100, acquisition testing
In region, each WAP receives signal strength data and the outdoor environment data of the sent out signal of client to be detected；Institute
State outdoor environment data include weather mark and with the weather corresponding humidity data of mark；S200, respectively by the signal
The input data layer of the location model after intensity data and outdoor environment data input training；S300, based on training after
The Internet of location model calculate the signal strength data and the outdoor environment data, and the output according to output layer
As a result determine the position of client to be detected.
It is further preferred that the outdoor environment data include weather mark and humidity number corresponding with weather mark
According to；The weather mark is determined according to state of weather, and the state of weather includes non-rainy day state, light rain state, moderate rain shape
State, heavy rain state and heavy rain state；The weather mark corresponding with the state of weather includes non-rainy day mark, light rain mark
Know, moderate rain mark, heavy rain mark and heavy rain are identified, each described weather identifies a corresponding humidity data.
It is further preferred that also including step before step S100：S000, training in advance deep neural network, will
Deep neural network after training is used as the location model.
It is further preferred that step S000 further includes step：S001, pre-set training location tags；
Under S002, respectively collection different weather state, each WAP receives training terminal in the training location tags in detection
The signal strength data signaled on correspondence position in region and the humidity data；Training sample is generated according to state of weather
Notebook data, the training sample data include that each WAP of collection under same state of weather receives training terminal in institute
State signal strength data, the humidity data and the weather corresponding with state of weather of the signal sent on training location tags
Mark；S003, the training sample data generation training data generated according to state of weather according to all training location tags
Collection, and send in deep neural network；S004, the input data layer of deep neural network is defined as Three-channel data layer, institute
The node for stating Three-channel data layer is corresponding with each WAP, according to the node and WAP of Three-channel data layer
Each signal strength data corresponding with WAP in each described training sample data is combined by corresponding mode respectively
Weather mark and corresponding humidity data are input into three passages of corresponding node, through deep neural network output with
The corresponding training result of training location tags described in the training sample data；S005, by output training result and its
Corresponding described training location tags be compared, deep neural network is trained according to comparative result, by training after
Deep neural network is used as the location model.
It is further preferred that also including step between step S003 and step S004：S035, respectively to all
Signal strength data in the training sample data, weather mark and humidity data are normalized；The step
Also include step between S100 and step S200：S150, each WAP reception client to be detected to collection
The signal strength data of sent out signal, outdoor environment data are normalized.
The invention also discloses a kind of outdoor positioning server based on humidity, including：Data acquisition module, for gathering
In detection zone, each WAP receives the signal strength data and outdoor environment number of the sent out signal of client to be detected
According to；The outdoor environment data include weather mark and with the weather corresponding humidity data of mark；Locating module, for inciting somebody to action
The input data layer of the location model after the signal strength data for collecting and outdoor environment data input training,
Internet based on location model calculates the signal strength data and the outdoor environment data, and according to the defeated of output layer
Go out the position that result determines client to be detected.
It is further preferred that the outdoor environment data include weather mark and humidity number corresponding with weather mark
According to；The weather mark is determined according to state of weather, and the state of weather includes non-rainy day state, light rain state, moderate rain shape
State, heavy rain state and heavy rain state；The weather mark corresponding with the state of weather includes non-rainy day mark, light rain mark
Know, moderate rain mark, heavy rain mark and heavy rain are identified, each described weather identifies a corresponding humidity data.
It is further preferred that also including：Training module, for training in advance deep neural network, by training after depth
Neutral net is used as the location model.
It is further preferred that the training module is further included：Submodule preset by label, for pre-setting for instructing
Experienced training location tags；Training dataset generates submodule, for each wireless access under collection different weather state respectively
Point receives the signal strength data signaled on correspondence position in detection zone by training terminal in the training location tags
And the humidity data；Training sample data are generated according to state of weather, the training sample data include vaporous on the same day
Under state, each WAP of collection receives the signal intensity of the signal that training terminal is sent on the training location tags
Data, the humidity data and weather corresponding with state of weather mark；According to all training location tags according to day
The training sample data that gaseity is generated generate training dataset, and send in deep neural network；Input data layer definition
Module, is defined as Three-channel data layer, the node of the Three-channel data layer for the input data layer by deep neural network
Corresponding with each WAP；Training prediction submodule, for node and WAP according to Three-channel data layer
Each signal strength data corresponding with WAP in each described training sample data is combined by corresponding mode respectively
Weather mark and corresponding humidity data are input into three passages of corresponding node, through deep neural network output with
The corresponding training result of training location tags described in the training sample data；Will be corresponding for the training result of output
Described training location tags be compared, deep neural network is trained according to comparative result, by training after depth god
Through network as the location model.
It is further preferred that also including：Data processing module, for respectively to the letter in all training sample data
Number intensity data, weather mark and humidity data are normalized, and for each wireless access to gathering
Point receives the signal strength data of the sent out signal of client to be detected, outdoor environment data and is normalized.
Compared with prior art, a kind of outdoor positioning method and server based on humidity that the present invention is provided, by receiving
Collect the signal strength data and the outdoor environment number comprising weather mark and the data of humidity of client position to be measured
According to the location model that input is trained, you can determine client position to be measured, by outdoor environment data binding signal intensity
Input of the data as deep neural network, improves the precision of outdoor positioning under different weather state.
Description of the drawings
Below by the way of clearly understandable, preferred implementation is described with reference to the drawings, the present invention is given furtherly
Bright.
Fig. 1 is a kind of key step schematic diagram of the outdoor positioning method based on humidity of the present invention；
The step of Fig. 2 is a kind of training deep neural network based on the outdoor positioning method of humidity of present invention schematic diagram；
Fig. 3 is a kind of main composition schematic diagram of the outdoor positioning server based on humidity of the present invention；
Fig. 4 is that a kind of present invention outdoor positioning server based on humidity is fully composed schematic diagram.
Reference：
100th, data acquisition module, 200, locating module, 300, training module, 311, the default submodule of label, 312, instruction
Practice data set generation submodule, 313, input data layer define submodule, 314, training prediction submodule, 400, data processing mould
Block.
Specific embodiment
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below by control description of the drawings
The specific embodiment of the present invention.It should be evident that drawings in the following description are only some embodiments of the present invention, for
For those of ordinary skill in the art, on the premise of not paying creative work, can be obtaining other according to these accompanying drawings
Accompanying drawing, and obtain other embodiments.
For making simplified form, in each figure, part related to the present invention is only schematically show, they do not represent
Its practical structures as product.In addition, so that simplified form is readily appreciated, there is in some figures identical structure or function
Part, only symbolically depicts one of those, or has only marked one of those.Herein, " one " is not only represented
" only this ", it is also possible to represent the situation of " more than one ".
Fig. 1 is a kind of key step schematic diagram of the outdoor positioning method based on humidity of the present invention, as shown in figure 1, a kind of
Based on the outdoor positioning method of humidity, methods described includes step：In S100, acquisition testing region, each WAP is received
The signal strength data of the sent out signal of client to be detected and outdoor environment data；The outdoor environment data include weather mark
Know and with the weather corresponding humidity data of mark；S200, respectively by the signal strength data and the outdoor environment
The input data layer of the location model after data input training；S300, based on training after location model Internet calculate institute
Signal strength data and the outdoor environment data are stated, and the position of client to be detected is determined according to the output result of output layer
Put.
Specifically, above-mentioned client to be detected (hereinafter referred to as STA) is with smart mobile phone, notebook computer or personal flat board
The intelligent terminals such as computer are carrier.
Outdoor environment data described in the present embodiment specifically include weather mark and with the weather corresponding humidity of mark
Data；The weather mark is determined according to state of weather, and the state of weather includes non-rainy day state, light rain state, moderate rain
State, heavy rain state and heavy rain state；The weather mark corresponding with the state of weather includes non-rainy day mark, light rain
Mark, moderate rain mark, heavy rain mark and heavy rain mark, each described weather identify a corresponding humidity data.
Wherein, each WAP receives the signal strength data of the sent out signal of client to be detected by with lower section
Formula is obtained：STA sends detection frame within a detection region in real time, and WAP obtains detection frame signal after receiving is strong
Degree, each WAP report signal intensity to home server or Cloud Server, and server is according to each WAP
The RSSI signal intensitys for reporting generate signal strength data.For example, the form of signal strength data is<RSSI1, RSSI2,
RSSI3, RSSI4, RSSI5>, the RSSI of the STA that wherein RSSI1 is received for AP1, the RSSI of the STA that RSSI2 is received for AP2, with
This analogizes.
Signal strength data and the outdoor environment data of the client to be detected gathered in the present invention are described below.Assume
Now with outdoor AP1, AP2, AP3.Three signal strength datas corresponding with AP, are represented with RSSI, are further added by two inputs：1.
Humidity data is input into the mark input of 2. weather.Wherein humidity data input is actual humidity data during data acquisition.Weather mark
Knowing input is input into according to current weather state, and the corresponding weather of state of weather is designated：Non- rainy day (value is 0), light rain (1),
Moderate rain (2), heavy rain (3), heavy rain (4).
Assume there is same client to be detected gathered data under same position different weather state, STA1 is expressed as fine
Its collection, STA2 are expressed as gathering during moderate rain, then be exemplified below：
Table one
| AP1 | AP2 | AP3 | Humidity | Weather | |
| STA1 | -32dBm | -52dBm | -60dBm | 45% | 0 |
| STA2 | -20dBm | -30dBm | -40dBm | 80% | 2 |
As shown in Table 1, gathered data under same position different weather state, it is clear that signal strength data has differences.
The form of present invention data of collection when outdoor positioning is carried out is in above-mentioned table one shown in STA1.
The existing outdoor positioning based on WiFi, the general signal strength data for obtaining STA by AP are used as positioning input
Data, but generally have a factor not to be taken into account：The humidity of air and rainy situation.When non-rainy, humidity is to wireless
The transmission of electric wave has an impact, and when rainy, then as raindrop are liquid, affects the impact of humidity ratio to want on the transmission of radio wave
Big is more.Therefore, when being positioned in outdoor environment, the signal strength data difference that STA is received under different state of weather
Larger, outdoor environment data are taken into account by the present invention, by state of weather and corresponding humidity data binding signal intensity number
According to the initial data as input location model, so as to further increase the positioning precision of WIFI outdoor positionings, positioning is improved accurate
True rate.
Preferably, also include step before step S100：S000, training in advance deep neural network, after training
Deep neural network as the location model.
Specifically, the output result difference for being obtained according to positioning in the present invention, can include two kinds of specific implementations, side
Formula one is used as location model by deep neural network and exports belonging to client position to be detected that certain pre-sets
The probit of classification, mode two are to be used as location model by deep neural network directly to export client position to be detected
Preset position coordinates.The present invention is not construed as limiting to concrete training method.
Method of the present invention using the global parameter training for having supervision：The known signal strength data for receiving and outdoor ring
The physical location of border data, causes the output of the Internet of deep neural network and real knot by constantly adjustment network parameter
Really identical.
The step of Fig. 2 is a kind of training deep neural network based on the outdoor positioning method of humidity of present invention schematic diagram.
Preferably, as shown in Fig. 2 step S000 further includes step：S001, pre-set training location tags；S002, point
Training terminal Cai Ji not received in the training location tags in detection zone by each WAP under different weather state
The signal strength data signaled on correspondence position and the humidity data；Number of training is generated according to state of weather
According to the training sample data include that each WAP of collection under same state of weather receives training terminal in the instruction
Practice signal strength data, the humidity data and the weather mark corresponding with state of weather of the signal sent on location tags
Know；S003, the training sample data generation training dataset generated according to state of weather according to all training location tags,
And send in deep neural network；S004, the input data layer of deep neural network is defined as Three-channel data layer, described three
The node of channel data layer is corresponding with each WAP, and the node according to Three-channel data layer is corresponding with WAP
Mode each signal strength data corresponding with WAP in each described training sample data is combined weather respectively
Mark and corresponding humidity data are input into three passages of corresponding node, through deep neural network output with described
The corresponding training result of training location tags described in training sample data；S005, the training result that will be exported are corresponding
The training location tags be compared, deep neural network is trained according to comparative result, by training after depth
Neutral net is used as the location model.
Specifically, because signal strength data and outdoor environment data are multidimensional data in the present embodiment, therefore define
The input data layer for being used as the deep neural network of location model is Three-channel data layer.
Exported belonging to client position to be detected as location model in mode one by deep neural network below
As a example by the probit of certain classification for pre-setting, the concrete process for introducing the present invention to deep neural network training.
1st, in training, gather each WAP first and training terminal is received in default training location tags in inspection
Survey the signal strength data and outdoor environment data signaled on correspondence position in region.Training position is preset in the present embodiment
Label is put for self-defining, specifically can be by stress and strain model detection zone, the grid point that detection zone is divided into predetermined number
Class, by each corresponding default training location tags of grid classification distribution, also can be by setting up flat square seat in detection zone
Mark system, arranges corresponding position coordinateses respectively in a coordinate system for default training location tags.Entered in mode one in the present embodiment
Row citing, explains the network number of each default training location tags correspondence position of collection in the present invention below with real data
According to.
All initial datas that a default training location tags position is collected wherein are assumed in the non-rainy day
As follows：
<(- 32,45%, 0), (- 52,45%, 0), (- 60,45%, 0), 34>
Represent：
RSSI1=-32dBm, humidity 45%, weather 0 (non-rainy day)
RSSI2=-52dBm, humidity 45%, weather 0 (non-rainy day)
RSSI3=-60dBm, humidity 45%, weather 0 (non-rainy day)
Label=34, represent this default training location tags are designated 34, represent the net for being designated 34 in monitored area
Lattice position.
Gather the data under different weather state successively on each default training location tags, form number of training
According to.
2nd, training sample data training deep neural network is passed sequentially through.
Initial data due to gathering is three-dimensional data, and therefore, definition is used as the defeated of the deep neural network of location model
It is also Three-channel data layer to enter data Layer, and the node of Three-channel data layer is corresponding with each WAP.According to triple channel
The node of data Layer mode corresponding with WAP is respectively by each and wireless access in each described training sample data
The corresponding signal strength data of point combines three passages that weather mark and corresponding humidity data are input into corresponding node, with
Said one presets training location tags position as a example by all initial datas that the non-rainy day is collected, by the original of collection
Beginning data input Three-channel data layer, the data of each passage input are as shown in Table 2：
Table two
As shown in Table 2, in table two, passage 1 represents the signal strength data corresponding with each WAP of collection, single
Position is DB, and passage 2 represents corresponding humidity data under state of weather, adopts and be expressed as a percentage, and passage 3 represents that state of weather is corresponding
Weather mark.Successively by each default threeway for training the corresponding training sample data of location tags to send into deep neural network
Three passages of track data layer, finally output training result and the error for training location tags, neural finally by percentage regulation
Parameter in network causes the Loss i.e. error of whole network minimum.
It should be noted that do not indicate design parameter in entire depth neutral net, because these parameters and specific
The number of space and AP is relevant, not in the range of this patent.
Preferably, also include step between step S003 and step S004：S035, respectively to all instructions
Practice the signal strength data in sample data, weather mark and humidity data to be normalized；Step S100 and
Also include step between step S200：S150, to receive client to be detected to each WAP of collection sent out
The signal strength data of signal, outdoor environment data are normalized.
As the unit of the initial data for gathering is differed, AP corresponds to RSSI, and humidity is percentage ratio, and weather is to enumerate
Value.So gathered data is when deep neural network is input into, (concrete method for normalizing is not especially limited, and can adopt to answer normalization
With all suitable normalization processing methods in prior art).As deep neural network is in training, while having taken into account signal
Intensity data, humidity data and state of weather, so the deep neural network for training is can take into account when location prediction is carried out
Humidity and the impact of weather so that training is more accurate, so that positioning is more accurate.
Fig. 3 is a kind of main composition schematic diagram of the outdoor positioning server based on humidity of the present invention, as shown in figure 3, one
The outdoor positioning server based on humidity is planted, including：Data acquisition module 100, in acquisition testing region, each wirelessly connects
Access point receives the signal strength data of the sent out signal of client to be detected and outdoor environment data；The outdoor environment packet
Include weather mark and with the weather corresponding humidity data of mark；Locating module 200, for will be strong for the signal for collecting
The input data layer of the location model after degrees of data and outdoor environment data input training, the network based on location model
Layer calculates the signal strength data and the outdoor environment data, and determines visitor to be detected according to the output result of output layer
The position at family end.
Specifically, above-mentioned client to be detected (hereinafter referred to as STA) is with smart mobile phone, notebook computer or personal flat board
The intelligent terminals such as computer are carrier.
Outdoor environment data described in the present embodiment specifically include weather mark and with the weather corresponding humidity of mark
Data；The weather mark is determined according to state of weather, and the state of weather includes non-rainy day state, light rain state, moderate rain
State, heavy rain state and heavy rain state；The weather mark corresponding with the state of weather includes non-rainy day mark, light rain
Mark, moderate rain mark, heavy rain mark and heavy rain mark, each described weather identify a corresponding humidity data.
Wherein, the signal of the signal sent in detection zone by each WAP reception client to be detected is strong
Degrees of data is obtained in the following manner：STA sends detection frame within a detection region in real time, and WAP obtains described after receiving
The signal intensity of detection frame, each WAP report signal intensity to home server or Cloud Server, server according to
The RSSI field intensity message that each WAP is reported generates signal strength data.For example, the form of signal strength data is<
RSSI1, RSSI2, RSSI3, RSSI4, RSSI5>, the RSSI of the STA that wherein RSSI1 is received for AP1, RSSI2 are received for AP2
The RSSI of STA, by that analogy.
The existing outdoor positioning based on WiFi, the general signal strength data for obtaining STA by AP are used as positioning input
Data, but generally have a factor not to be taken into account：The humidity of air and rainy situation.When non-rainy, humidity is to wireless
The transmission of electric wave has an impact, and when rainy, then as raindrop are liquid, affects the impact of humidity ratio to want on the transmission of radio wave
Big is more.Therefore, when being positioned in outdoor environment, the signal strength data difference that STA is received under different state of weather
Larger, outdoor environment data are taken into account by the present invention, by state of weather and corresponding humidity data binding signal intensity number
According to the initial data as input location model, so as to further increase the positioning precision of WIFI outdoor positionings, positioning is improved accurate
True rate.
Fig. 4 is that a kind of present invention outdoor positioning server based on humidity is fully composed schematic diagram.As shown in figure 4, excellent
Choosing, as shown in figure 4, also include：Training module 300, for training in advance deep neural network, by training after depth nerve
Network is used as the location model.
Specifically, the output result difference for being obtained according to positioning in the present invention, can include two kinds of specific implementations, side
Formula one is used as location model by deep neural network and exports belonging to client position to be detected that certain pre-sets
The probit of classification, mode two are to be used as location model by deep neural network directly to export client position to be detected
Preset position coordinates.The present invention is not construed as limiting to concrete training method.
Method of the present invention using the global parameter training for having supervision：Known signal corresponding with each WAP is strong
The physical location of degrees of data and outdoor environment data belongs to certain default training location tags, is made by constantly adjustment network parameter
The output for obtaining the Internet of deep neural network is identical with real result.
Preferably, the training module is further included：Submodule 311 preset by label, for pre-setting for training
Training location tags；Training dataset generates submodule 312, for each wireless access under collection different weather state respectively
Point receives the signal strength data signaled on correspondence position in detection zone by training terminal in the training location tags
And the humidity data；Training sample data are generated according to state of weather, the training sample data include vaporous on the same day
Under state, each WAP of collection receives the signal intensity of the signal that training terminal is sent on the training location tags
Data, the humidity data and weather corresponding with state of weather mark；According to all training location tags according to day
The training sample data that gaseity is generated generate training dataset, and send in deep neural network；Input data layer definition
Module 313, is defined as Three-channel data layer, the section of the Three-channel data layer for the input data layer by deep neural network
Point is corresponding with each WAP；Training prediction submodule 314, for according to the node of Three-channel data layer with wirelessly connect
The corresponding mode of access point is respectively by each signal strength data corresponding with WAP in each described training sample data
In conjunction with three passages that weather mark and corresponding humidity data are input into corresponding node, defeated through the deep neural network
Go out the training result corresponding with training location tags described in the training sample data；Will be right with which for the training result of output
The training location tags that answers are compared, and deep neural network are trained according to comparative result, by training after depth
Degree neutral net is used as the location model.
It should be noted that referring to the inventive method part for training for the training process of above-mentioned training module 300
The explanation of deep neural network, is no longer repeated herein.The contents such as information exchange, implementation procedure in book server between each module
Same design is based on said method embodiment, particular content can be found in the narration in the inventive method embodiment, herein no longer
Repeat.
Preferably, also include：Data processing module 400, for respectively to the signal in all training sample data
Intensity data, weather mark and humidity data are normalized, and connect for each WAP to gathering
Receive the signal strength data of the sent out signal of client to be detected, outdoor environment data to be normalized.
As the unit of the initial data for gathering is differed, AP corresponds to RSSI, and humidity is percentage ratio, and weather is to enumerate
Value.So gathered data is when deep neural network is input into, (concrete method for normalizing is not especially limited, and can adopt to answer normalization
With all suitable normalization processing methods in prior art).As deep neural network is in training, while having taken into account signal
Intensity data, humidity data and state of weather, so the deep neural network for training is can take into account when location prediction is carried out
Humidity and the impact of weather so that training is more accurate, so that positioning is more accurate.
The contents such as information exchange, implementation procedure in book server between each module and said method embodiment are based on same
Design, particular content can be found in the narration in the inventive method embodiment, and here is omitted.
It should be noted that above-described embodiment can independent assortment as needed.The above is only the preferred of the present invention
Embodiment, it is noted that for those skilled in the art, in the premise without departing from the principle of the invention
Under, some improvements and modifications can also be made, these improvements and modifications also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of outdoor positioning method based on humidity, it is characterised in that methods described includes step：
In S100, acquisition testing region, each WAP receives the signal strength data of the sent out signal of client to be detected
With outdoor environment data；The outdoor environment data include weather mark and with the weather corresponding humidity data of mark；
S200, respectively by the signal strength data and the outdoor environment data input training after location model input
Data Layer；
S300, based on training after the Internet of location model calculate the signal strength data and the outdoor environment number
According to, and the position of client to be detected is determined according to the output result of output layer.
2. the outdoor positioning method based on humidity as claimed in claim 1, it is characterised in that the outdoor environment data include
Weather mark and with the weather corresponding humidity data of mark；The weather mark is determined according to state of weather, the day
Gaseity includes non-rainy day state, light rain state, moderate rain state, heavy rain state and heavy rain state；With the state of weather pair
The weather mark that answers includes non-rainy day mark, light rain mark, moderate rain mark, heavy rain mark and heavy rain mark, each institute
State the corresponding humidity data of weather mark.
3. the outdoor positioning method based on humidity as claimed in claim 2, it is characterised in that also wrap before step S100
Include step：S000, training in advance deep neural network, using training after deep neural network as the location model.
4. the outdoor positioning method based on humidity as claimed in claim 3, it is characterised in that step S000 is further wrapped
Include step：
S001, pre-set training location tags；
Under S002, respectively collection different weather state, each WAP receives training terminal and exists in the training location tags
The signal strength data signaled on correspondence position in detection zone and the humidity data；Instruction is generated according to state of weather
Practice sample data, the training sample data include that each WAP of collection under same state of weather receives training terminal
The signal strength data of signal that sends on the training location tags, the humidity data and corresponding with state of weather
Weather is identified；
S003, the training sample data generation training data generated according to state of weather according to all training location tags
Collection, and send in deep neural network；
S004, the input data layer of deep neural network is defined as Three-channel data layer, the node of the Three-channel data layer
Corresponding with each WAP, according to the node of Three-channel data layer mode corresponding with WAP respectively by each
In the training sample data, each signal strength data corresponding with WAP combines weather and identifies and corresponding wet
Degrees of data is input into three passages of corresponding node, through deep neural network output and institute in the training sample data
State the corresponding training result of training location tags；
S005, the training location tags corresponding for the training result of output are compared, according to comparative result to depth
Degree neutral net be trained, using training after deep neural network as the location model.
5. the outdoor positioning method based on humidity as claimed in claim 4, it is characterised in that：
Also include step between step S003 and step S004：
S035, respectively to the signal strength data in all training sample data, weather identify and humidity data carry out
Normalized；
Also include step between step S100 and step S200：
S150, the signal strength data of the signal sent out to each WAP reception client to be detected of collection, outdoor
Environmental data is normalized.
6. a kind of outdoor positioning server based on humidity, it is characterised in that include：
Data acquisition module, receives the sent out signal of client to be detected for each WAP in acquisition testing region
Signal strength data and outdoor environment data；The outdoor environment data include that weather is identified and corresponding with weather mark
Humidity data；
Locating module, for determining after training the signal strength data for collecting and the outdoor environment data input
The input data layer of bit model, the Internet based on location model calculate the signal strength data and the outdoor environment number
According to, and the position of client to be detected is determined according to the output result of output layer.
7. the outdoor positioning server based on humidity as claimed in claim 6, it is characterised in that the outdoor environment packet
Include weather mark and with the weather corresponding humidity data of mark；The weather mark is determined according to state of weather, described
State of weather includes non-rainy day state, light rain state, moderate rain state, heavy rain state and heavy rain state；With the state of weather
The corresponding weather mark includes non-rainy day mark, light rain mark, moderate rain mark, heavy rain mark and heavy rain mark, each
The weather mark corresponds to a humidity data.
8. the outdoor positioning server based on humidity as claimed in claim 7, it is characterised in that also include：
Training module, for training in advance deep neural network, using training after deep neural network as the location model.
9. the outdoor positioning server based on humidity as claimed in claim 8, it is characterised in that the training module is further
Including：
Submodule preset by label, for pre-setting the training location tags for training；
Training dataset generates submodule, receives training terminal for each WAP under collection different weather state respectively
The signal strength data signaled on correspondence position in detection zone in the training location tags and the humidity number
According to；Training sample data are generated according to state of weather, the training sample data include under same state of weather each of collection
WAP receives the signal strength data of the signal that training terminal is sent on the training location tags, the humidity number
According to this and weather corresponding with state of weather mark；According to the training that all training location tags are generated according to state of weather
Sample data generates training dataset, and sends in deep neural network；
Input data layer defines submodule, is defined as Three-channel data layer, institute for the input data layer by deep neural network
The node for stating Three-channel data layer is corresponding with each WAP；
Training prediction submodule, for the mode corresponding with WAP of the node according to Three-channel data layer respectively by each
In the training sample data, each signal strength data corresponding with WAP combines weather and identifies and corresponding wet
Degrees of data is input into three passages of corresponding node, through deep neural network output and institute in the training sample data
State the corresponding training result of training location tags；The training location tags corresponding for the training result of output are carried out
Relatively, deep neural network is trained according to comparative result, using training after deep neural network as the positioning mould
Type.
10. the outdoor positioning server based on humidity as claimed in claim 9, it is characterised in that also include：
Data processing module, for respectively to the signal strength data in all training sample data, weather identify and
Humidity data is normalized, and for the sent out letter of each WAP reception client to be detected to collection
Number signal strength data, outdoor environment data are normalized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611044942.5A CN106507477A (en) | 2016-11-22 | 2016-11-22 | A kind of outdoor positioning method and server based on humidity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611044942.5A CN106507477A (en) | 2016-11-22 | 2016-11-22 | A kind of outdoor positioning method and server based on humidity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106507477A true CN106507477A (en) | 2017-03-15 |
Family
ID=58328380
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611044942.5A Pending CN106507477A (en) | 2016-11-22 | 2016-11-22 | A kind of outdoor positioning method and server based on humidity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106507477A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108828512A (en) * | 2018-06-25 | 2018-11-16 | 北京易途客信息技术有限公司 | Accurate positioning method and equipment based on the base station LBS |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1602021A (en) * | 2004-10-27 | 2005-03-30 | 上海宽鑫信息科技有限公司 | Indoor precision positioner and positioning algorithm of radio local network terminal appliance |
| CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
| CN103945332A (en) * | 2014-04-28 | 2014-07-23 | 清华大学 | Received signal strength and multi-path information combined neural network indoor positioning method |
| CN104574386A (en) * | 2014-12-26 | 2015-04-29 | 速感科技（北京）有限公司 | Indoor positioning method based on three-dimensional environment model matching |
| CN104683945A (en) * | 2013-11-29 | 2015-06-03 | 中国移动通信集团公司 | Mobile terminal positioning method, equipment and system |
-
2016
- 2016-11-22 CN CN201611044942.5A patent/CN106507477A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1602021A (en) * | 2004-10-27 | 2005-03-30 | 上海宽鑫信息科技有限公司 | Indoor precision positioner and positioning algorithm of radio local network terminal appliance |
| CN104683945A (en) * | 2013-11-29 | 2015-06-03 | 中国移动通信集团公司 | Mobile terminal positioning method, equipment and system |
| CN103945332A (en) * | 2014-04-28 | 2014-07-23 | 清华大学 | Received signal strength and multi-path information combined neural network indoor positioning method |
| CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
| CN104574386A (en) * | 2014-12-26 | 2015-04-29 | 速感科技（北京）有限公司 | Indoor positioning method based on three-dimensional environment model matching |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108828512A (en) * | 2018-06-25 | 2018-11-16 | 北京易途客信息技术有限公司 | Accurate positioning method and equipment based on the base station LBS |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106792507A (en) | A kind of WiFi localization methods and server based on network data | |
| CN106535134A (en) | Multi-room locating method based on wifi and server | |
| CN106507476A (en) | A kind of WiFi localization methods and server and location model construction method | |
| CN108810911B (en) | Low-power-consumption wide area network planning method based on data mining | |
| CN106793067A (en) | A kind of many floor indoor orientation methods and server based on joint network | |
| CN106792506A (en) | A kind of WiFi localization methods and server | |
| CN106792769A (en) | A kind of WiFi localization methods and server and location model method for building up | |
| CN106535326A (en) | WiFi locating method based on depth neural network and server | |
| CN106792553A (en) | A kind of many floor location methods and server based on wifi | |
| CN106793070A (en) | A kind of WiFi localization methods and server based on reinforcement deep neural network | |
| CN106792808A (en) | Los path recognition methods under a kind of indoor environment based on channel condition information | |
| US9345032B2 (en) | Method and apparatus for determining network clusters for wireless backhaul networks | |
| CN108988916B (en) | A kind of wave beam training method and device, communication system | |
| JP2000059292A (en) | Parallel optimization of radio network | |
| CN108462965B (en) | Iron tower demand site sharing planning method | |
| CN107736071A (en) | It is determined that the apparatus and method of the wave beam for guiding the signal that be sent to user equipment | |
| US11240676B2 (en) | Analysis method and apparatus for distributed-processing-based network design in wireless communication system | |
| US20230025445A1 (en) | Method and system for beam alignment in wireless network | |
| CN106488559A (en) | A kind of outdoor positioning method based on visibility and server | |
| CN107196683A (en) | Communication system, communication means, base station apparatus and terminal installation | |
| CN106559107A (en) | A kind of method and device for determining dual-mode antenna | |
| CN106507477A (en) | A kind of outdoor positioning method and server based on humidity | |
| CN106500698A (en) | A kind of indoor orientation method and device based on propagation operator | |
| CN107896122A (en) | A kind of beam scanning and search and track method and device | |
| CN117560104A (en) | Construction method of interpretable machine learning-assisted channel model in mixed traffic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170315 |
|
| WD01 | Invention patent application deemed withdrawn after publication |