CN109738863A - A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level - Google Patents
A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level Download PDFInfo
- Publication number
- CN109738863A CN109738863A CN201910274242.2A CN201910274242A CN109738863A CN 109738863 A CN109738863 A CN 109738863A CN 201910274242 A CN201910274242 A CN 201910274242A CN 109738863 A CN109738863 A CN 109738863A
- Authority
- CN
- China
- Prior art keywords
- signal strength
- mean square
- square error
- reference point
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000694 effects Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000004927 fusion Effects 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 11
- 238000000034 method Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 238000012935 Averaging Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000012952 Resampling Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000005457 optimization Methods 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000009191 jumping Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
Landscapes
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The present invention proposes a kind of WiFi fingerprint indoor positioning algorithms and system for merging confidence level, include the following steps: to acquire each reference point multiple AP signal strength characteristics values used for positioning using acquisition equipment in offline acquisition phase, and the signal strength characteristics value is pre-processed, calculate signal strength characteristics mean value and mean square deviation；Confidence level is determined using the virtual map table of the mean square deviation section of building and confidence level after acquisition mean square deviation, in location fingerprint database of finally uploading onto the server together with the serial number of the reference point, signal strength characteristics mean value collection, geographical position coordinates；In the tuning on-line stage, confidence level is added when carrying out Euclidean distance matching primitives with characteristic in database in the user point to be determined signal strength characteristics Value Data obtained in real time, can reach the effect for optimizing its distance.The present invention uses the WiFi fingerprint indoor positioning optimization algorithm for merging confidence level, it is possible to reduce jump increases stability, improves positioning accuracy.
Description
Technical Field
The invention relates to the technical field of indoor positioning, in particular to a WiFi fingerprint indoor positioning algorithm and system fusing confidence coefficients.
Background
People stay in the indoor environment for more than 80% of the time, but the indoor positioning is not widely applied due to factors such as technology and cost. At present, scholars at home and abroad propose indoor positioning technologies and application systems based on wireless fidelity, Bluetooth, infrared rays, radio frequency identification, ultrasonic waves, ultra wide bands and the like, and comprehensively consider factors such as deployment cost, positioning precision and the like, wherein the WiFi-based WLAN indoor positioning technology has the widest application prospect.
The RSS-based WLAN indoor positioning technology uses the association between RSS values and geographical location coordinates to achieve the location estimation of a target, and has the following advantages: first, deployment costs are low and deployment is simple and quick. The technology utilizes the existing WLAN system and the portable mobile terminal in the user's hand to estimate the user's position through a positioning algorithm. Meanwhile, aiming at high cost in an offline acquisition stage and ensuring acquisition accuracy, the high-quality offline database plays a great role in positioning accuracy. The online positioning error is increased due to inaccurate signal acquisition caused by factors such as indoor environment complexity, multipath effect and radio frequency interference.
Therefore, it is very important to design a stable offline acquisition step, and the positioning accuracy can be further improved by fusing the confidence coefficient in the offline acquisition stage.
Disclosure of Invention
The invention aims to provide a WiFi fingerprint indoor positioning algorithm and system fusing confidence coefficient, which can reduce jumping, increase stability, optimize Euclidean distance and improve positioning accuracy.
In order to achieve the above object, an aspect of the embodiments of the present invention provides a WiFi fingerprint indoor positioning algorithm with fusion confidence, including the following steps:
in an off-line acquisition stage, acquiring a plurality of AP signal strength characteristic values of each reference point for positioning by using acquisition equipment, preprocessing the signal strength characteristic values, and calculating a signal strength characteristic mean value and a mean square error;
after the mean square difference is obtained, the confidence coefficient is determined by using the constructed virtual mapping table of the mean square difference interval and the confidence coefficient, and finally the confidence coefficient, the serial number of the reference point, the signal intensity characteristic mean value set and the geographic position coordinate are uploaded to a server position fingerprint database;
in the on-line positioning stage, when Euclidean distance matching calculation is carried out on the signal intensity characteristic value data of the point to be positioned acquired in real time and each group of characteristic data in the database, confidence coefficient is added, namely the reciprocal of the confidence coefficient of the corresponding AP is multiplied before the sum of squares is added in the calculation of the Euclidean distance, the geographic position coordinate corresponding to the reference point with the minimum Euclidean distance is used as the position estimation of the point to be positioned of the user, and the position estimation is returned to the user, namely the positioning is finished.
Further, the step of calculating the mean of the signal strength characteristics includes:
according to the formulaAcquiring n times of signal intensity characteristic values of a single AP of a certain reference point, and carrying out averaging processing to obtain an AP signal intensity average value;
wherein,is the average value of the AP signal strength,the sum of the signal strength characteristics is acquired n times for the AP.
According to the formulaSignal strengths of all APs collected for each reference pointAveraging the characteristic values to obtain the average value of the signal intensity of each AP of each reference point;
wherein,the signal strength characteristic mean value of the mth AP of a certain reference point,collecting the sum of the signal strength characteristic values of n times for the mth AP of a certain reference point, wherein n is the collection times of the collection equipment, i is an independent variable, m is the number of the APs,a set of signal strength averages is separately made for all APs acquired for a single reference point,and respectively solving a set of the sums of the signal strength characteristic values for all the APs acquired by a single reference point.
Further, the calculating the mean square error of the signal strength eigenvalue is as follows:
after each reference point receives each AP signal strength characteristic value, mean value processing is carried out, and mean square deviation is calculated;
the mean square error formula is
Wherein,the signal strength characteristic value acquired for the nth time of a single AP,the AP signal strength average is obtained.
Further, the calculating the mean square error of the signal strength characteristic value comprises the following steps:
when the signal intensity characteristic value of one reference point is acquired, all APs independently calculate the mean square error and compare the mean square error with a threshold value, wherein the threshold value is the maximum value of the mean square error in a virtual mapping table of the constructed mean square error interval and confidence coefficient;
if the mean square error is larger than the threshold value, subtracting the acquired signal intensity characteristic values one by calculating the mean value, taking absolute values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values, recording, and judging whether the mean square error is within the threshold value or not until the mean square error is consistent with the maximum absolute values.
Further, the determining whether the mean square error is within a threshold value further includes:
if the signal of a certain AP is not stable all the time, the mean square error is always larger than the threshold value, and then sampling is carried out again;
if the signal intensity characteristic values are larger than the threshold value after resampling, subtracting the absolute values one by one through the calculated mean value and the acquired signal intensity characteristic values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values and recording the result until the last three signal intensity characteristic values are remained, and recording the minimum mean square error and the mean value in the whole process.
Further, the mean square error obtained by each AP of each reference point is converted according to the mean square error and a confidence coefficient mapping table to obtain the AP confidence coefficient of the reference point; the mapping table of the mean square error and the confidence coefficient is a virtual mapping table which can be created in a program and is divided into two elements of a mean square error interval and the confidence coefficient.
Further, uploading the obtained confidence of each AP of each reference point and the geographical position coordinate, the sequence number and the signal strength characteristic mean value set of the reference point to a server position fingerprint database, wherein the signal strength characteristic mean value set in the database is recorded as:n is the number of reference points, and m is the number of APs.
Further, in the online positioning stage, signal strength acquisition is performed at a certain to-be-positioned point for a period of time, signal strength characteristic values of all APs used for positioning are acquired in the period of time, and the signal strength characteristic values of all APs are respectively averaged, so that a group of AP signal strength characteristic average value sets are obtained as:and m is the number of the APs, uploading the mean value set to a server, adding a confidence coefficient when performing Euclidean distance matching calculation with each group of feature data in a database, namely multiplying the squared sum in the Euclidean distance calculation by the reciprocal of the corresponding confidence coefficient of the AP before adding, taking the geographic position coordinate corresponding to the reference point with the minimum Euclidean distance as the position estimation of the to-be-positioned point of the user, and returning the position estimation to the user to finish positioning.
The original Euclidean distance formula is as follows:
let the confidence of the kth AP under the jth reference point in the database beThen the euclidean distance formula is changed to:
wherein m is the number of APs, N is the total number of reference points in the database, AkThe signal strength characteristic value of the kth AP measured by the user at the point to be located, BjkThe signal strength characteristic value of the kth AP under the jth reference point in the database.
In order to achieve the above object, another aspect of the embodiments of the present invention further provides a WiFi fingerprint indoor positioning system with fusion confidence, including a mobile terminal, and a cloud server in network communication with the mobile terminal, where the mobile terminal includes a WiFi obtaining unit and a processing program, and the cloud server includes a WiFi characteristic parameter storage unit and a positioning unit.
The WiFi acquisition unit and the processing program are used for acquiring a plurality of AP signal strength characteristic values received by each reference point in an off-line acquisition stage, and carrying out mean value and mean square deviation processing and recording on the signal strength characteristic values, wherein each reference point comprises a plurality of AP signal strength characteristic values.
The WiFi characteristic parameter storage unit is used for storing the MAC address, the confidence coefficient, the geographical position coordinates of each AP, and the signal strength characteristic mean value and the mean square error of each AP at each reference point.
And the positioning unit is used for adding confidence coefficient when Euclidean distance matching calculation is carried out on the signal intensity characteristic value data of the user to be positioned acquired in real time and each group of signal intensity characteristic value data in the database in the online positioning stage, namely multiplying the sum of squares in the Euclidean distance calculation by the reciprocal of the confidence coefficient of the corresponding AP before the sum of squares is added, so that the effect of optimizing the distance is achieved.
Compared with the prior art, the invention has the beneficial effects that:
the WiFi fingerprint indoor positioning optimization algorithm with fusion confidence coefficient is used, so that the jumping can be reduced, the stability is improved, the Euclidean distance is optimized, and the positioning precision is improved. The WiFi fingerprint indoor positioning optimization algorithm with the fused confidence coefficient mainly has the effects of reducing errors caused by real-time acquisition and setting a lower confidence coefficient for a reference point which is reached with a small probability.
Drawings
Fig. 1 is a schematic block diagram of a WiFi fingerprint indoor positioning method with fusion confidence proposed by the present invention;
fig. 2 is an offline acquisition flow chart of the WiFi fingerprint indoor positioning method with fusion confidence proposed by the present invention;
fig. 3 is a flowchart of a WiFi fingerprint indoor positioning system incorporating confidence level proposed by the present invention;
fig. 4 is a schematic diagram of WiFi fingerprint indoor positioning with fusion confidence proposed by the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
These and other aspects of embodiments of the invention will be apparent with reference to the following description and attached drawings. In the description and drawings, particular embodiments of the invention have been disclosed in detail as being indicative of some of the ways in which the principles of the embodiments of the invention may be practiced, but it is understood that the scope of the embodiments of the invention is not limited correspondingly. On the contrary, the embodiments of the invention include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.
Due to factors such as indoor complex environment, multipath effect, indoor fixed furniture, radio frequency interference and the like, the on-line positioning error is enlarged due to inaccurate signal acquisition. Aiming at the problem, the invention provides a WiFi fingerprint indoor positioning optimization algorithm with fusion confidence coefficient, which can reduce jumping, increase stability and improve positioning precision. The WiFi fingerprint indoor positioning optimization algorithm with the fused confidence coefficient mainly has the effects of reducing errors caused by real-time acquisition and setting the confidence coefficient to be lower for a reference point which is reached with a small probability. That is, when the strength characteristic value of the positioning signal is calculated, only the mean value is not required to be calculated, but the mean square error of the mean data set is also calculated and recorded, and the mean square error represents the quality of the signal. And converting the mean square error by using the mean square error and confidence coefficient mapping table, and finally uploading the converted mean square error, the serial number of the reference point, the signal intensity characteristic mean value set and the geographic position coordinate to a server position fingerprint database.
One aspect of an embodiment of the present invention provides a WiFi fingerprint indoor positioning algorithm with fusion confidence, including the following steps:
s101, in an off-line acquisition stage, acquiring a plurality of AP signal strength characteristic values of each reference point for positioning by using acquisition equipment, and preprocessing the signal strength characteristic values, wherein the preprocessing comprises calculating a mean value and a mean square error.
According to the formulaAnd acquiring n times of signal intensity characteristic values of a single AP of a certain reference point, and averaging to obtain an AP signal intensity average value.
Wherein,is the average value of the AP signal strength,the sum of the signal strength characteristics is acquired n times for the AP.
In this embodiment, the collectors use the mobile smart phone to collect the reference points that have been laid one by one in the same direction. The number of times of acquiring each reference point is 30, each time is to acquire the signal strength characteristic values of all the APs, and the time is about 1 minute and a half. Can be represented by formulaRespectively averaging the signal intensity characteristic values of all APs acquired by each reference pointAnd processing to obtain the signal intensity average value of each AP of each reference point.
Wherein,the signal strength characteristic mean value of the mth AP of a certain reference point,collecting the sum of the signal strength characteristic values of n times for the mth AP of a certain reference point, wherein n is the collection times of the collection equipment, i is an independent variable, m is the number of the APs,a set of signal strength averages is separately made for all APs acquired for a single reference point,and respectively solving a set of the sums of the signal strength characteristic values for all the APs acquired by a single reference point.
Mean value is carried out and then mean square error processing is carried out, and the mean square error can be obtained according to a mean square error formulaThe mean square error is calculated and,the signal strength characteristic value acquired for the nth time of a single AP,the AP signal strength average is obtained. The mean square error, also commonly referred to as the standard deviation, is the arithmetic square root of the variance. The standard deviation can reflect the degree of dispersion of a data set. The mean square deviations are not necessarily the same for two sets of data with the same mean. For example, the signal strength characteristics of group X are (-95 dBm, -85dBm, -75dBm, -65dBm, -55dBm, -45 dBm), and the signal strength characteristics of group B are (-73dBm, -72dBm, -71dBm, -69dBm, -68dBm, -67 dBm). The mean values of both groups were-70 dBm, but the mean square of group AThe difference is about 17.08dBm, the mean square error of the B group is about 2.16dBm, which indicates that the B group signal strength characteristic is lower and more stable than the a group signal strength characteristic, so the present invention uses the mean square error when performing the conversion.
It should be noted here that when the next reference point acquisition is performed, the position should be waited for 10s to ensure the stability of the signal.
S102, comparing the mean square deviations of the APs of all the obtained reference points with a threshold value; the threshold is the maximum value of the mean square error in the virtual mapping table of the mean square error interval and the confidence coefficient constructed by the invention.
If the mean square error is larger than the threshold value, subtracting the acquired signal intensity characteristic values one by calculating the mean value, taking absolute values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values, recording, and judging whether the mean square error is within the threshold value or not until the mean square error is consistent with the maximum absolute values.
It should be noted that, if the signal of a certain AP is not stable all the time, the mean square error is always greater than the threshold, and then the sampling is performed again.
If the signal intensity characteristic values are larger than the threshold value after resampling, subtracting the absolute values one by one through the calculated mean value and the acquired signal intensity characteristic values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values and recording the result until the last three signal intensity characteristic values are remained, and recording the minimum mean square error and the mean value in the whole process.
And converting the mean square error obtained by each AP of each reference point according to the mean square error and a confidence coefficient mapping table to obtain the AP confidence coefficient of the reference point.
The mapping table of the mean square error and the confidence coefficient is a virtual mapping table which can be created in a program and is divided into two elements of a mean square error interval and the confidence coefficient.
As shown in the following table, each confidence is mapped with a mean square error interval, and when the mean square error obtained by obtaining the signal strength characteristic value of an AP at a certain reference point falls into a certain mean square error interval in the following table, the confidence of the signal strength characteristic value of the AP at the reference point is the confidence corresponding to the mean square error.
| Serial number | Mean square error interval | Confidence level |
| 1 | （10.00，50.00） | 0.60 |
| 2 | （1.00，10.00） | 0.70 |
| 3 | （0.50,1.00） | 0.80 |
| 4 | （0.25,0.50） | 0.90 |
| 5 | （0.00,0.25） | 1.00 |
The confidence degree is also called credibility, and the threshold value is determined by the following method: the number of reference points in the whole experimental area is 98, the number of APs is 4, signal intensity characteristic values of 4 APs need to be collected for each reference point, namely the calculated number of mean square deviations is 98 × 4=392, 392 mean square deviation values are used for eliminating outliers by using an outlier detection algorithm in a data analysis tool, the remaining mean square deviation interval is (0.00, 50.00), and the maximum value of the mean square deviation is taken as a threshold value.
The method for determining the mean square error interval comprises the following steps: firstly, dividing the mean square error interval of 0.00 to 50.00 into 5 parts by taking the same number as a standard, and then preliminarily determining each mean square error interval. After the completion, the data is decreased in a decreasing mode of once by 10% from 100% according to the confidence coefficient, and the mean square error interval is adjusted.
And then, continuously verifying the mean square error interval by taking the confidence as a reference: if the mean square error interval is 0.00-0.25, finding out a reference point of the mean square error in the interval, re-acquiring data, calculating the mean square error for 30 times, and then obtaining the mean square error in the interval, wherein the reliability is 100%, namely the confidence coefficient is 1.00, if not, amplifying the mean square error interval until the confidence coefficient is 1.00, and determining a virtual mapping table between the mean square error interval and the confidence coefficient by the same method for other intervals.
After the mean square error interval and the confidence coefficient mapping table are determined, the confidence coefficient can be determined by using the mapping table in other regions which are not collected, and the process is not required to be repeated. If the mean square error calculated for a single AP is 0.10, then the confidence for that AP for that reference point is 1.00.
The confidence degree of each AP of each reference point obtained by the processing can be uploaded to a server position fingerprint database together with the geographic position coordinate, the signal strength characteristic mean value set and the serial number of the reference point. Wherein the set of signal strength feature means in the database is:n is the number of reference points, and m is the number of APs.
S103, optimizing Euclidean distance by using the confidence coefficient in the positioning matching stage.
The user uses the intelligent mobile device originally used for collection, and the signal intensity collection of a period of time is carried out at a certain point to be positioned, and the signal intensity characteristic values of all the APs used for positioning can be collected in the period of time, and the signal intensity characteristic values of all the APs are respectively averaged, so that a group of AP signal intensity characteristic average value sets can be obtained and recorded as:and m is the number of the APs, uploading the mean value set to a server, adding a confidence coefficient when performing Euclidean distance matching calculation with each group of feature data in a database, namely multiplying the squared sum in the Euclidean distance calculation by the reciprocal of the corresponding confidence coefficient of the AP before adding, taking the geographic position coordinate corresponding to the reference point with the minimum Euclidean distance as the position estimation of the to-be-positioned point of the user, and returning the position estimation to the user to finish positioning.
The original Euclidean distance formula is as follows:
let the confidence of the kth AP under the jth reference point in the database beThen the euclidean distance formula is changed to:
wherein m is the number of APs, N is the total number of reference points in the database, AkThe signal strength characteristic value of the kth AP measured by the user at the point to be located, BjkThe signal strength characteristic value of the kth AP under the jth reference point in the database.
The invention further provides a WiFi fingerprint indoor positioning system fusing confidence degrees, which comprises a mobile terminal and a cloud server in network communication with the mobile terminal, wherein the mobile terminal comprises a WiFi acquisition unit and a processing program, and the cloud server comprises a WiFi characteristic parameter storage unit and a positioning unit.
The WiFi acquisition unit and the processing program are used for acquiring a plurality of AP signal strength characteristic values received by each reference point in an off-line acquisition stage, and carrying out mean value and mean square deviation processing and recording on the signal strength characteristic values, wherein each reference point comprises a plurality of AP signal strength characteristic values.
The WiFi characteristic parameter storage unit is used for storing the MAC address, the confidence coefficient, the geographical position coordinates of each AP, and the signal strength characteristic mean value and the mean square error of each AP at each reference point.
The positioning unit is used for adding confidence coefficient when Euclidean distance matching calculation is carried out on the signal intensity characteristic value data of the user to be positioned acquired in real time and each group of signal intensity characteristic value data in the database in the online positioning stage, namely, the reciprocal of the confidence coefficient of the corresponding AP is multiplied before the sum of squares is added in the calculation of the Euclidean distance, and the effect of optimizing the distance can be achieved.
The above-mentioned embodiments only express one embodiment of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (9)
1. A WiFi fingerprint indoor positioning algorithm fused with confidence coefficients is characterized in that: the method comprises the following steps:
in an off-line acquisition stage, acquiring a plurality of AP signal strength characteristic values of each reference point for positioning by using acquisition equipment, preprocessing the signal strength characteristic values, and calculating a signal strength characteristic mean value and a mean square error;
after the mean square difference is obtained, the confidence coefficient is determined by using the constructed virtual mapping table of the mean square difference interval and the confidence coefficient, and finally the confidence coefficient, the serial number of the reference point, the signal intensity characteristic mean value set and the geographic position coordinate are uploaded to a server position fingerprint database;
in the on-line positioning stage, when Euclidean distance matching calculation is carried out on the signal intensity characteristic value data of the point to be positioned acquired in real time and each group of characteristic data in the database, confidence coefficient is added, namely the reciprocal of the confidence coefficient of the corresponding AP is multiplied before the sum of squares is added in the calculation of the Euclidean distance, the geographic position coordinate corresponding to the reference point with the minimum Euclidean distance is used as the position estimation of the point to be positioned of the user, and the position estimation is returned to the user, namely the positioning is finished.
2. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 1, wherein: the step of calculating the mean of the signal strength features comprises the following steps:
according to the formulaAcquiring n times of signal intensity characteristic values of a single AP of a certain reference point, and carrying out averaging processing to obtain an AP signal intensity average value;
wherein,is the average value of the AP signal strength,collecting the sum of the signal intensity characteristic values for the AP for n times;
according to the formula
Respectively carrying out averaging processing on the signal intensity characteristic values of all the APs acquired by each reference point to obtain the signal intensity average value of each AP of each reference point;
wherein,for mth AP of a certain reference pointThe mean value of the signal strength characteristics is,collecting the sum of the signal strength characteristic values of n times for the mth AP of a certain reference point, wherein n is the collection times of the collection equipment, i is an independent variable, m is the number of the APs,a set of signal strength averages is separately made for all APs acquired for a single reference point,and respectively solving a set of the sums of the signal strength characteristic values for all the APs acquired by a single reference point.
3. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 1, wherein: the mean square error of the calculated signal strength characteristic value is as follows:
after each reference point receives each AP signal strength characteristic value, mean value processing is carried out, and mean square deviation is calculated;
the mean square error formula is
Wherein,the signal strength characteristic value acquired for the nth time of a single AP,the AP signal strength average is obtained.
4. The WiFi fingerprint indoor location algorithm with fusion confidence as claimed in claim 1 or 3, wherein: the calculating the mean square error of the signal strength characteristic value comprises the following steps:
when the signal intensity characteristic value of one reference point is acquired, all APs independently calculate the mean square error and compare the mean square error with a threshold value, wherein the threshold value is the maximum value of the mean square error in a virtual mapping table of the constructed mean square error interval and confidence coefficient;
if the mean square error is larger than the threshold value, subtracting the acquired signal intensity characteristic values one by calculating the mean value, taking absolute values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values, recording, and judging whether the mean square error is within the threshold value or not until the mean square error is consistent with the maximum absolute values.
5. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 4, wherein: the judging whether the mean square error is within the threshold value further comprises:
if the signal of a certain AP is not stable all the time, the mean square error is always larger than the threshold value, and then sampling is carried out again;
if the signal intensity characteristic values are larger than the threshold value after resampling, subtracting the absolute values one by one through the calculated mean value and the acquired signal intensity characteristic values, then sorting in a descending order, eliminating the signal intensity characteristic values corresponding to the maximum absolute values of the first three bits, recalculating the mean square error of the rest signal intensity characteristic values and recording the result until the last three signal intensity characteristic values are remained, and recording the minimum mean square error and the mean value in the whole process.
6. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 1, wherein: converting the mean square error obtained by each AP of each reference point according to the mean square error and a confidence mapping table to obtain the AP confidence of the reference point; the mapping table of the mean square error and the confidence coefficient is a virtual mapping table which can be created in a program and is divided into two elements of a mean square error interval and the confidence coefficient.
7. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 1, wherein: subjecting the obtained ginseng toUploading the confidence degrees of all APs of the examination points and the geographical position coordinates, the sequence numbers and the signal strength characteristic mean value sets of the reference points to a server position fingerprint database, wherein the signal strength characteristic mean value sets in the database are recorded as:n is the number of reference points, and m is the number of APs.
8. The WiFi fingerprint indoor positioning algorithm with fusion confidence as claimed in claim 1, wherein: in the on-line positioning stage, signal strength acquisition is performed for a period of time at a certain point to be positioned, signal strength characteristic values of all APs used for positioning are acquired in the period of time, the signal strength characteristic values of all APs are respectively averaged, and a group of AP signal strength characteristic average value sets are obtained as follows:the mean value set is uploaded to a server, confidence coefficient is added when Euclidean distance matching calculation is carried out on the mean value set and each group of characteristic data in a database, namely the square sum is added in the Euclidean distance calculation and multiplied by the reciprocal of the corresponding confidence coefficient of the AP, the geographic position coordinate corresponding to the reference point with the minimum Euclidean distance is used as the position estimation of the position to be positioned by the user, and the position estimation is returned to the user, so that the positioning is completed;
the original Euclidean distance formula is as follows:
let the confidence of the kth AP under the jth reference point in the database beThen the euclidean distance formula is changed to:
wherein m is the number of APs, N is the total number of reference points in the database, AkThe signal strength characteristic value of the kth AP measured by the user at the point to be located, BjkThe signal strength characteristic value of the kth AP under the jth reference point in the database.
9. The utility model provides a fuse indoor positioning system of wiFi fingerprint of confidence which characterized in that: the mobile terminal comprises a WiFi acquisition unit and a processing program, and the cloud server comprises a WiFi characteristic parameter storage unit and a positioning unit;
the WiFi acquisition unit and the processing program are used for acquiring a plurality of AP signal strength characteristic values received by each reference point in an off-line acquisition stage, and carrying out mean value and mean square deviation processing and recording on the signal strength characteristic values, wherein each reference point comprises a plurality of AP signal strength characteristic values;
the WiFi characteristic parameter storage unit is used for storing the MAC address, the confidence coefficient, the geographical position coordinates of each AP, and the signal strength characteristic mean value and the mean square error of each AP at each reference point;
and the positioning unit is used for adding confidence coefficient when Euclidean distance matching calculation is carried out on the signal intensity characteristic value data of the user to be positioned acquired in real time and each group of signal intensity characteristic value data in the database in the online positioning stage, namely multiplying the sum of squares in the Euclidean distance calculation by the reciprocal of the confidence coefficient of the corresponding AP before the sum of squares is added, so that the effect of optimizing the distance is achieved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274242.2A CN109738863A (en) | 2019-04-08 | 2019-04-08 | A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274242.2A CN109738863A (en) | 2019-04-08 | 2019-04-08 | A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109738863A true CN109738863A (en) | 2019-05-10 |
Family
ID=66371409
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910274242.2A Pending CN109738863A (en) | 2019-04-08 | 2019-04-08 | A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109738863A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110267209A (en) * | 2019-06-28 | 2019-09-20 | 深圳数位传媒科技有限公司 | A kind of indoor orientation method and device based on WiFi longitude and latitude |
| CN110456308A (en) * | 2019-07-08 | 2019-11-15 | 广西工业职业技术学院 | A kind of three dimension location method for fast searching |
| CN111050275A (en) * | 2019-11-26 | 2020-04-21 | 武汉虹信技术服务有限责任公司 | Bluetooth positioning method based on RSSI characteristic value |
| CN113050137A (en) * | 2021-03-09 | 2021-06-29 | 江西师范大学 | Multi-point cooperative measurement spatial information acquisition method |
| CN113079466A (en) * | 2020-10-21 | 2021-07-06 | 中移(上海)信息通信科技有限公司 | Fingerprint database construction method, device, equipment and computer storage medium |
| CN116800203A (en) * | 2023-06-27 | 2023-09-22 | 深圳市安科讯实业有限公司 | Photovoltaic inverter with operation supervision function based on Internet of things |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103354660A (en) * | 2013-06-21 | 2013-10-16 | 北京邮电大学 | Positioning method and device based on signal intensity in mobile communication network |
| CN104135768A (en) * | 2014-08-21 | 2014-11-05 | 哈尔滨工业大学 | Wireless sensor network positioning method based on signal intensity mapping |
| CN104703143A (en) * | 2015-03-18 | 2015-06-10 | 北京理工大学 | Indoor positioning method based on WIFI signal strength |
| CN104883734A (en) * | 2015-05-12 | 2015-09-02 | 北京邮电大学 | Indoor passive positioning method based on geographic fingerprints |
| CN106102163A (en) * | 2016-06-03 | 2016-11-09 | 杭州电子科技大学 | WLAN fingerprint positioning method based on RSS linear correlation Yu secondary weighted centroid algorithm |
| US20170079004A1 (en) * | 2013-08-06 | 2017-03-16 | Google Technology Holdings LLC | Method and apparatus for wireless network data collection |
| CN107271951A (en) * | 2017-06-06 | 2017-10-20 | 上海工程技术大学 | UAV Navigation System and its air navigation aid based on WiFi fingerprint locations |
| CN107333276A (en) * | 2017-05-27 | 2017-11-07 | 南京邮电大学 | WiFi location fingerprint localization methods based on weighted chi-square distance |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
-
2019
- 2019-04-08 CN CN201910274242.2A patent/CN109738863A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103354660A (en) * | 2013-06-21 | 2013-10-16 | 北京邮电大学 | Positioning method and device based on signal intensity in mobile communication network |
| US20170079004A1 (en) * | 2013-08-06 | 2017-03-16 | Google Technology Holdings LLC | Method and apparatus for wireless network data collection |
| CN104135768A (en) * | 2014-08-21 | 2014-11-05 | 哈尔滨工业大学 | Wireless sensor network positioning method based on signal intensity mapping |
| CN104703143A (en) * | 2015-03-18 | 2015-06-10 | 北京理工大学 | Indoor positioning method based on WIFI signal strength |
| CN104883734A (en) * | 2015-05-12 | 2015-09-02 | 北京邮电大学 | Indoor passive positioning method based on geographic fingerprints |
| CN106102163A (en) * | 2016-06-03 | 2016-11-09 | 杭州电子科技大学 | WLAN fingerprint positioning method based on RSS linear correlation Yu secondary weighted centroid algorithm |
| CN107333276A (en) * | 2017-05-27 | 2017-11-07 | 南京邮电大学 | WiFi location fingerprint localization methods based on weighted chi-square distance |
| CN107271951A (en) * | 2017-06-06 | 2017-10-20 | 上海工程技术大学 | UAV Navigation System and its air navigation aid based on WiFi fingerprint locations |
| CN107948930A (en) * | 2017-12-31 | 2018-04-20 | 电子科技大学 | Indoor positioning optimization method based on location fingerprint algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 毛永毅等: "基于WiFi的一种改进的室内定位算法", 《测控技术》 * |
| 王佳: "基于迭代匹配与置信度的室内定位算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110267209A (en) * | 2019-06-28 | 2019-09-20 | 深圳数位传媒科技有限公司 | A kind of indoor orientation method and device based on WiFi longitude and latitude |
| CN110267209B (en) * | 2019-06-28 | 2021-09-10 | 深圳数位传媒科技有限公司 | Indoor positioning method and device based on WiFi longitude and latitude |
| CN110456308A (en) * | 2019-07-08 | 2019-11-15 | 广西工业职业技术学院 | A kind of three dimension location method for fast searching |
| CN111050275A (en) * | 2019-11-26 | 2020-04-21 | 武汉虹信技术服务有限责任公司 | Bluetooth positioning method based on RSSI characteristic value |
| CN113079466A (en) * | 2020-10-21 | 2021-07-06 | 中移(上海)信息通信科技有限公司 | Fingerprint database construction method, device, equipment and computer storage medium |
| CN113079466B (en) * | 2020-10-21 | 2022-04-26 | 中移(上海)信息通信科技有限公司 | Fingerprint database construction method, device, equipment and computer storage medium |
| CN113050137A (en) * | 2021-03-09 | 2021-06-29 | 江西师范大学 | Multi-point cooperative measurement spatial information acquisition method |
| CN113050137B (en) * | 2021-03-09 | 2022-04-26 | 江西师范大学 | Multi-point cooperative measurement spatial information acquisition method |
| CN116800203A (en) * | 2023-06-27 | 2023-09-22 | 深圳市安科讯实业有限公司 | Photovoltaic inverter with operation supervision function based on Internet of things |
| CN116800203B (en) * | 2023-06-27 | 2024-06-04 | 深圳市安科讯实业有限公司 | Photovoltaic inverter with operation supervision function based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109738863A (en) | A kind of WiFi fingerprint indoor positioning algorithms and system merging confidence level | |
| CN106793082B (en) | Mobile equipment positioning method in WLAN/Bluetooth heterogeneous network environment | |
| CN103402256B (en) | A kind of indoor orientation method based on WiFi fingerprint | |
| CN106851573B (en) | Log path loss model-based joint weighting K nearest neighbor indoor positioning method | |
| CN103945332B (en) | A kind of received signal strength and multi-path information united NNs indoor orientation method | |
| CN105898692B (en) | A kind of indoor orientation method and device | |
| CN107333238B (en) | Indoor fingerprint rapid positioning method based on support vector regression | |
| CN110996387B (en) | LoRa positioning method based on TOF and position fingerprint fusion | |
| CN105704677B (en) | One kind being based on barometrical indoor orientation method and device | |
| Elbakly et al. | A robust zero-calibration RF-based localization system for realistic environments | |
| CN105792356A (en) | Wifi-based location fingerprint positioning method | |
| CN103905992B (en) | Indoor positioning method based on wireless sensor networks of fingerprint data | |
| CN110166930A (en) | A kind of indoor orientation method and system based on WiFi signal | |
| CN104507050B (en) | Probabilistic type finger print matching method in a kind of WiFi indoor positionings | |
| CN103581831B (en) | Indoor locating method based on WiFi and mobile terminal | |
| CN105120433A (en) | WLAN indoor positioning method based on continuous sampling and fuzzy clustering | |
| CN102932738A (en) | Improved positioning method of indoor fingerprint based on clustering neural network | |
| CN102427603A (en) | Positioning method of WLAN (Wireless Local Area Network) indoor mobile user based on positioning error estimation | |
| WO2022062177A1 (en) | Adaptive indoor fusion positioning method based on dynamic environment | |
| CN106792554A (en) | A kind of localization method based on Dual Matching fingerprint location technology | |
| CN108414970B (en) | Indoor positioning method | |
| CN107290715A (en) | It is a kind of that the indoor orientation method changed with fingerprint is calibrated based on fingerprint | |
| CN105163382A (en) | Indoor region location optimization method and system | |
| Ding et al. | AP weighted multiple matching nearest neighbors approach for fingerprint-based indoor localization | |
| CN110351660A (en) | A kind of bluetooth indoor orientation method based on two-step fingerprint matching framework |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190510 |