CN116056140A - Cellular network wireless sensing and positioning integrated method based on machine learning - Google Patents
Cellular network wireless sensing and positioning integrated method based on machine learning Download PDFInfo
- Publication number
- CN116056140A CN116056140A CN202310007214.0A CN202310007214A CN116056140A CN 116056140 A CN116056140 A CN 116056140A CN 202310007214 A CN202310007214 A CN 202310007214A CN 116056140 A CN116056140 A CN 116056140A
- Authority
- CN
- China
- Prior art keywords
- positioning
- cell
- positioning request
- reference signal
- cellular network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000001413 cellular effect Effects 0.000 title claims abstract description 23
- 238000010801 machine learning Methods 0.000 title claims abstract description 21
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000001914 filtration Methods 0.000 claims description 9
- 238000007637 random forest analysis Methods 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 abstract description 12
- 230000008447 perception Effects 0.000 abstract description 5
- 238000004891 communication Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000004165 Methyl ester of fatty acids Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 229940049705 immune stimulating antibody conjugate Drugs 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/10—Scheduling measurement reports ; Arrangements for measurement reports
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/309—Measuring or estimating channel quality parameters
- H04B17/318—Received signal strength
- H04B17/327—Received signal code power [RSCP]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
- H04B17/30—Monitoring; Testing of propagation channels
- H04B17/391—Modelling the propagation channel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electromagnetism (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The technical scheme of the invention provides a cellular network wireless sensing and positioning integrated method based on machine learning. The invention fully utilizes the user measurement report collected from the cellular network, and the proposed wireless sensing and positioning integrated method is more in line with the trend of the wireless network test to the user active report mode, solves the problem that indoor and outdoor MRs in a fingerprint database are mixed together, effectively classifies fingerprints based on integrated learning, and eliminates the interference of indoor fingerprints on outdoor positioning. On the one hand, the obtained positioning result far exceeds the standards of the United states federal communications commission, and further improvement of positioning accuracy by fingerprint denoising is proved to be feasible. On the other hand, the scene perception is increased before positioning, the computational complexity is not obviously increased, and the time delay can be effectively reduced when more data are processed.
Description
Technical Field
The invention relates to a wireless sensing and positioning integrated method for a cellular network.
Background
Communication awareness integration (integrated sensing and communication, ISAC) is one of the most promising technological directions in the B5G/6G era. However, with the explosive growth of mobile terminals in changing scenarios, how to provide accurate human-centered services (HCS) by network operators becomes a technical hotspot and difficulty. Scene perception is the basis for providing intelligent context-aware services for users, especially location-based services and real-time location services, and the adjustment of networks through indoor/outdoor multiple scene classification to enhance the context type of user services is a fundamental problem for various intelligent services.
The mainstream satellite positioning technology, while substantially meeting the criteria for outdoor positioning, does not perform well in a flow-dense urban canyon environment. Due to the signal strength, satellite signals are likely to be interfered by shielding or dense traffic of buildings, so that satellite re-searching is very time-consuming, and therefore, the requirement of E911 (an operator providing emergency rescue service for users) on outdoor positioning delay cannot be met by simply positioning by means of a global satellite positioning system. In order to shorten the time delay, 3GPP incorporates a positioning mechanism based on radio frequency fingerprinting into LTE architecture.
Currently, wireless network testing has been turned to a user active reporting mode to replace traditional drive test which has the disadvantages of large consumption of manpower and material resources, large investment of funds, long test period and the like. 3GPP release 10 introduces an automated drive test technique in LTE, namely minimization of drive test (Minimization of Drive Test, MDT). User measurement reports (Measurement Reports, MRs) collected by the MDT method achieve cost effectiveness for the operator. Because the data collected by the MDT through the terminal is automatically reported by a user, the indoor and outdoor measurement reports are mixed in the database, and therefore the positioning performance is affected. In some cases, the mobile device that enters the room from outdoors, as well as the indoor device near the window or exit, still retains GPS information while outdoors. These data samples collected as fingerprints cannot represent the true position of the device, so that the use of cellular data for indoor and outdoor scene recognition is of great significance for reducing positioning errors by denoising the fingerprint library and contextualized network operation.
Disclosure of Invention
The purpose of the invention is that: scene sensing and positioning are carried out aiming at the operation of the cellular network, fingerprints are preprocessed before the positioning of the radio frequency fingerprints, and the influence of interference fingerprints on the positioning performance is eliminated.
In order to achieve the above purpose, the technical scheme of the invention is to provide a cellular network wireless sensing and positioning integrated method based on machine learning, which is characterized by comprising the following steps:
step 2, preprocessing the MRs acquired in the step 1, classifying the MRs by using a trained machine learning model, wherein I represents an indoor fingerprint, O represents an outdoor fingerprint, deleting and filtering indoor MRs samples deviating from the actual position according to labels output by the machine learning model, filtering the indoor fingerprints, and establishing a fingerprint library;
step 3, sending a positioning request, checking the validity of data in the positioning request, and deleting repeated data;
and 4, filtering fingerprints farther from the user from a fingerprint library according to the number of neighbor cells by using a data screening mechanism:
when the location request has only 1 neighbor: firstly, trying to find MRs with neighbor cells also being 1 in a fingerprint library, and then strictly requiring that the MR and the service cell ID of a positioning request are respectively identical to the first neighbor cell ID; if the MR with the number of the adjacent cells being 1 cannot be found in the fingerprint library, the reference signal receiving power of the second adjacent cell requiring the alternative MR on the basis of the same cell ID is required to be 20dB smaller than that of the serving cell;
when the positioning request has 2 neighbor cells, the MR is selected as long as the service cell ID or the first neighbor cell ID of the MR is the same as the service cell ID or the first neighbor cell ID of the positioning request;
when the positioning request does not have a neighbor cell, if MRs without the neighbor cell exist in the fingerprint library, the serving cell ID is only required to be the same as that of the positioning request;
and 7, obtaining a predicted position by using the similarity as a weight coefficient in the WKNN algorithm.
Preferably, in step 2, when training the random forest, feature engineering is established by combining the characteristics of electric wave propagation, and corresponding variables are selected as features to train the random forest.
Preferably, in step 2, the selected variables include reference signal received powers and reference signal received qualities of the serving cell and the neighbor cells, a difference between the reference signal received powers estimated by the standardized channel model and the reference signal received power actual measurement value, and a difference between the reference signal received powers and reference signal received qualities of the serving cell and the strongest neighbor cells.
Preferably, in step 2, the difference between the reference signal received power estimated by the standardized channel model and the reference signal received power measured value is Δrsrp, and then there is:
ΔRSRP＝RSTP-(46.3+33.9log(f)+44.9log(78T a )+C-RSRP
wherein: RSTP represents the reference signal received power RSRP of the normalized channel model estimate; f. c represents the carrier frequency and the correct coefficient, respectively; t (T) a Representing the time advance; RSRP represents the measured value of the reference signal received power.
Preferably, in step 2, the machine learning model is a decision tree, a support vector machine, a random forest or a K-nearest neighbor.
Preferably, in step 3, if there is repeated data, the data with the strongest signal is reserved, and the remaining data is deleted.
Preferably, in step 5, the similarity of the nth MR is denoted as d (n), and then there is:
wherein: f (f) i And g i (n) represents the RSRP of the current positioning request and the nth MR in the ith cell, respectively; l (L) min A signal level value representing a miss for penalizing a cell that does not match in the positioning request; m is the sum of i and j;
traversing all cells in the REQ, taking the cells of the positioning request as a reference when comparing the positioning request with the alternative MRs, and generating sigma if the cells in the positioning request are not in the MR j (f j -l min ) 2 Otherwise, the method has no influence; when there are 2 neighbors in the positioning request, d (n) and the corresponding l are set min When the positioning request has only 1 neighbor cell or no neighbor cell, the Sigma is not considered j (f j -l min ) 2 。
Preferably, in step 6, calculating the distance of the positioning request to the serving cell comprises the steps of:
step 601, finding the longitude and latitude of a service cell of a positioning request in a cell database, and calculating the distance between the service cell and an MR;
step 602, estimating the actual distance from the user to the serving cell according to the TA of the positioning request, wherein 1TA represents 78m;
step 603, comparing the two distance values obtained in step 601 and step 602, and if the distances are consistent within a certain range, not changing the similarity; and if the two images are inconsistent, adjusting the similarity.
Preferably, in step 7, K adjacent MRs are selected to estimate the final position EstPos according to the WKNN algorithm, and then:
wherein: p (n) is the position of the nth MR;
d (n) is the similarity of the nth MR to the positioning request.
The invention fully utilizes the user measurement report collected from the cellular network, and the proposed wireless sensing and positioning integrated method is more in line with the trend of the wireless network test to the user active report mode, solves the problem that indoor and outdoor MRs in a fingerprint database are mixed together, effectively classifies fingerprints based on integrated learning, and eliminates the interference of indoor fingerprints on outdoor positioning. On the one hand, the obtained positioning result far exceeds the standards of the United states federal communications commission, and further improvement of positioning accuracy by fingerprint denoising is proved to be feasible. On the other hand, the scene perception is increased before positioning, the computational complexity is not obviously increased, and the time delay can be effectively reduced when more data are processed.
Compared with the traditional radio frequency fingerprint positioning, the method for integrating the perception and positioning has smaller positioning error and can provide further personalized services based on a refined situation. Moreover, the results are analyzed through evaluation experiments, so that the invention is more convincing and universal. The invention is suitable for MDT for automatically uploading mass data by users, so that the invention can be easily expanded to finer and dynamic scene sensing and positioning tasks in future intelligent environments.
Drawings
FIG. 1 is a flow chart of the method of the present invention, wherein "I" represents an indoor fingerprint and "O" represents an outdoor fingerprint;
FIGS. 2 (a) and 2 (b) are schematic diagrams of measurement activities of the method of the present invention, wherein FIG. 2 (a) is a measurement device and main index, and FIG. 2 (b) is an example measurement location and RSRP distribution;
FIG. 3 is a schematic diagram of the positioning of the method of the present invention;
fig. 4 (a) and fig. 4 (b) are graphs of results obtained by the method according to the embodiment of the present invention, where fig. 4 (a) is an IO classification effect, and fig. 4 (b) is a comparison of positioning accuracy before and after scene classification.
Detailed Description
The invention will be further illustrated with reference to specific examples. It is to be understood that these examples are illustrative of the present invention and are not intended to limit the scope of the present invention. Further, it is understood that various changes and modifications may be made by those skilled in the art after reading the teachings of the present invention, and such equivalents are intended to fall within the scope of the claims appended hereto.
The invention utilizes the user measurement report collected from the actual urban scene to perform characteristic engineering according to the radio propagation rule, realizes indoor/outdoor classification to sense the mobile scene and filter the positioning fingerprint, and further utilizes the combination of Enhanced Cell ID (ECID) based on machine learning and the MRs method to perform cellular network positioning and effectively improve the positioning precision.
The cellular network wireless sensing and positioning integrated method based on machine learning disclosed by the embodiment comprises the following steps:
1) And (5) data acquisition.
56232 fingerprint records are collected from a typical urban scene covering a commercial cellular network, the test scene comprises most of outdoor main roads in the urban scene and 7 different indoor scenes, a schematic diagram of measurement activities is shown in fig. 2, and at most information from one service cell and six adjacent cells can be monitored in the MR collected at each sampling point. In the actual drive test process of simulating MDT, a tester holds a smart phone for installing a TEMS application program in a hand, continuously collects MRs by applying data services in an LTE network and imports the MRs on a server.
The collected MRs include cell identities of the serving cell and its six neighbors and corresponding reference signal received powers (Reference Signal Received Power, RSRP) and reference signal received qualities (Reference Signal Received Quality, RSPQ).
2) Scene perception.
And (3) establishing a characteristic engineering by combining the characteristics of electric wave propagation, selecting 20 variables including RSRP and RSRQ values of a serving cell and adjacent cells thereof, the difference value of the RSRP and the RSRQ of the serving cell and the strongest adjacent cell and the difference value of the channel model estimated and measured RSRP of the serving cell as characteristics to train a random forest, and then classifying the scene of the test set through the trained random forest.
The difference between estimated and measured RSRP is:
ΔRSRP＝RSTP-(46.3+33.9log(f)+44.9log(78T a )+C-RSRP
wherein: RSTP denotes reference signal transmit power; f. c represents the carrier frequency and the correct coefficient, respectively; t (T) a Representing the time advance; RSRP represents the reference signal received power.
The test set is formed by the data outside the bag to accurately estimate the sample, and the classification accuracy can reach 97%.
3) And deleting and filtering the indoor samples based on the classification result of the step 2). And carrying out validity check on the data in the positioning request REQ, deleting the repeated data, if the repeated data is repeated, taking the data with the strongest signal, and filtering fingerprints farther from the user from a fingerprint library according to the number of neighbor cells by utilizing a data screening mechanism.
Specifically, when the positioning request REQ has only 1 neighbor cell (REQ Nb =1), first try to find MRs (MR) whose neighbor is also 1 in the fingerprint library Nb =1), then the serving cell ID and the first neighbor cell ID of MR and REQ are strictly required to be the same, respectively; if no MR with the number of neighbors of 1 is found, the RSRP of the second neighbor requiring the alternative MR on the basis of the same cell ID must be 20dB smaller than its serving cell. When REQ Nb When=2, this fingerprint record is selected as long as the serving cell ID or the first neighbor ID of the MR and the serving cell ID or the first neighbor ID of the REQ are the same. When REQ Nb When=0, ifMR Nb =0, then only its serving cell ID is the same as REQ.
4) After the similar candidate MRs are screened out through the data screening mechanism, similarity calculation is needed to be carried out on the screened data so as to select the fingerprints which are the closest. In this embodiment, the similarity of the nth fingerprint record is denoted as d (n), and the similarity is lower as d (n) increases. The method for calculating the similarity is based on the LMS, and the specific formula is as follows:
wherein: f (f) i And g i (n) represents RSRP of REQ and n-th MR in the i-th cell, respectively; l (L) min A signal level value representing a miss for penalizing a cell that does not match in the REQ; m is the sum of i and j. The similarity calculation process is shown in fig. 3. When traversing all cells in the REQ, it should be noted that the cells in the REQ are used as references when comparing the REQ with the candidate MRs, if the cells in the REQ are not in the MR, a penalty of the second term in the formula will be generated, otherwise, no effect will be generated. Thus, when REQ Nb When=2, d (n) and the corresponding l are set min When REQ Nb With 0 or 1, the second sum of the formulas need not be considered.
5) The similarity is adjusted according to the time advance, which can be converted into the distance from the REQ to the serving cell, 1TA representing 78m. First, find the longitude and latitude of the service cell of REQ in the cell database, calculate its distance with MR. Then, the actual distance to the user to the serving cell is estimated from the TA of the REQ. Comparing the two distance values, and if the distances are consistent within a certain range, not changing the similarity; if not, the similarity is adjusted.
6) And obtaining a predicted position by using the similarity as a weight coefficient in the WKNN algorithm, and representing the predicted position by using the longitude and latitude of the generated ellipse center. According to the WKNN algorithm, K adjacent fingerprints are selected to estimate the final position (Estimated Position, estPos) as shown in the following equation:
wherein: p (n) is the position of the nth fingerprint record;
w (n) is represented by the following formula:
where d (n) is the similarity of the fingerprint records.
7) Positioning accuracy (error) and positioning accuracy (probability) are selected as evaluation indexes of the positioning system.
Positioning accuracy refers to the distance between the predicted position and the actual position, and positioning accuracy refers to the duty cycle of successful positioning in all REGs. The positioning requirements of the FCC for mobile operators to determine the location of a user are: the probability of the positioning accuracy being within 100m cannot be lower than 67%, and the probability of the positioning accuracy being within 300m cannot be lower than 90%.
TABLE 1 comparison of positioning errors at different positioning probabilities
As can be seen from table 1, with the probability kept unchanged, the overall positioning error can be reduced by filtering the positioning fingerprint with the IO classifier or improving the position accuracy. Wherein the positioning error after denoising is reduced by about 4% when the probability is 67%, and by about 2% when the probabilities are 80% and 90%.
8) To better demonstrate the effectiveness of the present invention, the present invention compares it to popular machine learning algorithms for other IO classifications, and the results indicate that SVM performs poorly because it is more suited to sparse and small sample data. In addition, the improved WKNN-based method proposed by the present invention may significantly improve positioning accuracy compared to WKNN.
Claims (9)
1. The cellular network wireless sensing and positioning integrated method based on machine learning is characterized by comprising the following steps of:
step 1, acquiring indoor and outdoor information data, and collecting fingerprint records from a scene covering a commercial cellular network, wherein the fingerprint records comprise longitude and latitude, reference signal receiving power and reference signal receiving quality of a service cell and a neighboring cell, one fingerprint record is expressed as MR, and a plurality of fingerprint records are expressed by MRs;
step 2, preprocessing the MRs acquired in the step 1, classifying the MRs by using a trained machine learning model, wherein I represents an indoor fingerprint, O represents an outdoor fingerprint, deleting and filtering indoor MRs samples deviating from the actual position according to labels output by the machine learning model, filtering the indoor fingerprints, and establishing a fingerprint library;
step 3, sending a positioning request, checking the validity of data in the positioning request, and deleting repeated data;
and 4, filtering fingerprints farther from the user from a fingerprint library according to the number of neighbor cells by using a data screening mechanism:
when the location request has only 1 neighbor: firstly, trying to find MRs with neighbor cells also being 1 in a fingerprint library, and then strictly requiring that the MR and the service cell ID of a positioning request are respectively identical to the first neighbor cell ID; if the MR with the number of the adjacent cells being 1 cannot be found in the fingerprint library, the reference signal receiving power of the second adjacent cell requiring the alternative MR on the basis of the same cell ID is required to be 20dB smaller than that of the serving cell;
when the positioning request has 2 neighbor cells, the MR is selected as long as the service cell ID or the first neighbor cell ID of the MR is the same as the service cell ID or the first neighbor cell ID of the positioning request;
when the positioning request does not have a neighbor cell, if MRs without the neighbor cell exist in the fingerprint library, the serving cell ID is only required to be the same as that of the positioning request;
step 5, after similar alternative MRs are screened out through a data screening mechanism, similarity calculation is carried out on the screened data and the positioning request so as to select the most similar MR;
step 6, adjusting the similarity obtained in the step 5 according to the time advance, wherein the time advance can be converted into the distance from the positioning request to the service cell;
and 7, obtaining a predicted position by using the similarity as a weight coefficient in the WKNN algorithm.
2. The machine learning-based cellular network wireless sensing and positioning integrated method according to claim 1, wherein in the step 2, when training the random forest, feature engineering is established by combining the characteristics of electric wave propagation, and the corresponding variable is selected as the feature to train the random forest.
3. The integrated wireless sensing and positioning method of cellular network according to claim 1, wherein in step 2, the selected variables include reference signal received power and reference signal received quality of the serving cell and the neighboring cell, a difference between the reference signal received power estimated by the standardized channel model and the reference signal received power actual measurement value, and a difference between the reference signal received power and reference signal received quality of the serving cell and the strongest neighboring cell.
4. A machine learning based cellular network wireless sensing and positioning integrated method as set forth in claim 3, wherein in step 2, the difference between the reference signal received power estimated by the standardized channel model and the reference signal received power actual measurement value is Δrsrp, and then:
ΔRSRP＝RSTP-(46.3+33.9log(f)+44.9log(78T a )+C-RSRP
wherein: RSTP represents the reference signal received power RSRP of the normalized channel model estimate; f. c represents the carrier frequency and the correct coefficient, respectively; t (T) a Representing the time advance; RSRP represents the measured value of the reference signal received power.
5. The method for integrating wireless sensing and positioning of a cellular network based on machine learning according to claim 1, wherein in the step 2, the machine learning model is a decision tree, a support vector machine, a random forest or a K nearest neighbor.
6. The integrated wireless sensing and positioning method of cellular network based on machine learning as claimed in claim 1, wherein in step 3, if there is repeated data, the strongest data of the signal is reserved, and the remaining data is deleted.
7. The integrated machine learning based cellular network wireless sensing and positioning method of claim 1, wherein in step 5, the similarity of the nth MR is denoted as d (n), and then there are:
wherein: f (f) i And g i (n) represents the RSRP of the current positioning request and the nth MR in the ith cell, respectively; l (L) min A signal level value representing a miss for penalizing a cell that does not match in the positioning request; m is the sum of i and j;
traversing all cells in the REQ, taking the cells of the positioning request as a reference when comparing the positioning request with the alternative MRs, and generating sigma if the cells in the positioning request are not in the MR j (f j -l min ) 2 Otherwise, the method has no influence; when there are 2 neighbors in the positioning request, d (n) and the corresponding l are set min When the positioning request has only 1 neighbor cell or no neighbor cell, the Sigma is not considered j (f j -l min ) 2 。
8. The machine learning based cellular network wireless sensing and positioning integrated method of claim 1, wherein in step 6, calculating the distance of the positioning request to the serving cell comprises the steps of:
step 601, finding the longitude and latitude of a service cell of a positioning request in a cell database, and calculating the distance between the service cell and an MR;
step 602, estimating the actual distance from the user to the serving cell according to the TA of the positioning request, wherein 1TA represents 78m;
step 603, comparing the two distance values obtained in step 601 and step 602, and if the distances are consistent within a certain range, not changing the similarity; and if the two images are inconsistent, adjusting the similarity.
9. The machine learning based cellular network wireless sensing and positioning integrated method of claim 1, wherein in step 7, K adjacent MRs are selected to estimate the final position EstPos according to the WKNN algorithm, and then:
wherein: p (n) is the position of the nth MR;
d (n) is the similarity of the nth MR to the positioning request. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310007214.0A CN116056140A (en) | 2023-01-04 | 2023-01-04 | Cellular network wireless sensing and positioning integrated method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310007214.0A CN116056140A (en) | 2023-01-04 | 2023-01-04 | Cellular network wireless sensing and positioning integrated method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116056140A true CN116056140A (en) | 2023-05-02 |
Family
ID=86130798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310007214.0A Pending CN116056140A (en) | 2023-01-04 | 2023-01-04 | Cellular network wireless sensing and positioning integrated method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116056140A (en) |
-
2023
- 2023-01-04 CN CN202310007214.0A patent/CN116056140A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102480677B (en) | A kind of determination method and apparatus of fingerprint positioning error | |
| CN109640269B (en) | Fingerprint positioning method based on CSI and time domain fusion algorithm | |
| CN108307427B (en) | LTE network coverage analysis and prediction method and system | |
| CN112867147B (en) | Positioning method and positioning device | |
| CN109151839A (en) | A kind of network plan method of LPWA network | |
| Zhang et al. | Machine learning-based integrated wireless sensing and positioning for cellular network | |
| CN105916202A (en) | Probabilistic WiFi indoor positioning fingerprint database construction method | |
| CN108064075A (en) | The method and apparatus of the reference signal transmission power of the one or more cells of adjustment | |
| Bejarano-Luque et al. | A data-driven algorithm for indoor/outdoor detection based on connection traces in a LTE network | |
| Nekrasov et al. | Evaluating LTE coverage and quality from an unmanned aircraft system | |
| WO2023026024A2 (en) | Methods and apparatus for determining above ground coverage of a mobile telecommunications network | |
| CN109889975B (en) | Terminal fingerprint positioning method based on NB-IoT | |
| Ramamurthy et al. | Ml-based classification of device environment using wi-fi and cellular signal measurements | |
| Fang et al. | An accurate and real-time commercial indoor localization system in LTE networks | |
| CN108574927B (en) | Mobile terminal positioning method and device | |
| Wang et al. | Mobile device localization in 5G wireless networks | |
| Zheng et al. | RSS-based indoor passive localization using clustering and filtering in a LTE network | |
| Alves et al. | A novel approach for user equipment indoor/outdoor classification in mobile networks | |
| Huang et al. | Experimental study of telco localization methods | |
| Ma et al. | RSRP difference elimination and motion state classification for fingerprint-based cellular network positioning system | |
| Al Saadi et al. | Ground Level Mobile Signal Prediction Using Higher Altitude UAV Measurements and ANN | |
| CN116056140A (en) | Cellular network wireless sensing and positioning integrated method based on machine learning | |
| Waheed et al. | DeepChannel: Robust Multimodal Outdoor Channel Model Prediction in LTE Networks Using Deep Learning | |
| US20230403575A1 (en) | Cell Similarity Indicator Based on Coverage Area Morphology | |
| CN112839353B (en) | Method and device for identifying interference in LTE (Long term evolution) system |
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 |