CN116527462A - Wireless positioning method based on channel state change CSI value - Google Patents
Wireless positioning method based on channel state change CSI value Download PDFInfo
- Publication number
- CN116527462A CN116527462A CN202310604282.5A CN202310604282A CN116527462A CN 116527462 A CN116527462 A CN 116527462A CN 202310604282 A CN202310604282 A CN 202310604282A CN 116527462 A CN116527462 A CN 116527462A
- Authority
- CN
- China
- Prior art keywords
- csi
- data
- feature
- information
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000008859 change Effects 0.000 title claims abstract description 14
- 238000012360 testing method Methods 0.000 claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000000605 extraction Methods 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000005562 fading Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B7/00—Radio transmission systems, i.e. using radiation field
- H04B7/02—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas
- H04B7/04—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas
- H04B7/06—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station
- H04B7/0613—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission
- H04B7/0615—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal
- H04B7/0619—Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas using two or more spaced independent antennas at the transmitting station using simultaneous transmission of weighted versions of same signal using feedback from receiving side
- H04B7/0621—Feedback content
- H04B7/0626—Channel coefficients, e.g. channel state information [CSI]
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L25/00—Baseband systems
- H04L25/02—Details ; arrangements for supplying electrical power along data transmission lines
- H04L25/03—Shaping networks in transmitter or receiver, e.g. adaptive shaping networks
- H04L25/03006—Arrangements for removing intersymbol interference
- H04L2025/03433—Arrangements for removing intersymbol interference characterised by equaliser structure
-
- 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)
- Power Engineering (AREA)
- Mobile Radio Communication Systems (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a wireless positioning method based on channel state change CSI value, which belongs to the field of wireless positioning, and starts with CSI data collected by a test point after channel state change, eliminates errors in CSI data information collected after channel state change through the equalization capability of a channel equalization network, wherein the equalization capability of the channel equalization network is obtained through algorithm model training, and combines and enhances the data originally collected by the test point and the data collected by the test point after equalization of the channel equalization network to extract more abundant characteristic information. The invention has important application value in the aspects of intelligent building, constructor management and the like.
Description
Technical Field
The invention relates to the field of radio positioning, in particular to a wireless positioning method based on channel variation CSI value.
Background
With the rapid development of communication technology, a 5G mobile communication network has been widely used and implemented for large-scale deployment, and a wireless positioning technology is one of key technologies of location services, and has very important significance in environments with complex and changeable channel environments such as indoor and mine, and common positioning methods have two kinds: one is a ranging method based on signal strength and distance of shadow fading model; the other is a positioning method based on signal fingerprints, and the position information of the positioning point is represented by the signal fingerprints at the position of the positioning point. The common method is to locate by a second signal fingerprint method, and to extract the CSI value in the signal and convert the CSI value into fingerprint information, compared with a ranging method based on RSSI (received signal strength indication), the method can avoid multipath fading effect caused by complex environment conditions, and meanwhile, the extracted CSI value in different positions has better discrimination, and compared with a method for locating by adopting fingerprint features based on the CSI value, the method has obvious advantages. Although the interference of multipath fading can be avoided to a certain extent, under the conditions of indoor, mine and the like, the channel environment is complex, the characteristics of the channel are in dynamic balance along with the interference of environmental factors such as temperature, humidity and the like, the CSI value extracted from the signal is also changed at any time, the fingerprints extracted from the CSI value collected from the point to be detected are distorted to a certain extent, and the difficulty is increased in the stage of online fingerprint classification and matching.
The invention provides a wireless positioning method based on a CSI value under the condition of channel state change, which starts from the CSI data collected by a test point after the channel state is changed, balances the channel state by utilizing the equalization capability of a channel equalization network, balances the CSI data collected by the test point by utilizing the channel equalization network, enhances the characteristic data by utilizing the balanced CSI data and the CSI information collected by the test point, eliminates the influence of the CSI data distortion caused by the channel state change and enriches the characteristic data information, thereby effectively improving the positioning accuracy.
Disclosure of Invention
The invention aims to solve the problem that the traditional wireless positioning method based on the CSI information does not consider the data distortion caused by the channel state change between the constructed fingerprint database and the CSI data acquired by the test points, and the problem can cause the reduction of the final positioning efficiency. According to the above-mentioned problems, the present invention provides a wireless positioning method based on a CSI value of a channel state change.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows: a wireless positioning method based on channel state change CSI value, comprising the steps of:
step 1: dividing the positioning area into grids, and collecting CSI information data for data collecting points at the center of each grid, wherein the number of CSI data information transmitting antennas is set as A, the number of receiving antennas is set as B, the number of subcarriers is set as m, and the CSI data format is { CSI } 1 ,CSI 2 ,…,CSI m } A×B ；
Step 2: selecting a pretrained Resnet50 as a feature extraction network to obtain fingerprint feature data in each positioning grid area, recording coordinate information at corresponding positions, and establishing a fingerprint database corresponding to the position coordinates and the fingerprint features one by one;
step 3: selecting n reference positions in a positioning area subjected to grid division, wherein the value of n is smaller than or equal to the number of blocks of a grid, and respectively acquiring channel state information (CSI, { CSI) at each reference position 1 ,CSI 2 ,…,CSI n } A×B And obtaining the CSI data information at the reference point position.
Step 4: selecting a fully connected network as a channel equalization network model Equali_net, inputting CSI information acquired by a set reference point as a network model, taking data in a fingerprint database as a label, performing supervised fitting training on the channel equalization network model, training the channel equalization capacity of the network, fixing network node parameters after training is completed, and obtaining the channel equalization network model with channel state restoration;
step 5: collecting CSI data at a test point, inputting the collected CSI data of the test point into the channel equalization network model obtained in the step 4, and outputting the CSI data of the test point after channel state restoration;
step 6: performing feature extraction on the CSI data acquired by the test points through a Resnet50 feature extraction network to obtain a high-dimensional data feature_1, inputting the CSI data subjected to channel equalization by a channel equalization network into an attention mechanism to obtain feature weights, and multiplying the feature weights with the feature_1 to obtain weighted data feature; important characteristic data in the test point data characteristics can be focused through the weighted data characteristics.
Step 7: calculating weighted feature obtained by test points and fingerprint feature at different positions in fingerprint database i The euclidean distance between the two,and selecting the position coordinate corresponding to the fingerprint with the largest spatial distance as the predicted position to output.
Further, the specific process in step 6 includes:
s1: for the input CSI data sequence { a } 1 ,a 2 ,…,a n Coding the symbols by multiplying each symbol by a matrix, alpha 1 ＝a 1 W, initializing two matrices W q ,W k Calculate q 1 ＝α 1 ·W q ，k 1 ＝α 1 ·W k Obtaining q and k values corresponding to each symbol, calculating the weight score of each q value to the rest k values,
wherein, the calculation formula is thatWhere d is the data dimension of q and k, score is the calculated score;
s2: the CSI data obtained from the test point is subjected to the same coding operation to obtain alpha 1,test Initializing a matrix W k Calculate k=α 1,test ·W k ，
S3: multiplying the weight score calculated in the restored CSI data information by the k value obtained by the CSI information originally acquired by the acquisition point, and obtaining the CSI weight,i ＝score i ·k i And obtaining weighted data information, inputting the information into a feature extraction network to obtain weighted feature output feature, wherein the related matrix concrete value is optimized through training to obtain an optimal value.
The invention has the beneficial effects that:
the invention starts from the channel state change process which is not concerned, the phenomenon of data distortion can be generated between the CSI data collected when the fingerprint database is built and the CSI data collected by the corresponding test points due to the time-varying property of the channel state. The CSI value at the point to be measured is restored, the influence of the distortion of the CSI data value caused by the change of the channel state characteristics can be reduced, the extraction of data which is closer to the data in the fingerprint library established in the off-line stage is facilitated, the accuracy of the classification in the on-line stage is improved, meanwhile, the weighted feature extraction is carried out through the CSI value acquired at the point to be measured and the CSI value restored through the channel equalization network, the CSI data feature acquired at the point to be measured can be extracted in a targeted mode according to the weight information trained in the restored CSI feature information, the data validity of the fingerprint feature is effectively improved, the difficulty of classification matching is reduced, and the positioning accuracy is effectively improved.
Drawings
FIG. 1 is a system workflow diagram of the present invention;
FIG. 2 is a schematic diagram of a positioning area information acquisition according to the present invention;
FIG. 3 is a schematic diagram of information acquisition after the channel of the positioning area is changed;
FIG. 4 is a workflow diagram of one embodiment of the present invention;
FIG. 5 is a graph showing the effect of the presence or absence of the reference points on the classification results according to one embodiment of the present invention.
Detailed Description
The invention is further described in connection with the following detailed description, in order to make the technical means, the creation characteristics, the achievement of the purpose and the effect of the invention easy to understand.
Referring to fig. 1 to 5, an embodiment of the present invention includes:
as shown in fig. 1-4, a wireless positioning method based on channel state change CSI value is based on the following system steps:
step 1: dividing the positioning area into grids, and collecting CSI information data for data collecting points at the center of each grid, wherein the number of CSI data information transmitting antennas is set as A, the number of receiving antennas is set as B, the number of subcarriers is set as m, and the CSI data format is { CSI } 1 ,CSI 2 ,…,CSI m } A×B ；
Step 2: selecting a pretrained Resnet50 as a feature extraction network to obtain fingerprint feature data in each positioning grid area, recording coordinate information at corresponding positions, and establishing a fingerprint database corresponding to the position coordinates and the fingerprint features one by one;
step 3: selecting n reference positions in a positioning area subjected to grid division, wherein the value of n is smaller than or equal to the number of blocks of a grid, and respectively acquiring channel state information (CSI, { CSI) at each reference position 1 ,CSI 2 ,…,CSI n } A×B And obtaining the CSI data information at the reference point position.
Step 4: selecting a fully connected network as a channel equalization network model Equali_net, inputting CSI information acquired by a set reference point as a network model, taking data in a fingerprint database as a label, performing supervised fitting training on the channel equalization network model, training the channel equalization capacity of the network, fixing network node parameters after training is completed, and obtaining the channel equalization network model with channel state restoration;
step 5: collecting CSI data at a test point, inputting the collected CSI data of the test point into the channel equalization network model obtained in the step 4, and outputting the CSI data of the test point after channel state restoration;
step 6: performing feature extraction on the CSI data acquired by the test points through a Resnet50 feature extraction network to obtain a high-dimensional data feature_1, inputting the CSI data subjected to channel equalization by a channel equalization network into an attention mechanism to obtain feature weights, and multiplying the feature weights with the feature_1 to obtain weighted data feature; important characteristic data in the test point data characteristics can be focused through the weighted data characteristics.
The specific process comprises the following steps: for the input CSI data sequence { a } 1 ,a 2 ,…,a n Coding the symbols by multiplying each symbol by a matrix, alpha 1 ＝a 1 W, initializing two matrices W q ,W k Calculate q 1 ＝α 1 ·W q ，k 1 ＝α 1 ·W k Obtaining q and k values corresponding to each symbol, calculating the weight fraction of each q value to the rest k values, wherein the calculation formula is thatWhere d is the data dimension of q and k, score is the calculated score; the CSI data obtained from the test point is subjected to the same coding operation to obtain alpha 1,test Initializing a matrix W k Calculate k=α 1,test ·W k Multiplying the weight score calculated in the restored CSI data information by the k value obtained by the CSI information originally acquired by the acquisition point, and obtaining the CSI weight,i ＝score i ·k i And obtaining weighted data information, inputting the information into a feature extraction network to obtain weighted feature output feature, wherein the related matrix concrete value is optimized through training to obtain an optimal value.
Step 7: calculating weighted feature obtained by test points and fingerprint feature at different positions in fingerprint database i The euclidean distance between the two,and selecting the position coordinate corresponding to the fingerprint with the largest spatial distance as the predicted position to output.
In fig. 5, whether reference points are set or not is shown to collect data, and the influence of reduction processing on classification results is performed. The upper graph abscissa is a training batch of the deep learning network, the ordinate represents the accuracy of network classification, and it can be seen from the graph that after the channel state changes, the effect of the traditional positioning algorithm without a new reference point is inferior to that of the classification method with a new reference point, and it is proved that after the channel equalization processing is performed by using the set reference point as training data of the channel equalization network model, the influence factors of the channel state changes can be reduced. Therefore, after the channel state changes, the CSI positioning method of the newly added reference point obviously leads to the improvement of positioning precision.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The present embodiments are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present disclosure describes embodiments, not every embodiment is provided with a separate embodiment, and that this description is provided for clarity only, and that the disclosure is not limited to the embodiments described in detail below, and that the embodiments described in the examples may be combined as appropriate to form other embodiments that will be apparent to those skilled in the art.
Claims (2)
1. The wireless positioning method based on the channel state change CSI value is characterized by comprising the following steps of:
step 1: dividing the positioning area into grids, and collecting CSI information data for data collecting points at the center of each grid, wherein the number of CSI data information transmitting antennas is set as A, the number of receiving antennas is set as B, the number of subcarriers is set as m, and the CSI data format is { CSI } 1 ,CSI 2 ,…,CSI m } A×B ；
Step 2: selecting a pretrained Resnet50 as a feature extraction network to obtain fingerprint feature data in each positioning grid area, recording coordinate information at corresponding positions, and establishing a fingerprint database corresponding to the position coordinates and the fingerprint features one by one;
step 3: selecting n reference positions in a positioning area subjected to grid division, wherein the value of n is smaller than or equal to the number of blocks of a grid, and respectively acquiring channel state information (CSI, { CSI) at each reference position 1 ,CSI 2 ,…,CSI n } A×B Obtaining CSI data information at the reference point position;
step 4: selecting a fully connected network as a channel equalization network model Equali_net, inputting CSI information acquired by a set reference point as a network model, taking data in a fingerprint database as a label, performing supervised fitting training on the channel equalization network model, training the channel equalization capacity of the network, fixing network node parameters after training is completed, and obtaining the channel equalization network model with channel state restoration;
step 5: collecting CSI data at a test point, inputting the collected CSI data of the test point into the channel equalization network model obtained in the step 4, and outputting the CSI data of the test point after channel state restoration;
step 6: performing feature extraction on the CSI data acquired by the test points through a Resnet50 feature extraction network to obtain a high-dimensional data feature_1, inputting the CSI data subjected to channel equalization by a channel equalization network into an attention mechanism to obtain feature weights, and multiplying the feature weights with the feature_1 to obtain weighted data feature; important characteristic data in the test point data characteristics can be focused through the weighted data characteristics;
step 7: calculating test points to obtainWeighted feature of (c) and fingerprint feature at a different location in the fingerprint database i The euclidean distance between the two,and selecting the position coordinate corresponding to the fingerprint with the largest spatial distance as the predicted position to output.
2. The wireless positioning method based on the CSI value according to claim 1, wherein the specific process in step 6 includes:
s1: for the input CSI data sequence { a } 1 ,a 2 ,…,a n Coding the symbols by multiplying each symbol by a matrix, alpha 1 ＝a 1 W, initializing two matrices W q ,W k Calculate q 1 ＝α 1 ·W q ，k 1 ＝α 1 ·W k Obtaining q and k values corresponding to each symbol, calculating the weight score of each q value to the rest k values,
wherein, the calculation formula is thatWhere d is the data dimension of q and k, score is the calculated score;
s2: the CSI data obtained from the test point is subjected to the same coding operation to obtain alpha 1,test Initializing a matrix W k Calculate k=α 1,test ·W k ；
S3: multiplying the weight score calculated in the restored CSI data information by the k value obtained by the CSI information originally acquired by the acquisition point, and obtaining the CSI weight,i ＝score i ·k i And obtaining weighted data information, inputting the information into a feature extraction network to obtain weighted feature output feature, wherein the related matrix concrete value is optimized through training to obtain an optimal value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310604282.5A CN116527462B (en) | 2023-05-25 | 2023-05-25 | Wireless positioning method based on channel state change CSI value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310604282.5A CN116527462B (en) | 2023-05-25 | 2023-05-25 | Wireless positioning method based on channel state change CSI value |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116527462A true CN116527462A (en) | 2023-08-01 |
| CN116527462B CN116527462B (en) | 2024-02-02 |
Family
ID=87395977
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310604282.5A Active CN116527462B (en) | 2023-05-25 | 2023-05-25 | Wireless positioning method based on channel state change CSI value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116527462B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108882151A (en) * | 2018-07-02 | 2018-11-23 | 上海大学 | Indoor orientation method based on CSI information areaization mark |
| CN109640269A (en) * | 2018-12-18 | 2019-04-16 | 上海大学 | Fingerprint positioning method based on CSI Yu Time Domain Fusion algorithm |
| CN110381440A (en) * | 2019-06-16 | 2019-10-25 | 西安电子科技大学 | The fingerprint indoor orientation method of joint RSS and CSI based on deep learning |
| CN110536245A (en) * | 2019-08-28 | 2019-12-03 | 杭州电子科技大学 | A kind of indoor wireless positioning method and system based on deep learning |
| CN110933628A (en) * | 2019-11-26 | 2020-03-27 | 西安电子科技大学 | Fingerprint indoor positioning method based on twin network |
| CN114531729A (en) * | 2022-04-24 | 2022-05-24 | 南昌大学 | Positioning method, system, storage medium and device based on channel state information |
| US20220205808A1 (en) * | 2020-12-25 | 2022-06-30 | Mapsted Corp. | Localization using tessellated grids |
| EP4085664A1 (en) * | 2019-12-30 | 2022-11-09 | Airbus Defence and Space GmbH | System and method for object localization in an indoor environment |
-
2023
- 2023-05-25 CN CN202310604282.5A patent/CN116527462B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108882151A (en) * | 2018-07-02 | 2018-11-23 | 上海大学 | Indoor orientation method based on CSI information areaization mark |
| CN109640269A (en) * | 2018-12-18 | 2019-04-16 | 上海大学 | Fingerprint positioning method based on CSI Yu Time Domain Fusion algorithm |
| CN110381440A (en) * | 2019-06-16 | 2019-10-25 | 西安电子科技大学 | The fingerprint indoor orientation method of joint RSS and CSI based on deep learning |
| CN110536245A (en) * | 2019-08-28 | 2019-12-03 | 杭州电子科技大学 | A kind of indoor wireless positioning method and system based on deep learning |
| CN110933628A (en) * | 2019-11-26 | 2020-03-27 | 西安电子科技大学 | Fingerprint indoor positioning method based on twin network |
| EP4085664A1 (en) * | 2019-12-30 | 2022-11-09 | Airbus Defence and Space GmbH | System and method for object localization in an indoor environment |
| US20220205808A1 (en) * | 2020-12-25 | 2022-06-30 | Mapsted Corp. | Localization using tessellated grids |
| CN114531729A (en) * | 2022-04-24 | 2022-05-24 | 南昌大学 | Positioning method, system, storage medium and device based on channel state information |
Non-Patent Citations (3)
| Title |
|---|
| 刘兆岩;陈立伟;黄璐;: "基于CSI相位矫正的室内指纹定位技术研究", 无线电工程, no. 02, pages 22 - 27 * |
| 李新春;王藜谚;王浩童;: "基于3DCNN的CSI-cluster室内指纹定位算法", 重庆邮电大学学报(自然科学版), no. 03, pages 21 - 31 * |
| 韩卓宜;王延昭;修春娣;: "基于CSI指纹序列匹配的LTE室内定位方法", 无线电工程, no. 08, pages 34 - 37 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116527462B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101794396B (en) | System and method for recognizing remote sensing image target based on migration network learning | |
| CN103096466A (en) | Wireless fidelity (Wi-Fi) indoor positioning method | |
| CN107027148A (en) | A kind of Radio Map classification and orientation methods based on UE speed | |
| CN111585922A (en) | Modulation mode identification method based on convolutional neural network | |
| CN111523667B (en) | RFID positioning method based on neural network | |
| CN113015093B (en) | Indoor wireless positioning method based on three-dimensional depth residual error neural network | |
| CN103945531B (en) | Method for WLAN indoor positioning Radio Map updating based on information entropy | |
| CN106412841A (en) | Indoor location method based on DBSCAN algorithm | |
| CN110062410B (en) | Cell interruption detection positioning method based on self-adaptive resonance theory | |
| CN115659254A (en) | Power quality disturbance analysis method for power distribution network with bimodal feature fusion | |
| CN116527462B (en) | Wireless positioning method based on channel state change CSI value | |
| CN116756633A (en) | Power amplifier fingerprint feature identification method based on supervised contrast learning | |
| CN110972174B (en) | Wireless network interruption detection method based on sparse self-encoder | |
| CN102202018B (en) | Channel estimation method based on support vector machine (SVM) | |
| CN113543026B (en) | Multi-floor indoor positioning method based on radial basis function network | |
| CN112867021B (en) | Improved TrAdaBoost-based indoor positioning method for transfer learning | |
| CN109121081A (en) | A kind of indoor orientation method based on position Candidate Set Yu EM algorithm | |
| CN110880020B (en) | Self-adaptive trans-regional base station energy consumption model migration and compensation method | |
| CN114679683B (en) | Indoor intelligent positioning method based on derived fingerprint migration | |
| CN112348700B (en) | Line capacity prediction method combining SOM clustering and IFOU equation | |
| CN112014821B (en) | Unknown vehicle target identification method based on radar broadband characteristics | |
| CN111612097B (en) | GRU network-based master user number estimation method | |
| CN104378176B (en) | A kind of robust communication signal modulate method | |
| CN109274613B (en) | Channel estimation method, system and storage medium | |
| CN112199452A (en) | Large-scale community network detection method based on random optimization and non-uniform sampling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |