CN111931121A - Distributed positioning and speed measuring method based on large-scale antenna array - Google Patents
Distributed positioning and speed measuring method based on large-scale antenna array Download PDFInfo
- Publication number
- CN111931121A CN111931121A CN202010991979.9A CN202010991979A CN111931121A CN 111931121 A CN111931121 A CN 111931121A CN 202010991979 A CN202010991979 A CN 202010991979A CN 111931121 A CN111931121 A CN 111931121A
- Authority
- CN
- China
- Prior art keywords
- scale antenna
- neural network
- deep neural
- distributed
- antenna array
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Abstract
The invention discloses a distributed positioning and speed measuring method based on a large-scale antenna array, which comprises the following steps: obtaining a deep neural network model through offline deep neural network training; the deep neural network model is utilized to process the multi-path parallel receiving signals of the large-scale antenna array in real time to obtain a Doppler measurement result; gathering Doppler measurement results measured by a plurality of distributed large-scale antenna arrays to a central station; correlating the reported results of all distributed large-scale antenna arrays at a central station; position and velocity resolution is performed using the doppler measurements on the correlations. The invention can solve the problem that the traditional positioning and speed measuring method has overhigh real-time calculation complexity under the system of a large-scale antenna array.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a distributed positioning and speed measuring method based on a large-scale antenna array.
Background
Massive Multiple Input Multiple Output (Massive MIMO) technology is used as one of the core technologies of the fifth Generation (5 th Generation, 5G) and subsequent broadband mobile communication. Compared with the traditional MIMO, the technology adopts a complex three-dimensional space multiplexing technology by using a larger-scale three-dimensional antenna array, greatly improves the multiplexing capability of the air interface time and the spectrum resource of the 5G system, and has higher communication capacity and better service capability.
Speed measurement and positioning are typical applications of a wireless information system, compared with a conventional uniform linear array and a conventional uniform circular array, the large-scale array antenna improves the number of antenna units by one order of magnitude, the receiver can obtain higher signal space resolution capability due to the increase of the number of the antenna units, for example, the receiver can perform resolution of azimuth and elevation three-dimensional spaces, the large-scale antenna array can obtain the spatial resolution capability better than 1 degree in a dense signal space by combining with a spatial spectrum (such as MUSIC, ESPRIT and the like), and on the basis, higher positioning accuracy can be obtained based on azimuth crossing.
Taking ESPRIT as an example: assuming that radiation sources located in the far field emit simultaneouslykThe statistical independence and the same wavelength of the narrowband signals, then:
in the formula:A 1andA 2respectively representing an array manifold for dividing the large-scale antenna array into two sub-arrays which are in a mutually offset relationship;X 1、X 2、N 1、N 2respectively representing incoming wave signal matrixes received by the two sub-arrays and corresponding Gaussian white noise matrixes;Srepresenting a signal vector; phi denotes a phase shift matrix of the incoming wave signal arriving at the two sub-arrays,
；θ k indicating the angle of incidence of each incoming wave signal
。
For the whole array, the received incoming wave signal matrixXCan be expressed as follows:
a covariance matrix of the above equation can be obtained:
and performing characteristic decomposition on the covariance matrix to obtain:
in the formula (I), the compound is shown in the specification,U S is a signal subspace spanned by eigenvectors corresponding to the large eigenvalues;U N is a noise subspace spanned by the eigenvectors corresponding to the small eigenvalues.
With unique non-singular matricesTSo that:
U S can be decomposed into:
therefore, the temperature of the molten metal is controlled,
wherein, in the step (A),
。
solving linear equations
To obtain
The arrival direction can be obtained, and the spatial positioning can be completed based on the intersection of the directions.
In the above positioning process, in order to obtain the azimuth information, the covariance of the received signal needs to be solved, then the eigenvalue decomposition is performed, then the linear equation is solved, and in the process of solving the linear equation, the matrix needs to be inverted. As the number of antenna elements of a large-scale antenna array increases by orders of magnitude, the complexity of the matrix operation increases by a multiple of the square of the orders of magnitude, accordingly. Therefore, the traditional positioning and speed measuring method has the problem of overhigh real-time calculation complexity under the large-scale antenna array system.
Disclosure of Invention
In view of the above problems, the present invention provides a distributed positioning and velocity measuring method based on a large-scale antenna array, so as to solve the problem that the real-time computation complexity is too high in the case of a large-scale antenna array system in the conventional positioning and velocity measuring method.
A distributed positioning and speed measuring method based on a large-scale antenna array comprises the following steps:
obtaining a deep neural network model through offline deep neural network training;
processing multi-path parallel receiving signals of the large-scale antenna array in real time by using a deep neural network model;
gathering Doppler measurement results measured by a plurality of distributed large-scale antenna arrays to a central station;
correlating the reported results of all distributed large-scale antenna arrays at a central station;
position and velocity resolution is performed using the doppler measurements on the correlations.
According to the distributed positioning and speed measuring method based on the large-scale antenna array, the Doppler measurement problem is divided into two stages of off-line training and on-line real-time calculation, the process of complicated calculation is placed in the off-line training stage, and the multi-path parallel receiving signals of the large-scale antenna array are intelligently processed in real time through a deep neural network model of off-line training; then, converging Doppler measurement results measured by a plurality of distributed large-scale antenna arrays to a central station; and finally, the central station correlates the reported results of all the distributed large-scale antenna arrays and performs position and speed calculation by using the correlated Doppler measurement results, so that the real-time calculation process is simpler and quicker, and the problem of overhigh real-time calculation complexity under the large-scale antenna array system is effectively solved.
In addition, the distributed positioning and velocity measurement method based on the large-scale antenna array according to the present invention may further have the following additional technical features:
the method for obtaining the deep neural network model through the offline deep neural network training specifically comprises the following steps:
firstly, constructing a signal training set, wherein the signal training set comprises input data matrixes and output results, each output result contained in the signal training set is an accurate output result of a corresponding input data matrix after passing through a deep neural network model, and each input data matrix isN×MA matrix of dimensions is formed by a matrix of dimensions,Nrepresenting the number of radio frequency links for a large-scale antenna array,Mthe number of signal sampling points of one training is represented, each output result is data with 1 x 1 dimension and represents Doppler frequency offset, an input data matrix corresponds to one output result, each row of input data corresponds to a radio frequency link of the large-scale antenna array and is correspondingly input to one input node, namely, the 1 st row is input to the 1 st input node, the 2 nd row is input to the 2 nd input node, and the like;
then, grouping the signal training set, sequentially and sequentially compiling two input nodes into a group, inputting the group into a preprocessing unit, and preprocessing the group;
then, the training set of signals is preprocessed, each preprocessing unit corresponds to two paths of signals inputted to the preprocessing unitFirst, time delayDA number of sample points, wherein,Dif the signal is a non-negative number, the other signal is straight-through, the straight-through signal and the delay signal are multiplied, and the average value of multiplication results is calculated;
finally, deep neural network training is carried out, and each input data matrix passes throughNAfter being processed by 2 pretreatment units, the obtained productNAnd inputting the 2 preprocessing results into the deep neural network to obtain a current output result of the deep neural network, calculating the performance of the deep neural network by using the current output result of the deep neural network and an output result corresponding to the input data matrix, selecting a mean square error as a performance function, and continuously training until the performance of the deep neural network reaches a preset threshold to obtain a deep neural network model.
The method for processing the multi-path parallel receiving signals of the large-scale antenna array in real time by using the deep neural network model specifically comprises the following steps:
in thatKA plurality of distributed large-scale antenna arrays,Kand grouping and preprocessing the measured data to be a positive integer, sending the data to a trained deep neural network model, obtaining a distributed measurement value of the Doppler frequency offset in real time, and recording the measurement time and signal characteristic information.
The step of converging the doppler measurement results measured by the plurality of distributed large-scale antenna arrays to the central station specifically includes:
and reporting the measured Doppler frequency offset and the correspondingly recorded measurement time and signal characteristic information to a central station through a wired network or a wireless network.
In the step of associating the reported results of the distributed large-scale antenna arrays by the central station, the association conditions are as follows: the time deviation of the measurement time is less than a preset threshold, and the normalized deviation of the signal characteristics is less than the preset threshold.
When the central station correlates the reported results of each distributed large-scale antenna array, if the record of the signal characteristics is lacked, the correlation is only carried out according to the measurement time.
Wherein, in the step of calculating the position and the speed by using the associated Doppler measurement result, the following calculation equation is adopted for calculation:
wherein the content of the first and second substances,cwhich represents the speed of propagation of the light,f c which is indicative of the center frequency of the signal,
the position of the object is indicated and,
is shown askThe location of the individual distributed large-scale antenna arrays,
which represents the speed of movement of the object,t m which represents the time of the measurement,fd m,k is shown askA large-scale antenna arrayt m The measured doppler frequency offset.
Specifically, in a predefined time window, the Doppler measurement results associated with the K distributed large-scale antenna arrays are brought into a calculation equation, and the solution of the calculation equation is solved by adopting an interior point method or a Newton method or a gradient descent method to obtain the position of the target
And speed of movement
。
Drawings
The above and/or additional aspects and advantages of embodiments of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a schematic flowchart of a distributed positioning and velocity measurement method based on a large-scale antenna array according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating a distributed positioning and velocity measurement method based on a large-scale antenna array according to an embodiment of the present invention;
fig. 3 is a schematic diagram of the operation performed on each preprocessing unit.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1 and fig. 2, a distributed positioning and velocity measurement method based on a large-scale antenna array according to an embodiment of the present invention includes steps S101 to S105.
And S101, obtaining a deep neural network model through offline deep neural network training.
In this embodiment, step S101 specifically includes the following steps:
the first step is as follows: the large-scale antenna array hasNNumber of radio frequency links is =32, when a test set is constructed, 100 different relative motion speeds are set for the aerial unmanned aerial vehicle and the large-scale antenna array, and each radio frequency link continuously samplesMAnd =1024 points, recording 100 groups of 32 × 1024 input data matrices, calculating 100 corresponding doppler frequency offsets according to the set relative motion speed to form 100 output results, forming a training set by the 100 groups of 32 × 1024 input data matrices and the 100 output results, and correspondingly inputting each row of input data to one input node.
The second step is that: two input nodes in sequence are organized into a group and input into a preprocessing unit for preprocessing.
The third step: the operation process of each preprocessing unit is shown in FIG. 3. first, one of the two signals input to the preprocessing unit is delayedDA number of sample points, wherein,D=0, i.e. samplingThe point does not carry out delay operation and directly enters a multiplication unit; the other path of signals is straight-through; then, multiplying the DC signal and the delay signal; finally, the average of 100 sets of multiplication results is found.
The fourth step: inputting 16 results obtained by preprocessing input data matrixes in a test set by 16 preprocessing units into a deep neural network, selecting a mean square error for a performance function of the deep neural network, inputting each input data matrix into a deep neural network model to obtain an output result, calculating the mean square error between the output result and a corresponding output result contained in a training set, continuously iterating and training by adopting a reverse error propagation and gradient descent algorithm until the mean square error of the output result of the deep neural network is lower than a preset threshold, finishing training, and obtaining the deep neural network model after finishing training.
And S102, carrying out real-time processing on the multi-channel parallel receiving signals of the large-scale antenna array by using the deep neural network model to obtain a Doppler measurement result.
In this embodiment, in 3 distributed large-scale antenna arrays, data received by 32 radio frequency links is processed in the second step and the third step in step S101, and then is sent to the deep neural network model after the training in the fourth step, so as to obtain a doppler frequency offset measurement value corresponding to measured data, and record measurement time and a center frequency of a signal.
And S103, converging Doppler measurement results measured by the plurality of distributed large-scale antenna arrays to a central station.
In this embodiment, the 3 distributed large-scale antenna arrays report the measured doppler frequency offset and the corresponding recorded measurement time and signal characteristic information (such as center frequency and modulation mode) to the central station via the ethernet or 5G network, and the central station is one of the 3 distributed large-scale antenna arrays or other devices.
And S104, correlating the reported results of the distributed large-scale antenna arrays at the central station.
In this embodiment, the central station associates the doppler frequency offset measurement result according to the measurement time and the signal characteristics, and the association criterion is as follows:
the time deviation of the measurement time is less than a preset threshold (e.g., 10 ms) and the normalized deviation of the signal characteristic is less than a preset threshold (e.g., 2%).
In the above-mentioned association process, if there is no record of the signal characteristics, the association is performed only according to the measurement time.
And S105, calculating the position and the speed by using the associated Doppler measurement result.
In this embodiment, the central station uses the doppler measurement results associated with the 3 distributed large-scale antenna arrays to complete the solution of the target position and velocity, and the specific solution equation is as follows:
by using
The position of the object is indicated and,
is shown askThe location of the individual distributed large-scale antenna arrays,
which represents the speed of movement of the object,t m which represents the time of the measurement,fd m,k is shown askA large-scale antenna arrayt m The measured Doppler frequency offset satisfies the following equation:
in the present embodiment, the first and second electrodes are,
，m=1,2,3,4,5, that is, the measurement results of consecutive 5 time windows of 3 distributed large-scale antenna arrays are substituted into the above formula to find the position of the target
And speed of movement
。
In this embodiment, the number of unknowns is 6, and under the optimal condition, that is, under the condition that the measurement results of continuous 5 time windows of 3 distributed large-scale antenna arrays can be correlated, the equation set has 15 equations, which belongs to the overdetermined problem, and the solution of the equation set can be solved by adopting an interior point method, a newton method or a gradient descent method, so as to finally achieve the effect of optimizing the positioning error.
Practical tests have shown that the normalized mean square error of the positioning of the present embodiment is better than 2R%, where R represents the target distance.
In conclusion, according to the distributed positioning and speed measuring method based on the large-scale antenna array, the Doppler measurement problem is divided into two stages of off-line training and on-line real-time calculation, the complicated calculation process is put into the off-line training stage, and the multi-channel parallel receiving signals of the large-scale antenna array are intelligently processed in real time through the off-line training deep neural network model; then, converging Doppler measurement results measured by a plurality of distributed large-scale antenna arrays to a central station; and finally, the central station correlates the reported results of all the distributed large-scale antenna arrays and performs position and speed calculation by using the correlated Doppler measurement results, so that the real-time calculation process is simpler and quicker, and the problem of overhigh real-time calculation complexity under the large-scale antenna array system is effectively solved.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (9)
1. A distributed positioning and speed measuring method based on a large-scale antenna array is characterized by comprising the following steps:
obtaining a deep neural network model through offline deep neural network training;
the deep neural network model is utilized to process the multi-path parallel receiving signals of the large-scale antenna array in real time to obtain a Doppler measurement result;
gathering Doppler measurement results measured by a plurality of distributed large-scale antenna arrays to a central station;
correlating the reported results of all distributed large-scale antenna arrays at a central station;
position and velocity resolution is performed using the doppler measurements on the correlations.
2. The distributed positioning and velocity measurement method based on the large-scale antenna array as claimed in claim 1, wherein the step of obtaining the deep neural network model through offline deep neural network training specifically comprises:
constructing a signal training set, wherein the signal training set comprises input data matrixes and output results, each output result contained in the signal training set is an accurate output result of the corresponding input data matrix after passing through a deep neural network model, and each input data matrix isN×MA matrix of dimensions, N representing the number of radio frequency links of the large-scale antenna array,Mrepresenting the number of signal sampling points of one training, each output result is data with 1 x 1 dimension, representing Doppler frequency offset, an input data matrix corresponds to one output result, each row of input data corresponds to a radio frequency link of a large-scale antenna array, and the input data is correspondingly input to an input node；
Grouping the signal training sets, sequentially and sequentially compiling two input nodes into a group, inputting the group into a preprocessing unit, and preprocessing the group;
preprocessing a signal training set, wherein each preprocessing unit corresponds to one of two paths of signals input to the preprocessing units, and delayingDA number of sample points, wherein,Dif the signal is a non-negative number, the other signal is straight-through, the straight-through signal and the delay signal are multiplied, and the average value of multiplication results is calculated;
deep neural network training, each input data matrix passingNAfter the processing of the/2 preprocessing units, inputting N/2 preprocessing results obtained into the deep neural network to obtain a current output result of the deep neural network, calculating the performance of the deep neural network by using the current output result of the deep neural network and an output result corresponding to the input data matrix, and continuously training until the performance of the deep neural network reaches a preset threshold to obtain a deep neural network model.
3. The distributed positioning and velocity measurement method based on large-scale antenna arrays as claimed in claim 2, wherein the mean square error is used as the performance function when calculating the performance of the deep neural network.
4. The distributed positioning and velocity measurement method based on the large-scale antenna array as claimed in claim 2, wherein the step of processing the multi-path parallel received signals of the large-scale antenna array in real time by using the deep neural network model specifically comprises:
in thatKA plurality of distributed large-scale antenna arrays,Kand grouping and preprocessing the measured data to be a positive integer, sending the data to a trained deep neural network model, obtaining a distributed measurement value of the Doppler frequency offset in real time, and recording the measurement time and signal characteristic information.
5. The distributed positioning and velocity measurement method based on large-scale antenna arrays as claimed in claim 4, wherein the step of converging the Doppler measurement results measured by the plurality of distributed large-scale antenna arrays to the central station specifically comprises:
and reporting the measured Doppler frequency offset and the correspondingly recorded measurement time and signal characteristic information to a central station through a wired network or a wireless network.
6. The distributed positioning and velocity measurement method based on large-scale antenna arrays according to claim 5, wherein in the step of associating the reported results of each distributed large-scale antenna array by the central station, the association conditions are as follows: the time deviation of the measurement time is less than a preset threshold, and the normalized deviation of the signal characteristics is less than the preset threshold.
7. The distributed positioning and velocity measuring method based on large-scale antenna arrays as claimed in claim 6, wherein when the central station correlates the reported results of each distributed large-scale antenna array, if there is no record of signal characteristics, then correlation is performed only according to the measurement time.
8. The distributed positioning and velocity measurement method based on large-scale antenna array as claimed in claim 6, wherein in the step of performing position and velocity solution using associated Doppler measurement results, the solution is performed using the following solution equation:
wherein the content of the first and second substances,cwhich represents the speed of propagation of the light,f c which is indicative of the center frequency of the signal,
the position of the object is indicated and,
is shown askThe location of the individual distributed large-scale antenna arrays,
which represents the speed of movement of the object,t m which represents the time of the measurement,fd m,k is shown askA large-scale antenna arrayt m The measured doppler frequency offset.
9. The distributed positioning and velocity measurement method based on large-scale antenna arrays according to claim 8, wherein the step of performing position and velocity solution using correlated doppler measurements further comprises:
in a predefined time window, the Doppler measurement results associated with the K distributed large-scale antenna arrays are brought into a calculation equation, and the solution of the calculation equation is solved by adopting an interior point method or a Newton method or a gradient descent method to obtain the position of the target
And speed of movement
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010991979.9A CN111931121B (en) | 2020-09-21 | 2020-09-21 | Distributed positioning and speed measuring method based on large-scale antenna array |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010991979.9A CN111931121B (en) | 2020-09-21 | 2020-09-21 | Distributed positioning and speed measuring method based on large-scale antenna array |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111931121A true CN111931121A (en) | 2020-11-13 |
| CN111931121B CN111931121B (en) | 2020-12-22 |
Family
ID=73333546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010991979.9A Active CN111931121B (en) | 2020-09-21 | 2020-09-21 | Distributed positioning and speed measuring method based on large-scale antenna array |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111931121B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260240A (en) * | 2013-05-23 | 2013-08-21 | 北京邮电大学 | Scattering information source locating method based on distribution matching in large-scale MIMO system |
| US20180292510A1 (en) * | 2017-04-07 | 2018-10-11 | Texas Instruments Incorporated | Calibration of a cascaded radar system |
| CN110068815A (en) * | 2018-01-22 | 2019-07-30 | 英飞凌科技股份有限公司 | System and method and storage medium for human behavioral modeling and power control |
| WO2019195327A1 (en) * | 2018-04-05 | 2019-10-10 | Google Llc | Smart-device-based radar system performing angular estimation using machine learning |
| CN111313943A (en) * | 2020-02-20 | 2020-06-19 | 东南大学 | Three-dimensional positioning method and device under deep learning assisted large-scale antenna array |
-
2020
- 2020-09-21 CN CN202010991979.9A patent/CN111931121B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103260240A (en) * | 2013-05-23 | 2013-08-21 | 北京邮电大学 | Scattering information source locating method based on distribution matching in large-scale MIMO system |
| US20180292510A1 (en) * | 2017-04-07 | 2018-10-11 | Texas Instruments Incorporated | Calibration of a cascaded radar system |
| CN110068815A (en) * | 2018-01-22 | 2019-07-30 | 英飞凌科技股份有限公司 | System and method and storage medium for human behavioral modeling and power control |
| WO2019195327A1 (en) * | 2018-04-05 | 2019-10-10 | Google Llc | Smart-device-based radar system performing angular estimation using machine learning |
| CN111313943A (en) * | 2020-02-20 | 2020-06-19 | 东南大学 | Three-dimensional positioning method and device under deep learning assisted large-scale antenna array |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111931121B (en) | 2020-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2022259835A1 (en) | Direction of arrival estimation | |
| CN109922427B (en) | Intelligent wireless positioning system and method using large-scale array antenna | |
| CN112637950B (en) | Fingerprint positioning method based on angle similarity | |
| CN112995892A (en) | Large-scale MIMO fingerprint positioning method based on complex neural network | |
| CN110927669A (en) | CS (circuit switched) multi-sound-source positioning method and system for wireless sound sensor network | |
| CN112929962B (en) | Positioning method, positioning device, computer equipment and storage medium | |
| CN113329491A (en) | Positioning parameter determination method, device, equipment and storage medium | |
| Kia et al. | A CNN approach for 5G mm wave positioning using beamformed CSI measurements | |
| CN111931121B (en) | Distributed positioning and speed measuring method based on large-scale antenna array | |
| CN114269014B (en) | Large-scale MIMO dynamic environment fingerprint positioning method based on domain adaptive network | |
| CN111610488A (en) | Method for estimating wave arrival angle of any array based on deep learning | |
| CN112180326B (en) | Hierarchical distributed positioning and speed measuring method based on large-scale antenna array | |
| CN113194401B (en) | Millimeter wave indoor positioning method and system based on generative countermeasure network | |
| CN112162238B (en) | Doppler frequency offset measuring method based on large-scale antenna array | |
| CN115908547A (en) | Wireless positioning method based on deep learning | |
| CN112996106B (en) | Honeycomb-removing large-scale MIMO system positioning method | |
| CN115494466A (en) | Self-calibration method for distributed radar | |
| CN111239682B (en) | Electromagnetic emission source positioning system and method | |
| CN114047474A (en) | Generalized regression neural network-based uniform linear array target orientation estimation method | |
| CN109274613B (en) | Channel estimation method, system and storage medium | |
| CN111323750A (en) | Direct positioning method based on acoustic vector array network | |
| Gong et al. | Improved K-nearest neighbor algorithm for indoor positioning using 5G channel state information | |
| Kanters et al. | A Supervised Learning Framework for Joint Estimation of Angles-of-Arrival and Number of Sources | |
| CN113514808B (en) | Intelligent identification method for judging target number of small unmanned aerial vehicle | |
| Ayub et al. | Disambiguation of measurements for multiple acoustic source localization using deep multi-dimensional assignments |
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 |