CN110995365B - Radio frequency gene library establishing method and illegal radio wave detection method - Google Patents
Radio frequency gene library establishing method and illegal radio wave detection method Download PDFInfo
- Publication number
- CN110995365B CN110995365B CN201910253233.5A CN201910253233A CN110995365B CN 110995365 B CN110995365 B CN 110995365B CN 201910253233 A CN201910253233 A CN 201910253233A CN 110995365 B CN110995365 B CN 110995365B
- Authority
- CN
- China
- Prior art keywords
- radio frequency
- layer
- individual
- radio
- neural 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.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B17/00—Monitoring; Testing
-
- 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
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention provides a radio frequency gene library establishing method and a illegal radio wave detection method, wherein the radio frequency gene library establishing method comprises the following steps: determining a range of a target geographic area; determining individual division modes according to the communication environment of the target geographic area; dividing the target geographic area into a plurality of individuals according to the individual dividing mode; detecting each individual to obtain basic radio frequency data of each individual; performing deep neural network calculation based on the basic radio frequency data of each individual to obtain the radio frequency gene of each individual; and storing the radio frequency gene of each individual to generate a radio frequency gene library of the target geographical area. The technical scheme provided by the invention can realize the intellectualization and automation of radio monitoring work on the basis of a radio management integrated platform, reduce unnecessary waste of people, property, materials and time, improve the work efficiency of radio management and perfect a radio management system.
Description
Technical Field
The invention relates to the field of wireless communication, in particular to a radio frequency gene library establishing method and an illegal radio wave detection method.
Background
In traditional radio monitoring work, technical personnel mainly analyze radio environment monitoring data to judge whether illegal violation signals exist. The traditional radio monitoring has high dependence on technicians on accuracy and timeliness, and the professional quality and related working experience of the technicians have high influence on the analysis and judgment results of the monitoring data; in addition, due to the randomness and discontinuity of the operation of the radio equipment, technicians are required to analyze the monitoring data from time to time, which results in the defects of large workload, high repeatability, poor timeliness and the like of radio management.
Disclosure of Invention
The invention provides a radio frequency gene library establishing method and a illegal radio wave detection method so as to overcome the problems or at least partially solve the problems.
According to an aspect of the present invention, there is provided a method for establishing a radio frequency gene library, comprising:
determining a range of a target geographic area;
determining individual division modes according to the communication environment of the target geographic area;
dividing the target geographic area into a plurality of individuals according to the individual dividing mode;
detecting each individual to obtain basic radio frequency data of each individual;
performing deep neural network calculation based on the basic radio frequency data of each individual to obtain the radio frequency gene of each individual;
and storing the radio frequency gene of each individual to generate a radio frequency gene library of the target geographical area.
Optionally, the radiofrequency gene comprises at least one of: longitude and latitude coordinates, coverage area range, radio monitoring frequency band, total power of a monitoring receiving signal, modulation mode of the monitoring receiving signal and a frequency spectrogram of the monitoring receiving signal.
Optionally, the determining the individual division manner according to the communication environment of the target geographic area includes:
when the communication environment of the target geographic area is mainly public network communication, dividing the individuals in a cellular form;
when the communication environment of the target geographic area is mainly direct communication, dividing the individuals in a grid form;
when the primary communication mode of the communication environment of the target geographical area cannot be determined, the individuals are divided in a cellular form.
Optionally, the performing deep neural network computation based on the basic radio frequency data of each individual includes:
initializing a deep neural network parameter by adopting a greedy layer-by-layer pre-training algorithm based on the basic radio frequency data;
and carrying out deep neural network model training, adjusting parameters of the deep neural network layer by layer, and fitting the deep neural network model to an approximate real model.
Optionally, initializing the deep neural network parameters by using a greedy layer-by-layer pre-training algorithm based on the basic radio frequency data includes:
transmitting the basic radio frequency data to an input layer of a deep neural network to serve as observable data of a first layer of a hidden layer;
training observable data of the first layer of the hidden layer by adopting an unsupervised learning algorithm to generate initial parameters of the first layer of the hidden layer;
taking the initial parameters of the first layer of the hidden layer as observable data of the second layer of the hidden layer, and continuing to train the second layer of the hidden layer by adopting the unsupervised learning algorithm to generate the initial parameters of the second layer of the hidden layer;
repeating the steps until all layers of the hidden layer are initialized to obtain initialization parameters of each layer;
and inputting the last layer of initialization parameters of the hidden layer into an output layer of the deep neural network, and initializing the parameters of the output layer by adopting a supervised learning algorithm.
Optionally, after the generating the radio frequency gene library of the target geographic area, the method further includes:
and repeatedly executing the steps of obtaining the basic radio frequency data and calculating the corresponding radio frequency genes, and updating the radio frequency gene library.
According to another aspect of the present invention, there is also provided a violation radio wave detection method including:
establishing a radio frequency gene library based on any radio frequency gene library establishing method;
performing radio wave detection in each individual to acquire radio frequency parameters of radio waves existing in each individual;
and determining whether the illegal radio waves exist or not by comparing the detected radio frequency parameters of the radio waves existing in each individual with the radio frequency genes of the individuals in the radio frequency gene library.
Based on the technical scheme provided by the invention, the intellectualization and automation of radio monitoring work can be realized on the basis of a radio management integrated platform, unnecessary waste of people, property, materials and time is reduced, the work efficiency of radio management is improved, and a radio management system is perfected.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
The above and other objects, advantages and features of the present invention will become more apparent to those skilled in the art from the following detailed description of specific embodiments thereof, taken in conjunction with the accompanying drawings.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a flow chart of a method for creating a radio frequency gene library according to an embodiment of the present invention;
FIG. 2 is a schematic representation of a radio frequency gene bank according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of partitioning individuals in a cellular format in accordance with an embodiment of the present invention;
FIG. 4 is a schematic diagram of partitioning individuals in a grid according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a deep learning neural network.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
It should be noted that the technical features of the embodiments and the preferred embodiments of the present invention can be combined with each other without conflict.
FIG. 1 is a flowchart of a method for creating a radio frequency gene library according to an embodiment of the present invention. As shown in fig. 1, the method for establishing a radio frequency gene library according to the embodiment of the present invention includes:
step S102, determining the range of a target geographic area;
step S104, determining individual division modes according to the communication environment of the target geographic area;
step S106, dividing the target geographic area into a plurality of individuals according to the individual dividing mode;
step S108, detecting each individual to obtain basic radio frequency data of each individual;
step S110, performing deep neural network calculation based on the basic radio frequency data of each individual to obtain the radio frequency gene of each individual;
and step S112, storing the radio frequency gene of each individual, and generating a radio frequency gene library of the target geographical area.
Aiming at the defects in the prior art, the embodiment of the invention provides a scheme which can realize the intellectualization and automation of radio monitoring work on the basis of a radio management integrated platform, thereby reducing unnecessary waste of people, property, things and time, improving the work efficiency of radio management and perfecting a radio management system.
In the technical scheme provided by the embodiment, a concept of radio frequency genes is provided based on radio frequency fingerprints. Radio Frequency Fingerprint (RFF) of Radio equipment is the essential characteristics of the physical layer of the equipment extracted by analyzing the output signal of the Radio equipment, including the information of the operating Frequency, signal power, modulation mode, etc. of the Radio equipment. The radio frequency gene of the radio communication environment refers to the basic characteristics of the radio communication environment in a certain geographic area range, including the longitude and latitude coordinates (ignoring altitude), the coverage area range, the radio monitoring frequency band, the total power of the monitored received signal, the modulation mode of the monitored received signal, the frequency spectrum schematic diagram of the monitored received signal, and the like of the radio communication environment, and the radio frequency gene library is the set of all the radio frequency genes in a certain geographic area range, as shown in fig. 2. The radio frequency gene library covering the radio monitoring frequency band is constructed, standard prior information of a radio communication environment in a certain geographic area can be provided, and the efficiency and accuracy of radio management work are improved.
The establishment of the radio frequency gene library is a progressive and long process, a radio management mechanism is required to store monitoring data with a certain magnitude in the initial construction, and the radio frequency gene library data is continuously updated in the later period according to the radio monitoring data. The coverage range of the monitoring equipment is used as the coverage range of an individual, the monitoring result of the radio-magnetic environment in the individual is used as the basic radio frequency data of the individual, and the basic radio frequency data of each individual is trained through an artificial intelligence technology to obtain the radio frequency gene of each individual.
In this embodiment, "individual" is a basic unit for determining a radio frequency gene, and is a smaller geographical area obtained by dividing a geographical area by a specific geometric shape. Preferably, the step S104 may include:
when the communication environment of the target geographic area is mainly public network communication, dividing individuals in a cellular mode;
when the communication environment of the target geographic area is mainly direct communication, dividing the individuals in a grid form;
when the primary communication means of the communication environment of the target geographical area cannot be determined, the individuals are divided in a cellular form.
In the embodiment, a self-adaptive individual division mode is preferentially adopted, and different individual division modes can be adaptively adopted in different communication environments. When the communication environment is mainly public network communication, dividing the individuals into honeycomb shapes, as shown in fig. 3; when the communication environment is mainly direct communication, dividing the individuals in a grid shape, as shown in fig. 4; when it cannot be determined, the individuals are divided in a honeycomb shape.
In order to determine the individual's rf gene as accurately as possible, the present embodiment employs a deep learning algorithm to calculate the individual's rf gene. The deep learning is an artificial intelligence learning method for realizing complex function fitting by learning a deep nonlinear network structure, which is essentially a deep neural network learning algorithm, wherein the deep neural network structure comprises an input layer, a hidden layer and an output layer, and is shown in fig. 5. The input layer is input data for learning, the hidden layer is used for extracting and analyzing the characteristics of the input data, and the output layer is output data for learning. The completeness of the deep neural network enables the deep neural network to represent any function, and therefore, the fitting of any function can be achieved through multiple layers of parameters and different network structures.
The greedy layer-by-layer pre-training algorithm is an unsupervised learning algorithm, and is an unsupervised deep learning method based on the greedy layer-by-layer pre-training algorithm. A semi-supervised algorithm of a greedy layer-by-layer pre-training algorithm is adopted, an unsupervised training learning method is adopted for a hidden layer, a supervised learning method is adopted for an output layer, and a better learning result can be obtained.
Based on the above technology, preferably, step S110 may include:
initializing deep neural network parameters by adopting greedy layer-by-layer pre-training algorithm based on basic radio frequency data
And (3) carrying out deep neural network model training, adjusting parameters of the deep neural network layer by layer, and fitting the deep neural network model to an approximate real model.
And the initialization process described above may include:
transmitting the basic radio frequency data to an input layer of a deep neural network to be used as observable data of a first layer of a hidden layer;
training observable data of the first layer of the hidden layer by adopting an unsupervised learning algorithm to generate initial parameters of the first layer of the hidden layer;
taking the initial parameters of the first layer of the hidden layer as observable data of the second layer of the hidden layer, and continuing to train the second layer of the hidden layer by adopting an unsupervised learning algorithm to generate the initial parameters of the second layer of the hidden layer;
repeating the steps until all layers of the hidden layer are initialized to obtain initialization parameters of each layer;
and inputting the last layer of initialization parameters of the hidden layer into an output layer of the deep neural network, and initializing the parameters of the output layer by adopting a supervised learning algorithm.
Preferably, in order to obtain more accurate data, after the radio frequency gene library of the target geographic region is generated, the steps of obtaining the basic radio frequency data and calculating the corresponding radio frequency gene may be repeatedly performed, so as to update the radio frequency gene library.
As can be seen from the above description, the embodiment of the present invention provides a technical solution:
1. establishing a radio frequency gene library of a radio communication environment in a certain geographical area: providing a standard radio frequency gene template (radio frequency gene library) in a certain geographic area and providing standard prior information of a radio communication radio frequency environment in a certain area. The radio frequency gene of the radio communication environment refers to basic characteristics of the radio communication environment in a certain geographic area range, and comprises information of the geographic position, the coverage area range, the working frequency, the signal power, the modulation mode and the like of the radio communication environment; and the radio frequency gene library is a set of all radio frequency genes in a certain geographic region.
2. Self-adaptive individual division mode: providing an adaptive individual partitioning approach under different communication environments. When the communication environment is mainly public network communication, the individuals are divided in a honeycomb manner as shown in fig. 2; when the communication environment is mainly direct communication, dividing the individuals in a grid shape, as shown in fig. 3; when it cannot be determined, the individuals are divided in a honeycomb shape. Taking a certain place in a certain area as an example, firstly selecting an individual dividing mode (honeycomb or grid shape) according to a radio communication environment, and then building a radio frequency gene of the area of the place by using a semi-supervised learning algorithm.
4. Intelligence and automation of radio management work: based on software and hardware infrastructures such as a radio monitoring system, a radio detection system and a simulation system, a user realizes intellectualization and automation of radio monitoring work on the basis of a radio management integrated platform, and a semi-supervised deep learning method adopting a greedy layer-by-layer pre-training algorithm is provided for constructing a radio frequency gene library covering a certain geographic area.
5. Maximizing the resource utilization rate: unnecessary waste of people, property, things and time is reduced, the working efficiency of radio management is improved, and a radio management system is perfected.
The above embodiment is described below by way of a specific preferred embodiment. The preferred embodiment provides a method for building a self-adaptive individual division radio frequency gene library based on a semi-supervised deep learning method, which comprises the following steps:
1) and determining an individual division mode. When the communication environment is mainly public network communication, dividing the individuals in a honeycomb manner; when the communication environment is mainly direct communication, dividing the individuals in a grid shape; when it cannot be determined, the individuals are divided in a honeycomb shape.
2) Determining the size of the coverage area of the divided individuals;
3) determining the geographical area range to be covered by the radio frequency gene library;
4) dividing the geographical area determined in 3) in a manner determined in 1) by taking an individual as a basic unit, as shown in FIG. 2 or FIG. 3;
5) the monitoring result of each individual is only used as a group of basic radio frequency data of the individual, and the basic radio frequency data collected in the construction of the radio frequency gene library ensures that the influence of factors such as extreme weather on the monitoring result is fully considered;
6) and initializing the deep neural network. Initializing the parameters of the deep neural network by adopting a greedy layer-by-layer pre-training algorithm, wherein the initialization process comprises the following steps:
a) transmitting individual monitoring data (namely basic radio frequency data) x to an input layer of the deep neural network, wherein the observable data h0(x) is used as a first layer of a hidden layer, namely h0(x) is x;
b) training observable data h0(x) of a first layer of a hidden layer by adopting an unsupervised learning algorithm to generate initial parameters R1(h0(x)) of the first layer of the hidden layer;
c) taking the hidden layer first layer initial parameter R1(h0(x)) as observable data h1(x) of the hidden layer second layer, namely h1(x) is R1(h0(x)), continuing to train the hidden layer second layer by adopting an unsupervised learning algorithm, and generating an initial parameter R2(h1(x)) of the hidden layer second layer;
d) repeating the step of c) to initialize all layers of the hidden layer to obtain initialization parameters R1(h0(x)), R2(h1(x)), R3(h2(x)), … and RL (hL-1(x)) of each layer;
e) inputting a final layer initialization parameter RL (hL-1(x)) of the hidden layer into the output layer, and initializing the output layer parameter by adopting a supervised learning algorithm;
7) and (5) deep neural network model training. Model training, namely the process of adjusting parameters layer by layer and gradually fitting, and finely adjusting the whole deep neural network by adopting a supervised learning algorithm so that the neural network model can approach a real model;
8) outputting the deep neural network model to obtain individual radio frequency genes;
9) training radio frequency genes of all individuals in a geographic region range to obtain a radio frequency gene library;
10) and repeating the steps 5) to 7), and continuously optimizing and supplementing the radio frequency gene library.
In another embodiment of the present invention, based on the above method for creating a radio frequency gene library, there is provided a method for detecting illegal violation radio waves, including the following steps:
establishing a radio frequency gene library based on the radio frequency gene library establishing method;
performing radio wave detection in each individual, and acquiring radio frequency parameters of radio waves existing in the individual, such as radio frequency fingerprints;
and determining whether illegal radio waves exist or not by comparing the detected radio frequency parameters of the radio waves existing in each individual with the radio frequency genes of the individuals in the radio frequency gene library.
When there exists a radio wave in an individual whose radio frequency parameters (such as radio frequency fingerprint) are greatly different from the radio frequency genes of the individual, the radio break is suspected to have illegal violation. Such operations and determinations can be automatically performed by the corresponding system.
As can be seen from the above description, the technical solution provided by the embodiment of the present invention can be well applied to a radio monitoring system. Firstly, the technical scheme provided by the embodiment of the invention provides a concept of a radio frequency gene library, and suspected illegal radio transmitting equipment in a certain monitored geographic area can be rapidly found by comparing a radio monitoring result with related information of the radio frequency gene library; secondly, the technical scheme provided by the embodiment of the invention adopts a self-adaptive individual division method for building a radio frequency gene library, and different individual division modes are selected according to different communication environments; thirdly, the technical scheme provided by the embodiment of the invention adopts a method for constructing a propagation path model map based on a semi-supervised deep learning method, the essence of the deep learning algorithm is a deep neural network learning algorithm, the semi-supervised algorithm of a greedy layer-by-layer pre-training algorithm is adopted to adopt an unsupervised training mode for a hidden layer, and a supervised learning mode is adopted for an output layer, so that a better learning result can be obtained; finally, from the aspect of resource utilization, the technical scheme provided by the embodiment of the invention realizes the effect of saving human, property, material and time cost.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments can be modified or some or all of the technical features can be equivalently replaced within the spirit and principle of the present invention; such modifications or substitutions do not depart from the scope of the present invention.
Claims (6)
1. A radio frequency gene library establishment method comprises the following steps:
determining a range of a target geographic area;
determining individual division modes according to the communication environment of the target geographic area;
dividing the target geographic area into a plurality of individuals according to the individual dividing mode;
detecting each individual to obtain basic radio frequency data of each individual;
performing deep neural network calculation based on the basic radio frequency data of each individual to obtain the radio frequency gene of each individual;
storing the radio frequency gene of each individual to generate a radio frequency gene library of the target geographical area; wherein
The radiofrequency gene comprises at least one of: longitude and latitude coordinates, coverage area range, radio monitoring frequency band, total power of monitoring received signals, modulation mode of monitoring received signals and spectrogram of monitoring received signals;
the rf gene bank is a collection of all rf genes of the target geographic region.
2. The method of claim 1, wherein the determining individual divisions from the communication environment of the target geographic region comprises:
when the communication environment of the target geographic area is mainly public network communication, dividing the individuals in a cellular form;
when the communication environment of the target geographic area is mainly direct communication, dividing the individuals in a grid form;
when the primary communication mode of the communication environment of the target geographical area cannot be determined, the individuals are divided in a cellular form.
3. The method of claim 1, wherein said performing deep neural network calculations based on each of said individual's underlying radio frequency data comprises:
initializing a deep neural network parameter by adopting a greedy layer-by-layer pre-training algorithm based on the basic radio frequency data;
and training a deep neural network model, adjusting parameters of the deep neural network layer by layer, and fitting the deep neural network model to an approximate real model.
4. The method of claim 3, wherein initializing deep neural network parameters using a greedy layer-by-layer pre-training algorithm based on the base radio frequency data comprises:
transmitting the basic radio frequency data to an input layer of a deep neural network to serve as observable data of a first layer of a hidden layer;
training observable data of the first layer of the hidden layer by adopting an unsupervised learning algorithm to generate initial parameters of the first layer of the hidden layer;
taking the initial parameters of the first layer of the hidden layer as observable data of the second layer of the hidden layer, and continuing to train the second layer of the hidden layer by adopting the unsupervised learning algorithm to generate the initial parameters of the second layer of the hidden layer;
repeating the steps until all layers of the hidden layer are initialized to obtain initialization parameters of each layer;
and inputting the last layer of initialization parameters of the hidden layer into an output layer of the deep neural network, and initializing the parameters of the output layer by adopting a supervised learning algorithm.
5. The method of claim 1, wherein after the generating the radio frequency gene bank for the target geographic region, further comprising:
and repeatedly executing the steps of obtaining the basic radio frequency data and calculating the corresponding radio frequency genes, and updating the radio frequency gene library.
6. A violation radio wave detection method, comprising:
establishing a radio frequency gene library based on the radio frequency gene library establishing method according to any one of claims 1 to 5;
performing radio wave detection in each individual to acquire radio frequency parameters of radio waves existing in each individual;
and determining whether the illegal radio waves exist or not by comparing the detected radio wave parameters of the radio waves existing in each individual with the radio wave genes of the individuals in the radio frequency gene bank.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910253233.5A CN110995365B (en) | 2019-03-29 | 2019-03-29 | Radio frequency gene library establishing method and illegal radio wave detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910253233.5A CN110995365B (en) | 2019-03-29 | 2019-03-29 | Radio frequency gene library establishing method and illegal radio wave detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110995365A CN110995365A (en) | 2020-04-10 |
CN110995365B true CN110995365B (en) | 2022-06-21 |
Family
ID=70081655
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910253233.5A Active CN110995365B (en) | 2019-03-29 | 2019-03-29 | Radio frequency gene library establishing method and illegal radio wave detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110995365B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113159311A (en) * | 2020-12-31 | 2021-07-23 | 光华临港工程应用技术研发(上海)有限公司 | Learning method of back propagation algorithm of neuron network |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
CN106375027A (en) * | 2016-08-31 | 2017-02-01 | 成都九华圆通科技发展有限公司 | Intelligent cloud monitoring system and method for radio |
CN108152791A (en) * | 2017-12-06 | 2018-06-12 | 南京航空航天大学 | Radio cheating signal framing system based on GRNN neural networks |
CN108390705A (en) * | 2018-03-29 | 2018-08-10 | 东南大学 | The extensive mimo system detection method of deep neural network based on BP algorithm structure |
CN109274455A (en) * | 2018-09-05 | 2019-01-25 | 北京众谱达科技有限公司 | Applied to the radio tube control equipment under complex electromagnetic environment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012106075A1 (en) * | 2011-02-05 | 2012-08-09 | Wifislam, Inc. | Method and apparatus for mobile location determination |
-
2019
- 2019-03-29 CN CN201910253233.5A patent/CN110995365B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103945533A (en) * | 2014-05-15 | 2014-07-23 | 济南嘉科电子技术有限公司 | Big data based wireless real-time position positioning method |
CN106375027A (en) * | 2016-08-31 | 2017-02-01 | 成都九华圆通科技发展有限公司 | Intelligent cloud monitoring system and method for radio |
CN108152791A (en) * | 2017-12-06 | 2018-06-12 | 南京航空航天大学 | Radio cheating signal framing system based on GRNN neural networks |
CN108390705A (en) * | 2018-03-29 | 2018-08-10 | 东南大学 | The extensive mimo system detection method of deep neural network based on BP algorithm structure |
CN109274455A (en) * | 2018-09-05 | 2019-01-25 | 北京众谱达科技有限公司 | Applied to the radio tube control equipment under complex electromagnetic environment |
Also Published As
Publication number | Publication date |
---|---|
CN110995365A (en) | 2020-04-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11664910B2 (en) | Processing of communications signals using machine learning | |
CN109743683B (en) | Method for determining position of mobile phone user by adopting deep learning fusion network model | |
Mazzoleni et al. | Can assimilation of crowdsourced data in hydrological modelling improve flood prediction? | |
EP2659697B1 (en) | Method for the prediction of coverage areas of a cellular network | |
CN110176226A (en) | A kind of speech recognition and speech recognition modeling training method and device | |
US10725008B2 (en) | Automatic siting for air quality monitoring stations | |
CN107843774B (en) | Electromagnetic situation calculation imaging method and electromagnetic situation imaging system | |
CN103889051B (en) | Indoor WLAN fingerprint positioning methods based on AP ID filterings and Kalman filtering | |
CN108709557B (en) | Indoor map generation method based on multi-user track fitting | |
CN110427878B (en) | Method and system for identifying rapid radio storm signals | |
CN112363251A (en) | Weather prediction model generation method, weather prediction method and device | |
WO2022021602A1 (en) | 5g reference signal received power prediction method based on geographic information | |
Redondi | Radio map interpolation using graph signal processing | |
CN104519571A (en) | Indoor positioning method based on RSS (Received Signal Strength) | |
CN104039008B (en) | A kind of hybrid locating method | |
CN112218330A (en) | Positioning method and communication device | |
CN116595121B (en) | Data display monitoring system based on remote sensing technology | |
JP6696859B2 (en) | Quality estimation device and quality estimation method | |
Rutagemwa et al. | Dynamic spectrum assignment for land mobile radio with deep recurrent neural networks | |
Gontier et al. | Polyphonic training set synthesis improves self-supervised urban sound classification | |
CN110995365B (en) | Radio frequency gene library establishing method and illegal radio wave detection method | |
CN114611388B (en) | Wireless channel characteristic screening method based on artificial intelligence | |
CN114205831B (en) | Method, device, storage medium and equipment for determining optimization scheme | |
CN110990500A (en) | Propagation path model map establishing method and path loss determining method | |
Kim et al. | Formulating human mobility model in a form of continuous time Markov chain |
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 |