CN111835454B - Environment identification method and system for cellular network electromagnetic interference system - Google Patents
Environment identification method and system for cellular network electromagnetic interference system Download PDFInfo
- Publication number
- CN111835454B CN111835454B CN202010654663.0A CN202010654663A CN111835454B CN 111835454 B CN111835454 B CN 111835454B CN 202010654663 A CN202010654663 A CN 202010654663A CN 111835454 B CN111835454 B CN 111835454B
- Authority
- CN
- China
- Prior art keywords
- base station
- environment
- data
- station signal
- radio frequency
- 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
- H04K—SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04K3/00—Jamming of communication; Counter-measures
- H04K3/60—Jamming involving special techniques
- H04K3/68—Jamming involving special techniques using passive jamming, e.g. by shielding or reflection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- H04K—SECRET COMMUNICATION; JAMMING OF COMMUNICATION
- H04K3/00—Jamming of communication; Counter-measures
- H04K3/40—Jamming having variable characteristics
- H04K3/43—Jamming having variable characteristics characterized by the control of the jamming power, signal-to-noise ratio or geographic coverage area
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Signal Processing (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention relates to an environment identification method and system for a cellular network electromagnetic interference system. The method comprises the following steps: acquiring detection data of an antenna array and radio frequency data of a base station in the environment; preprocessing the detection data and the radio frequency data; based on the preprocessed detection data, recognizing the environment type of the detection data by utilizing an environment recognition classification model; and identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing a base station signal intensity regression model based on the preprocessed radio frequency data. The invention can realize real-time analysis of the environment, further provide a self-adaptive adjustment basis for the electromagnetic interference process of the cellular network and reduce the power loss.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to an environment identification method and system for a cellular network electromagnetic interference system.
Background
In recent years, with the development of wireless communication technology, cellular network electromagnetic interference technology has received more and more attention. The electromagnetic interference technology in the cellular network is mainly to set an interference signal with a certain intensity aiming at a base station signal of a target space, thereby achieving the purpose of interfering a mobile communication terminal. However, due to the complexity of the application environment, the common omni-directional antenna shielding method cannot achieve a good use effect. The omnidirectional antenna shielding has two main problems, namely, the omnidirectional antenna shielding often causes interference and influence on a non-target shielding area, and much power consumption is wasted; secondly, because the size of the target space and the size of the target space base station signal are not known enough, the strength of the interference signal cannot be adjusted in a self-adaptive manner, and thus much power consumption is wasted.
Disclosure of Invention
The invention aims to provide an environment identification method and system for a cellular network electromagnetic interference system, so as to realize real-time analysis on the environment, further provide a self-adaptive adjustment basis for the cellular network electromagnetic interference process and reduce power loss.
In order to achieve the purpose, the invention provides the following scheme:
an environment identification method for a cellular network electromagnetic interference system, comprising:
acquiring detection data of an antenna array and radio frequency data of a base station in the environment;
preprocessing the detection data and the radio frequency data;
based on the preprocessed detection data, recognizing the environment type of the detection data by utilizing an environment recognition classification model;
and identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing a base station signal intensity regression model based on the preprocessed radio frequency data.
Optionally, the acquiring the detection data of the antenna array and the radio frequency data of the base station in the environment specifically includes:
transmitting a sounding signal using a transmitting antenna in the antenna array;
receiving electromagnetic signals returned by the detection signals through receiving antennas in the antenna array;
determining the detection data from the electromagnetic signal; the detection data comprises the intensity, phase and time taken for the signal to return of the electromagnetic signal;
and receiving radio frequency signals of base stations in the environment by using receiving antennas in the antenna array.
Optionally, the preprocessing the detection data and the radio frequency data specifically includes:
carrying out normalization pretreatment on the detection data to obtain pretreated detection data;
and carrying out normalization preprocessing on the radio frequency data to obtain preprocessed radio frequency data.
Optionally, the identifying the environment type of the detection data by using the environment identification classification model based on the preprocessed detection data further includes:
constructing the environment recognition classification model by adopting a machine learning method; the environment recognition classification model is a neural network model;
acquiring a detection data set labeled with an environment type; the probing data set comprises a first training set and a first testing set;
and training the environment recognition classification model by using the detection data set, and determining parameters of the environment recognition classification model.
Optionally, the identifying, based on the preprocessed radio frequency data, the base station signal strength of the environment where the radio frequency data is located by using a base station signal strength regression model further includes:
constructing a regression model of the signal intensity of the base station by adopting a machine learning method; the base station signal intensity regression model is a neural network model;
acquiring a base station signal data set marked with base station signal strength; the base station signal data set comprises a second training set and a second test set;
and training the base station signal intensity regression model by using the base station signal data set, and determining the parameters of the base station signal intensity regression model.
The present invention also provides an environment recognition system for a cellular network electromagnetic interference system, comprising:
the data acquisition module is used for acquiring detection data of the antenna array and radio frequency data of a base station in the environment;
the preprocessing module is used for preprocessing the detection data and the radio frequency data;
the environment type identification module is used for identifying the environment type of the detection data by utilizing an environment identification classification model based on the preprocessed detection data;
and the base station signal intensity identification module is used for identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing a base station signal intensity regression model based on the preprocessed radio frequency data.
Optionally, the data acquisition module specifically includes:
a transmitting unit, configured to transmit a sounding signal by using a transmitting antenna in the antenna array;
the receiving unit is used for receiving the electromagnetic signals returned by the detection signals through receiving antennas in the antenna array;
a detection data determination unit for determining the detection data from the electromagnetic signal; the detection data comprises the intensity, phase and time taken for the signal to return of the electromagnetic signal;
the receiving unit is further configured to receive a radio frequency signal of a base station in an environment by using a receiving antenna in the antenna array.
Optionally, the preprocessing module specifically includes:
the detection data preprocessing unit is used for carrying out normalization preprocessing on the detection data to obtain preprocessed detection data;
and the radio frequency data preprocessing unit is used for carrying out normalization preprocessing on the radio frequency data to obtain preprocessed radio frequency data.
Optionally, the method further includes:
the environment recognition classification model building module is used for building the environment recognition classification model by adopting a machine learning method before the environment type of the detection data is recognized by utilizing the environment recognition classification model based on the preprocessed detection data; the environment recognition classification model is a neural network model;
the detection data set acquisition module is used for acquiring a detection data set labeled with an environment type; the probing data set comprises a first training set and a first testing set;
and the environment recognition classification model training module is used for training the environment recognition classification model by utilizing the detection data set and determining the parameters of the environment recognition classification model.
Optionally, the method further includes:
the base station signal intensity regression model building module is used for building a base station signal intensity regression model by adopting a machine learning method before identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing the base station signal intensity regression model based on the preprocessed radio frequency data; the base station signal intensity regression model is a neural network model;
the base station signal data set acquisition module is used for acquiring a base station signal data set marked with base station signal strength; the base station signal data set comprises a second training set and a second test set;
and the base station signal intensity regression model training module is used for training the base station signal intensity regression model by using the base station signal data set and determining the parameters of the base station signal intensity regression model.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
the invention effectively collects the relevant information of the target space in real time: the method has the advantages that the data and the radio frequency data of the base stations in the environment are detected, the environment type where the detected data are located is identified in real time by adopting the environment identification classification model, the strength of the base station signal is identified in real time by adopting the base station signal strength regression model, the data analysis and processing capacity is improved, a basis is provided for adaptively setting the direction of the shielding antenna, the power consumption is favorably reduced, and the interference to a non-shielding area is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart illustrating an environment identification method for a cellular network EMI system according to the present invention;
fig. 2 is a schematic structural diagram of an environment recognition system for a cellular network electromagnetic interference system according to the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Fig. 1 is a flow chart illustrating an environment identification method for a cellular network electromagnetic interference system according to the present invention. As shown in fig. 1, the environment recognition method for the cellular network electromagnetic interference system of the present invention comprises the following steps:
step 100: acquiring detection data of the antenna array and radio frequency data of a base station in the environment. The invention utilizes the transmitting antenna in the antenna array to transmit the electromagnetic detection signal in the target space, receives the electromagnetic signal returned by the detection signal through the receiving antenna in the antenna array, and determines the strength and the phase of the electromagnetic signal and the time for returning the signal according to the electromagnetic signal to obtain the detection data. And meanwhile, receiving radio frequency signals of a base station in the environment in real time by using receiving antennas in the antenna array.
Step 200: the detection data and the radio frequency data are preprocessed. The preprocessing method can adopt normalization processing. For example, the detection data and the radio frequency data are respectively processed by a discrete standardization method to obtain preprocessed detection data and preprocessed radio frequency data. The formula for discrete normalization is:
in the formula, xi' is a preprocessed data value (preprocessed probe data or preprocessed radio frequency data), xiIs the data value to be processed (probe data or radio frequency data), xminAnd xmaxRespectively, the minimum and maximum values of the data value (the minimum and maximum values of the probe data or the minimum and maximum values of the radio frequency data).
Step 300: and based on the preprocessed detection data, identifying the environment type of the detection data by using an environment identification classification model. The environment recognition classification model is constructed by adopting a machine learning method, and the machine learning method can be a machine learning algorithm such as decision tree regression, random forest, neural network, deep learning and the like. The environment recognition classification model may be a neural network model, for example, a three-layer neural network model is constructed. When a neural network model is constructed, the electromagnetic detection signals are used as characteristic values, the environment types are used as target values, so that the number of nodes of an input layer of the neural network model is the same as the dimensionality of the electromagnetic detection signals, the number of nodes of an output layer is the same as the number of the environment types, the number of nodes of an implicit layer is tried and found according to an empirical formula, and the optimal number of nodes is selected according to experimental results. Wherein, a Sigmoid function is adopted as an activation function in the hidden layer, and a Softmax function is adopted as the activation function in the output layer.
After the environment recognition classification model is constructed, the model needs to be further trained, and the specific process is as follows:
firstly, manually marking the environment type Y corresponding to the detection signaliI 1,2, …, d (d is the number of environment categories), resulting in a detection dataset. The set-out method was then used on the probe data set according to 8: a ratio of 2 is randomly divided into a first training set and a first test set.
Inputting the first training set into the environment recognition classification model, optimizing weight parameters of the environment recognition classification model by using a stochastic gradient descent algorithm with the aim of minimizing cross entropy, iterating N (N >1000) times to obtain the trained environment recognition classification model and storing model parameters.
In order to ensure that the environment recognition classification model has good classification capability on the unknown environment, the generalization error of the environment recognition classification model needs to be evaluated, namely, the trained environment recognition classification model is used for predicting the samples of the first test set, the classification accuracy is calculated, when the accuracy is more than 99%, the environment recognition classification model is considered to have good generalization performance, and at the moment, the training is completed to obtain the trained environment recognition classification model. The invention adopts a cross validation method to evaluate the model, and the cross validation method comprises the following steps: leave-out, leave-one, and k-fold cross-validation.
Step 400: and identifying the base station signal intensity of the environment where the radio frequency data is based on the preprocessed radio frequency data by utilizing a base station signal intensity regression model. The base station signal intensity regression model is constructed by adopting a machine learning method, and can be a neural network model. For example, a three-layer neural network model is constructed. When a base station signal strength regression model is constructed, a base station radio frequency signal is used as a characteristic value, the base station signal strength is used as a target value, namely the node number of an input layer of a neural network is the same as the dimension of the base station radio frequency signal, the node number of an output layer is the same as the dimension of the base station signal strength, so that only one node is provided, the node number of an implicit layer is tested and found according to an empirical formula, and the optimal node number is selected according to an experimental result. Wherein, the hidden layer adopts a Sigmoid function as an activation function, and the output layer does not use the activation function.
The prior art is adopted to communicate with the base station corresponding to each base station signal, so as to obtain the base station signal intensity corresponding to each base station, and obtain the base station signal data set with the base station signal intensity. Using the leave-out method on the base station signal data set follows 8: a ratio of 2 is randomly divided into a second training set and a second test set. Inputting the second training set into the base station signal intensity regression model, optimizing the weight parameters of the base station signal intensity regression model by using a random gradient descent algorithm to minimize the mean square error, iterating N (N is more than 1000) times to obtain the trained base station signal intensity regression model, and storing the model parameters.
In order to ensure that the base station signal intensity regression model has good identification capability on the unknown environment, the generalization error of the base station signal intensity regression model needs to be evaluated, namely the trained base station signal intensity regression model is used for predicting samples of the second test set and calculating the mean square error, when the mean square error is less than 1, the base station signal intensity regression model is considered to have good generalization performance, and the trained base station signal intensity regression model is obtained after training is finished.
Fig. 2 is a schematic structural diagram of an environment recognition system for a cellular network electromagnetic interference system according to the present invention. As shown in fig. 2, the environment recognition system for a cellular network electromagnetic interference system of the present invention includes:
the data acquisition module 201 is configured to acquire detection data of the antenna array and radio frequency data of a base station in an environment.
A preprocessing module 202, configured to preprocess the detection data and the radio frequency data.
And the environment type identification module 203 is configured to identify, based on the preprocessed detection data, an environment type in which the detection data is located by using an environment identification classification model.
And the base station signal strength identification module 204 is configured to identify, based on the preprocessed radio frequency data, the base station signal strength of the environment where the radio frequency data is located by using a base station signal strength regression model.
As another embodiment, the data acquisition module 201 of the present invention is used in an environment identification system of a cellular network electromagnetic interference system, and specifically includes:
and the transmitting unit is used for transmitting the electromagnetic detection signal in the target space by using the transmitting antenna in the antenna array.
And the receiving unit is used for receiving the electromagnetic signals returned by the detection signals through the receiving antennas in the antenna array.
A detection data determination unit for determining the detection data from the returned electromagnetic signal; the probe data includes the strength, phase and time taken for the signal to return of the electromagnetic signal.
The receiving unit is further configured to receive a radio frequency signal of a base station in an environment by using a receiving antenna in the antenna array.
As another embodiment, the present invention is applied to an environment identification system of a cellular network electromagnetic interference system, and the preprocessing module 202 specifically includes:
and the detection data preprocessing unit is used for carrying out normalization preprocessing on the detection data to obtain preprocessed detection data.
And the radio frequency data preprocessing unit is used for carrying out normalization preprocessing on the radio frequency data to obtain preprocessed radio frequency data.
As another embodiment, the environment recognition system for a cellular network electromagnetic interference system of the present invention further comprises:
the environment recognition classification model building module is used for building the environment recognition classification model by adopting a machine learning method before the environment type of the detection data is recognized by utilizing the environment recognition classification model based on the preprocessed detection data; the environment recognition classification model is a neural network model.
The detection data set acquisition module is used for acquiring a detection data set labeled with an environment type; the probe data set includes a first training set and a first test set.
And the environment recognition classification model training module is used for training the environment recognition classification model by utilizing the detection data set and determining the parameters of the environment recognition classification model.
As another embodiment, the environment recognition system for cellular network electromagnetic interference system of the present invention further comprises:
the base station signal intensity regression model building module is used for building a base station signal intensity regression model by adopting a machine learning method before identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing the base station signal intensity regression model based on the preprocessed radio frequency data; the base station signal intensity regression model is a neural network model.
The base station signal data set acquisition module is used for acquiring a base station signal data set marked with base station signal strength; the base station signal data set includes a second training set and a second test set.
And the base station signal intensity regression model training module is used for training the base station signal intensity regression model by using the base station signal data set and determining the parameters of the base station signal intensity regression model.
As another embodiment, the environment recognition system for the cellular network electromagnetic interference system comprises a signal acquisition module, a recognition modeling module and a real-time recognition module. The signal acquisition module is used for sending electromagnetic detection signals and receiving detection signals of the antenna array, and simultaneously acquiring radio frequency signals of a base station in an environment received by the antenna array; and preprocessing the acquired detection signals and radio frequency signals and then sending the preprocessed detection signals and radio frequency signals to an identification modeling module or a real-time identification module.
And the identification modeling module is used for modeling and training the detection signals and the radio frequency signals sent by the signal acquisition module by using a machine learning algorithm to obtain an environment identification classification model and a base station signal intensity regression model, and sending the obtained model and algorithm related parameters to the real-time identification module.
And the real-time identification module is used for respectively transmitting the acquired real-time antenna detection data and the base station radio frequency signal into the environment identification classification model and the base station signal intensity regression model so as to realize space information identification and base station information identification. In this embodiment, the identification modeling module is configured to model and train, and send the relevant parameters of the trained model to the real-time identification module, and the real-time identification module analyzes and identifies the detection data and the radio frequency signal acquired by the signal acquisition module in real time by using the relevant parameters of the trained model, so as to obtain real-time spatial information (type of environment) and base station information (base station signal strength).
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (8)
1. An environment identification method for a cellular network electromagnetic interference system, comprising:
acquiring detection data of an antenna array and radio frequency data of a base station in the environment; the method specifically comprises the following steps: transmitting a sounding signal using a transmitting antenna in the antenna array; receiving electromagnetic signals returned by the detection signals through receiving antennas in the antenna array; determining the detection data from the electromagnetic signal; the detection data comprises the intensity, phase and time taken for the signal to return of the electromagnetic signal; receiving radio frequency signals of a base station in the environment by using receiving antennas in the antenna array;
preprocessing the detection data and the radio frequency data;
based on the preprocessed detection data, recognizing the environment type of the detection data by utilizing an environment recognition classification model; the environment recognition classification model is a neural network model constructed by adopting a machine learning method;
identifying the base station signal intensity of the environment where the radio frequency data are located by utilizing a base station signal intensity regression model based on the preprocessed radio frequency data; the base station signal intensity regression model is a neural network model constructed by adopting a machine learning method.
2. The environment recognition method for cellular network electromagnetic interference system according to claim 1, wherein the preprocessing the probe data and the radio frequency data specifically includes:
carrying out normalization pretreatment on the detection data to obtain pretreated detection data;
and carrying out normalization preprocessing on the radio frequency data to obtain preprocessed radio frequency data.
3. The environment recognition method for cellular network electromagnetic interference system according to claim 1, wherein the recognizing the type of the environment where the probe data is located by using the environment recognition classification model based on the preprocessed probe data further comprises:
constructing the environment recognition classification model by adopting a machine learning method; the environment recognition classification model is a neural network model;
acquiring a detection data set labeled with an environment type; the probing data set comprises a first training set and a first testing set;
and training the environment recognition classification model by using the detection data set, and determining parameters of the environment recognition classification model.
4. The method of claim 1, wherein the identifying the base station signal strength of the environment in which the radio frequency data is based on the preprocessed radio frequency data by using a base station signal strength regression model, further comprises:
constructing a regression model of the signal intensity of the base station by adopting a machine learning method; the base station signal intensity regression model is a neural network model;
acquiring a base station signal data set marked with base station signal strength; the base station signal data set comprises a second training set and a second test set;
and training the base station signal intensity regression model by using the base station signal data set, and determining the parameters of the base station signal intensity regression model.
5. An environment identification system for a cellular network electromagnetic interference system, comprising:
the data acquisition module is used for acquiring detection data of the antenna array and radio frequency data of a base station in the environment; the data acquisition module specifically includes: a transmitting unit, configured to transmit a sounding signal by using a transmitting antenna in the antenna array; the receiving unit is used for receiving the electromagnetic signals returned by the detection signals through receiving antennas in the antenna array; a detection data determination unit for determining the detection data from the electromagnetic signal; the detection data comprises the intensity, phase and time taken for the signal to return of the electromagnetic signal; the receiving unit is further configured to receive a radio frequency signal of a base station in an environment by using a receiving antenna in the antenna array;
the preprocessing module is used for preprocessing the detection data and the radio frequency data;
the environment type identification module is used for identifying the environment type of the detection data by utilizing an environment identification classification model based on the preprocessed detection data; the environment recognition classification model is a neural network model constructed by adopting a machine learning method;
the base station signal intensity identification module is used for identifying the base station signal intensity of the environment where the radio frequency data are located by utilizing a base station signal intensity regression model based on the preprocessed radio frequency data; the base station signal intensity regression model is a neural network model constructed by adopting a machine learning method.
6. The environment recognition system for cellular network electromagnetic interference systems according to claim 5, wherein the preprocessing module specifically comprises:
the detection data preprocessing unit is used for carrying out normalization preprocessing on the detection data to obtain preprocessed detection data;
and the radio frequency data preprocessing unit is used for carrying out normalization preprocessing on the radio frequency data to obtain preprocessed radio frequency data.
7. The environment identification system for a cellular network electromagnetic interference system of claim 5, further comprising:
the environment recognition classification model building module is used for building the environment recognition classification model by adopting a machine learning method before the environment type of the detection data is recognized by utilizing the environment recognition classification model based on the preprocessed detection data; the environment recognition classification model is a neural network model;
the detection data set acquisition module is used for acquiring a detection data set labeled with an environment type; the probing data set comprises a first training set and a first testing set;
and the environment recognition classification model training module is used for training the environment recognition classification model by utilizing the detection data set and determining the parameters of the environment recognition classification model.
8. The environment identification system for a cellular network electromagnetic interference system of claim 5, further comprising:
the base station signal intensity regression model building module is used for building a base station signal intensity regression model by adopting a machine learning method before identifying the base station signal intensity of the environment where the radio frequency data is located by utilizing the base station signal intensity regression model based on the preprocessed radio frequency data; the base station signal intensity regression model is a neural network model;
the base station signal data set acquisition module is used for acquiring a base station signal data set marked with base station signal strength; the base station signal data set comprises a second training set and a second test set;
and the base station signal intensity regression model training module is used for training the base station signal intensity regression model by using the base station signal data set and determining the parameters of the base station signal intensity regression model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010654663.0A CN111835454B (en) | 2020-07-09 | 2020-07-09 | Environment identification method and system for cellular network electromagnetic interference system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010654663.0A CN111835454B (en) | 2020-07-09 | 2020-07-09 | Environment identification method and system for cellular network electromagnetic interference system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111835454A CN111835454A (en) | 2020-10-27 |
| CN111835454B true CN111835454B (en) | 2021-03-19 |
Family
ID=72900873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010654663.0A Active CN111835454B (en) | 2020-07-09 | 2020-07-09 | Environment identification method and system for cellular network electromagnetic interference system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111835454B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107250945A (en) * | 2015-02-12 | 2017-10-13 | 高通股份有限公司 | For detecting the behavioural analysis in the equipment of failure caused by RF is disturbed |
| CN109699002A (en) * | 2018-12-06 | 2019-04-30 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of interior WiFi localization method, device and terminal device |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103051573B (en) * | 2012-12-12 | 2016-07-06 | 锐迪科科技有限公司 | Gsm system disturbs signal cancellation module and its implementation |
| CN103648098B (en) * | 2013-12-28 | 2017-04-12 | 山东闻远通信技术有限公司 | Cooperation method and system between cellular network base station and wireless local area network router |
| CN106211084B (en) * | 2016-09-07 | 2019-07-12 | 中国人民解放军国防科学技术大学 | Environment perception method based on GSM signal |
| CN107171766A (en) * | 2017-07-21 | 2017-09-15 | 中国电子科技集团公司第二十九研究所 | A kind of LTE signal shielding methods and system based on system information |
| CN107682102B (en) * | 2017-11-24 | 2021-02-26 | 成都中星世通电子科技有限公司 | Method for automatically monitoring and identifying interference signal of GSM-R communication system |
| US10805862B2 (en) * | 2018-08-03 | 2020-10-13 | T-Mobile Usa, Inc. | Sensor and self-learning based dynamic frequency assignment for wireless networks |
| CN110944354B (en) * | 2019-11-12 | 2022-10-04 | 广州丰石科技有限公司 | Base station interference monitoring method and system based on waveform analysis and deep learning |
-
2020
- 2020-07-09 CN CN202010654663.0A patent/CN111835454B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107250945A (en) * | 2015-02-12 | 2017-10-13 | 高通股份有限公司 | For detecting the behavioural analysis in the equipment of failure caused by RF is disturbed |
| CN109699002A (en) * | 2018-12-06 | 2019-04-30 | 深圳市中电数通智慧安全科技股份有限公司 | A kind of interior WiFi localization method, device and terminal device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111835454A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105790813B (en) | Code book selection method based on deep learning under a kind of extensive MIMO | |
| CN106959444B (en) | A kind of RFID indoor locating system and method based on artificial neural network | |
| CN112748397B (en) | UWB positioning method based on self-adaptive BP neural network under non-line-of-sight condition | |
| CN111428819B (en) | CSI indoor positioning method based on stacked self-coding network and SVM | |
| CN109379153B (en) | Spectrum sensing method | |
| Huang et al. | An accurate and efficient device-free localization approach based on sparse coding in subspace | |
| CN108038419B (en) | Wi-Fi-based indoor personnel passive detection method | |
| Wang et al. | Multi-classification of UWB signal propagation channels based on one-dimensional wavelet packet analysis and CNN | |
| CN110932807B (en) | Spectrum sensing method and system for MIMO (multiple input multiple output) system under non-Gaussian noise | |
| CN111817803A (en) | Frequency spectrum sensing method and system based on correlation coefficient and K-means clustering algorithm and computer readable storage medium | |
| CN116192307A (en) | Distributed cooperative multi-antenna cooperative spectrum intelligent sensing method, system, equipment and medium under non-Gaussian noise | |
| Mo et al. | A deep learning-based human identification system with wi-fi csi data augmentation | |
| Bastwesy et al. | Deep learning sign language recognition system based on wi-fi csi | |
| CN111835454B (en) | Environment identification method and system for cellular network electromagnetic interference system | |
| CN114915526B (en) | Communication signal modulation identification method, device and system | |
| CN112350790A (en) | Deep learning-based spectrum sensing detection method, device and equipment | |
| Sanam et al. | CoMuTe: A convolutional neural network based device free multiple target localization using CSI | |
| Chen et al. | Deep learning for cooperative spectrum sensing in cognitive radio | |
| Wang et al. | Indoor fingerprinting localization based on fine-grained CSI using principal component analysis | |
| Wang et al. | Deep convolutional auto-encoder based indoor light positioning using RSS temporal image | |
| CN113642457B (en) | Cross-scene human body action recognition method based on antagonistic meta-learning | |
| CN115002703A (en) | Passive indoor people number detection method based on Wi-Fi channel state information | |
| Gu et al. | Radio frequency fingerprinting driven drone identification based on complex-valued CNN | |
| Agarwal et al. | Hardware implementation of k-means clustering based spectrum sensing using usrp in a cognitive radio system | |
| Pu et al. | Primary user emulation detection algorithm based on distributed sensor networks |
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 |