CN112329568A - Radiation source signal generation method and device and storage medium - Google Patents
Radiation source signal generation method and device and storage medium Download PDFInfo
- Publication number
- CN112329568A CN112329568A CN202011160560.5A CN202011160560A CN112329568A CN 112329568 A CN112329568 A CN 112329568A CN 202011160560 A CN202011160560 A CN 202011160560A CN 112329568 A CN112329568 A CN 112329568A
- Authority
- CN
- China
- Prior art keywords
- radiation source
- discriminator
- generator
- source signal
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005855 radiation Effects 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 title claims abstract description 13
- 238000012549 training Methods 0.000 claims abstract description 32
- 230000006870 function Effects 0.000 claims description 25
- 238000011478 gradient descent method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004891 communication Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000013135 deep learning Methods 0.000 description 5
- 210000002569 neuron Anatomy 0.000 description 5
- 238000004088 simulation Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The application discloses a radiation source signal generation method, a radiation source signal generation device and a storage medium, relates to the technical field of radar communication, and solves the problem that in the prior art, a sample set is small in radar radiation source identification. The method comprises the following steps: constructing an initial one-dimensional generation type confrontation network, wherein the initial one-dimensional generation type confrontation network comprises a generator and a discriminator; training the initial generation type countermeasure network to obtain an available generation type countermeasure network; generating a group of radar radiation source signal samples according to the available generative countermeasure network; according to the method, a radiation source signal generation method is adopted, and the effect of enlarging a radar radiation source identification sample set is achieved.
Description
Technical Field
The present application relates to the field of radar communication technologies, and in particular, to a method and an apparatus for generating a radiation source signal, and a storage medium.
Background
The identification of the radiation source signal is an important component in radar electronic countermeasure, and the radar radiation source identification is to compare the characteristic parameters of the radar signal obtained by radar detection with the technical performance of a radar all the time, further to identify the type of the radar transmitting the signal in real time, and to determine the application, carrier, threat level and identification reliability of the radar.
At present, the identification of radiation source signals mainly depends on the supervised learning in the deep learning of massive data set samples, and the methods have good effects under certain conditions.
However, in practical situations, a large amount of data set samples are very difficult to obtain in practical application environments, and in practical application environments, the sample sampling becomes a difficult process due to the non-cooperative nature of electronic reconnaissance, so that the radar radiation source identification based on deep learning is converted into a radiation source signal sample set small problem.
Disclosure of Invention
The embodiment of the application solves the problem that a radiation source signal sample set is small in radar radiation source identification in the prior art by providing a radiation source signal generation method, a radiation source signal generation device and a storage medium.
In a first aspect, an embodiment of the present invention provides a radiation source signal generation method, including:
constructing an initial one-dimensional generation type confrontation network, wherein the initial one-dimensional generation type confrontation network comprises a generator and a discriminator;
training the initial generative confrontation network to obtain an available generative confrontation network;
generating a set of radar radiation source signal samples according to the available generative countermeasure network.
With reference to the first aspect, in a possible implementation manner, the training the initially generated countermeasure network includes:
constructing an original signal set;
selecting a random sequence in a preset interval to obtain a randomly generated signal set;
fixing the generator parameters, inputting the original signal set and the randomly generated signal set into a discriminator, and training the discriminator;
fixing the description of the discriminator, inputting the randomly generated signal set into a generator, and training the generator;
and judging whether the output of the discriminator is a preset value or not, and if not, repeatedly executing the three steps.
With reference to the first aspect, in a possible implementation manner, the training the discriminator includes: optimizing a cost function of the discriminator using a gradient ascent method.
With reference to the first aspect, in one possible implementation manner, the gradient ascent method formula is as follows:
wherein theta isdRepresents a network parameter in the discriminator, η represents a learning rate,
representing the gradient calculation;
with reference to the first aspect, in a possible implementation manner, the training the generator includes: the loss function of the generator is optimized using a gradient descent method.
With reference to the first aspect, in one possible implementation manner, the gradient descent method is as follows:
wherein theta isgRepresents a network parameter in the discriminator, η represents a learning rate,
the gradient is indicated.
With reference to the first aspect, in one possible implementation manner, the generating a set of radar radiation source signal samples according to the available generative countermeasure network includes:
and inputting random sequences which are uniformly distributed in a plurality of preset intervals into the generator which is trained to obtain a group of radar radiation source signal samples.
In a second aspect, an embodiment of the present invention provides an apparatus for generating a radiation source signal, including:
constructing a module: the system comprises a generator and a discriminator, wherein the generator is used for generating an initial one-dimensional generative confrontation network;
the training module is used for training the initial generative confrontation network to obtain an available generative confrontation network;
and the output module is used for generating a group of radar radiation source signal samples according to the available generative countermeasure network.
In a third aspect, an embodiment of the present invention provides an apparatus for generating a radiation source signal, including a memory and a processor;
the memory is to store computer-executable instructions;
the processor is configured to execute the computer-executable instructions to implement the method of the first aspect and various implementations of the first aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where the computer-readable storage medium stores executable instructions, and the computer can implement the executable instructions when executing the executable instructions, so as to implement the method according to the first aspect and various implementation manners of the first aspect.
The technical solutions provided in the embodiments of the present invention at least have the following technical effects or advantages:
the embodiment of the invention provides a method for generating a radiation source signal, which comprises the following steps: constructing an initial one-dimensional generation type countermeasure network; training the initial generation type countermeasure network to obtain an available generation type countermeasure network; a set of radar radiation source signal samples is generated according to the available generative countermeasure network. The problem that a sample set is small in radar radiation source identification in the prior art is effectively solved, and the radar radiation source identification sample set is enlarged.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for generating a radiation source signal according to an embodiment of the present disclosure;
fig. 2 is a specific flowchart for training an initially generated countermeasure network in the method for generating a radiation source signal according to the embodiment of the present application;
FIG. 3 is a diagram comparing a generated signal and an original signal of five signals provided by an embodiment of the present application;
FIG. 4 is a schematic diagram of an apparatus for generating a radiation source signal according to an embodiment of the present disclosure;
fig. 5 is a schematic physical device diagram of a radiation source signal generation method according to an embodiment of the present application.
Detailed Description
The technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all 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.
The identification of radar radiation source information in modern society is an important component in radar electronic countermeasure, and plays an important role in electronic support and threat warning systems. Radar radiation source information identification is one of the important functions of Electronic Support Measures (ESM) and intelligence detection, and is used for intercepting, positioning, analyzing and identifying radar signals. In recent years, with the development of artificial intelligence technology, deep learning technology is also used in radar radiation source identification. In the prior art, good effects are achieved under certain conditions, but a common limitation is that the dependence on massive data set samples is very large, and supervised learning in deep learning needs a large number of samples as supports, which is very difficult to realize in an actual application environment. In practical application environments, the non-cooperative nature of electronic reconnaissance makes sample acquisition a difficult process, which translates deep learning-based radar radiation source identification into a radiation source signal sample set small problem.
The present application provides a radiation source signal generating method, the basic steps of which are shown in fig. 1.
Step S101: and constructing an initial one-dimensional generation type countermeasure network, wherein the initial one-dimensional generation type countermeasure network comprises a generator and an arbiter.
Step S102: training the initial generative confrontation network to obtain the usable generative confrontation network.
Step S103: a set of radar radiation source signal samples is generated according to the available generative countermeasure network.
Specifically, in step S101, the generator includes seven layers of deep neural networks, and each of the 7 layers of deep neural networks is an input layer including 100 neurons, a one-dimensional convolutional layer having 128 convolutional cores, a one-dimensional convolutional layer having 64 convolutional cores, a one-dimensional convolutional layer having 32 convolutional cores, a one-dimensional convolutional layer having one convolutional core, a fully-connected layer having 1024 neurons, and an output layer having 600 neurons. The discriminator comprises six layers of deep neural networks, wherein the 6 layers of deep neural networks are respectively a one-dimensional convolutional layer with 32 convolutional cores, a one-dimensional convolutional layer with 64 convolutional cores, a one-dimensional convolutional layer with 128 convolutional cores, a full-connection layer consisting of 1024 neurons and an output layer consisting of one neuron. The method effectively solves the problem that the sample set is small in radar radiation source identification in the prior art, and enlarges the radar radiation source identification sample set.
Of course, the specific configuration of the generator and the discriminator is not limited to the above, and may include a neural network having another number of layers, a one-dimensional convolution layer having another number of convolution kernels, and the like.
In this embodiment, through step S101 to step S103, the problem that a sample set is small in radar radiation source identification in the prior art is effectively solved, and a radar radiation source identification sample set is enlarged.
As shown in fig. 2, specifically, training the initially generated countermeasure network in step 102 includes the following steps.
Step S201: an original signal set is constructed.
Step S202: and selecting a random sequence in a preset interval to obtain a randomly generated signal set.
Step S203: and fixing generator parameters, inputting the original signal set and the randomly generated signal set into a discriminator, and training the discriminator.
Step S204: fixing the parameters of the discriminator, inputting the randomly generated signal set into a generator and training the generator.
Step S205: and judging whether the output of the discriminator is a preset value or not, and if not, repeatedly executing the three steps.
In step S201, specifically, the existing radiation source signals are put into a set, which is called an original signal set, in this embodiment, a preset interval [ -1,1] is selected, in this interval, a random sequence is selected to obtain a randomly generated signal set, the original signal set and the randomly generated signal set are input into a discriminator, and parameters of the generator are fixed first, and the discriminator is trained.
The preset interval of the random sequence can be selected according to the actual situation, is not limited by [ -1,1], and the specific interval is selected when the actual situation requires.
The value formula of the discriminator is:
in the above formula, V: cost function to optimize, D: discriminator, G: generator, x: original signal sample set, z: random sequence, Pdata(x) The method comprises the following steps Original signal sample distribution probability, Pz(z): a probability distribution of the data is generated.
In the above formula of the value of the discriminator, when Pg＝PdataAn optimal generator is obtained when the probability of distribution of the original signal is, and only when it is, equal to the probability of distribution of the generated data. If we need to compute the maximization process, an equivalent training method can be used. If we have a binary classifier D (with the parameter θ _ D), which of course could be a deep neural network, then the output of the maximization process is that classificationDevice D (x). We now extract samples from P _ data (x) as positive samples, samples from P _ G (x) as negative samples, and a function approximating negative V (D, G) as a loss function, and we therefore describe this as a training process for a standard binary classifier. The maximum value of the integration can be converted into the maximum value of the integrand, and the maximum value of the integrand is calculated in the embodiment to find the optimal discriminator D, so that terms not related to the discriminator can be regarded as constant terms. The integrand can thus be expressed as:
a*D(x)+b*log(1-D(x))，
converting this problem into a mathematical problem, i.e. let d (x) be y in the discriminator, the integrand can be written as:
f(y)＝a log y+b log(1-y)，
when a + b is not equal to 0, firstly solving a first derivative of the formula to obtain
Then, the second derivative is obtained
Wherein a, b ∈ (0, 1).
From the two derivation processes we can get the first derivative equal to 0; the second derivative is less than 0, namely the method can obtain
Is a maximum value. Substituting the original a ═ P _ data (x) and b ═ P _ g (x) into the maximum value for expression, the value function of the discriminator is obtained as:
let D (x) be P _ data/(P _ data + P _ G), we can make the cost function V (G, D) take the maximum value. Because f (y) has a unique maximum within the defined domain, the optimal D is also unique, and no other D can achieve a maximum.
The loss function of the generator is as follows:
in the above formula, min: minimum, V: cost function to optimize, D: discriminator, G: generator, x: raw data, Z: random sequence, Pdata(x) The method comprises the following steps Probability distribution of raw data, Pg(z): distribution probability of generated data, KL: KL divergence.
And when the parameters of the discriminator are fixed, inputting the randomly generated signal set into a generator, and training the generator.
In this embodiment, the preset value output by the discriminator may be set to 0.5, and when the output value of the discriminator is 0.5, the generated radiation source signal is output, and if the output value is not equal to the preset value of 0.5, the three steps, i.e., step S202, step S203, and step S204, are repeatedly executed.
Certainly, the preset value output by the discriminator is not limited to 0.5, and may be selected according to the actual situation, for example, when the actual situation requires, the preset value output by the discriminator may be selected to be 0.6.
Specifically, the training of the arbiter in step S203 includes: the cost function of the discriminator is optimized using a gradient ascent method. One way to find the maximum value of the cost function of the arbiter is to look along the gradient direction of the cost function of the arbiter, the gradient operator always pointing in the direction where the function value decreases the fastest.
The gradient ascent method formula is as follows:
wherein theta isdRepresents a network parameter in the discriminator, η represents a learning rate,
indicating the gradient. Using the gradient ascent method, the maximum value of the discriminator cost function can be found.
Specifically, the training generator in step S204 includes: the loss function of the generator is optimized using a gradient descent method. One way to find the minimum of the loss function of the generator is to look along the gradient of the loss function of the generator, the gradient operator always pointing in the direction where the function value increases the fastest.
The gradient descent method formula is as follows:
wherein theta isgRepresents a network parameter in the discriminator, η represents a learning rate,
the gradient is indicated. Using the gradient descent method, the minimum of the generator loss function can be found.
Step S103, generating a group of radar radiation source signal samples according to the available generative countermeasure network, and the method comprises the following steps: and inputting random sequences uniformly distributed in a plurality of preset intervals into a generator after training to obtain a group of radar radiation source signal samples.
For example, a random sequence evenly distributed among a plurality of [ -1,1] can be input into a generator in the generation countermeasure network to generate a plurality of radar radiation source signals. By this method, a large number of radar radiation source signals can be obtained. Of course, the preset interval can be selected according to the actual situation, and is not limited to [ -1,1], and can also be selected to [ -2,2] and the like when the actual situation requires.
When the application is simulated, the hardware platform used in the simulation experiment of the embodiment of the present invention may be: intel (R) core (TM) i9CPU, memory 64G. The software platform and the open source library of the simulation experiment of the invention are as follows: MATLAB, TensorFlow, Keras. In this embodiment, the radar signals used in the simulation experiment are generated by an MATLAB software platform, and the simulation experiment uses original signal sets generated by five signals, where each original signal set has 100 signal samples. One-dimensional signal generation frameworks were constructed using Tensorflow and Keras, and generation of signals was performed using the constructed on-site countermeasure networks, each signal generating 10000 signals. Fig. 3 shows a comparison of the original sample signal and the generated signal. It can be seen that the use of the constructed generative countermeasure network can generate a radar radiation source signal with an output of the discriminator equal to or greater than 0.5. I.e. the trained generator is already able to generate the required radar radiation source signal, a large number of radar radiation source signals can be obtained by the trained generator. The problem of sample set is little in the radar radiation source discernment among the prior art is solved, the problem that it is less to have realized enlarging radar radiation source discernment sample set.
Although the present application provides method steps as described in an embodiment or flowchart, additional or fewer steps may be included based on conventional or non-inventive efforts. The sequence of steps recited in this embodiment is only one of many steps performed and does not represent a unique order of execution. When an actual apparatus or client product executes, it can execute sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the methods shown in this embodiment or the figures.
The embodiment of the present invention further provides an apparatus for generating a radiation source signal, which includes a building module 400, a training module 410, and an output module 420, as shown in fig. 4. The construction module 400 is used to construct an initial one-dimensional generative confrontation network, which includes a generator and an arbiter. The training module 410 is used for training the initial generative confrontation network to obtain an available generative confrontation network; the output module 420 is configured to generate a set of radar radiation source signal samples according to the available generative countermeasure network.
The apparatuses or modules illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. The functionality of the modules may be implemented in the same one or more software and/or hardware implementations of the present application. Of course, a module that implements a certain function may be implemented by a plurality of sub-modules or sub-units in combination.
The embodiment of the present application further provides an apparatus for generating a radiation source signal, which, as shown in fig. 5, from a hardware structure, includes a memory 500 and a processor 510; the memory 500 is used to store computer executable instructions; the processor 510 is configured to execute the computer-executable instructions to implement the radiation source signal generation method provided by the present embodiment. The device can solve the problem that a sample set is small in radar radiation source identification in the prior art, and the problem that the radar radiation source identification sample set is small is enlarged.
The embodiment of the present application further provides a computer-readable storage medium, where executable instructions are stored in the computer-readable storage medium, and when the computer executes the executable instructions, the method for generating a radiation source signal provided by the present embodiment can be implemented.
The storage medium includes, but is not limited to, a Random Access Memory (RAM), a Read-Only Memory (ROM), a Cache, a Hard Disk (Hard Disk Drive), or a Memory Card (HDD).
From the above description of the embodiments, it is clear to those skilled in the art that the present application can be implemented by software plus necessary hardware. Based on such understanding, the technical solutions of the present application may be embodied in the form of software products or in the implementation process of data migration, which essentially or partially contributes to the prior art. The computer software product may be stored in a storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, mobile terminal, server, or network device, etc.) to perform the methods described in the various embodiments or portions of the embodiments of the present application.
The embodiments in the present specification are described in a progressive manner, and the same or similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. All or portions of the present application are operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, mobile communication terminals, multiprocessor systems, microprocessor-based systems, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications or substitutions do not depart from the spirit and scope of the present disclosure.
Claims (10)
1. A radiation source signal generating method, comprising:
constructing an initial one-dimensional generation type confrontation network, wherein the initial one-dimensional generation type confrontation network comprises a generator and a discriminator;
training the initial generative confrontation network to obtain an available generative confrontation network;
generating a set of radar radiation source signal samples according to the available generative countermeasure network.
2. The method of claim 1, wherein training the initially generated counterpoise network comprises:
constructing an original signal set;
selecting a random sequence in a preset interval to obtain a randomly generated signal set;
fixing the generator parameters, inputting the original signal set and the randomly generated signal set into the discriminator, and training the discriminator;
fixing the discriminator parameters, inputting the randomly generated signal set into the generator, and training the generator;
and judging whether the output of the discriminator is a preset value or not, and if not, repeatedly executing the three steps.
3. The method of claim 2, wherein the training the arbiter comprises: optimizing a cost function of the discriminator using a gradient ascent method.
4. The method of claim 3, wherein the gradient ascent method is formulated as follows:
wherein theta isdRepresents a network parameter in the discriminator, η represents a learning rate,
indicating the gradient.
5. The method of any of claims 2-4, wherein training the generator comprises: the loss function of the generator is optimized using a gradient descent method.
6. The method of claim 5, wherein the gradient descent method is formulated as follows:
wherein theta isgRepresents a network parameter in the discriminator, η represents a learning rate,
the gradient is indicated.
7. The method of claim 1, wherein generating a set of radar radiator signal samples from the available generative countermeasure network comprises:
and inputting random sequences which are uniformly distributed in a plurality of preset intervals into the generator which is trained to obtain a group of radar radiation source signal samples.
8. An apparatus for radiation source signal generation, comprising:
constructing a module: the system comprises a generator and a discriminator, wherein the generator is used for generating an initial one-dimensional generative confrontation network;
a training module: the system is used for training the initial generative confrontation network to obtain an available generative confrontation network;
an output module: for generating a set of radar radiation source signal samples in accordance with the available generative countermeasure network.
9. An apparatus for radiation source signal generation comprising a memory and a processor;
the memory is to store computer-executable instructions;
the processor is configured to execute the computer-executable instructions to implement the method of any of claims 1-7.
10. A computer-readable storage medium having stored thereon executable instructions that, when executed by a computer, are capable of implementing the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011160560.5A CN112329568A (en) | 2020-10-27 | 2020-10-27 | Radiation source signal generation method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011160560.5A CN112329568A (en) | 2020-10-27 | 2020-10-27 | Radiation source signal generation method and device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112329568A true CN112329568A (en) | 2021-02-05 |
Family
ID=74312375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011160560.5A Pending CN112329568A (en) | 2020-10-27 | 2020-10-27 | Radiation source signal generation method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329568A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492764A (en) * | 2018-10-24 | 2019-03-19 | 平安科技（深圳）有限公司 | Training method, relevant device and the medium of production confrontation network |
| CN109523493A (en) * | 2017-09-18 | 2019-03-26 | 杭州海康威视数字技术股份有限公司 | A kind of image generating method, device and electronic equipment |
| CN111582348A (en) * | 2020-04-29 | 2020-08-25 | 武汉轻工大学 | Method, device, equipment and storage medium for training condition generating type countermeasure network |
| CN111814393A (en) * | 2020-06-29 | 2020-10-23 | 哈尔滨工业大学 | APU (auxiliary Power Unit) degradation parameter generation method based on generation countermeasure network |
-
2020
- 2020-10-27 CN CN202011160560.5A patent/CN112329568A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109523493A (en) * | 2017-09-18 | 2019-03-26 | 杭州海康威视数字技术股份有限公司 | A kind of image generating method, device and electronic equipment |
| CN109492764A (en) * | 2018-10-24 | 2019-03-19 | 平安科技（深圳）有限公司 | Training method, relevant device and the medium of production confrontation network |
| CN111582348A (en) * | 2020-04-29 | 2020-08-25 | 武汉轻工大学 | Method, device, equipment and storage medium for training condition generating type countermeasure network |
| CN111814393A (en) * | 2020-06-29 | 2020-10-23 | 哈尔滨工业大学 | APU (auxiliary Power Unit) degradation parameter generation method based on generation countermeasure network |
Non-Patent Citations (2)
| Title |
|---|
| 朱克凡等: "基于GAN的半监督低分辨雷达目标识别算法", 《探测与控制学报》 * |
| 李昆等: "基于MDGAN网络的数据集扩增方法", 《雷达科学与技术》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084365B (en) | Service providing system and method based on deep learning | |
| US11038913B2 (en) | Providing context associated with a potential security issue for an analyst | |
| US11025649B1 (en) | Systems and methods for malware classification | |
| CN105989288A (en) | Deep learning-based malicious code sample classification method and system | |
| US20190205094A1 (en) | Mixed-precision processing elements, systems, and methods for computational models | |
| US11625583B2 (en) | Quality monitoring and hidden quantization in artificial neural network computations | |
| CN115563610B (en) | Training method, recognition method and device for intrusion detection model | |
| EP3803580B1 (en) | Efficient incident management in large scale computer systems | |
| Dong et al. | Multi‐task learning method for classification of multiple power quality disturbances | |
| CN113486302A (en) | Data processing method and device | |
| US11068784B2 (en) | Generic quantization of artificial neural networks | |
| CN111967584A (en) | Method, device, electronic equipment and computer storage medium for generating countermeasure sample | |
| CN112329568A (en) | Radiation source signal generation method and device and storage medium | |
| CN116232694A (en) | Lightweight network intrusion detection method and device, electronic equipment and storage medium | |
| CN115589339A (en) | Network attack type identification method, device, equipment and storage medium | |
| ALI et al. | A Novel Leader Election Algorithm for Honeycomb Mesh Networks | |
| CN113934813A (en) | Method, system and equipment for dividing sample data and readable storage medium | |
| Arango‐López et al. | Cloud‐based deep learning architecture for DDoS cyber attack prediction | |
| Ji et al. | An adaptive radial basis function method using weighted improvement | |
| CN116541252B (en) | Computer room fault log data processing method and device | |
| Dunaev et al. | Logs analysis to search for anomalies in the functioning of large technology platforms | |
| Hasanaj et al. | Cooperative edge deepfake detection | |
| Na et al. | A Model Based on GCN and TCN for Malicious Code Detection in Power Information System | |
| CN118018260A (en) | Network attack detection method, system, equipment and medium | |
| Oleiwi et al. | A Meta-Model to Predict and Detect Malicious Activities in 6G-Structured Wireless Communication Networks. Electronics 2023, 12, 643 |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210205 |