CN110222748B - OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion - Google Patents
OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion Download PDFInfo
- Publication number
- CN110222748B CN110222748B CN201910446014.9A CN201910446014A CN110222748B CN 110222748 B CN110222748 B CN 110222748B CN 201910446014 A CN201910446014 A CN 201910446014A CN 110222748 B CN110222748 B CN 110222748B
- Authority
- CN
- China
- Prior art keywords
- radar signal
- layer
- ofdm radar
- ofdm
- network structure
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Electromagnetism (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses an OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion, which comprises the following specific steps: 1. performing feature learning on the OFDM radar signal by adopting a two-path one-dimensional convolutional neural network structure, and respectively learning time domain and frequency domain features of the OFDM radar signal; 2. fusing the OFDM radar signal characteristics learned by the time domain characteristic network structure and the frequency domain characteristic network structure to form a multi-domain characteristic fusion network structure; 3. inputting an OFDM radar signal data set into a multi-domain feature fusion network structure for model training, and obtaining a radar signal classification model through training; 4. implanting the radar signal classification model obtained by training in the step 3 into an industrial control computer, and realizing the identification of the OFDM radar signal modulation mode of the real environment through the model; the method is more beneficial to quickly learning the deep-level characteristics of the characterization signals, and has better identification effect on the OFDM radar signal modulation mode.
Description
Technical Field
The invention belongs to the field of radar identification, and particularly relates to an OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion.
Background
Due to the development of radio technology, more and more novel modulated radar signals appear in an electromagnetic environment, and a new system radar radiation source has the characteristics of low interception performance, strong anti-interference capability and the like, and is frequently used in electronic combat. Orthogonal Frequency Division Multiplexing (OFDM) radar signals have outstanding advantages as a new system radar: flexible waveform design, high distance resolution, good measurement accuracy, good clutter rejection capability, low interception capability and the like. Nowadays, with increasingly complex informatization battlefield, OFDM radar signals are widely used in radar systems, but electronic reconnaissance of OFDM radar signals is difficult, so that it is of great significance to realize modulation and identification of OFDM radar signals. In an electronic investigation environment, identification of OFDM radar signals requires not only identifying whether the signals belong to an OFDM radar system, but also identifying which modulation mode the OFDM radar signals belong to.
Generally, a convolutional neural network is adopted to identify OFDM radar signals, a two-dimensional convolutional neural network is used for learning time-frequency domain characteristics of the OFDM radar signals and a one-dimensional convolutional neural network is used for learning characteristics of the OFDM radar signals, the two-dimensional convolutional neural network needs to perform time-frequency transformation on the radar signals when learning the characteristics of the OFDM radar signals, network parameters are relatively more, accordingly, the requirement on hardware configuration of a training computer is high, and a large amount of time can be consumed in the preprocessing and training processes. The one-dimensional convolutional neural network cannot sufficiently learn the characteristics of the OFDM radar signal, and the OFDM radar signal is difficult to accurately identify under the condition of complex noise.
Disclosure of Invention
In order to solve the technical problem, the invention provides an OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion, which specifically comprises the following steps:
step 1: and (3) performing feature learning on the OFDN radar signals by adopting two paths of one-dimensional convolutional neural network structures, and respectively learning the time domain and frequency domain features of the OFDM radar signals.
Step 2: and fusing the OFDM radar signal characteristics learned by the time domain characteristic network structure and the frequency domain characteristic network structure to form a multi-domain characteristic fusion network structure.
And step 3: and inputting the OFDM radar signal data set into a multi-domain feature fusion network structure for model training, and obtaining a radar signal classification model through training.
And 4, step 4: and (3) implanting the radar signal classification model obtained by training in the step (3) into an industrial control computer, and realizing the identification of the OFDM radar signal modulation mode of the real environment through the model.
Further, the network structure for learning the time domain characteristics in step 1 is specifically: input layer, convolutional layer, pooling layer, convolutional layer, globalagepoiling 1D, full connection layer, dropout. The network structure for learning the frequency domain features specifically comprises: input layer, lambda, convolutional layer, pooling layer, convolutional layer, globalaveragePooling1D, fully connected layer, dropout. Wherein the Lambda layer is a defined Fourier transform layer; the Dropout layer is to prevent overfitting of the network.
Further, in step 2, the time domain feature and the frequency domain feature are fused in a way of adding through an Add layer; and then connecting the full connection layer, the Dropout layer and the output layer to form the multi-domain feature fusion network structure.
Further, the OFDM radar signal includes Phase Shift Keying (PSK) OFDM radar signal (PSK-OFDM), linear Frequency Modulation (LFM) OFDM radar signal (LFM-OFDM), and Multi-segment Linear Frequency Modulation (MLFM-OFDM).
Compared with the prior art, the invention has the beneficial technical effects that:
the convergence speed of the 1D-CNN network structure is faster than that of the 2D-CNN network structure, the two-dimensional network needs more time for processing the one-dimensional data converted into the two-dimensional data, the one-dimensional network only needs to perform Fourier transform on the data once, and the time needed by the one-dimensional network is far shorter than that needed by the two-dimensional network; when the two-dimensional network is adopted, more parameters can be generated, the requirement on a platform of the training network is far higher than that of the one-dimensional network, the batch processing size of the training platform with the same configuration is larger than that of the two-dimensional network, and the deep level characteristics of the representation signals can be learned more conveniently and rapidly. Meanwhile, when the OFDM radar signal modulation mode is identified, a good identification effect is obtained.
Drawings
Fig. 1 is a schematic diagram of a multi-domain feature fusion network structure according to the present invention.
Fig. 2 is a graph of the success rate of the invention for identifying three radar signals.
Detailed Description
The invention is described in further detail below with reference to the drawings and the detailed description.
The method includes the basic idea that radar data professional acquisition equipment is installed in a complex and dense electromagnetic environment, OFDM radar time domain signals are acquired in real time, the acquired OFDM radar time domain signals are subjected to (Convolutional Neural Networks, CNN) Convolutional Neural network learning to obtain a classification model, in an OFDM radar signal identification system, time domain and frequency domain feature learning is carried out on the signals through a designed network structure to obtain the classification model, and a test data set is used for predicting on a trained model to obtain an identification result. Because the main modulation characteristics of the OFDM radar signal show obvious difference in a frequency domain and a time domain, the network structure for learning the characteristics of the OFDM radar signal by adopting two paths of training has better recognition effect.
The method comprises the following steps:
step 1: according to the characteristic that a convolutional neural network is adopted to identify radar signals at present, two paths of one-dimensional convolutional neural network structures are adopted to carry out feature learning on OFDN radar signals, and time domain and frequency domain features of the OFDM radar signals are learned respectively. The training round is set to be 50 times in the experiment of the invention, and the batch size is set to be 64. The modulation identification of the OFDM radar signal mainly comprises three types, namely: phase Shift Keying (PSK) OFDM radar signals (PSK-OFDM), linear Frequency Modulation (LFM) OFDM radar signals (LFM-OFDM), and segmented Linear Frequency Modulation (MLFM-OFDM) OFDM radar signals (MLFM-OFDM).
The network structure for learning the time domain features specifically comprises: input layer, convolutional layer, pooling layer, convolutional layer, globalavogePooling 1D, full-link layer, dropout. Comprises two convolution layers, two pooling layers and a full-link layer, and 5 learning layers. The fully connected tier output dimension is 64 x 256.
The network structure for learning the frequency domain features specifically comprises: input layer, lambda, convolutional layer, pooling layer, convolutional layer, globalaveragePooling1D, full connection layer, dropout, where Lambda layer is the defined Fourier transform layer. Comprises two convolution layers, two pooling layers, a full-connection layer and a self-defining layer, and 6 learning layers. The fully connected tier output dimension is 64 x 256.
The feature learning steps are described as follows:
the essence of the process of learning the characteristics is that the process of learning the characteristics consists of forward propagation and backward propagation, the essence of the backward propagation in the training process is to calculate the gradient of a loss function, and network parameters are corrected according to the error between an actual output value and an ideal output value. The error is defined as
Wherein E n An error value representing the nth sample is calculated,
represents the current output value of the neuron,
is the true tag value of the current sample.
The forward propagation formula is
Wherein
A kth feature matrix representing the l-th layer,
represents the weight between the ith feature matrix of the l-1 layer and the kth feature matrix of the l layer,
offset term, N, of the kth feature matrix representing the l layer l+1 The number of neurons in the output layer is the adjustment direction of the weight and the bias term
Wherein
Representing the residuals of the kth feature matrix at layer l.
The back propagation calculation formula is
Wherein
Representing the kth feature matrix representing the l-th layer,
indicating that the convolution kernel is inverted by 180 degrees, conv1Dz (·) is a full convolution operation. The weight and bias term are calculated according to the formula
Step 2: and fusing the OFDM radar signal characteristics learned by the time domain characteristic network structure and the frequency domain characteristic network structure to form a multi-domain characteristic fusion network structure. The fusion mode is that addition is carried out through an Add layer, and the output dimension after fusion is 64 × 256. And after fusion, connecting the full connection layer, the Dropout and the output layer. The output dimension of the fully-connected layer is 64 x 3 (64 is the number of samples of the signal, 3 is the number of classes of the signal, and there are PSK-OFDM radar signal, LFM-OFDM radar signal and MLFM-OFDM radar signal class 3).
In the designed multi-domain feature fusion network structure, the number of learning layers of a time domain feature learning structure is 5, the number of learning layers of a frequency domain feature learning structure is 6, and the total number of the learning layers is 13 after the fusion, wherein the specific structure is shown in fig. 1.
And step 3: and inputting a large number of OFDM radar signal data sets serving as sample data into the multi-domain fusion network for model training. The learning rate is automatically adjusted through an optimizer Adadelta function provided under a keras frame, the training round is set to be 50 times in the implementation, and the batch size is set to be 64. When the signal-to-noise ratio is changed at intervals of 2dB in the range of-10 dB to 10dB, 2000 samples are generated under each signal-to-noise ratio, wherein the number of samples in a training set is 1600, the number of samples in a test set is 400, and the samples respectively comprise 3 types of PSK-OFDM radar signals, LFM-OFDM radar signals and MLFM-OFDM radar signals. The radar signal is subjected to feature learning by adopting the one-dimensional convolutional neural network, the training speed and the convergence speed are very high, and a radar signal classification model is obtained through training. The result when the signal-to-noise ratio is selected as-6 dB is specifically explained as follows: the 3 types of radar signals generate 2000 samples in total, the length of the generated signals is set to be 2048, the OFDM radar time domain signals are subjected to data characteristic learning through a 1D-CNN network structure, so that the OFDM radar signal modulation mode is identified, and the final identification rate can reach 93%. The recognition success rate curve is shown in fig. 2. It can be seen that when the signal-to-noise ratio exceeds-2 dB, the identification rate of the OFDM radar signal basically reaches 100%.
And 4, step 4: and (3) implanting the radar signal classification model obtained by training in the step (3) into an industrial control computer, and realizing the identification of the OFDM radar signal modulation mode of the real environment through the model. And outputting the test result and making a report.
Claims (4)
1. An OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion is characterized by comprising the following steps:
step 1: performing feature learning on the OFDN radar signal by adopting two paths of one-dimensional convolutional neural network structures, and respectively learning time domain and frequency domain features of the OFDM radar signal;
the network structure for learning the time domain features specifically comprises: an input layer, a convolutional layer, a pooling layer, a convolutional layer, a globalagepoiling 1D, a full connection layer, and Dropout; the network structure for learning the frequency domain features specifically comprises: an input layer, lambda, a convolutional layer, a pooling layer, a convolutional layer, globalaveragePooling1D, a full-link layer, dropout; the Lambda layer is a defined Fourier transform layer;
step 2: fusing the OFDM radar signal characteristics learned by the time domain characteristic network structure and the frequency domain characteristic network structure to form a multi-domain characteristic fusion network structure;
and 3, step 3: inputting an OFDM radar signal data set into a multi-domain feature fusion network structure for model training, and obtaining a radar signal classification model through training;
and 4, step 4: and (3) implanting the radar signal classification model obtained by training in the step (3) into an industrial control computer, and realizing the identification of the OFDM radar signal modulation mode of the real environment through the model.
2. The method for identifying the OFDM radar signal based on the 1D-CNN multi-domain feature fusion according to claim 1, wherein the step 2 specifically comprises: fusing the time domain characteristics and the frequency domain characteristics in a mode of adding through an Add layer; the full connection layer, dropout, output layer are then connected.
3. The method for identifying the OFDM radar signal based on the 1D-CNN multi-domain feature fusion as claimed in claim 1 or 2, wherein the Dropout layer is to prevent overfitting of the network.
4. The method for identifying the OFDM radar signal based on the 1D-CNN multi-domain feature fusion, according to claim 1, wherein the OFDM radar signal includes three types, namely PSK-OFDM radar signal, LFM-OFDM radar signal and MLFM-OFDM radar signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910446014.9A CN110222748B (en) | 2019-05-27 | 2019-05-27 | OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910446014.9A CN110222748B (en) | 2019-05-27 | 2019-05-27 | OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110222748A CN110222748A (en) | 2019-09-10 |
| CN110222748B true CN110222748B (en) | 2022-12-20 |
Family
ID=67818418
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910446014.9A Active CN110222748B (en) | 2019-05-27 | 2019-05-27 | OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110222748B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110569928B (en) * | 2019-09-23 | 2023-04-07 | 深圳大学 | Micro Doppler radar human body action classification method of convolutional neural network |
| CN110825852B (en) * | 2019-11-07 | 2022-06-14 | 四川长虹电器股份有限公司 | Long text-oriented semantic matching method and system |
| CN110826630B (en) * | 2019-11-08 | 2022-07-15 | 哈尔滨工业大学 | Radar interference signal feature level fusion identification method based on deep convolutional neural network |
| CN111652040A (en) * | 2020-04-14 | 2020-09-11 | 广西万云科技有限公司 | Method and system for recognizing human body activity based on radio frequency and signal self-adaptive convolutional neural network |
| CN111624570B (en) * | 2020-04-30 | 2023-09-26 | 南京理工大学 | Radar target identification method based on two-dimensional convolutional neural network |
| CN114070684B (en) * | 2020-08-05 | 2024-02-09 | 西南交通大学 | Modulation signal identification method based on two-dimensional convolutional neural network |
| CN112287784B (en) * | 2020-10-20 | 2022-05-31 | 哈尔滨工程大学 | Radar signal classification method based on deep convolutional neural network and feature fusion |
| CN112308133A (en) * | 2020-10-29 | 2021-02-02 | 成都明杰科技有限公司 | Modulation identification method based on convolutional neural network |
| CN114509736B (en) * | 2022-01-19 | 2023-08-15 | 电子科技大学 | Radar target identification method based on ultra-wide band electromagnetic scattering characteristics |
| CN114114227B (en) * | 2022-01-27 | 2022-05-31 | 安徽京淮健锐电子科技有限公司 | Radar signal modulation type identification method based on dual-channel heterogeneous fusion network |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537387A (en) * | 2014-12-16 | 2015-04-22 | 广州中国科学院先进技术研究所 | Method and system for classifying automobile types based on neural network |
| CN104677987A (en) * | 2015-03-15 | 2015-06-03 | 何赟泽 | Eddy radar defect detecting, quantifying and imaging method and system |
| CN107220606A (en) * | 2017-05-22 | 2017-09-29 | 西安电子科技大学 | The recognition methods of radar emitter signal based on one-dimensional convolutional neural networks |
| CN107832794A (en) * | 2017-11-09 | 2018-03-23 | 车智互联（北京）科技有限公司 | A kind of convolutional neural networks generation method, the recognition methods of car system and computing device |
| EP3352112A1 (en) * | 2017-01-20 | 2018-07-25 | Nokia Technologies Oy | Architecture adapted for recognising a category of an element from at least one image of said element |
| CN109036467A (en) * | 2018-10-26 | 2018-12-18 | 南京邮电大学 | CFFD extracting method, speech-emotion recognition method and system based on TF-LSTM |
| CN109254274A (en) * | 2018-11-23 | 2019-01-22 | 哈尔滨工程大学 | A kind of Radar emitter discrimination method based on Fusion Features |
| CN109597043A (en) * | 2018-11-16 | 2019-04-09 | 江苏科技大学 | Radar Signal Recognition method based on quantum particle swarm convolutional neural networks |
-
2019
- 2019-05-27 CN CN201910446014.9A patent/CN110222748B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537387A (en) * | 2014-12-16 | 2015-04-22 | 广州中国科学院先进技术研究所 | Method and system for classifying automobile types based on neural network |
| CN104677987A (en) * | 2015-03-15 | 2015-06-03 | 何赟泽 | Eddy radar defect detecting, quantifying and imaging method and system |
| EP3352112A1 (en) * | 2017-01-20 | 2018-07-25 | Nokia Technologies Oy | Architecture adapted for recognising a category of an element from at least one image of said element |
| CN107220606A (en) * | 2017-05-22 | 2017-09-29 | 西安电子科技大学 | The recognition methods of radar emitter signal based on one-dimensional convolutional neural networks |
| CN107832794A (en) * | 2017-11-09 | 2018-03-23 | 车智互联（北京）科技有限公司 | A kind of convolutional neural networks generation method, the recognition methods of car system and computing device |
| CN109036467A (en) * | 2018-10-26 | 2018-12-18 | 南京邮电大学 | CFFD extracting method, speech-emotion recognition method and system based on TF-LSTM |
| CN109597043A (en) * | 2018-11-16 | 2019-04-09 | 江苏科技大学 | Radar Signal Recognition method based on quantum particle swarm convolutional neural networks |
| CN109254274A (en) * | 2018-11-23 | 2019-01-22 | 哈尔滨工程大学 | A kind of Radar emitter discrimination method based on Fusion Features |
Non-Patent Citations (2)
| Title |
|---|
| Shallow Convolutional Neural Networks for Acoustic Scene Classification;LU Lu等;《Wuhan University Journal of Natural Sciences》;20180313(第02期);169-173 * |
| 深度学习优化算法研究;仝卫国等;《计算机科学》;20181115;411-415 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110222748A (en) | 2019-09-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110222748B (en) | OFDM radar signal identification method based on 1D-CNN multi-domain feature fusion | |
| CN109597043B (en) | Radar signal identification method based on quantum particle swarm convolutional neural network | |
| CN109993280B (en) | Underwater sound source positioning method based on deep learning | |
| CN110133599B (en) | Intelligent radar radiation source signal classification method based on long-time and short-time memory model | |
| CN110632572A (en) | Radar radiation source individual identification method and device based on unintentional phase modulation characteristics | |
| CN114595732B (en) | Radar radiation source sorting method based on depth clustering | |
| CN112949387A (en) | Intelligent anti-interference target detection method based on transfer learning | |
| CN114531729B (en) | Positioning method, system, storage medium and device based on channel state information | |
| Li | A new robust signal recognition approach based on holder cloud features under varying SNR environment | |
| CN112036239A (en) | Radar signal working mode identification method and system based on deep learning network | |
| CN114726692B (en) | SERESESESENet-LSTM-based radiation source modulation mode identification method | |
| Shang et al. | Sea clutter suppression method of HFSWR based on RBF neural network model optimized by improved GWO algorithm | |
| CN114117912A (en) | Sea clutter modeling and inhibiting method under data model dual drive | |
| CN113472415B (en) | Signal arrival angle estimation method and device, electronic equipment and storage medium | |
| CN115661869A (en) | Radio frequency signal fingerprint identification method and system based on multi-dimensional feature intelligent fusion | |
| CN114325245A (en) | Transmission line fault line selection and positioning method based on traveling wave data deep learning | |
| CN115494466A (en) | Self-calibration method for distributed radar | |
| CN115632970A (en) | Method, device and storage medium for estimating communication interference signal bandwidth under non-Gaussian noise | |
| CN115481667A (en) | UWB fuze target identification method based on multi-scale UDA and feature learning | |
| CN113852433B (en) | Wireless channel shadow fading model prediction method based on computer vision | |
| Liao et al. | Intra-pulse modulation recognition of radar signals based on multi-feature random matching fusion network | |
| CN114814776A (en) | PD radar target detection method based on graph attention network and transfer learning | |
| CN111914802B (en) | Ionosphere return scattering propagation pattern identification method based on transfer learning | |
| CN115422977A (en) | Radar radiation source signal identification method based on CNN-BLS network | |
| CN114997326B (en) | Airborne radar working mode identification method based on multi-feature fusion |
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 |