CN111062322B - Phased array radar behavior recognition method based on Support Vector Machine (SVM) - Google Patents
Phased array radar behavior recognition method based on Support Vector Machine (SVM) Download PDFInfo
- Publication number
- CN111062322B CN111062322B CN201911298143.4A CN201911298143A CN111062322B CN 111062322 B CN111062322 B CN 111062322B CN 201911298143 A CN201911298143 A CN 201911298143A CN 111062322 B CN111062322 B CN 111062322B
- Authority
- CN
- China
- Prior art keywords
- phased array
- array radar
- svm
- signals
- behavior
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The invention discloses a phased array radar behavior recognition method based on a Support Vector Machine (SVM), which mainly solves the problems that the summary of phased array radar behavior patterns is incomplete and the recognition accuracy is low in the prior art. The implementation scheme is as follows: 1) Simulating and generating a data set of a phased array radar airspace signal by using commercial software; 2) Performing characteristic extraction on a space domain signal of a phased array radar data set, and outputting the space domain signal in a signal characteristic vector form; 3) Labeling the category of the signal in a data set output in a signal feature vector form to prepare a training set and a test set; 4) Constructing a phased array radar behavior recognition cascading Support Vector Machine (SVM) model, and training the model by using a training set; 5) And (5) sending the test set data into a trained model, and outputting a predicted behavior mode. The invention fully summarizes various behaviors of the phased array radar, improves the recognition rate of various behavior modes, and can be used for the phased array radar behavior recognition under complex electromagnetic environment.
Description
Technical Field
The invention belongs to the technical field of signal processing, and particularly relates to a phased array radar behavior identification method which can be used in an electronic information reconnaissance, electronic support and threat warning system.
Background
With the development of the electronic information field, electronic countermeasure plays an important role in electronic information reconnaissance, electronic support and threat alarm systems, and phased array radar behavior identification is an important link in electronic countermeasure.
With the electromagnetic environment becoming very complicated in electronic countermeasure, the number of radar radiation sources is large, and the spatial distribution range is wide, so that the situation that signals are mixed in the time domain and the frequency domain is increased gradually. Radar signals can appear in tens of thousands or hundreds of thousands in a short time, and a large number of signals can appear at the same time at a certain moment. In addition to the increasing number of signals, the scanning mode of the transmitting antenna is also significantly different from the conventional mechanical scanning mode. The phased array radar controls the feed phase of each radiation unit through a computer in an electric scanning mode, and realizes the spatial scanning of beams by utilizing the interference principle of electromagnetic waves. The phased array radar can realize flexible beam emission and rapid data processing, has multi-target processing, multiple functions and high self-adaption capability, and becomes the key point of development of major military and large countries. Meanwhile, the phased array radar has different working modes, and each mode has different threat degrees to a target, so how to judge the working mode of the phased array radar by using the intercepted information so as to evaluate the threat degree of the phased array radar, which becomes an important content of electronic reconnaissance and is a precondition for implementing accurate interference.
An identification method based on fuzzy clustering is disclosed in an article 'working mode identification method research of phased array radar' by the university of electronic technology, such as trypan, wu Huan, zheng Yong and Bao Jing, aiming at the defects in the traditional clustering algorithm, the aim of optimizing clustering identification is fulfilled by establishing an uncertainty membership relation and utilizing multiple iterations of a fuzzy clustering cost function. However, the method has the defects that only three working modes of the phased array radar are identified, the identification model is single in structure, the feature processing is not sufficient, and the identification rate still has room for improvement.
An identification method based on envelope analysis is disclosed in the article "airborne fire control radar working mode identification" of Liujunjiang of China electronic department group company 29, and the method reduces data volume by utilizing the group variation characteristic of the airborne fire control radar, then carries out pulse group matching connection on time continuity, and finally carries out identification of the airborne fire control radar working mode from the envelope amplitude variation condition. However, the method still has the defects that only three working modes of the airborne fire control radar are identified, the identification method is more traditional, only the mode identification is carried out from the envelope information, and the identification rate still has a space for improvement.
Disclosure of Invention
The invention aims to provide a Support Vector Machine (SVM) -based recognition method aiming at the defects of the prior art, so as to extract characteristics from the perspective of a phased array radar airspace signal, perform multi-mode recognition and improve the recognition rate of the phased array radar behavior.
To achieve the above object, the implementation scheme of the present invention comprises the following steps:
1) Generating a data set of phased array radar airspace signals by using MATLAB software simulation, wherein the data set signals comprise seven signals of a speed searching mode signal, a high repetition frequency side ranging side searching mode signal, a medium repetition frequency side ranging side searching mode signal, a side searching side tracking mode signal, a searching and tracking mode signal, a single-target tracking mode signal and a situation perception mode signal, and each signal generates 1000 samples from 5dB to 20dB at intervals of 5dB signal-to-noise ratio;
2) Preprocessing the data set signal:
2a) Outputting the signals of the data set generated in the step 1) in a sequence mode, then performing feature extraction on the signals of the data set, and outputting the signals in a signal feature vector mode;
2b) Labeling the category of a signal in a data set output in a signal feature vector form, randomly extracting 900 samples from each category of signals as training samples, and taking the remaining 100 samples as test samples;
3) Constructing a cascading SVM model:
3a) Selecting a nonlinear Support Vector Machine (SVM) to construct a phased array radar behavior recognition model, setting the relaxation variable of a sample point to be 0.001, setting the soft interval penalty parameter in the SVM model to be 0.01, setting the Gaussian kernel denominator sigma in the SVM model to be 1, and mapping the original features to a new feature space by using a Gaussian radial basis function;
3b) Aiming at different characteristics of various behaviors of the phased array radar, selecting a certain behavior which is obviously different from other behaviors, and searching an optimal separation hyperplane of the behavior and other behaviors through a nonlinear Support Vector Machine (SVM);
3c) Repeating above 3 b) after the selected behavior is separated from the other behaviors until all phased array radar behaviors are distinguished;
4) Training a cascading Support Vector Machine (SVM) model:
4a) Setting the iteration times of the non-linear support vector machine SVM to be 500;
4b) Inputting training sample data of the signal feature vector into a nonlinear Support Vector Machine (SVM) set in 3 a), and finishing training when the iteration number reaches 500 or each sample point meets the Karaoke-Kun-Tak KKT condition to obtain a trained single behavior recognition model;
4c) Removing the recognized behavior samples from the data set, repeating the step 4 b) until all behavior patterns are recognized, and obtaining a trained cascading Support Vector Machine (SVM) model;
5) And inputting the data of the test set into a trained cascade Support Vector Machine (SVM) model, and outputting a predicted behavior mode of each test sample.
The invention has the following advantages:
firstly, the support vector machine SVM in statistical machine learning is applied to phased array radar behavior recognition, and an optimal separation hyperplane is easier to find out from signal characteristics of different behaviors by utilizing relaxation variables, soft interval punishment and Gaussian radial basis functions of the support vector machine SVM.
Secondly, compared with the essence of a binary model of a Support Vector Machine (SVM), the method uses a cascading behavior recognition thought, provides a phased array radar behavior recognition flow framework through a behavior mode combined experiment, and obviously improves the recognition rate of various behaviors.
Drawings
FIG. 1 is a flow chart of the overall implementation of the present invention;
fig. 2 is a diagram of a phased array radar behavior recognition model of the present invention.
Detailed Description
The embodiments of the present invention are described in detail below with reference to the accompanying drawings.
Referring to fig. 1, the phased array radar behavior identification method of the present example includes the following implementation steps:
step 1: and generating a phased array radar space domain signal data set.
Generating a data set of phased array radar airspace signals by using MATLAB software simulation, wherein the data set signals comprise seven signals of a speed searching mode signal, a high repetition frequency side ranging side searching mode signal, a medium repetition frequency side ranging side searching mode signal, a side searching side tracking mode signal, a searching and tracking mode signal, a single-target tracking mode signal and a situation perception mode signal, and each signal generates 1000 samples from 5dB to 20dB at intervals of 5dB signal-to-noise ratio;
the above seven phased array radar airspace signals have the same characteristics and also have different characteristics, wherein:
a) The space domain signals of the seven phased array radars are respectively set as follows according to different behavior modes:
the pulse dwell number of the speed search mode signal is set to 1500-6000;
the pulse dwell numbers of the 2 phased array radar signals, namely the high repetition frequency side ranging search mode signal and the medium repetition frequency side ranging search mode signal, are set to be 250-2000;
the pulse dwell numbers of the 2 phased array radar signals of the searching and tracking mode signal and the searching and tracking mode signal are set to be 16-128;
the pulse dwell number of the single target tracking mode signal is set to 20000;
setting the pulse dwell number of the situation perception mode signal to be 1000-8000;
b) The sampling frequency and the carrier frequency of the seven phased array radar space domain signals are the same, and the sampling frequency is set to be 2GHz, and the carrier frequency is set to be 1GHz;
c) And the search and tracking mode signal and the situation perception mode signal have consistent retrospective characteristics and are set to retrospective target once every 5 search wave positions.
Step 2: preprocessing a data set of the phased array radar airspace signals to obtain training samples and test samples.
Outputting the signals of the data set generated in the step 1 in a sequence mode, then extracting the characteristics of the signals of the data set, and outputting the signals in a signal characteristic vector mode;
the class to which the signal belongs is labeled in the data set output in the form of the signal feature vector, 900 samples are randomly extracted from each class of signals to be used as training samples, and the remaining 100 samples are used as test samples.
And step 3: and constructing a cascading Support Vector Machine (SVM) model.
3a) A nonlinear Support Vector Machine (SVM) is selected to construct a phased array radar behavior recognition model, and the method is realized as follows:
3a1) Let the constraint of the relaxation variables of the sample points be:
y i (w·x i +b)≥1-ξ i
in the formula, x i Is the ith feature vector, y i Is x i W represents the normal vector of the hyperplane, b represents the intercept of the hyperplane, ξ i Represents the ith sample point (x) i ,y i ) A relaxation variable of (d);
3a2) Selecting a target function of soft interval penalty parameters in the non-linear support vector machine SVM:
in the formula, w represents a normal vector of a hyperplane, C represents a penalty parameter, when the value of C is large, the penalty of misclassification is increased, when the value of C is small, the penalty of misclassification is reduced, and xi i Represents the ith sample point (x) i ,y i ) G (w, C) represents the objective function;
3a3) Setting a relaxation variable in 3a 1) to be 0.001, setting a soft interval penalty parameter in 3a 2) to be 0.01, mapping original features to a new feature space by using a Gaussian radial basis function, and constructing a phased array radar behavior recognition model aiming at various behaviors of the phased array radar based on a cascading behavior recognition thought, as shown in FIG. 2;
the identification model comprises the following modules:
an input data module: for inputting a certain type of behavior pattern of the radiation source;
a first-stage cascade module: the device comprises a speed search mode VS recognizer, a single target tracking mode STT recognizer, a high repetition frequency side-ranging and side-searching mode HRWS recognizer, a side-searching and side-tracking mode TWS recognizer and type converters corresponding to various behavior modes;
a secondary cascade module: the device comprises a TAS (search and tracking) mode recognizer, an MRWS (middle repetition frequency and ranging) mode recognizer and a type converter corresponding to each action mode;
and an output result module: for outputting a predicted behavior pattern;
the first-stage cascade module and the second-stage cascade module are connected by a logic judger, and the second-stage cascade module and the output result module are also connected by the logic judger;
3b) Setting a kernel function:
common kernel functions include linear kernel functions, polynomial kernel functions, complex kernel functions and gaussian radial basis functions, but the example selects but is not limited to gaussian radial basis functions, and the formula is as follows:
wherein x represents any point in the feature space, z represents the center of the kernel function, K (x, z) represents the euclidean distance from x to z, and σ represents the width of the kernel function, and is used for defining the radial action range of the kernel function;
3c) Setting an optimal separation hyperplane:
aiming at different characteristics of various behaviors of the phased array radar, selecting a certain behavior which is obviously different from other behaviors, and searching an optimal separation hyperplane of the behavior and other behaviors through a nonlinear Support Vector Machine (SVM), wherein the formula is as follows:
wherein sign represents the sign operation, N represents the total number of samples,
optimal Lagrange multiplier, y, representing the ith sample point i Indicates the ith sample label，K(x i And x) represents x i Euclidean distance to x, b * Represents the optimal hyperplane intercept, and f (x) represents the optimal separation hyperplane.
And 4, step 4: and training a cascading Support Vector Machine (SVM) model.
4a) Setting the iteration times of a nonlinear Support Vector Machine (SVM) to be 500;
4b) Inputting training sample data of the signal feature vector into a3 a) set nonlinear Support Vector Machine (SVM), and finishing training when the iteration number reaches 500 or each sample point meets the Kaluo-Kunn-Tak KKT condition to obtain a trained single behavior recognition mode;
4c) And (5) removing the recognized behavior samples from the data set, and repeating the step (4 b) until all behavior patterns are recognized, so as to obtain the trained cascading type Support Vector Machine (SVM) model.
And 5: and inputting the data of the test set into a trained cascade Support Vector Machine (SVM) model, and outputting a predicted behavior mode of each test sample.
The foregoing description is only an example of the present invention and is not intended to limit the present invention, and it will be apparent to those skilled in the art that modifications and variations in form and detail may be made without departing from the spirit and structure of the invention, but these modifications and variations are within the scope of the invention as defined in the appended claims.
Claims (5)
1. The phased array radar behavior identification method based on the support vector machine SVM is characterized by comprising the following steps:
1) Generating a data set of phased array radar airspace signals by using MATLAB software simulation, wherein the data set signals comprise seven signals of a speed searching mode signal, a high repetition frequency side distance measuring side searching mode signal, a middle repetition frequency side distance measuring side searching mode signal, a side searching side tracking mode signal, a searching and tracking mode signal, a single target tracking mode signal and a situation perception mode signal, and each signal generates 1000 samples from 5dB to 20dB every 5dB signal-to-noise ratio;
2) Preprocessing the data set signals:
2a) Outputting the signals of the data set generated in the step 1) in a sequence mode, then performing feature extraction on the signals of the data set, and outputting the signals in a signal feature vector mode;
2b) Labeling the category of a signal in a data set output in a signal feature vector form, randomly extracting 900 samples from each category of signals as training samples, and taking the remaining 100 samples as test samples;
3) Constructing a cascading SVM model:
3a) A nonlinear Support Vector Machine (SVM) is selected to construct a phased array radar behavior recognition model, a relaxation variable of a sample point is set to be 0.001, a soft interval punishment parameter in the SVM model is set to be 0.01, and original features are mapped to a new feature space by using a Gaussian radial basis function;
3b) Aiming at different characteristics of various behaviors of the phased array radar, selecting a certain behavior which is obviously different from other behaviors, and searching an optimal separation hyperplane of the behavior and other behaviors through a nonlinear Support Vector Machine (SVM);
3c) Repeating above 3 b) after the selected behavior is separated from the other behaviors until all phased array radar behaviors are distinguished;
4) Training a cascading Support Vector Machine (SVM) model:
4a) Setting the iteration times of the non-linear support vector machine SVM to be 500;
4b) Inputting training sample data of the signal feature vector into a nonlinear Support Vector Machine (SVM) set in 3 a), and finishing training when the iteration number reaches 500 or each sample point meets the Karaoke-Kun-Tak KKT condition to obtain a trained single behavior recognition model;
4c) Removing the recognized behavior samples from the data set, repeating the step 4 b) until all behavior patterns are recognized, and obtaining a trained cascading Support Vector Machine (SVM) model;
5) And inputting the data of the test set into a trained cascade Support Vector Machine (SVM) model, and outputting a predicted behavior mode of each test sample.
2. The method according to claim 1, wherein the non-linear support vector machine SVM is selected from 3 a) to construct the phased array radar behavior recognition model, and the method is realized as follows:
3a1) The constraints for the relaxation variables for the sample points are set as follows:
y i (w·x i +b)≥1-ξ i
in the formula, x i Is the ith feature vector, y i Is x i W represents the normal vector of the hyperplane, b represents the intercept of the hyperplane, ξ i Represents the ith sample point (x) i ,y i ) A relaxation variable of (d);
3a2) The formula of the objective function of the soft interval penalty parameter in the nonlinear support vector machine SVM is as follows:
in the formula, w represents a normal vector of a hyperplane, C represents a penalty parameter, when the value of C is large, the penalty of misclassification is increased, when the value of C is small, the penalty of misclassification is reduced, and xi i Represents the ith sample point (x) i ,y i ) G (w, C) represents the objective function.
3a3) Setting a relaxation variable in 3a 1) to be 0.001, setting a soft interval punishment parameter in 3a 2) to be 0.01, mapping original features to a new feature space by using a Gaussian radial basis function, and constructing a phased array radar behavior recognition model aiming at various behaviors of the phased array radar based on a cascading behavior recognition thought.
3. The method of claim 1, wherein the gaussian radial basis function in 3 a) is given by the following formula:
in the formula, x represents any point in the feature space, z represents the center of the kernel function, σ represents the width parameter of the function, the radial action range of the function is controlled, and K (x, z) represents the euclidean distance from x to z.
4. The method of claim 1, wherein the finding of the optimal separating hyperplane of the selected behavior from other behaviors in 3 b) by the non-linear Support Vector Machine (SVM) is performed by the following formula:
wherein sign represents the sign operation, N represents the total number of samples,
the optimal Lagrange multiplier, y, representing the ith sample point i Denotes the ith sample tag, K (x) i X) represents x i Euclidean distance to x, b * Represents the optimal hyperplane intercept, and f (x) represents the optimal separation hyperplane.
5. The method according to claim 1, wherein the parameters of 7 different phased array radar space domain signals in 1) are set as follows:
searching and tracking mode signals and situation perception mode signals in the 7 phased array radar airspace signals are set to be at intervals of 5 searching wave positions and irradiate back to the target once;
the sampling frequency of the 7 phased array radar airspace signals is 2GHz, and the carrier frequency is 1GHz;
the pulse dwell numbers of the 7 phased array radar airspace signals are respectively set as follows:
the pulse dwell number of the speed search mode signal is set to 1500-6000;
the pulse dwell numbers of the 2 phased array radar signals, namely the high repetition frequency side ranging search mode signal and the medium repetition frequency side ranging search mode signal, are set to be 250-2000;
the pulse dwell numbers of the 2 phased array radar signals of the searching and tracking mode signal and the searching and tracking mode signal are set to be 16-128;
the pulse dwell number of the single target tracking mode signal is set to 20000;
the pulse dwell number of the situation awareness mode signal is set to 1000-8000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298143.4A CN111062322B (en) | 2019-12-17 | 2019-12-17 | Phased array radar behavior recognition method based on Support Vector Machine (SVM) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911298143.4A CN111062322B (en) | 2019-12-17 | 2019-12-17 | Phased array radar behavior recognition method based on Support Vector Machine (SVM) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111062322A CN111062322A (en) | 2020-04-24 |
| CN111062322B true CN111062322B (en) | 2023-03-14 |
Family
ID=70301081
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911298143.4A Active CN111062322B (en) | 2019-12-17 | 2019-12-17 | Phased array radar behavior recognition method based on Support Vector Machine (SVM) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111062322B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111680737B (en) * | 2020-06-03 | 2023-03-24 | 西安电子科技大学 | Radar radiation source individual identification method under differential signal-to-noise ratio condition |
| CN112305509A (en) * | 2020-11-02 | 2021-02-02 | 南京理工大学 | Radar track classification and identification method based on HOG _ SVM |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7660437B2 (en) * | 1992-05-05 | 2010-02-09 | Automotive Technologies International, Inc. | Neural network systems for vehicles |
| CN101807258B (en) * | 2010-01-08 | 2012-05-23 | 西安电子科技大学 | SAR (Synthetic Aperture Radar) image target recognizing method based on nuclear scale tangent dimensionality reduction |
| CN108700652B (en) * | 2015-12-09 | 2023-04-21 | 欧利景无线有限公司 | Method, apparatus and system for wireless event detection and monitoring |
| CN107784320B (en) * | 2017-09-27 | 2019-12-06 | 电子科技大学 | Method for identifying radar one-dimensional range profile target based on convolution support vector machine |
| CN109726653A (en) * | 2018-12-19 | 2019-05-07 | 西安电子科技大学 | Radar Signal Recognition method based on RNN-DenseNet network |
| CN109507648A (en) * | 2018-12-19 | 2019-03-22 | 西安电子科技大学 | Recognition Method of Radar Emitters based on VAE-ResNet network |
-
2019
- 2019-12-17 CN CN201911298143.4A patent/CN111062322B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111062322A (en) | 2020-04-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shao et al. | Convolutional neural network-based radar jamming signal classification with sufficient and limited samples | |
| CN110954872B (en) | Multi-layer perceptron MLP-based phased array radar working mode identification method | |
| Li et al. | Work modes recognition and boundary identification of MFR pulse sequences with a hierarchical seq2seq LSTM | |
| CN111444790B (en) | Pulse-level intelligent identification method for multifunctional radar working mode sequence | |
| Li et al. | Radar emitter classification with attention-based multi-RNNs | |
| Liu | Recognition of multifunction radars via hierarchically mining and exploiting pulse group patterns | |
| CN111062322B (en) | Phased array radar behavior recognition method based on Support Vector Machine (SVM) | |
| Liu | Multi-feature fusion for specific emitter identification via deep ensemble learning | |
| CN108051781A (en) | A kind of radar signal operating mode recognition methods based on DBN model | |
| CN107830996B (en) | Fault diagnosis method for aircraft control surface system | |
| CN106483514B (en) | Airplane motion mode identification method based on EEMD and support vector machine | |
| Cain et al. | Convolutional neural networks for radar emitter classification | |
| Wang et al. | Automatic modulation classification exploiting hybrid machine learning network | |
| CN112036239A (en) | Radar signal working mode identification method and system based on deep learning network | |
| Kim et al. | Classification of the trained and untrained emitter types based on class probability output networks | |
| Zhao et al. | A novel aggregated multipath extreme gradient boosting approach for radar emitter classification | |
| CN116643246A (en) | Deep clustering radar pulse signal sorting method based on inner product distance measurement | |
| Jeong et al. | Neural network-based radar signal classification system using probability moment and ApEn | |
| Yeo et al. | Expeditious diagnosis of linear array failure using support vector machine with low-degree polynomial kernel | |
| Arasaratnam et al. | Tracking the mode of operation of multi-function radars | |
| Matuszewski | Application of clustering methods for recognition of technical objects | |
| CN103076595B (en) | Abnormal type identifying method for multivariate discrete radar emitter signal | |
| CN114492583B (en) | LSTM-based radar search mode identification method | |
| Wang et al. | Automatic jamming modulation classification exploiting convolutional neural network for cognitive radar | |
| CN115932770A (en) | Method, system, equipment and terminal for accurately and intelligently identifying radar radiation source individuals |
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 |