Sensing the external complex electromagnetic environment is an important function for cognitive radar, and the concept of cognition has attracted wide attention in the field of radar since it was proposed. In this paper, a novel method based on an idea of multidimensional feature map and convolutional neural network (CNN) is proposed to realize the automatic modulation classification of jamming entering the cognitive radar system. The multidimensional feature map consists of two envelope maps before and after the pulse compression processing and a time-frequency map of the receiving beam signal. Drawing the one-dimensional envelope in a 2-dimensional plane and quantizing the time-frequency data to a 2-dimensional plane, we treat the combination of the three planes (multidimensional feature map) as one picture. A CNN-based algorithm with linear kernel sensing the three planes simultaneously is selected to accomplish jamming classification. The classification of jamming, such as noise frequency modulation jamming, noise amplitude modulation jamming, slice jamming, and dense repeat jamming, is validated by computer simulation. A performance comparison study on convolutional kernels in different size demonstrates the advantage of selecting the linear kernel.
Cognitive radar proposed in [
Different antijamming techniques are suitable for different jamming modulation mode. Therefore, in order to make the selection of the antijamming measures more intelligent for cognitive radar, it is essential to recognize the modulation class of different types of interferences. We give an explanation of the antijamming process in a cognitive radar in Figure
The principle of antijamming for a cognitive radar.
The classes of jamming modulation can be divided into noise frequency modulation jamming [
In the related fields of communication and electronic warfare, there are a great number of studies on automatic modulation classification of communication signals and radar signals. AMC is regarded as an issue of pattern recognition with two processing stages. Firstly, the features of the signals are extracted by various processing algorithms, such as cumulants [
From the above literature, it can be seen that using deep learning to achieve AMC of signals is a hot research topic. As a new research direction of machine learning, deep learning [
Besides cognitive radar, modulation classification has been considered in cognitive radio systems, for military application in communication systems, and more frequently in optical communication systems [
The rest of this paper is organized as follows. Section
The AMCOJ for a cognitive radar consists of multidimensional feature map construction and CNN design. This paper mainly aims at the AMC of seven types of common jamming, namely, noise frequency modulation jamming (NFMJ), noise amplitude modulation jamming (NAMJ), monofrequency pulse jamming (MFPJ), noise frequency-modulated pulse jamming (NFMPJ), dense repeater jamming (DRJ), sparse repeater jamming (SRJ), and slice jamming (SJ, also known as interrupted-sampling and repeater jamming (ISRJ)). The characteristics of the above interferences are as listed in Table
The characteristics of the seven types of jamming.
Types | Characteristics |
---|---|
NFMJ | Noise-modulated frequency and constant envelope |
NAMJ | Noise-modulated amplitude |
MFPJ | Pulses modulated in single frequency |
NFMPJ | Random pulse width and noise-modulated frequency |
DRJ | Repeat back radar signal with pulse repetition interval less than the transmitted pulse width of the radar |
SRJ | Repeat back radar signal with pulse repetition interval greater than the transmitted pulse width of the radar |
SJ | Repeat back radar signal in cutting segments |
Figure
The principle diagram of AMCOJ in a cognitive radar.
This paper mainly focuses on the radar environment perception processing consisting of multidimensional feature map construction and CNN model design. The differences of different jamming types can be observed in time and frequency domain, so that maps of short-time Fourier transform (STFT) and envelopes before and after PC can be used as features. This paper proposes the method of constructing multidimensional feature map to ensure the correct recognition rate, since single feature map is not effective in discriminating some jamming types. For instance, it is difficult to discriminate noise frequency modulation jamming from noise amplitude modulation jamming in the time-frequency domain. However, there is an obvious difference between them in the time domain before PC. As shown in Figure
Deep learning based on CNN is now widely employed in the field of image recognition. If we transform the jamming features into images in a two-dimensional map, CNN will be possible to be applied to extract their differences as its recognition process of an image. In order to improve the classification accuracy of the jamming using CNN approach, this paper proposes the idea of extracting multiple jamming features from a multidimensional feature map. Envelope features and time-frequency spectrum features are selected to form the feature map. The one-dimensional envelope features before and after pulse compression are plotted in the time domain as planar maps, and the time-frequency features are quantified in amplitude and turn into a two-dimensional planar map, either. Then the above planar maps are combined to form a multidimensional feature map used as the input of CNN. The construction process of each feature map is discussed as follows.
Obvious differences can be observed in the time-frequency map of the interferences. The short-time Fourier transform (STFT) can be used to obtain the time-frequency spectrum and can be written as
The preprocessing of
The time-frequency feature of SJ. (a) Time-frequency spectrum of SJ. (b) Binary time-frequency feature map of SJ.
Binary time-frequency feature maps of different types of jamming. (a) NFMJ. (b) NAMJ. (c) MFPJ. (d) NFMPJ. (e) DRJ. (f) SRJ.
According to the characteristics of the seven classes of jamming in the time domain, the envelope features before PC can be extracted. The data before PC (after DBF) is a one-dimensional vector; it can be depicted as a binary map by drawing the envelope in the time domain. The envelope feature map before PC is termed as
The schematic diagram of decision matrix.
The envelope feature of SJ before PC. (a) The envelope of SJ before PC. (b) The corresponding binary envelope feature map of SJ.
The multidimensional feature map of the seven classes of jamming. (a) NFMJ. (b) NAMJ. (c) MFPJ. (d) NFMPJ. (e) DRJ. (f) SRJ. (g) SJ.
We further extract the envelope feature after PC. Since the data processed by PC is a one-dimensional vector, it is essential to form a binary map
The envelope feature of SJ after PC. (a) The envelope after PC. (b) The corresponding binary envelope feature map.
Viewed from the time-frequency feature map, noise frequency modulation jamming, noise amplitude modulation jamming, and noise frequency-modulated pulse jamming are not easy to be distinguished. From the perspective of the envelope before PC, monofrequency pulse jamming, noise frequency-modulated pulse jamming, and sparse repeater jamming are prone to be confused and indistinguishable. Through the envelope feature map after PC, it is difficult to differentiate between noise frequency modulation jamming and noise amplitude modulation jamming. The schematic diagram of multidimensional feature map
The schematic diagram of multidimensional feature map.
The architecture of a typical CNN is generally composed of five stages: input layer, convolution layer, sampling layer, full connection layer, and output layer [
The training process of CNN mainly includes two stages: forward propagation and backward feedback. Firstly, the training samples carry out forward propagation network according to the flow of Figure
Diagram of the CNN model.
In this section, we present a variety of simulation experiments to demonstrate the performance of our proposed AMCOJ algorithm using CNN based on multidimensional feature map (MD-CNN). Seven different modulation candidates are considered here, namely, noise frequency modulation jamming, noise amplitude modulation jamming, monofrequency pulse jamming, noise frequency-modulated pulse jamming, dense repeater jamming, sparse repeater jamming, and slice jamming. Since the robustness of the MD-CNN algorithm is deeply affected by the training data samples, training samples in different conditions should be included in the sample database. Hence, we generate the training samples via changing the jamming principal parameters such as time delay, slice period, and repeat interval. The jamming parameter settings are shown in Table
Parameter setting of different types of jamming.
Type | Parameter setting |
---|---|
NFMJ | Noise-modulated frequency |
NAMJ | Noise-modulated amplitude |
MFPJ | The carrier frequency: 10 kHz–100 kHz; |
NFMPJ | Pulse repetition period: random in 140–250; |
DRJ | Repeat interval (sample point): random value (50–100), less than the transmitted pulse width |
SRJ | Repeat interval (sample point): random value (180–250), greater than the transmitted pulse width |
SJ | The slice period (sample point): 20; |
In the network training stage, the feature maps are gained by the processing of the envelope and time-frequency spectrum. We merge three feature maps with the size of 64 × 512 separately into one 192 × 512 multidimensional feature map and use it as the sample input for CNN. The iteration number of CNN is set to 50. The network model is trained by 350 samples and tested by another 175 samples.
The correct recognition rates of the seven jamming classes using MD-CNN algorithm under different JNRs are illustrated in Table
Numbers of mispredicted samples of MD-CNN at different JNRs.
Type | JNR = 3 dB | JNR = 5 dB | JNR = 8 dB | JNR = 10 dB | JNR = 13 dB | JNR = 15 dB |
---|---|---|---|---|---|---|
NFMJ | 3 | 0 | 0 | 0 | 0 | 0 |
NAMJ | 0 | 0 | 0 | 0 | 0 | 0 |
MFPJ | 0 | 0 | 0 | 0 | 0 | 0 |
NFMPJ | 7 | 5 | 2 | 1 | 0 | 0 |
DRJ | 1 | 0 | 0 | 0 | 0 | 0 |
SRJ | 1 | 0 | 0 | 0 | 0 | 0 |
SJ | 5 | 4 | 1 | 0 | 0 | 0 |
We compare the performance of the proposed method with the single feature map method using STFT feature map and envelope feature map before and after PC. The total correct recognition rates based on the single feature maps and the multidimensional feature map are plotted in Figure
Correct recognition rates for different algorithms.
The selection of the CNN kernel is of great significance to the CNN performance. As shown in Figure
CNNs model with different kernel structures.
Performance comparisons between CNNs with different kernel structures.
Model | Channel number | Convolution kernel sizes in each channel | Correct recognition rates (%) |
---|---|---|---|
CNN1 (linear kernel) | 1 | 192 × 1 | 100 |
CNN2 | 1 | 192 × 9 | 98.28 |
CNN3 | 1 | 192 × 13 | 99.42 |
CNN4 | 1 | 13 × 13 | 14.28 |
CNN5 | 1 | 13 × 9 | 14.28 |
CNN6 | 3 | 64 × 1 | 92.57 |
CNN7 | 3 | 64 × 9 | 82.86 |
CNN8 | 3 | 64 × 13 | 90.86 |
The same conclusion can be drawn that the performance of CNN6, CNN7, and CNN8 with three channels sensing the three feature maps degrades slightly in comparison with CNNs1–3. We take the CNN6 model with three channels as an example to analyze the numbers of mispredicted samples of each jamming class in detail, as shown in Table
Numbers of mispredicted samples of CNN6 at different JNRs.
Type | JNR = 3 dB | JNR = 5 dB | JNR = 8 dB | JNR = 10 dB | JNR = 13 dB | JNR = 15 dB |
---|---|---|---|---|---|---|
NFMJ | 1 | 0 | 0 | 0 | 0 | 0 |
NAMJ | 2 | 0 | 0 | 0 | 0 | 0 |
MFPJ | 5 | 5 | 1 | 0 | 0 | 0 |
NFMPJ | 5 | 5 | 2 | 1 | 1 | 1 |
DRJ | 9 | 4 | 2 | 1 | 0 | 0 |
SRJ | 11 | 10 | 10 | 10 | 9 | 8 |
SJ | 17 | 12 | 11 | 8 | 7 | 4 |
As a conventional approach, radar ambiguity function has been utilized to extract the modulation type of the jamming feature. Here, as a comparison study, we use the combination of radar ambiguity function and a type of classical CNN called LeNet5 (termed as RA + LeNet5) to classify different jamming signals.
LeNet5 here used is composed of 7 layers: (1) the first convolution layer with 5 × 5 kernels; (2) the first pooling layer with 6 2 × 2 kernels; (3) the second convolution layer with 16 5 × 5 kernels; (4) the second pooling layer with 16 5 × 5 kernels; (5) the third convolution layer with 120 5 × 5 kernels; (6) full connection layer with 120 output; (7) output layer with 7 types of output.
We test the performance of RA + LeNet5 and our proposed method of CNN1 in Table
Numbers of mispredicted samples of RA + LeNet5 and the method of this paper.
JNR | 6 dB | 8 dB | ||
---|---|---|---|---|
Method | CNN1 of this paper | RA + LeNet5 | CNN1 of this paper | RA + LeNet5 |
NFMJ | 0 | 5 | 0 | 3 |
NAMJ | 0 | 19 | 0 | 15 |
MFPJ | 0 | 22 | 0 | 14 |
NFMPJ | 0 | 23 | 0 | 14 |
DRJ | 3 | 25 | 1 | 11 |
SRJ | 8 | 22 | 6 | 16 |
SJ | 10 | 16 | 6 | 17 |
The algorithm complexity of RA + LeNet5 and the method of this paper can be analyzed in two aspects, the feature extraction phase and the classification phase.
Algorithm complexity in feature extraction map construction phase is as follows: The method of this paper: there are 64-point FFT of 30 times to calculate the short Fourier transform and 2 RA + LeNet5: to calculate the radar ambiguity function, there is a 64-point FFT of 30 times in the time delay domain and 64-point FFT of 30 times in the Doppler domain
The number of convolutions is used to compare the algorithm complexity in the classification phase, since convolutions can represent the main complexity for these phases: Classification method of this paper: convolution kernel of 192 × 1 RA + LeNet5: 6 5 × 5 convolution kernels + 16 5 × 5 convolution kernels + 120 5 × 5 convolution kernels
We can conclude from this comparison that, in the feature extraction map construction phase, the complexity of the two methods is the same, while in the classification phase, the multikernel and multiconvolution layer structure makes RA + LeNet5 more complex than that of our method from the viewpoint of the convolution numbers.
We employ the CNN approach to solve the recognition of jamming for cognitive radar. Considering the differences between different types of jamming in envelope and time-frequency spectrum, the multidimensional feature map is constructed by combining three features of the received signal including amplitude before and after PC and STFT analysis. After the training process, the CNN observes the local features on the combined map and gives the classification result automatically. Computer simulation reveals that the sensing and classification of the jamming classes based on the multidimensional feature map achieve superior performance in comparison with the single feature map method. In addition, multifeature comprehensive perception of the three pictures simultaneously with a linear kernel CNN is superior to CNN with other kernel types.
The data used to support the findings of this study are from the simulation conditions of open literature, and the authors made computer simulations to generate all the simulation data according to these conditions.
The authors declare that they have no conflicts of interest.
This work was partially supported by the Foundation of Science and Technology on Electronic Information Control Laboratory.