As the real electromagnetic environment grows complex and the quantity of radar signals turns massive, traditional methods, which require a large amount of prior knowledge, are time-consuming and ineffective for radar emitter signal recognition. In recent years, convolutional neural network (CNN) has shown its superiority in recognition so that experts have applied it in radar signal recognition. However, in the field of radar emitter signal recognition, the data are usually one-dimensional (1-D), which takes more time and storage space than by using the original two-dimensional CNN model directly. Moreover, the features extracted from convolutional layers are redundant so that the recognition accuracy is low. In order to solve these problems, this paper proposes a novel one-dimensional convolutional neural network with an attention mechanism (CNN-1D-AM) to extract more discriminative features and recognize the radar emitter signals. In this method, features of the given 1-D signal sequences are extracted directly by the 1-D convolutional layers and are weighted in accordance with their importance to recognition by the attention unit. The experiments based on seven different radar emitter signals indicate that the proposed CNN-1D-AM has the advantages of high accuracy and superior performance in radar emitter signal recognition.

The intra-pulse modulation of radar emitter signals is a key feature for analyzing radar systems. Traditional methods which require a tremendous amount of prior knowledge are insufficient to accurately classify the intra-pulse modulations. Recently, deep learning-based methods, especially convolutional neural networks (CNN), have been used in classification of intra-pulse modulation of radar emitter signals. However, those two-dimensional CNN-based methods, which require dimensional transformation of the original sampled signals in the stage of data preprocessing, are resource-consuming and poorly feasible. In order to solve these problems, we proposed a one-dimensional selective kernel convolutional neural network (1-D SKCNN) to accurately classify the intra-pulse modulation of radar emitter signals. Compared with other previous methods described in the literature, the data preprocessing of the proposed method merely includes zero-padding, fast Fourier transformation (FFT) and amplitude normalization, which is much faster and easier to achieve. The experimental results indicate that the proposed method has the advantages of faster speed in data preprocessing and higher accuracy in intra-pulse modulation classification of radar emitter signals.

To solve the difficulty associated with radar signal classification in the case of few-shot signals, we propose an adaptive focus loss algorithm based on transfer learning. Firstly, we trained a one-dimensional convolutional neural network (CNN) with radar signals of three intra-pulse modulation types in the source domain, which were effortlessly obtained and had sufficient samples. Then, we transferred the knowledge obtained by the convolutional layer to nine types of few-shot complex intra-pulse modulation classification tasks in the target domain. We propose an adaptive focal loss function based on the focal loss function, which can estimate the parameters based on the ratio of hard samples to easy samples in the data set. Compared with other existing algorithms, our proposed algorithm makes good use of transfer learning to transfer the acquired prior knowledge to new domains, allowing the CNN model to converge quickly and achieve good recognition performance in case of insufficient samples. The improvement based on the focal loss function allows the model to focus on the hard samples while estimating the focusing parameter adaptively instead of tediously repeating experiments. The experimental results show that the proposed algorithm had the best recognition rate at different sample sizes with an average recognition rate improvement of 4.8%, and the average recognition rate was better than 90% for different signal-to-noise ratios (SNRs). In addition, upon comparing the training processes of different models, the proposed method could converge with the least number of generations and the shortest time under the same experimental conditions.

In recent years, radar emitter signal recognition has enjoyed a wide range of applications in electronic support measure systems and communication security. More and more deep learning algorithms have been used to improve the recognition accuracy of radar emitter signals. However, complex deep learning algorithms and data preprocessing operations have a huge demand for computing power, which cannot meet the requirements of low power consumption and high real-time processing scenarios. Therefore, many research works have remained in the experimental stage and cannot be actually implemented. To tackle this problem, this paper proposes a resource reuse computing acceleration platform based on field programmable gate arrays (FPGA), and implements a one-dimensional (1D) convolutional neural network (CNN) and long short-term memory (LSTM) neural network (NN) model for radar emitter signal recognition, directly targeting the intermediate frequency (IF) data of radar emitter signal for classification and recognition. The implementation of the 1D-CNN-LSTM neural network on FPGA is realized by multiplexing the same systolic array to accomplish the parallel acceleration of 1D convolution and matrix vector multiplication operations. We implemented our network on Xilinx XCKU040 to evaluate the effectiveness of our proposed solution. Our experiments show that the system can achieve 7.34 giga operations per second (GOPS) data throughput with only 5.022 W power consumption when the radar emitter signal recognition rate is 96.53%, which greatly improves the energy efficiency ratio and real-time performance of the radar emitter recognition system.

Intra-pulse modulation classification of radar emitter signals is beneficial in analyzing radar systems. Recently, convolutional neural networks (CNNs) have been used in classification of intra-pulse modulation of radar emitter signals, and the results proved better than the traditional methods. However, there is a key disadvantage in these CNN-based methods: the CNN requires enough labeled samples. Labeling the modulations of radar emitter signal samples requires a tremendous amount of prior knowledge and human resources. In many circumstances, the labeled samples are quite limited compared with the unlabeled samples, which means that the classification will be semi-supervised. In this paper, we propose a method which could adapt the CNN-based intra-pulse classification approach to the case where a very limited number of labeled samples and a large number of unlabeled samples are provided, to classify the intra-pulse modulations of radar emitter signals. The method is based on a one-dimensional CNN and uses pseudo labels and self-paced data augmentation, which could improve the accuracy of intra-pulse classification. Extensive experiments show that our proposed method can improve the intra-pulse modulation classification performance in the semi-supervised situations.

In recent years, deep learning has been widely used in radar emitter signal identification and has significantly increased recognition rates. However, with the emergence of new institutional radars and an increasingly complex electromagnetic environment, the collection of high-quality signals becomes difficult, leading to a result that the amount of some signal types we own are too few to converge a deep neural network. Moreover, in radar emitter signal identification, most existing networks ignore the signal recognition of unknown classes, which is of vital importance for radar emitter signal identification. To solve these two problems, an improved prototypical network (IPN) belonging to metric-based meta-learning is proposed. Firstly, a reparameterization VGG (RepVGG) net is used to replace the original structure that severely limits the model performance. Secondly, we added a feature adjustment operation to prevent some extreme or unimportant samples from affecting the prototypes. Thirdly, open-set recognition is realized by setting a threshold in the metric module.